Abdominal Radiology

Introduction to the special section on ovarian cancer

Diagnostic accuracy of contrast-enhanced CT versus PET/CT for advanced ovarian cancer staging: a comparative systematic review and meta-analysis

Accurate staging of ovarian cancer is critical to guide optimal management pathways. North American guidelines recommend contrast-enhanced CT as the primary work-up for staging ovarian cancer. This meta-analysis aims to compare the diagnostic accuracy of contrast-enhanced CT alone to PET/CT for detecting abdominal metastases in patients with a new or suspected diagnosis of ovarian cancer. A systematic review of MEDLINE, EMBASE, Scopus, the Cochrane Library, and the gray literature from inception to October 2022 was performed. Studies with a minimum of 5 patients evaluating the diagnostic accuracy of contrast-enhanced CT and/or PET/CT for detecting stage 3 ovarian cancer as defined by a surgical/histopathological reference standard ± clinical follow-up were included. Study, clinical, imaging, and accuracy data for eligible studies were independently acquired by two reviewers. Primary meta-analysis was performed in studies reporting accuracy on a per-patient basis using a bivariate mixed-effects regression model. Risk of bias was evaluated using QUADAS-2. From 3701 citations, 15 studies (918 patients with mean age ranging from 51 to 65 years) were included in the systematic review. Twelve studies evaluated contrast-enhanced CT (6 using a per-patient assessment and 6 using a per-region assessment) and 11 studies evaluated PET/CT (7 using a per-patient assessment and 4 using a per-region assessment). All but one reporting study used consensus reading. Respective sensitivity and specificity values on a per-patient basis were 82% (67-91%, 95% CI) and 72% (59-82%) for contrast-enhanced CT and 87% (75-94%) and 90% (82-95%) for PET/CT. There was no significant difference in sensitivities between modalities (p = 0.29), but PET/CT was significantly more specific than CT (p < 0.01). Presumed variability could not be assessed in any single category due to limited studies using per-patient assessment. Studies were almost entirely low risk for bias and applicability concerns using QUADAS-2. Contrast-enhanced CT demonstrates non-inferior sensitivity compared to PET/CT, although PET/CT may still serve as an alternative and/or supplement to CT alone prior to and/or in lieu of diagnostic laparoscopy in patients with ovarian cancer. Future revisions to existing guidelines should consider these results to further refine the individualized pretherapeutic diagnostic pathway.

Prognostic significance of MRI-derived sarcopenia in patients with endometrial cancer

To investigate the prognostic significance of MRI-derived sarcopenia in patients with endometrial cancer (EC), and to explore its association with clinicopathological features, treatment characteristics, and survival outcomes. This retrospective cohort study included 289 EC patients undergoing surgical staging between 2009 and 2018. Sarcopenia was measured as the lowest quartile of the third lumbar vertebra total psoas muscle area (L3 TPMA) on preoperative MRI. Associations between sarcopenia and pathological characteristics were evaluated using Pearson's Chi-square test or Fisher's exact test for categorical variables, and independent t-tests or Mann-Whitney U tests for continuous variables. To provide a contextual reference for sarcopenia-related parameters, 289 age-matched healthy women were retrospectively selected as controls. Kaplan-Meier and multivariate Cox proportional hazards analyses were conducted to assess the impact of sarcopenia on disease-free survival (DFS) and overall survival (OS). Sarcopenia was identified in 24.9% (n = 72/289) of EC patients. Uterine serosal invasion was significantly more frequent in sarcopenic patients compared to non-sarcopenic patients (60.0% vs. 23.7%, p = 0.018). Adjuvant treatments, including chemotherapy, radiotherapy, and brachytherapy, did not significantly differ by sarcopenia status. L3 TPMA was significantly lower in sarcopenic patients (642 ± 110 mm²) compared to non-sarcopenic patients (1144 ± 261 mm²) and controls (1029 ± 258 mm²) (p < 0.001). In multivariate analysis, sarcopenia remained an independent predictor of both reduced DFS (p = 0.023) and OS (p = 0.035), along with FIGO 2023 stage, chemotherapy administration, and elevated CA-125 levels. MRI-derived sarcopenia was identified in 24.9% of patients with EC and was independently associated with unfavorable pathological characteristics and poor survival outcomes.

Multiparametric magnetic resonance imaging of endometrial polypoid lesions

Endometrial polypoid lesions encompass various conditions from physiologic changes to benign or malignant disease. Differentiating between the various causes of endometrial polypoid lesions remains difficult by transvaginal sonography. Magnetic resonance imaging (MRI) can provide valuable information regarding endometrial polypoid lesions in situations where it is difficult to obtain histologic samples. Multiparametric MRI including T2-weighted images, T1-weighted fat-saturation contrast-enhanced images, and diffusion-weighted images may be helpful for differentiating the various endometrial polypoid lesions and establishing specific diagnoses and appropriate treatment.

Isthmic uterine lesions: a comprehensive pictorial review of MRI features and management strategies

The uterine isthmus, the narrowest portion of the uterus, plays an essential role in female reproductive health and can be the site of several gynecological pathologies. Due to its strategic location, lesions in this region have unique characteristics and can lead to a wide variety of symptoms and diagnostic challenges. Diagnosis is usually made through imaging tests, such as ultrasound (US) or magnetic resonance imaging (MRI), with appropriate treatment depending on the precise identification of the type of lesion and evaluation of factors such as size, location, and risk of malignancy. This pictorial essay provides a comprehensive, image-rich review of multiple uterine isthmic lesions-including isthmoceles (cesarean scar defects) and their complications, fibroids in the isthmus, cesarean scar ectopic pregnancies (CSEP), isthmic endometriosis, adenomyosis/adenomyomas, post-curettage vascular malformations, niche-related intrauterine device (IUD) malposition, trophoblastic tissue implants, and endometrial polyps-highlighting their MRI appearances, epidemiological and clinical correlations, and management options.

Direct comparison of full protocol MRI and modified non-contrast MRI in staging of cervical cancer: a retrospective study

Cervical cancer is the fourth most common cancer and the fourth leading cause of cancer death among women worldwide. Appropriate treatment can reduce mortality rate and improve prognosis, where the choice of appropriate treatment option is closely related to the preoperative staging. In this study, we compared full protocol MRI (including contrast-enhanced images) and modified protocol (including only T2-weighted sequence and DWI + ADC map images) in preoperative cervical cancer staging based on the 2018 Federation of Gynecology and Obstetrics (FIGO) classification system. In this retrospective cross-sectional study, pelvic MRIs of 128 patients with cervical cancer were evaluated. For all patients, staging was performed by two independent radiologists according to the 2018 FIGO Staging Classification, first based on modified protocol and then based on full protocol MRI. Inter-modality agreement was evaluated by Cohen's kappa, intraclass correlation coefficient (ICC), and concordance correlation coefficient (CCC). There was very good agreement between the modified and full protocols in preoperative staging of cervical cancer (weighted kappa: 0.967) with a low number of discrepancies. There was also a high level of agreement between two modalities in the determination of parametrium, pelvic side wall, bladder, intestine, uterine, and lymph node involvements, as well as hydronephrosis and vascular encasement. Tumors at stage I had significantly higher ADC values compared to higher-stage tumors (p-value: 0.003). Based on our study, modified MRI (including T2WI and DWI images) had substantial agreement with full protocol MRI in preoperative cervical cancer staging, suggesting its potential as a reliable contrast-free alternative for clinical practice.

Diagnostic and clinical utility of ultrasound elastography for uterine cervical neoplasms—a comprehensive systematic review and meta-analysis

Cervical cancer remains a major burden, especially in low-resource settings, due to limited screening. Traditional diagnostic tools, like colposcopy, are operator-dependent and often lack accuracy. Ultrasound elastography, including strain elastography (SE) and shear wave elastography (SWE), is a cost-effective, non-invasive tool for assessing tissue stiffness, aiding in distinguishing benign from malignant cervical lesions, and monitoring treatment. This review evaluates elastography's diagnostic accuracy and clinical utility in cervical cancer management. This systematic review and meta-analysis was performed following PRISMA 2020 guidelines and was registered with PROSPERO (CRD42025639380). PubMed, Embase, Cochrane Library, Web of Science, and Scopus were searched up to January 2025 for studies utilizing elastography in cervical cancer. Study quality was assessed using the Newcastle-Ottawa Scale. Pooled sensitivity, specificity, and SROC curves were calculated using R software and Stata, with heterogeneity and publication bias evaluated. A total of twenty-three studies were included, with 19 in the meta-analysis. Elastography demonstrated high diagnostic accuracy for both detecting cervical cancer (sensitivity 88.3%, specificity 92%, AUC 0.965) and cervical intraepithelial neoplasia (CIN). SE trended to a non-significantly higher diagnostic accuracy than SWE (p = 0.51). Quantitative parameters differentiated cervical cancer from controls (SMD = 2.59, p < 0.001) and CIN (SMD = 1.75, p = 0.015). Elastography can effectively assess treatment response and tumor invasion. Elastography aids cervical cancer diagnosis with high sensitivity and specificity, ideal for resource-limited settings due to its affordability and safety. Standardized training and guidelines are needed for consistent use. Future studies should compare SE and SWE, minimize variability, benchmark against MRI, and assess prognostic value.

Histogram analysis of apparent diffusion coefficient for preoperative prediction of mid-term efficacy of high-intensity focused ultrasound in the treatment of uterine fibroids

This study was designed to investigate the preoperative prediction of the mid-term efficacy of high-intensity focused ultrasound (HIFU) in the treatment of uterine fibroids by apparent diffusion coefficient (ADC) histogram analysis. Eighty-six patients with a total of 101 uterine fibroids were retrospectively collected consecutively. The region of interest (ROI) was outlined layer by layer on diffusion-weighted imaging (DWI) images with b = 1000 s/mm The markedly effective group included 42 fibroids, and the noneffective group included 59 fibroids. The results of the univariate analysis showed that ADCmean, ADCmax, ADC10th, ADC25th, skewness, kurtosis, and entropy were significantly different between the two groups. The results of the multivariate analysis showed that ADC10th and skewness were statistically significant indicators, the area under the ROC curve (AUC) was 0.678 and 0.739, respectively, and the combined AUC of the two was 0.790. Major study limitations include: this is a single-center retrospective study, the investigator manually segmented the lesions, and no further analysis of postoperative pathology regarding the findings of the study. ADC histogram analysis helps to preoperatively predict the mid-term efficacy of HIFU in the treatment of uterine fibroids. ADC10th and skewness are independent predictors of the mid-term efficacy of HIFU, and the combined efficacy of the two is superior to that of a single indicator.

Magnetic resonance imaging features of uterine adenosarcoma: case series and systematic review

To comprehensively summarize the characteristics of magnetic resonance imaging (MRI) findings of uterine adenosarcoma through a systematic review and case series analysis. A literature search was conducted in MEDLINE, Scopus, and Embase databases on June 3, 2024. In total, 25 cases from 23 articles were selected, and five cases from the authors' institution were included. Two board-certified radiologists evaluated the demographic, clinical, and radiological data. The median age at diagnosis was 48.5 years (range: 9-79 years). The most frequent chief complaint was abnormal bleeding (96.7%), pathological T1 stage was predominant (85.2%), and 55.2% of the patients had sarcomatous overgrowth. Locoregional/distant recurrence occurred in 36.4% of the patients. MRI findings revealed that the mean longest lesion size was 9.3 cm. However, most lesions were located in the uterine body (93.1%) and primarily involved the endometrium (96.6%). Most cases (90.0%) were polypoid lesions with 80.8% protruding into the cervical canal. Cystic changes were prevalent (96.5%) and hemorrhage was observed in 84.6% of the evaluated cases. Lesions showed high (51.7%) or intermediate (48.3%) signal intensity compared with the uterine myometrium on T2-weighted imaging. Furthermore, all lesions showed heterogeneous enhancement on contrast-enhanced MRI, and the mean apparent diffusion coefficient value was 1.05 × 10 Our findings provide a comprehensive analysis of MRI features in uterine adenosarcoma cases, highlighting key characteristics that may aid in preoperative diagnosis and differentiation from other uterine malignancies.

A case of uterine leiomyosarcoma in a survivor of hereditary retinoblastoma

Survivors of hereditary retinoblastoma have increased risk of subsequent primary malignancies due to RB1 mutation. We report uterine leiomyosarcoma (LMS) in a hereditary retinoblastoma survivor. She had follow-up for leiomyomas, with pelvic MRI showing typical leiomyomas two years prior. She presented with abdominal distention, and MRI revealed a massive tumor with LMS characteristics where a leiomyoma was previously observed. Chest CT showed a nodule suspicious for metastasis in the left lung. Total hysterectomy with bilateral salpingo-oophorectomy and partial lung resection was performed. Pathology confirmed LMS with pulmonary metastasis. Immunostaining showed complete RB1 loss in tumor cells. LMS was suspected to have arisen near a pre-existing leiomyoma or resulted from its malignant transformation. Continuous follow-up is necessary in hereditary retinoblastoma survivors.

Deep learning assisted detection and segmentation of uterine fibroids using multi-orientation magnetic resonance imaging

To develop deep learning models for automated detection and segmentation of uterine fibroids using multi-orientation MRI. Pre-treatment sagittal and axial T2-weighted MRI scans acquired from patients diagnosed with uterine fibroids were collected. The proposed segmentation models were constructed based on the three-dimensional nnU-Net framework. Fibroid detection efficacy was assessed, with subgroup analyses by size and location. The segmentation performance was evaluated using Dice similarity coefficients (DSCs), 95% Hausdorff distance (HD95), and average surface distance (ASD). The internal dataset comprised 299 patients who were divided into the training set (n = 239) and the internal test set (n = 60). The external dataset comprised 45 patients. The sagittal T2WI model and the axial T2WI model demonstrated recalls of 74.4%/76.4% and precision of 98.9%/97.9% for fibroid detection in the internal test set. The models achieved recalls of 93.7%/95.3% for fibroids ≥ 4 cm. The recalls for International Federation of Gynecology and Obstetrics (FIGO) type 2-5, FIGO types 0\1\2(submucous), fibroids FIGO types 5\6\7(subserous) were 100%/100%, 73.3%/78.6%, and 80.3%/81.9%, respectively. The proposed models demonstrated good performance in segmentation of the uterine fibroids with mean DSCs of 0.789 and 0.804, HD95s of 9.996 and 10.855 mm, and ASDs of 2.035 and 2.115 mm in the internal test set, and with mean DSCs of 0.834 and 0.818, HD95s of 9.971 and 11.874 mm, and ASDs of 2.031 and 2.273 mm in the external test set. The proposed deep learning models showed promise as reliable methods for automating the detection and segmentation of the uterine fibroids, particularly those of clinical relevance.

Retrospective cohort study on the efficacy and safety of high-intensity focused ultrasound in non-invasive treatment of uterine leiomyomas and adenomyosis

To assess the advantages of High-Intensity Focused Ultrasound (HIFU) in the treatment of uterine leiomyomas and adenomyosis. Patients with uterine leiomyomas (435 cases) and adenomyosis (78 cases) treated in our hospital from March 2020 to October 2023 were selected to receive non-invasive treatment with HIFU. Clinical symptom improvement and fibroid shrinkage were observed, and the incidence of complications and adverse reactions during and after treatment were analyzed. The success rate of HIFU treatment in 435 cases of uterine leiomyomas was as high as 94.71%. The success rate of HIFU treatment was 96.15% in 78 cases of adenomyosis. Compared with before treatment, the improvement of clinical symptoms and the reduction of leiomyomas at one month, three months and six months after treatment were relatively better than those at the treatment period (P < 0.05). There were no serious adverse reactions in the patients during the treatment. The noninvasive application of HIFU on leiomyomas and adenomyosis effectively improves the clinical symptoms of patients, and the volume of fibroids decreases significantly. At the same time, HIFU is safe and worthy of clinical application.

The value of multiparametric MRI-based habitat imaging for differentiating uterine sarcomas from atypical leiomyomas: a multicentre study

To explore the feasibility of multiparametric MRI-based habitat imaging for distinguishing uterine sarcoma (US) from atypical leiomyoma (ALM). This retrospective study included the clinical and preoperative MRI data of 69 patients with US and 225 patients with ALM from three hospitals. At both the individual and cohort levels, the K-means and Gaussian mixture model (GMM) algorithms were utilized to perform habitat imaging on MR images, respectively. Specifically, T2-weighted images (T2WI) and contrast-enhanced T1-weighted images (CE-T1WI) were clustered to generate structural habitats, while apparent diffusion coefficient (ADC) maps and CE-T1WI were clustered to create functional habitats. Parameters of each habitat subregion were extracted to construct distinct habitat models. The integrated models were constructed by combining habitat and clinical independent predictors. Model performance was assessed using the area under the curve (AUC). Abnormal vaginal bleeding, lactate dehydrogenase (LDH), and white blood cell (WBC) counts can serve as clinical independent predictors of US. The GMM-based functional habitat model at the cohort level had the highest mean AUC (0.766) in both the training and validation cohorts, followed by the GMM-based structural habitat model at the cohort level (AUC = 0.760). Within the integrated models, the K-means functional habitat model based on the cohort level achieved the highest mean AUC (0.905) in both the training and validation cohorts. Habitat imaging based on multiparametric MRI has the potential to distinguish US from ALM. The combination of clinical independent predictors with the habitat models can effectively improve the performance.

Pseudo-myometrial thinning in placental site trophoblastic tumors: a case series with multiparametric MRI

Placental site trophoblastic tumor (PSTT) is a rare form of gestational trophoblastic neoplasm with few previous imaging case reports. We report multiparametric MRI findings in four cases of PSTT with special emphasis on the "pseudo-myometrial thinning" underlying the tumor. We reviewed multiparametric MRI and pathologic findings in four cases of PSTT from four institutions. Signal intensity, enhancement pattern, margins, and location of the tumors were evaluated, and myometrial thickness underlying the tumor and normal myometrial thickness contralateral to the tumor were measured on MRI. The myometrial thickness underlying the tumor was also measured in the resected specimen and compared with the myometrial thickness measured on MRI using the Friedman test. All tumors showed heterogeneous signal intensity on T1-weighted imaging, T2-weighted imaging (T2WI), and diffusion-weighted imaging. Three of the four tumors had a hypervascular area on dynamic contrast-enhanced (DCE) MRI. A hypointense rim on T2WI and DCE-MRI was seen in all tumors. All tumors protruded into the uterine cavity to varying degrees and extended into the myometrium close to the serosa. The myometrial thickness underlying the tumor measured on MRI (median thickness, 1.2 mm) was significantly thinner than that measured on pathology (median thickness, 9.5 mm) and normal myometrial thickness contralateral to the tumor on MRI (median thickness, 10.3 mm) (P = 0.02), and there was no significant difference between the latter two. The thickness of the myometrium underlying the tumor on MRI was approximately one tenth of the thickness on pathology. Thus, the tumors appeared to have almost transmural invasion even when pathologically located within the superficial myometrium. This "pseudo-thinning" of the underlying myometrium and the hypointense rim on MRI could be caused by focal compression of the myometrium by the tumor, possibly due to the fragility of the myometrium at the placental site.

Tumor and metastatic lymph nodes metabolic activity on 18F-FDG-PET/CT to predict progression-free survival in locally advanced cervical cancer

The present study investigated the predictive diseases progression value of preoperative fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) in patients with local advanced cervical cancer (LACC). In total, 267 patients [median age 58 (range: 27-85) years old] with LACC underwent The median follow-up was 36.52 (range: 3.09-61.29) months. During the observation period, 80 (30.0%) patients exhibited disease progression. Univariate analysis showed that FIGO stage, concurrent chemoradiotherapy (CRT), serum level of carcinoembryonic antigen (CEA) and squamous cell carcinoma antigen (SCC-Ag), primary tumor MTV (pMTV) and TLG (pTLG), lymph nodes SUV Pretreatment cervical and lymph nodes metabolic parameters were associated with PFS in patients with LACC.

Borderline epithelial ovarian tumors: what the radiologist should know

Ovarian borderline tumors are neoplasms of epithelial origin that are typically present in young patients and tend to have a less aggressive clinical course than malignant tumors. Accurate diagnosis and staging of borderline tumors has important prognostic and management implications (like fertility-sparing procedures) for women of child-bearing age. This article will review the sonographic, CT, and MRI features of borderline epithelial ovarian tumors with histopathologic correlation. Borderline tumors have less soft tissue and thinner walls/septations than malignant tumors. Serous borderline tumors more commonly have papillary projections, which can simulate the appearance of a sea anemone. Mucinous borderline tumors often are larger, multi-cystic, and more commonly unilateral. The borderline mucinous tumors may also present with pseudomyxoma peritonei, which can make it difficult to distinguish from malignant mucinous carcinoma. Ultrasound is usually the first-line modality for imaging these tumors with MRI reserved for further characterizing indeterminate cases. CT is best used to stage tumors for both locoregional and distant metastatic disease. Overall, however, the imaging features overlap with both benign and malignant ovarian tumors. Despite this, it is important for the radiologist to be familiar with the imaging appearances of borderline tumors because they can present in younger patients and may benefit from different clinical/surgical management.

Preoperative prediction of miliary changes in the small bowel mesentery in advanced high-grade serous ovarian cancer using MRI radiomics nomogram

To develop and validate an MRI-based radiomics nomogram for the preoperative prediction of miliary changes in the small bowel mesentery (MCSBM) in advanced high-grade serous ovarian cancer (HGSOC). One hundred and twenty-eight patients with pathologically proved  advanced HGSOC (training cohort: n = 91; validation cohort: n = 37) were retrospectively included. All patients were initially evaluated as MCSBM-negative by preoperative imaging modalities but were finally confirmed by surgery and histopathology (MCSBM-positive: n = 53; MCSBM-negative: n = 75). Five radiomics signatures were built based on the features from multisequence magnetic resonance images. Independent clinicoradiological factors and radiomics-fusion signature were further integrated to construct a radiomics nomogram. The performance of the nomogram was assessed using receiver operating characteristic (ROC) curves, calibration curves and clinical utility. Radiomics signatures, ascites, and tumor size were independent predictors of MCSBM. A nomogram integrating radiomics features and clinicoradiological factors demonstrated satisfactory predictive performance with areas under the curves (AUCs) of 0.871 (95% CI 0.801-0.941) and 0.858 (95% CI 0.739-0.976) in the training and validation cohorts, respectively. The net reclassification index (NRI) and integrated discrimination improvement (IDI) revealed that the nomogram had a significantly improved ability compared with the clinical model in the training cohort (NRI = 0.343, p = 0.002; IDI = 0.299, p < 0.001) and validation cohort (NRI = 0.409, p = 0.015; IDI = 0.283, p = 0.001). Our proposed nomogram has the potential to serve as a noninvasive tool for the prediction of MCSBM, which is helpful for the individualized assessment of advanced HGSOC patients.

Radiomics and radiogenomics in ovarian cancer: a literature review

Ovarian cancer remains one of the most lethal gynecological cancers in the world despite extensive progress in the areas of chemotherapy and surgery. Many studies have postulated that this is because of the profound heterogeneity that underpins response to therapy and prognosis. Standard imaging evaluation using CT or MRI does not take into account this tumoral heterogeneity especially in advanced stages with peritoneal carcinomatosis. As such, newly emergent fields in the assessment of tumor heterogeneity have been proposed using radiomics to evaluate the whole tumor burden heterogeneity as opposed to single biopsy sampling. This review provides an overview of radiomics, radiogenomics, and proteomics and examines the use of these newly emergent fields in assessing tumor heterogeneity and its implications in ovarian cancer.

Endometriosis in pregnancy

Endometriosis constitutes the presence of ectopic endometrial glands and stroma outside the uterine endometrium, which is hormonally responsive and responds to pregnancy hormones as well. Decidualization is a physiologic process, where the normal endometrium readies itself for optimal accommodation of a pregnancy. A similar hormonal response can be seen with ectopic endometrium as well. As such, ovarian endometriomas and deep endometriosis implants can undergo decidualization. Overall, the progestational state of pregnancy favors an improvement in endometriosis, however, decidualization can lead to findings that can lead to increased size of endometriomas and deep infiltrative endometriosis implants, changes in imaging appearance and even complications, such as spontaneous hemoperitoneum in pregnancy. Awareness of this process can help prevent misdiagnosis of decidualized endometriomas as ovarian malignancy and recognize common imaging manifestations of hormonal effects of pregnancy on endometriosis.

Differentiation of borderline tumors from type I ovarian epithelial cancers on CT and MR imaging

To investigate the value of CT and MR imaging features in differentiating borderline ovarian tumor (BOT) from type I ovarian epithelial cancer (OEC), which could be significant for suitable clinical treatment and assessment of the prognosis of the patient. Thirty-three patients with BOTs and 35 patients with type I OECs proven by pathology were retrospectively evaluated. The clinico-pathological information (age, premenopausal status, CA-125, and Ki-67) and imaging characteristics were compared between two groups of ovarian tumors. The diagnostic performance of the imaging features was evaluated using receiver operating characteristic analysis. The best predictor variables for type I EOCs were recognized via multivariate analyses. BOTs are more likely to involve younger patients and frequently show lower CA-125 values and lower proliferation indices (Ki-67 < 15%) than type I OECs. Compared with type I OECs, BOTs were more often purely cystic (15/33, 45.45% vs. 1/35, 2.86%; p < 0.001) and displayed less frequent mural nodules (16/33, 48.48% vs. 28/35, 80.00%; p = 0.007), less frequently unclear margin (3/33, 9.09% vs. 11/35, 31.43%; p = 0.023), smaller solid portion (0.56 ± 2.66 vs. 4.51 ± 3.88; p < 0.001), and thinner walls (0.3 ± 0.17 vs. 0.55 ± 0.24; p < 0.001). The maximum wall thickness presented the largest area under the curve (AUC, 0.848). Multivariate analysis revealed that the solid portion size (OR 10.822, p = 0.002) and maximum wall thickness (OR 9.130, p = 0.001) were independent indicators for the differential diagnosis between the two groups of lesions. The solid portion size and maximum wall thickness significantly influenced the classification of the two groups of ovarian tumors.

Intra- and peritumoral radiomics for predicting early recurrence in patients with high-grade serous ovarian cancer

To explore values of intra- and peritumoral CT-based radiomics for predicting recurrence in high-grade serous ovarian cancer (HGSOC) patients. This study enrolled 110 HGSOC patients from our hospital between Aug 2017 and Apr 2021. All patients underwent contrast-enhanced CT scans before treatment. The least absolute shrinkage and selection operator (LASSO) regression was used to select radiomics features from intra- and peritumoral areas. Radiomics signatures were built based on selected features from Intra-RS, Peri-RS, and in Com-RS. A nomogram was constructed by combining radiomics signatures and clinical parameters with predictive potential. Receiver operating characteristics (ROC), calibration, and decision curve analyses (DCA) curves were used to evaluate performance of the nomogram. The intra- and peritumoral combined Com-RS showed effective ability in predicting recurrent HGSOC in the training (AUCs, Intra-RS vs. Peri-RS vs. Com-RS, 0.861 vs. 0.836 vs. 899) and validation (AUCs, Intra-RS vs. Peri-RS vs. Com-RS, 0.788 vs. 0.762 vs. 815) cohort. The Federation of International of FIGO stage, menstruation, and location were found to be strongly associated with tumor recurrence. The nomogram has the best predictive ability in the training (AUCs, Com-RS vs. clinical model vs. nomogram, 0.899 vs. 0.648 vs. 0.901) and validation (AUCs, Com-RS vs. clinical model vs. nomogram, 0.815 vs. 0.666 vs. 0.818) cohort. Our findings suggested values of intra- and peritumoral-based radiomics for predicting recurrent HGSOC. The constructed nomogram may be of importance in clinical application.

The efficiency of susceptibility-weighted MRI in the differentiation of endometriomas from haemorrhagic ovarian cysts

The aim of the study was to investigate the efficiency of susceptibility-weighted magnetic resonance (MR) imaging (SWIs) in differentiating endometriomas from haemorrhagic ovarian cysts. Between July 2017 and January 2019, 89 ovarian cystic lesions (57 endometriomas and 32 haemorrhagic cysts) that were identified as complicated cystic lesions on ultrasonography (US) and underwent lower abdominal MRI with susceptibility weighting were retrospectively evaluated. Final diagnoses were obtained with surgical pathological correlation and radiological-clinical follow-up. Two radiologists blinded to the final diagnoses retrospectively reviewed the images in consensus. The signal intensity on T1- and T2-weighted images and curved linear or punctate signal void areas on SWI were noted for the presence of lesions. Forty of the 57 endometriomas demonstrated the defined MRI criteria, including a cystic hyperintensity on T1-weighted images and hypointensity on T2-weighted images. The remaining 17 lesions did not demonstrate these criteria on conventional MR images. SWI showed punctate or curved linear signal void areas in 53 of 57 endometriomas (92.9%) and none of the haemorrhagic cysts. The sensitivity, specificity and accuracy of SWI in differentiating endometrioma from haemorrhagic cyst were 92.9%, 100.0%, and 95.5%, respectively. The addition of the SWI sequence to conventional MRI can help distinguish endometriomas from haemorrhagic ovarian cysts.

Vaginal recurrence of endometrial cancer: MRI characteristics and correlation with patient outcome after salvage radiation therapy

Abstract Purpose To evaluate MRI characteristics in vaginal recurrence of endometrial cancer (EC) including tumor volume shrinkage during salvage radiotherapy, and to identify imaging features associated with survival. Methods Patients with vaginal recurrence of EC treated with external beam radiotherapy (EBRT) followed by brachytherapy (BT), and with available pelvic MRI at two time points: baseline and/or before BT were retrospectively identified from 2004 to 2017. MRI features including recurrence location and tissue characteristics on T2- and T1-weighted images were evaluated at baseline only. Tumor volumes were measured both at baseline and pre-BT. Survival rates and associations were evaluated by Cox regression and Fisher’s exact test, respectively. Results Sixty-two patients with 36 baseline and 50 pre-BT pelvic MRIs were included (24/62 with both MRIs). Vaginal recurrence of EC was most commonly located in the vaginal apex (27/36, 75%). Tumors with a post-contrast enhancing peripheral rim or low T2 signal rim at baseline showed longer recurrence-free survival (RFS) (HR 0.2, 95% CI 0.1–0.9, P &lt; 0.05 adjusted for histology; HR 0.2, 95% CI 0.1–0.8, P &lt; 0.05, respectively). The median tumor shrinkage at pre-BT was 69% (range 1–99%). Neither absolute tumor volumes nor volume regression at pre-BT were associated with RFS. Lymphovascular space invasion (LVSI) at hysterectomy and adjuvant RT were associated with recurrence involving the distal vagina (both P &lt; 0.05). Conclusion Vaginal recurrences with rim enhancement at baseline MRI predicted improved RFS, while tumor volume shrinkage at pre-BT did not. Distal vaginal recurrence was more common in patients with LVSI and adjuvant RT at EC diagnosis.

Can conventional DWI accurately assess the size of endometrial cancer?

AbstractPurposeTo compare T2-weighted image (T2WI) and conventional Diffusion-weighted image (cDWI) of magnetic resonance imaging (MRI) for sensitivity of qualitative diagnosis and accuracy of tumor size (TS) measurement in endometrial cancer (EC). Meanwhile, the effect of the lesion size itself and tumor grade on the ability of T2WI and cDWI of TS assessment was explored. Ultimately, the reason of deviation on size evaluation was studied.Materials and methods34 patients with EC were enrolled. They were all treated with radical hysterectomy and performed MR examinations before operation. Firstly, the sensitivity of T2WI alone and T2WI–DWI in qualitative diagnosis of EC were compared according to pathology. Secondly, TS on T2WI and cDWI described with longitudinal (LD) and horizontal diameter (HD) were compared to macroscopic surgical specimen (MSS) quantitatively in the entire lesions and the subgroup lesions which grouped by postoperative tumor size itself and tumor grade. Thirdly, the discrepancy of mean ADC values (ADC mean) and range ADC values (ADC range) between different zones of EC were explored.ResultsFor qualitative diagnosis, the sensitivity of T2WI–DWI (97%) was higher than T2WI alone (85%) (p = 0.046).For TS estimation, no significant difference (PLD = 0.579; PHD = 0.261) was observed between T2WI (LDT2WI = 3.90 cm; HDT2WI = 2.88 cm) and MSS (LD = 4.00 cm; HD = 3.06 cm), whereas TS of cDWI (LDDWI = 3.01 cm; HDDWI = 2.54 cm) were smaller than MSS (PLD = 0.002; PHD = 0.002) in all lesions. In subgroup of tumor with G1 (grade 1) and small lesion (defined as maximum diameter &lt; 3 cm), both T2WI and cDWI were not significantly different from MSS; In subgroup of tumor with G2 + 3 (grade 2 and grade 3) and big lesion (maximum diameter ≥ 3 cm), T2WI matched well with MSS still, but DWI lost accuracy significantly. The result of ADC values between different zones of tumor showed ADC mean of EC rose from central zone to peripheral zone of tumor gradually and ADC range widened gradually.ConclusioncDWI can detect EC very sensitively. The TS on cDWI was smaller than the fact for the ECs with G2/3 and big size. The TS of T2WI was in accordance with the actual size for all ECs. The heterogeneity may be responsible for the inaccuracy of cDWI.

Assessing CT imaging features combined with CEA and CA125 levels to identify endometriosis-associated ovarian cancer

To improve the diagnosis and identification of ovarian clear cell carcinoma (CCC) and ovarian endometrioid carcinoma (EC), we evaluated CT imaging findings and cut-off values for CEA and CA125. The CT features and tumour markers (tumour size, location, morphology, composition, number of cysts, growth pattern of the mural nodules, mural nodule HWR, enhancement of the mural nodules, ascites, complications, CEA level, CA125 level) of 55 tumours in 52 patients with CCC, confirmed by surgery and pathology at the Yunnan Cancer Hospital from January 1, 2012 to December 30, 2018, were compared with those of 41 tumours in 36 patients with EC. All patients had a long history of endometriosis. Statistical analysis was performed using t test, chi-square test, Mann-Whitney U test, univariate analysis, multivariate logistic regression analysis and receiver-operating characteristic (ROC) curves. CCC and EC presented as large oval or irregular mixed cystic-solid masses in the pelvic region, with moderately delayed enhancement of the solid components. There was a statistically significant difference between the number of cysts, the growth pattern of the mural nodules, the presence/absence of ascites, and the levels of CEA and CA125 (P < 0.05). Most CCCs had unilocular cysts, mural nodules that were polypoid structures, and no ascites (46/55, 33/55, 42/55); most ECs had multilocular cysts and broad-based nodular structures and were ascites positive (28/41, 31/41, 21/41). The CEA positive rate was lower in the CCC group than in the EC group (2/52, 3.8% versus 11/36, 30.6%, P < 0.05), and the CA125 positive rate was high in both the CCC and EC groups (44/52, 84.6% versus EC = 35/36, 97.2%, P = 0.118). The ROC curves revealed that when the values of CEA and CA125 were higher than the cut-off values (CEA = 3.270 µg/L, CA125 = 589.400 kU/L), the diagnostic efficiency of CEA was 0.723, and the diagnostic specificity of CEA was as high as 0.903. The number of cysts, growth pattern of the mural nodules, presence/absence of ascites, and levels of CEA and CA125 were useful factors for distinguishing CCC from EC; the best cut-off values of CEA and CA125 for distinguishing CCC from EC were 3.270 and 589.40, respectively. These findings may be helpful for correctly diagnosing and identifying CCC and EC.

Adenocarcinoma of the uterine cervix, gastric-type (GAS): a review of the literature focused on pathology and multimodality imaging

Adenocarcinoma of the uterine cervix, gastric-type (GAS) is a rare, well-differentiated subtype of HPV-independent endocervical adenocarcinoma. It classically arises in middle-aged women with symptoms, including profuse watery vaginal discharge and abnormal uterine bleeding. Given the rarity of this disease, misdiagnosis is common and prognosis remains poorly defined. Distinct pathology and imaging findings can aid in diagnosis. A literature review was performed to ascertain recurring pathologic and radiologic characteristics of GAS. Key pathologic features of GAS include cytologically benign appearing mucinous glands that infiltrate into the deep stroma and may demonstrate lymphovascular or perineural invasion. Multiple imaging modalities including transvaginal ultrasound, CT, and MRI may aid in diagnosis of GAS, which characteristically is seen as a multicystic mass with solid components. MRI in particular is the preferred imaging study because it offers the best chance of identifying a potential solid component, which is key to making the diagnosis of GAS and distinguishing it from other endocervical diseases processes. Careful attention to histopathologic and radiologic details, in conjunction with clinical correlation, is necessary to distinguish GAS from other multicystic cervical lesions.

Fallopian fimbriae entrapped in an ovarian endometriotic cyst mimicking malignancy: a case report

Ovarian endometriotic cysts are associated with an increased risk of clear cell and endometrioid carcinomas, as well as borderline neoplasms. Although contrast-enhancing nodules on magnetic resonance imaging (MRI) suggest malignancy, benign endometriotic cysts can also present with such features, complicating differentiation from malignancy. When malignancy is suspected, minimally invasive procedures, such as laparoscopic cystectomy, are typically avoided. However, preserving fertility and ovarian function warrants careful consideration when selecting invasive surgical procedures. From the perspective of selecting appropriate surgical approaches, accurate preoperative differentiation between benign and malignant ovarian tumors is essential. We present the first case of MRI showing fallopian fimbriae entrapped in an endometriotic cyst mimicking malignancy. A 49-year-old female presented with atypical genital bleeding. MRI revealed a right ovarian endometriotic cyst with a contrast-enhancing mural nodule (10 mm), suggestive of malignancy. The nodule demonstrated T2-weighted hypointensity equivalent to the cyst fluid without diffusion restriction. Laparotomy revealed the nodule as entrapped fallopian fimbriae within the endometriotic cyst, with no malignancy detected. In this case, the fallopian fimbriae entrapped in the endometriotic cyst appeared as an enhancing nodule because of their vascularity, mimicking malignancy. Fallopian fimbriae are inconspicuous structures that can produce false findings suggestive of malignancy, similar to other benign enhancing nodules, such as polypoid endometriosis and decidualization. However, their lack of diffusion restriction and low T2-weighted signal intensity may help distinguish them from malignancy. This knowledge is crucial for accurate diagnosis and avoiding unnecessary interventions.

Development and validation of ADC-based nomogram model for predicting the prognostic factors in preoperative clinical early-stage cervical cancer patients

To investigate the feasibility of ADC-based nomogram models for predicting cervical cancer (CC) subtype, lymphovascular space invasion (LVSI) and lymph node metastases (LNM) status in preoperative clinical early-stage CC patients. A total of 535 CC patients from three independent centers [center A (n = 251) for model training, and centers B (n = 193) and C (n = 91) for external validation] were included. Volumetric ADC histogram metrics (volume, minADC, meanADC, maxADC, skewness, kurtosis, entropy, P10_ADC, P25_ADC, P50_ADC, P75_ADC, and P90_ADC) derived the whole-tumor were calculated. Univariate and multivariate analyses were used to screen the independent predictors and develop nomogram models, with the area under the receiver operating characteristic curve (AUC) for predicting performance estimation. In differentiating adenosquamous carcinoma (ASC)/adenocarcinoma (AC) from squamous cell carcinoma (SCC), the independent predictors of P25_ADC, SCC antigen (SCC-Ag), and CA199 constructed the nomogram_1 model, with AUCs of 0.900 and 0.873 in training and validation sets, respectively. In differentiating AC from ASC, the independent predictors of P50_ADC and SCC-Ag constructed the nomogram_2 model, with AUCs of 0.837 and 0.829 in training and validation sets, respectively. Tumor volume is the only independent predictor of LVSI(+) and LNM(+), with AUCs of 0.608 and 0.694 in the training set, and 0.553 and 0.656 in the validation set, respectively. The ADC-based nomogram models can effectively predict the CC subtypes, but might be insufficient in predicting the LVSI and LNM status in preoperative clinical early-stage patients.

mpMRI-based habitat analysis for predicting prognoses in patients with high-grade serous ovarian cancer: a multicenter study

To evaluate the value of multiparametric MRI (mpMRI)-based habitat analysis for predicting prognoses in patients with high-grade serous ovarian cancer (HGSOC), and to develop combined models by integrating habitat analysis with clinical predictors. This retrospective study included 503 HGSOC patients from four centers. A K-means algorithm was used to identify voxel clusters and generate habitats on mpMRI. Radiomics features were extracted from each habitat sub-region. After feature selection, habitat models were developed to predict overall survival (OS) and progression-free survival (PFS). Cox regression analyses were performed to identify clinical predictors and construct clinical models. Combined models were developed by integrating habitat signatures with clinical predictors. Model performance was evaluated using C-index and time-dependent receiver operating characteristic area under the curves (AUCs). Compared with the clinical models (OS: 0.713 and 0.695; PFS: 0.727 and 0.700) and habitat models (OS: 0.707 and 0.672; PFS: 0.627 and 0.641), the combined models integrating habitat features and clinical independent predictors such as neoadjuvant chemotherapy (OS: 0.752 and 0.745; PFS: 0.784 and 0.754) achieved the highest C-indices for predicting OS and PFS in the internal validation cohort and external test cohort. The combined models also achieved the highest AUCs in all cohorts. The habitat models based on mpMRI demonstrated potential value in predicting the prognoses of HGSOC patients, but no significant advantages over the clinical models. The combined models were expected to improve the prognoses from the level of individual clinical characteristics and habitat features reflecting intratumoral heterogeneity.

A clinicoradiological model based on clinical and CT features for preoperative prediction of histological classification in patients with epithelial ovarian cancers: a two-center study

To develop and validate a clinicoradiological model integrating clinical and computed tomography (CT) features to preoperative predict histological classification in patients with epithelial ovarian cancers (EOCs). This retrospective study included 470 patients who were pathologically proven EOCs and performed by contrast enhanced CT before treatment from center I (training cohort, N = 329; internal test cohort, N = 141) and 83 EOC patients who were included as an external test cohort from center II. The univariate analysis and multivariate logistic regression analysis were used to select significant clinical and CT features. The significant clinical model was developed based on clinical characteristics. The significant radiological model was established by CT features. The significant clinical and CT features were used to construct the clinicoradiological model. Model performances were evaluated using the area under the receiver operating characteristic curve (AUC), calibration curve, the Brier score and decision curve analysis (DCA). The AUCs were compared by net reclassification index (NRI) and integrated discrimination improvement (IDI). The significant clinical and CT parameters including age, transverse diameter, morphology, margin, ascites and lymphadenopathy were incorporated to build the clinicoradioligical model. The clinicoradiological model showed relatively satisfactory discrimination between type I and type II EOCs with the AUC of 0.841 (95% confidence interval [CI] 0.797-0.886), 0.874 (95% CI 0.811-0.937) and 0.826 (95% CI 0.729-0.923) in the training, internal and external test cohorts, respectively. The NRI and IDI showed the clinicoradiological model significantly performed than those of the clinical model (all P < 0.05). No statistical significance was found between radiological and clinicoradiological model. The clinicoradiological model demonstrated optimal classification accuracy and clinical application value. The easily accessible nomogram based on the clinicoradiologic model showed favorable performance in distinguishing between type I and type II EOCs and could therefore be used to improve the clinical management of EOC patients.

Preoperative magnetic resonance evaluation of Struma Ovarii and its importance for the surgical modality: a retrospective study from two institutions

To improve preoperative diagnostic accuracy of struma ovarii by retrospectively reviewing magnetic resonance (MR) findings. It is beneficial to choose the most appropriate surgical modality for the patient. We retrospectively reviewed the clinical course and MR characteristics of 52 patients who were diagnosed postoperatively with struma ovarii, pathologically, from two institutions. All patients were performed routine and contrast enhanced MR scans. All tumors were unilateral. Forty- eight tumors (92.3%) were multicystic with variable signal intensity. On T2-weighted images, some loculi or small cysts with very low signal intensity were recognized in forty-two tumors (80.8%). The solid part of the tumor was significantly enhanced on T1-weighted enhanced image in forty-two cases (80.8%), without diffusion restriction in forty-one cases (97.6%). Diffusion restriction was observed in only one patient (2.4%). Laparoscopic surgery was performed in 32 patients (61.5%) whose preoperative diagnosis was benign or borderline. The rest 20 cases (38.5%) underwent exploratory laparotomy, including 14 cases with malignant diagnosis, 5 cases of mucinous cystadenoma and a case of giant serous cystadenoma. A mass composed of multiple cysts with variable signal intensity, some loculi or small cysts with very low signal intensity on T2-weighted image and the solid part of the tumor significantly enhanced on T1-weighted enhanced image without diffusion restriction are appeared to be the characteristic MR findings of struma ovarii. Accurate preoperative diagnosis of struma ovarii is beneficial to choose the most appropriate surgical approach for the patient.

The added value of apparent diffusion coefficient assessments in O-RADS MRI evaluation for characterizing ovarian masses with solid components

Integrating diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) measurements with existing MR imaging protocols improves the differentiation between benign and malignant adnexal lesions. We aimed to assess the additional value of quantitative ADC in diagnosing adnexal masses classified by the O-RADS-MRI score and evaluate the impact on diagnostic performance. This retrospective cohort study analyzed 159 patients with 218 ovarian masses, classified into benign, borderline, and malignant groups via histopathological evaluation. We examined MRI parameters, including solid component size and signal intensity, time-intensity curves (TICs), ADC values and O-RADS categories. Receiver Operating Characteristic (ROC) curve analysis determined optimal ADC cut-off values for differentiating tumor classifications. The optimal cut-off values for the ADC between O-RADS MRI categories 3-4, and 4-5, were 1.36 × 10⁻³ mm²/sec and 0.99 × 10⁻³ mm²/sec respectively. the introduction of ORADS-ADC classification, utilizing these ADC cut-offs demonstrated superior diagnostic performance compared to traditional O-RADS, with improvements observed across several metrics: in ORADS-ADC 3-4 sensitivity increases from 69.2 to 94.12%, specificity from 88.4 to 98.36%, and accuracy from 76.0 to 96.84%. Similarly, in ORADS-ADC 4-5 sensitivity increases from 91.8 to 95.12%, specificity from 62.3 to 97.06%, and accuracy from 78.9 to 95.54%. Incorporating DWI and ADC measurements into the O-RADS MRI classification system significantly improves ovarian tumor classification. The ORADS-ADC model markedly increases diagnostic accuracy, enhancing both sensitivity and specificity compared to traditional O-RADS, which consequently enhances clinical and therapeutic management resulting in better patient outcomes during surgical planning.

Diagnostic performance of Node-RADS on MRI for a standardized assessment of lymph node metastasis in ovarian cancer

The Node-RADS score was proposed and provided a standardized, comprehensive assessment of lymph nodes (LNs), accounting for both size and configuration criteria. This study aimed to evaluate the diagnostic performance of the Node-RADS in LN metastasis of ovarian cancer (OC). From December 2018 to April 2023, 81 OC patients who underwent MRI and debulking surgery were included. The likelihood of LN metastasis was assessed by the Node-RADS with MRI. The chi-square test and Fisher's exact test were used to assess the differences in size and configuration between LNs with and without metastasis. The diagnostic performance of Node-RADS and its different criteria for LN metastasis was assessed with receiver operating characteristic (ROC) and area under the curve (AUC). Among all Node-RADS evaluation criteria, textural changes had the best performance with a sensitivity of 84.6%, a specificity of 78.7%, and a Youden's index of 0.63. At the LN level, the incidence of LN metastasis with Node-RADS scores 1, 2, 3, 4, and 5 was 3.2%, 4.5%, 13.0%, 85.7%, and 86.7%, respectively. The best performance in assessing LN status was observed at Node-RADS scores > 3, with sensitivity, specificity, and Youden's index of 73.1%, 97.8%, and 0.71, respectively. In addition, at the patient and LN levels, the AUC for Node-RADS assessment of LNs was 0.869 and 0.895, respectively. Node-RADS could be an appropriate choice for structured reporting of LN metastasis in OC. The diagnostic performance of LN metastasis in OC at a Node-RADS score > 3 was satisfactory.

Serous borderline ovarian tumor and low-grade serous ovarian cancer

Epithelial ovarian cancer (EOC) is the most frequent histological subtype of ovarian cancer, accounting for 95% of ovarian cancer. Radiologists are familiar with the imaging appearances of high-grade serous ovarian cancer (HGSOC) that accounts for about 70% of EOC. Low grade serous ovarian cancer (LGSOC) represents 2-5% of ovarian carcinomas and 5-10% of serous ovarian carcinoma. Historically, it was thought that LGSOC and HGSOC were a continuum. It is now clear that these are two completely separate entities. They have different molecular biology and clinical course. As a result of the low prevalence of LGSOC, there is limited data on its imaging findings. In this paper, we illustrate the pathology, molecular biology and treatment options of LGSOC. We present imaging appearances of LGSOC of primary tumor and metastasis in a cohort of 33 patients with pathologically-proven LGSOC. We also elucidate the differences between LGSOC and HGSOC. Since LGSOC often arise from serous borderline ovarian tumors (SBOT), we describe the imaging appearances of SBOT and highlight the differences between these two entities.

The utility of low-dose pre-operative CT of ovarian tumor with artificial intelligence iterative reconstruction for diagnosing peritoneal invasion, lymph node and hepatic metastasis

Diagnosis of peritoneal invasion, lymph node metastasis, and hepatic metastasis is crucial in the decision-making process of ovarian tumor treatment. This study aimed to test the feasibility of low-dose abdominopelvic CT with an artificial intelligence iterative reconstruction (AIIR) for diagnosing peritoneal invasion, lymph node metastasis, and hepatic metastasis in pre-operative imaging of ovarian tumor. This study prospectively enrolled 88 patients with pathology-confirmed ovarian tumors, where routine-dose CT at portal venous phase (120 kVp/ref. 200 mAs) with hybrid iterative reconstruction (HIR) was followed by a low-dose scan (120 kVp/ref. 40 mAs) with AIIR. The performance of diagnosing peritoneal invasion and lymph node metastasis was assessed using receiver operating characteristic (ROC) analysis with pathological results serving as the reference. The hepatic parenchymal metastases were diagnosed and signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were measured. The perihepatic structures were also scored on the clarity of porta hepatis, gallbladder fossa and intersegmental fissure. The effective dose of low-dose CT was 79.8% lower than that of routine-dose scan (2.64 ± 0.46 vs. 13.04 ± 2.25 mSv, p < 0.001). The low-dose AIIR showed similar area under the ROC curve (AUC) with routine-dose HIR for diagnosing both peritoneal invasion (0.961 vs. 0.960, p = 0.734) and lymph node metastasis (0.711 vs. 0.715, p = 0.355). The 10 hepatic parenchymal metastases were all accurately diagnosed on the two image sets. The low-dose AIIR exhibited higher SNR and CNR for hepatic parenchymal metastases and superior clarity for perihepatic structures. In low-dose pre-operative CT of ovarian tumor, AIIR delivers similar diagnostic accuracy for peritoneal invasion, lymph node metastasis, and hepatic metastasis, as compared to routine-dose abdominopelvic CT. It is feasible and diagnostically safe to apply up to 80% dose reduction in CT imaging of ovarian tumor by using AIIR.

Endometriosis: assessment on O-RADS and risk of malignant transformation

Endometriosis is a common disease, affecting approximately 10% of women of reproductive age. Several intersecting guidelines and consensus statements provide information on imaging diagnosis and surveillance strategies for endometriomas. SRU consensus panel recommendations provide information on initial detection of endometriosis on routine pelvic imaging. Revised American Society of Reproductive Medicine (rASRM) classification, the #ENZIAN classification, and the deep pelvic endometriosis index (dPEI) aim to assess the overall extent of disease and assist in presurgical planning. The Ovarian-Adnexal Reporting and Data System (O-RADS) aims to risk stratify lesions evaluated with US or MR based on their imaging morphology, from typical benign lesions to atypical presentations and malignant transformation. Emerging data shows increased risk of ovarian cancer in patients with endometriosis, especially following menopause and in those patients with long standing endometriosis. (Chen et al. in Front Oncol. 14:1329133, 2024;Streuli et al. in Climacteric. 20:138-143, 2017;Secosan et al. in Diagnostics (Basel). 10:134, 2020;Inceboz in Womens Health (Lond Engl). 11:711-715, 2015;Cassani et al. in Maturitas. 190, 2024;Gemmell et al. in Hum Reprod Update. 23:481-500, 2017;Giannella et al. in Cancers (Basel). 13:4026, 2021;) Current O-RADS guidelines mandate follow-up of endometriomas up to 2 years with further follow-up based on clinical factors. No consensus guidelines exist for imaging surveillance of patients with deep endometriosis from a malignancy standpoint. This review explores the imaging appearance of endometriomas, imaging features of malignant transformation, surveillance strategies and gaps in current literature, and attempts to better understand the risk of malignancy and to encourage further research for long-term imaging surveillance of endometriosis patients.

Ovarian masses suggested for MRI examination: assessment of deep learning models based on non-contrast-enhanced MRI sequences for predicting malignancy

We aims to assessed and compare four deep learning(DL) models using non-contrast-enhanced magnetic resonance imaging(MRI) to differentiate benign from malignant ovarian tumors, considering diagnostic efficacy and associated development costs. 526 patients (327 benign lesions vs 199 malignant lesions) who were recommended for MRI due to suspected ovarian masses, confirmed with histopathology, were included in this retrospective study. A training cohort (n=367) and a validation cohort (n=159) were constructed. Based on the images of T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), we evaluated the diagnostic performance of four DL models (ConvNeXt, FBNet, GhostNet, ResNet50) in distinguishing between benign and malignant ovarian tumors. Two radiologists with varying levels of experience independently reviewed all original non-contrast-enhanced MR images from the validation cohort to determine if each case was benign or malignant. The area under the receiver operating characteristic curve (AUC), confusion matrices, accuracy, sensitivity, specificity, positive predictive value(PPV) and negative predictive value(NPV) were used to compare performance. The study of 526 ovarian mass patients (ages 1-92) evaluated four DL models for predicting malignant tumors, with AUCs ranging from 0.8091 to 0.8572 and accuracy between 81.1% and 85.5%. An experienced radiologist achieved 86.2% accuracy, slightly surpassing the DL models, while a less experienced radiologist had 69.2% accuracy. Resnet50 had the highest sensitivity (78.3%) and NPV (87.3%), while ConvNeXt excelled in specificity and PPV (100%). GhostNet and FBNet are more parameter-efficient than other models. The four DL models effectively distinguished between benign and malignant ovarian tumors using non-contrast MRI. These models outperformed less experienced radiologists and were slightly less accurate than experienced ones. ResNet50 had the best predictive performance, while GhostNet was highly accurate with fewer parameters. Our study indicates that DL models based on non-contrast-enhanced MRI have the potential to assist in diagnosis.

Multiple perception contrastive learning for automated ovarian tumor classification in CT images

Ovarian cancer is among the most common malignant tumours in women worldwide, and early identification is essential for enhancing patient survival chances. The development of automated and trustworthy diagnostic techniques is necessary because traditional CT picture processing mostly depends on the subjective assessment of radiologists, which can result in variability. Deep learning approaches in medical image analysis have advanced significantly, particularly showing considerable promise in the automatic categorisation of ovarian tumours. This research presents an automated diagnostic approach for ovarian tumour CT images utilising supervised contrastive learning and a Multiple Perception Encoder (MP Encoder). The approach incorporates T-Pro technology to augment data diversity and simulates semantic perturbations to increase the model's generalisation capability. The incorporation of Multi-Scale Perception Module (MSP Module) and Multi-Attention Module (MA Module) enhances the model's sensitivity to the intricate morphology and subtle characteristics of ovarian tumours, resulting in improved classification accuracy and robustness, ultimately achieving an average classification accuracy of 98.43%. Experimental results indicate the method's exceptional efficacy in ovarian tumour classification, particularly in cases involving tumours with intricate morphology or worse picture quality, thereby markedly enhancing classification accuracy. This advanced deep learning framework proficiently tackles the complexities of ovarian tumour CT image interpretation, offering clinicians enhanced diagnostic support and aiding in the optimisation of early detection and treatment strategies for ovarian cancer.

Inter-reader reliability of Ovarian-Adnexal Reporting and Data System US: a systematic review and meta-analysis

Ovarian-Adnexal Reporting and Data System (O-RADS) US provides a standardized lexicon for ovarian and adnexal lesions, facilitating risk stratification based on morphological features for malignancy assessment, which is essential for proper management. However, systematic determination of inter-reader reliability in O-RADS US categorization remains unexplored. This study aimed to systematically determine the inter-reader reliability of O-RADS US categorization and identify the factors that affect it. Original articles reporting the inter-reader reliability of O-RADS US in lesion categorization were identified in the MEDLINE, EMBASE, and Web of Science databases from January 2018 to December 2023. DerSimonian-Laird random-effects models were used to determine the meta-analytic pooled inter-reader reliability of the O-RADS US categorization. Subgroup meta-regression analysis was performed to identify the factors causing study heterogeneity. Fourteen original articles with 5139 ovarian and adnexal lesions were included. The inter-reader reliability of O-RADS US in lesion categorization ranged from 0.71 to 0.99, with a meta-analytic pooled estimate of 0.83 (95% CI, 0.78-0.88), indicating almost perfect reliability. Substantial study heterogeneity was observed in the inter-reader reliability of the O-RADS US categorization (I The O-RADS US risk stratification system demonstrated almost perfect inter-reader reliability in lesion categorization. Our results highlight the importance of targeted training and descriptor simplification to improve inter-reader reliability and clinical adoption.

Size threshold as a risk for malignant transformation in typical ovarian dermoid lesions: a scoping review

The O-RADS malignancy risk stratification of typical ovarian dermoid cysts by using a 10 cm threshold is based on expert consensus rather than analysis of objective clinical data. This comprehensive scoping review consolidated all currently available studies evaluating typical benign ovarian dermoid cyst size and risk for malignant transformation. A systematic review of MEDLINE, Embase, Scopus and the Cochrane library was performed from inception to January 14, 2024, using PRISMA-ScR guidelines. A grey literature search and forward searching of reference lists from included studies were performed. Case reports and case series evaluating dermoid cyst size and malignant transformation as defined by a pathological reference standard were included. Data synthesis was provided as a qualitative review of the existing literature. Twenty-five studies were included in qualitative synthesis comprising 6 case reports and 19 retrospective studies with a total of 15,295 dermoid cysts. Of these, 215 lesions demonstrated malignant transformation. Studies reporting dermoid size with malignant transformation ranged from 1 to 32 cm with 46/173 (27%) total malignant transformation lesions measuring  1 cm when described. More than 25% of dermoid cysts with malignant transformation may be classified as "almost certainly benign" with the current 10 cm O-RADS malignancy risk threshold. Although surveillance of O-RADS 2 dermoid cysts may improve sensitivity, modifying a caveat recommendation for MRI O-RADS +/- gyn-oncologist referral when potentially solid components are present in otherwise typically benign dermoid cysts may be appropriate.

Does amide proton transfer-weighted MRI have diagnostic and differential value in ovarian cystic and predominantly cystic lesion?

This study aims to evaluate the diagnostic value of amide proton transfer-weighted (APTw) imaging in distinguishing cystic or predominantly cystic ovarian lesions. 49 patients underwent APTw imaging at 3T-MR before surgery, with 20 volunteers serving as the control group. Participants were divided into the following groups: solid components of normal ovaries (Group A, n = 29), solid components of malignant lesions (Group B, n = 7), cystic fluid of follicles (Group C, n = 31), cystic fluid of benign lesions (Group D, n = 46), functional cysts (Group d1, n = 8), endometriomas (Group d2, n = 28), cystadenomas (Group d3, n = 10), and cystic fluid of malignant lesions (Group E, n = 12). Independent t-tests or Mann-Whitney U tests and one-way ANOVA were used to compare group differences. Receiver operating characteristic (ROC) analysis was used to evaluate the diagnostic efficacy in distinguishing between different lesions. For solid components, significant differences in MTRasym values were observed between Groups A and B (P < 0.001). For cystic components, significant differences were found between Groups C and D, C and E, d1 and d2, d2 and d3, d1 and d3, C and d2, C and d3, E and d1, and E and d2 (all P < 0.01). ROC analysis of these results showed high AUC values (ranging from 0.813 to 1.0), all P < 0.05. APTw can reveal differences in MTRasym values between normal and diseased ovarian tissues, demonstrating high clinical value in differentiating functional cysts, endometriomas, and cystadenomas, as well as distinguishing benign lesions (functional cysts or endometriomas) from malignant tumors.

Feasibility of iodine concentration parameter and extracellular volume fraction derived from dual-energy CT for distinguishing type I and type II epithelial ovarian carcinoma

To investigate the feasibility of using the iodine concentration (IC) parameter and extracellular volume (ECV) fraction derived from dual-energy CT for distinguishing between type I and type II epithelial ovarian carcinoma (EOC). This study retrospectively included 172 patients with EOC preoperatively underwent dual-energy CT scans. Patients were grouped as type I and type II EOC according to postoperatively pathologic results. Normalized IC (NIC, %) values from arterial-phase (AP), venous-phase (VP) and delay-phase (DP) were measured by two observers. ECV fraction (%) was calculated by DP-NIC and hematocrit. Intra-observer correlation coefficient (ICC) was used to assess the agreement between measurements made by two observers. The differences of imaging parameters between the two groups were compared. Logistic regression was used to select independent predictive factors and establish combined parameter. Receiver operating characteristic curve was used to analyze performance of all parameters. The ICCs for all parameters exceeded 0.75. All parameters in type II EOC were all significantly higher than those in type I EOC (all P < 0.05). VP-NIC exhibited the highest Area under the curve (AUC) of 0.804, along with 80.39% sensitivity and 71.43% specificity. VP-NIC was identified as the independent factor. The sensitivity and specificity of ECV fraction were 78.43% and 71.43%, respectively. The combined parameter consisting of AP-NIC, VP-NIC, DP-NIC, and ECV fraction yielded an AUC of 0.823, with sensitivity of 76.47% and specificity of 77.14%. The sensitivity of the combined parameter was significantly higher than that of AP-NIC (P = 0.049). It is valuable for dual-energy CT IC-based parameters and ECV fraction in preoperatively identifying type I and type II EOC. Dual-energy CT-normalized iodine concentration and extracellular volume fraction achieved satisfactory discriminative efficacy, distinguishing between type I and type II epithelial ovarian carcinoma.

An optimized siamese neural network with deep linear graph attention model for gynaecological abdominal pelvic masses classification

An adnexal mass, also known as a pelvic mass, is a growth that develops in or near the uterus, ovaries, fallopian tubes, and supporting tissues. For women suspected of having ovarian cancer, timely and accurate detection of a malignant pelvic mass is crucial for effective triage, referral, and follow-up therapy. While various deep learning techniques have been proposed for identifying pelvic masses, current methods are often not accurate enough and can be computationally intensive. To address these issues, this manuscript introduces an optimized Siamese circle-inspired neural network with deep linear graph attention (SCINN-DLGN) model designed for pelvic mass classification. The SCINN-DLGN model is intended to classify pelvic masses into three categories: benign, malignant, and healthy. Initially, real-time MRI pelvic mass images undergo pre-processing using semantic-aware structure-preserving median morpho-filtering to enhance image quality. Following this, the region of interest (ROI) within the pelvic mass images is segmented using an EfficientNet-based U-Net framework, which reduces noise and improves the accuracy of segmentation. The segmented images are then analysed using the SCINN-DLGN model, which extracts geometric features from the ROI. These features are classified into benign, malignant, or healthy categories using a deep clustering algorithm integrated into the linear graph attention model. The proposed system is implemented on a Python platform, and its performance is evaluated using real-time MRI pelvic mass datasets. The SCINN-DLGN model achieves an impressive 99.9% accuracy and 99.8% recall, demonstrating superior efficiency compared to existing methods and highlighting its potential for further advancement in the field.

Comparing the diagnostic efficacy of [18F]FDG PET/CT and MRI in the initial diagnosis of ovarian cancer: a meta-analysis

This meta-analysis was conducted to assess the relative diagnostic effectiveness of [ A thorough literature search was conducted using PubMed, Embase, and Web of Science databases to locate relevant studies published up to April 2024. The selected studies were those that evaluated diagnostic performance of [ The meta-analysis included 23 articles encompassing a total of 1973 patients. The sensitivity of [ Our meta-analysis reveals that [

Multiparametric MRI-based radiomics nomogram for differentiation of primary mucinous ovarian cancer from metastatic ovarian cancer

To develop a multiparametric magnetic resonance imaging (mpMRI)-based radiomics nomogram and evaluate its performance in differentiating primary mucinous ovarian cancer (PMOC) from metastatic ovarian cancer (MOC). A total of 194 patients with PMOC (n = 72) and MOC (n = 122) confirmed by histology were randomly divided into the primary cohort (n = 137) and validation cohort (n = 57). Radiomics features were extracted from axial fat-saturated T2-weighted imaging (FS-T2WI), diffusion-weighted imaging (DWI), and contrast-enhanced T1-weighted imaging (CE-T1WI) sequences of each lesion. The effective features were selected by minimum redundancy maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) regression to develop a radiomics model. Combined with clinical features, multivariate logistic regression analysis was employed to develop a radiomics nomogram. The efficiency of nomogram was evaluated using the receiver operating characteristic (ROC) curve analysis and compared using DeLong test. Finally, the goodness of fit and clinical benefit of nomogram were assessed by calibration curves and decision curve analysis, respectively. The radiomics nomogram, by combining the mpMRI radiomics features with clinical features, yielded area under the curve (AUC) values of 0.931 and 0.934 in the primary and validation cohorts, respectively. The predictive performance of the radiomics nomogram was significantly superior to the radiomics model (0.931 vs. 0.870, P = 0.004; 0.934 vs. 0.844, P = 0.032), the clinical model (0.931 vs. 0.858, P = 0.005; 0.934 vs. 0.847, P = 0.030), and radiologists (all P < 0.05) in the primary and validation cohorts, respectively. The decision curve analysis revealed that the nomogram could provide higher net benefit to patients. The mpMRI-based radiomics nomogram exhibited notable predictive performance in differentiating PMOC from MOC, emerging as a non-invasive preoperative imaging approach.

Whole-tumor histogram analysis of multiple non-Gaussian diffusion models at high b values for assessing cervical cancer

To assess the diagnostic potential of whole-tumor histogram analysis of multiple non-Gaussian diffusion models for differentiating cervical cancer (CC) aggressive status regarding of pathological types, differentiation degree, stage, and p16 expression. Patients were enrolled in this prospective single-center study from March 2022 to July 2023. Diffusion-weighted images (DWI) were obtained including 15 b-values (0 ~ 4000 s/mm 89 women (mean age, 55 ± 11 years) with CC were enrolled in our study. The combined model, which incorporated the CTRW, DKI, FROC, and IVIM diffusion models, offered a significantly higher AUC than that from any individual models (0.836 vs. 0.664, 0.642, 0.651, 0.649, respectively; p < 0.05) in distinguishing cervical squamous cell cancer from cervical adenocarcinoma. To distinguish tumor differentiation degree, except the combined model showed a better predictive performance compared to the DKI model (AUC, 0.839 vs. 0.697, respectively; p < 0.05), no significant differences in AUCs were found among other individual models and combined model. To predict the International Federation of Gynecology and Obstetrics (FIGO) stage, only DKI and FROC model were established and there was no significant difference in predictive performance among different models. In terms of predicting p16 expression, the predictive ability of DKI model is significantly lower than that of FROC and combined model (AUC, 0.693 vs. 0.850, 0.859, respectively; p < 0.05). Multiple non-Gaussian diffusion models with whole-tumor histogram analysis show great promise to assess the aggressive status of CC.

MRI features of ovarian teratomas with somatic-type malignancy and mature cystic teratomas

We evaluated the magnetic resonance imaging (MRI) features of ovarian teratomas with somatic-type malignancy (TSMs) and benign ovarian mature cystic teratomas (MCTs) to determine the diagnostic contribution of the MRI findings for differentiating these two teratomas. We compared the MRI findings between ovarian TSMs (n = 10) and MCTs (n = 193), and we conducted a receiver operating characteristic (ROC) analysis to determine the MRI findings' contribution to the differentiation of TSMs from MCTs. The maximum diameters of whole lesion and the largest solid component in the TSMs were larger than those of the MCTs (p = 0.0001 and p < 0.0001, respectively). Fat tissue in solid components was seen in 73/116 (62.9%) MCTs but in none of the TSMs (p = 0.0001). Ring-like enhancement in solid components was seen in 60/116 (51.7%) MCTs and none of the TSMs (p = 0.0031). On dynamic contrast-enhanced MRI (DCE MRI), all of the solid components in the TSMs showed a high- or intermediate-risk time intensity curve (TIC), and those in 113 of the 116 (97.4%) MCTs showed a low-risk TIC (p < 0.0001). The area under the curve of the ROC analysis using the high-/intermediate-risk TIC on DCE MRI was the highest (0.99) for differentiating TSMs from MCTs: sensitivity 100%, specificity 97.4%, positive predictive value 75.0%, negative predictive value 100%, and accuracy, 97.6%. Compared to ovarian MCTs, ovarian TSMs are larger and have larger solid components with high- or intermediate-risk TICs on DCE MRI. Ovarian MCTs frequently show small solid components with fat tissue, ring-like enhancement, and a low-risk TIC on DCE MRI.

Validation of the 2018 FIGO staging system for stage IIIC cervical cancer by determining the metabolic and radiomic heterogeneity of primary tumors based on 18F-FDG PET/CT

This study aimed to validate the 2018 FIGO staging system of cervical cancer (CC) by determining the metabolic and radiomic heterogeneity of primary tumors between stage IIIC1 and IIIC2. 168 patients with squamous cell CC underwent pre-treatment fluorine-18 fluorodeoxyglucose positron emission computed tomography ( The IIIC1 and IIIC2 groups did not differ significantly in age, weight, height, or the 10 major metabolic parameters (P > 0.05). The AUCs of the 4 models were 0.577, 0.639, 0.763, and 0.506, respectively, in the training cohort, and 0.789, 0.699, 0.761, and 0.538, respectively, in the testing cohort. The model fit of the logistic regression model based on CT + PET data was good in both the training and testing cohorts. Our study offers additional diagnostic options for PALN metastasis, which could impact treatment decisions. Our results indirectly support the conclusions of previous studies recommending that primary tumors should be considered during IIIC staging.

Neoadjuvant chemotherapy for high-grade serous ovarian cancer: radiologic–pathologic correlation of response assessment and predictors of progression

Neoadjuvant chemotherapy is often administered for high-grade serous ovarian carcinoma (HGSC) prior to cytoreductive surgery. We evaluated treatment response by CT (simplified peritoneal carcinomatosis index [S-PCI]), pathology (chemotherapy response score [CRS]), laboratory markers (serum CA-125), and surgical outcomes, to identify predictors of disease-free survival. For this retrospective, HIPAA-compliant, IRB-approved study, we identified 396 women with HGSC receiving neoadjuvant chemotherapy between 2010 and 2019. Two hundred and ninety-nine patients were excluded (surgery not performed; imaging/pathology unavailable). Pre- and post-treatment abdominopelvic CTs were assigned CT S-PCI scores 0-24 (higher score indicating more tumor). Specimens were assigned CRS of 1-3 (minimal to complete response). Clinical data were obtained via chart review. Univariate, multivariate, and survival analyses were performed. Ninety-seven women were studied, with mean age of 65 years ± 10. Interreader agreement was good to excellent for CT S-PCI scores (ICC 0.64-0.77). Despite a significant decrease in CT S-PCI scores after treatment (p < 0.001), mean decrease in CT S-PCI did not differ significantly among CRS categories (p = 0.20) or between patients who were optimally versus suboptimally debulked (p = 0.29). In a survival analysis, lower CRS (more viable tumor) was associated with shorter time to progression (p < 0.001). A joint Cox proportional-hazard models showed that only residual pathologic disease (CRS 1/2) (HR 4.19; p < 0.001) and change in CA-125 (HR 1.79; p = 0.01) predicted progression. HGSC response to neoadjuvant therapy by CT S-PCI did not predict pathologic CRS score, optimal debulking, or progression, revealing discordance between imaging, pathologic, biochemical, and surgical assessments of tumor response.

MRI, clinical, and radiomic models for differentiation of uterine leiomyosarcoma and leiomyoma

To assess the predictive ability of conventional MRI features and MRI texture features in differentiating uterine leiomyoma (LM) from uterine leiomyosarcoma (LMS). This single-center, IRB-approved, HIPAA-compliant retrospective study included 108 patients (69 LM, 39 LMS) who had pathology, preoperative MRI, and clinical data available at our tertiary academic institution. Two radiologists independently evaluated 14 features on preoperative MRI. Texture features based on 3D segmentation were extracted from T2W-weighted MRI (T2WI) using commercially available texture software (TexRAD™, Feedback Medical Ltd., Great Britain). MRI conventional features, and clinical and MRI texture features were compared between LM and LMS groups. Dataset was randomly divided into training (86 cases) and testing (22 cases) cohorts (8:2 ratio); training cohort was further subdivided into training and validation sets using ten-fold cross-validation. Optimal radiomics model was selected out of 90 different machine learning pipelines and five models containing different combinations of MRI, clinical, and radiomics variables. 12/14 MRI conventional features and 2/2 clinical features were significantly different between LM and LMS groups. MRI conventional features had moderate to excellent inter-reader agreement for all but two features. Models combining MRI conventional and clinical features (AUC 0.956) and MRI conventional, clinical, and radiomics features (AUC 0.989) had better performance compared to models containing MRI conventional features alone (AUC 0.846 and 0.890) or radiomics features alone (0.929). While multiple MRI and clinical features differed between LM and LMS groups, the model combining MRI, clinical, and radiomic features had the best predictive ability but was only marginally better than a model utilizing conventional MRI and clinical data alone.

Comment on ‘Diagnostic performance of apparent diffusion coefficient (ADC) for differentiating endometrial carcinoma from benign lesions: a systematic review and meta-analysis’

Improving the performance of IOTA simple rules: sonographic assessment of adnexal masses with resource-effective use of a magnetic resonance scoring (ADNEX MR scoring system)

To compare the International Ovarian Tumor Analysis (IOTA) simple rules, simple rules risk ultrasound models, alone or in combination with magnetic resonance (MR) score to predict malignancy in women with adnexal masses. 171 women with adnexal masses were included from February 2014 to February 2016. 120 women had histopathological diagnosis obtained from surgery or percutaneous biopsy. The other 51 women were submitted to surveillance with ultrasound (US) for at least 1 year. Patients were examined with US and MR. US reports were rendered using IOTA systems. We compared five diagnostic approaches, aimed at diagnosing women with malignant tumors among those with adnexal masses: We calculated the performance and net benefits (decision curve analysis) for five distinct diagnostic approaches: (1) US simple rules (SR), (2) simple rules risk score (SRRisk), (3) US SR followed by subjective assessment (SA) of indeterminate cases, (4) SR followed by MR score for the indeterminate cases, and (5) MR score for all women. The MR score for all patients was the approach that yielded the best-standardized net benefit regardless of the risk threshold. However, referring women with indeterminate masses on SR to MR score yielded the second-best net benefit. Although this study leaves no doubt about the superiority of MR score over US-based methods for the discrimination of malignant tumors in women with adnexal masses, restricting the use of MR score only to women with indeterminate masses on US SR is a safe, appropriate way to triage women with adnexal masses.

Overview of imaging findings associated with systemic therapies in advanced epithelial ovarian cancer

To provide an overview for radiologists of the systemic agents used in the treatment of advanced epithelial ovarian cancer (EOC) and their associated toxicities. EOC is a common gynecological malignancy, with the majority of patients presenting with advanced stage disease at the time of diagnosis. Although primary cytoreductive surgery and chemotherapy are the principal treatments for EOC, recurrence rates of disease remain high. As several molecular targeted therapies have been developed in the last decade, various novel agents have shown efficacy in the treatment of advanced EOC. Advanced EOC will be discussed by outlining the relevant radiological features of toxicities. Knowledge of the systemic therapies utilized in the treatment of advanced EOC and their associated radiological features is critical in diagnostic image interpretation.

Multimodality imaging and genomics of granulosa cell tumors

The purpose of this article is to review the imaging findings and genomics of granulosa cell tumors (GCTs) in order to aid in diagnosis and management of GCTs. GCTs are the most common type of sex cord-stromal tumors of the ovary. They are usually diagnosed initially with ultrasound and are subsequently further characterized with CT and MRI. PET/CT is often ordered as well to measure the extent of disease and for follow-up, but its usefulness is in question as some GCTs lack FDG avidity. There is significant variability in imaging phenotypes of GCTs, ranging from mostly cystic to almost solid. More resources have recently been dedicated to understanding the genetics and molecular mechanisms of GCT development. Current research shows that the main cause of GCT carcinogenesis is the FOXL2 mutation, but there are several other noteworthy mutations that contribute to the pathogenesis of this disease. Certain mutations, like GATA4, are known to be associated with more aggressive disease and higher rates of recurrence. Using this information, imaging protocols can be altered depending on the genotype of the tumor. Further understanding of the genetic alterations that underpin the development of GCTs is indicated as genotypic knowledge could be used to guide optimal imaging and management strategies.

Ultrasound-based radiomics score: a potential biomarker for the prediction of progression-free survival in ovarian epithelial cancer

More than 80% of patients with ovarian epithelial cancer (OEC) show complete remission after initial treatment but eventually experience recurrence of the disease. This study aimed to develop a radiomics signature to identify a new prognostic indicator based on preoperative ultrasound imaging. A total of 111 patients with OEC who underwent transvaginal ultrasound before surgery were included. Of these, 76 were divided into the training cohort and 35 into the test cohort. We defined the region of interest (ROI) of the tumor by manually drawing the tumor contour on the ultrasound image of the lesion. The radiomics features were extracted from ultrasound images. The radiomics score (Rad-Score) was constructed using the least absolute shrinkage and selection operator (LASSO) analysis and Cox regression. Combined with the ultrasound radiomics features, significant clinical variables were also used to establish predictive models for 5-year progression-free survival (PFS) prediction. The efficiency of the model was evaluated using the area under the curve (AUC). Kaplan-Meier analysis was used to evaluate the association between the Rad-Score and PFS. The combined model was superior to the clinical and Rad-Score models in estimating 5-year PFS and achieved an AUC of 0.868 (95%CI 0.766-0.971) in the training cohort. The Rad-Score was negatively correlated with prognosis in the training and test cohorts. The combined model that incorporated both clinical parameters and ultrasound radiomics features achieved a good prognosis in patients with OEC, which might aid clinical decision-making.

Predictive value and prevalence of refractive edge shadow in diagnosis of ovarian dermoids

To evaluate the diagnostic performance of refractive edge shadow in evaluation of ovarian dermoids compared to other benign adnexal masses. Ultrasound images of 139 patients with 154 dermoids, endometriomas, and hemorrhagic cysts were retrospectively reviewed by 3 radiologists blinded to final diagnosis. Ultrasound and clinical features were compared to pathology or follow-up ultrasound results as reference standard. Inter-reader agreements with free-marginal kappa and diagnostic performance were evaluated. The former was compared using Fisher's exact test or Mann-Whitney test with p < 0.05 to determine statistical significance. The study sample consisted of 154 lesions: 50 dermoids, 50 endometriomas, and 54 hemorrhagic cysts. Refractive edge shadow, homogeneous echogenic appearance, tip of the iceberg sign, mural echogenic nodule, echogenic shadowing focus, and dot-dash sign all were statistically significant across all readers for the diagnosis of dermoid. Prevalence of each feature in dermoids compared to other entities were as follows: refractive edge shadow (70% vs 8%; p < 0.001), homogeneously echogenic appearance (34% vs 2%; p < 0.001), tip of the iceberg sign (16% vs 1%; p < 0.001), mural echogenic nodule (38% vs 2%; p < 0.001), echogenic shadowing focus (13% vs 1%; p < 0.001), and dot-dash sign (44% vs 1%; p < 0.001). Refractive edge shadow had the highest sensitivity, negative predictive value, and accuracy among all ultrasound features associated with dermoids (70%, 86%, and 85%, respectively). Refractive edge shadow is a promising ultrasound feature for diagnosis of dermoids, with the highest diagnostic accuracy and prevalence compared to other previously described features associated with dermoids.

Current update on the molecular genetics and management of hereditary ovarian cancers: a primer for radiologists

More than one-fifth of ovarian cancers are hereditary, with most of them caused by BRCA genes. Malignant ovarian neoplasms are primarily epithelial tumors, a heterogeneous group of tumors with variable genetic backgrounds that translate into different biologic behaviors and morphologic features. Radiologists play an increasingly important role in the diagnosis and management of oncology patients. Familiarity with hereditary ovarian cancers will have a positive impact on patient management and radiologists' involvement in the multidisciplinary approach needed for this delicate patient population. In this paper, we review the basic histologic and genetic backgrounds of ovarian tumors with an emphasis on hereditary ovarian cancers, as well as the effects that these factors have on patient workup, primarily with regard to imaging studies.

Comprehensive review of imaging features of sex cord-stromal tumors of the ovary

Sex cord-stromal tumors of the ovary (SCST) are uncommon ovarian tumors arising from sex cord and/or stromal cells of the ovaries. They may be nonfunctional and asymptomatic or functional presenting with hyperestrogenic, hyperandrogenic or cushingoid symptoms. They present in a wide age group of women, mostly in early stages and follow a nonaggressive clinical course after surgical resection. They differ from more prevalent epithelial ovarian tumors which tend to present in older women in advanced stages with poor prognosis. Some of SCSTs are associated with clinical syndromes. We will review imaging features on ultrasound, computed tomography and magnetic resonance imaging, epidemiology and clinical presentations of these tumors.

Are CT and MRI useful tools to distinguish between micropapillary type and typical type of ovarian serous borderline tumors?

To investigate the computed tomography (CT) and magnetic resonance imaging (MRI) characteristics of ovarian serous borderline tumors (SBTs), and evaluate whether CT and MRI can be used to distinguish micropapillary from typical subtypes. We retrospectively reviewed the clinical features and CT and MR imaging findings of 47 patients with SBTs encountered at our institute from September 2013 to December 2019. 30 patients with 58 histologically proven typical SBT and 17 patients with 26 micropapillary SBT were reviewed. Preoperative CT and MR images were evaluated, by two observers in consensus for the laterality, maximum diameter (MD), morphology patterns, internal architecture, attenuation or signal intensity, ADC value, enhancement patterns of solid portions (SP), and extra-ovarian imaging features. The median age were similar between typical SBT and SBT-MP (32.5 years, 36 years, respectively, P>0.05). Morphology patterns between two subtypes were significantly different on CT and MR images (P < 0.001). Irregular solid tumor (21/37, 56.76%) was the major morphology pattern of typical SBT tumor, while unilocular cyst with mural nodules (14/20, 70%) was the major morphology pattern of SBT-MP on CT images. Similarly, papillary architecture with internal branching (PA&IB) (17/21, 80.95%) was the major morphology pattern of typical SBT tumor, while unilocular cyst with mural nodules (4/6, 66.67%) was the major pattern of SBT-MP on MR images. PA&IB all showed slightly hyperintense papillary architecture with hypointense internal branching on T2-weighted MRI. More calcifications were found in typical SBT (24/37, 64.86%) than SBT-MP mass lesion (6/20, 30%) (P < 0.05). Hemorrhage was less frequently visible in (20/37, 54.05%) typical SBT lessons than SBT-MP mass lesion (18/20, 90%) (P < 0.05). The ovarian preservation is more seen in typical SBT (38/58, 65.52%) than SBT-MP (12/28, 42.86%) in our series (P < 0.05). Mean ADC value of solid portions (papillary architecture and mural nodules) was 1.68 (range from 1.44 to 1.85) × 10 Morphology and internal architecture are two major imaging features that can help to distinguish between SBT-MP and typical SBT.

Uterine and ovarian cancer DFP report

Ovarian teratomas: clinical features, imaging findings and management

Ovarian teratomas are the most common type of germ cell tumors. There are three major subtypes of ovarian teratomas including mature, immature, and monodermal teratomas. Ultrasound, computed tomography and magnetic resonance imaging can demonstrate specific imaging findings for mature teratoma. Imaging features of immature and monodermal teratomas are less specific, but a combination of clinical features and imaging findings can help in the diagnosis. Imaging is also very helpful in guiding management. In this article, we review the epidemiology, histopathology, clinical presentation, imaging features and management of ovarian teratomas.

Useful preoperative examination findings to classify the grade of ovarian primary mucinous tumor

To evaluate various imaging features on magnetic resonance imaging (MRI) and tumor markers and their utility to assess various grades of ovarian primary mucinous tumors (OPMTs): benign, borderline, or malignant. Ninety-five pathologically diagnosed OPMTs [53 benign, 24 borderline malignant (BM), and 18 malignant] were selected in this retrospective study. MRI features of the ovarian mass, namely the maximum diameter, honeycomb loculi, solid components (SC), stained-glass pattern, and signal intensity of the cyst on T1- (T1WI) and T2-weighted imaging (T2WI) with/without fat suppression, and preoperative STMs, namely carcinoembryonic antigen (CEA), carbohydrate antigen (CA) 19-9, and CA125, were compared between the three tumor grades using univariate analysis. We also analyzed the findings to estimate the pathological diagnosis using classification tree (CT) analysis. Maximum diameter, honeycomb loculi, SC, stained-glass pattern, signal intensity of the cyst [hyperintensity on both T1WI and T2WI (T1-hyper/T2-hyper), and hyperintense on T1WI and hypointense on T2WI (T1-hyper/T2-hypo)], and CEA and CA 19-9 concentrations were significantly different between the three tumor grades (p < 0.05). The concordance rate with the pathological diagnosis was the highest with diagnosis by the CT comprising T1-hyper/T2-hypo, CEA, and CA 19-9 and by the CT comprising T1-hyper/T2-hypo, CEA, and SC. Four types of findings were important for OPMT grading. Lesions negative for both T1-hyper/T2-hypo and CEA suggest benign; lesions positive for T1-hyper/T2-hypo and negative for CA 19-9 or SC suggest BM; and lesions negative for T1-hyper/T2-hypo and positive for CEA, or positive for both T1-hyper/T2-hypo and CA 19-9 or SC suggest malignancy.

Clinical significance of CT detected enlarged cardiophrenic nodes in ovarian cancer patients

To assess the relevance of enlarged cardiophrenic lymph nodes (CPLN) seen on staging CT of ovarian cancer patients. Retrospective cohort study of consecutive patients with primary ovarian malignancy who underwent staging CT between 2013 and 2016. Images were reviewed by two radiologists in consensus. Enlarged CPLN was defined as a short axis diameter ≥ 7 mm. Clinical and imaging findings; management decisions; outcome of cytoreductive surgery and survival were compared between patients with and without enlarged CPLN on staging CT. Enlarged CPLN were found in 42 patients (41.5%) and was significantly associated with higher radiological PCI (p = 0.002); large volume upper abdominal disease (p = 0.001); enlarged lesser omental, periportal and supra-renal para-aortic lymph nodes (p ≤ 0.05); unfavorable sites of disease involvement (p < 0.001) and extraperitoneal metastases (p = 0.004). While there was a significant difference in the number of patients who underwent primary and interval debulking (p = 0.002), there was no difference in the rates of optimal cytoreduction between the two groups (p = 0.469). After adjusting for outcomes of cytoreductive surgery, CT detected enlarged CPLN did not adversely affect the overall survival, HR 1.5 (0.708-3.4), p = 0.272, but adversely affected the recurrence free survival (HR 2.38 (1.25-4.53)), p = 0.008. Enlarged CPLN detected on staging CT in patients with primary ovarian cancer is clinically significant even in the developing world and is associated with higher volume of peritoneal, non-regional nodal and extraperitoneal disease and lower recurrence free survival.

Ovarian cancer during pregnancy

Adnexal masses during pregnancy are a relatively uncommon entity. Their clinical management is challenging given the overlapping features of certain entities on imaging and histopathology, which can mimic malignancy, and the potential side effects to the mother and fetus, whether expectant management versus surgery is pursued. Ultrasonography with Doppler evaluation is the modality of choice for evaluating adnexal masses during pregnancy. Magnetic resonance imaging is the second-line modality useful when US findings are inconclusive/indeterminate. Most adnexal masses in pregnant patients are benign in origin (e.g., functional cysts, mature cystic teratoma, decidualization of endometrioma), but a few are malignant in origin (e.g., dysgerminoma, granulosa cell tumor). Most cases of adnexal masses are asymptomatic, but complications such as ovarian torsion can occur. This review aims to familiarize the radiologist with the imaging of adnexal lesions during pregnancy so that the radiologist can identify ovarian cancer. Specifically, the review will detail the most common benign and malignant adnexal masses in pregnancy, mimickers, and their corresponding imaging findings on US and MRI.

Current update on vaginal malignancies

Primary vaginal cancers are rare and account for 1-3% of all gynecologic malignancies. There are several histological subtypes that affect a wide range of the population. Imaging plays an important role in the diagnosis, staging, and treatment planning of vaginal cancers. This article reviews the relevant anatomy, clinical findings, imaging characteristics, and recent advances in the management of vaginal malignancies.

Uterine extension determined by MRI: a useful parameter for differentiating subserosal leiomyomas from ovarian tumors

This study aimed to evaluate the utility of uterine extension determined via MRI for the differentiation of large subserosal leiomyomas from ovarian tumors. In total, 55 patients with subserosal leiomyomas and 127 patients with ovarian tumors were included in this study. These patients were selected from a cohort of female patients whose pelvic masses were larger than 10 cm and who underwent preoperative MRI. We retrospectively reviewed the MRI and compared the diagnostic ability of uterine extension measurements and bridging vascular signs for differentiating subserosal leiomyomas from ovarian tumors. The vertical height of the uterus (107.2 ± 36.4 mm vs. 59.9 ± 24.9 mm, p  81 mm, were 0.89, 89%, and 80% and those of the uterine length, using cutoff threshold > 84 mm, were 0.85, 69%, and 93%, respectively. Alternatively, the sensitivity and specificity of bridging vascular sign were 78% and 94%, respectively. Uterine extension determined via MRI is a useful parameter for differentiating large subserosal leiomyomas from ovarian tumors.

Quantitative kinetic parameters of primary tumor can be used to predict pelvic lymph node metastasis in early-stage cervical cancer

To investigate the role of kinetic parameters of primary tumor derived from dynamic contrast-enhanced MRI (DCE-MRI) in predicting pelvic lymph node metastasis (PLNM) in patients with cervical cancer. 66 women with newly diagnosed cervical cancer were included between July 2017 and August 2019. All patients had a FIGO stage IB-IIA cancer and treated with hysterectomy and bilateral lymphadenectomy. Kinetic parameters of the primary tumor were derived from DCE-MRI data. The tumor diameter, ADC value, kinetic parameters, and nodal short-axis diameter were compared between patients with or without PLNM. Logistic regression analysis was used to determine the independent predictors for PLNM and receiver operator characteristic curve was used to evaluate the predictive performance. There were 20 patients with PLNM and 46 patients without PLNM. Tumor diameter, the efflux rate constant (K K

Machine learning based evaluation of clinical and pretreatment 18F-FDG-PET/CT radiomic features to predict prognosis of cervical cancer patients

To examine the usefulness of machine learning to predict prognosis in cervical cancer using clinical and radiomic features of 2-deoxy-2-[ This retrospective study included 50 cervical cancer patients who underwent The five top predictors of disease progression were: stage, surface area, metabolic tumor volume, gray-level run length non-uniformity (GLRLM_RLNU), and gray-level non-uniformity for run (GLRLM_GLNU). The naive Bayes model was the best-performing classifier for predicting disease progression (AUC = 0.872, accuracy = 0.780, F1 score = 0.781, precision = 0.788, and recall = 0.780). In the naive Bayes model, 5-year PFS was significantly higher in predicted non-progression than predicted progression (80.1% vs. 9.1%, p < 0.001) and was only the independent factor for PFS in multivariate analysis (HR, 6.89; 95% CI, 1.92-24.69; p = 0.003). A machine learning approach based on clinical and pretreatment

Magnetic resonance imaging-based texture analysis for the prediction of postoperative clinical outcome in uterine cervical cancer

Magnetic resonance imaging (MRI)-based texture analysis (MRTA) is a novel image analysis tool that offers objective information about the spatial arrangement of MRI signal intensity. We aimed to investigate the value of MRTA in predicting the postoperative clinical outcome of patients with uterine cervical cancer. This retrospective study included 115 patients with surgically proven cervical cancer who underwent preoperative pelvic 3T-MRI, and MRTA was performed on T2-weighted images (T2), apparent diffusion coefficient (ADC) maps, and contrast-enhanced T1-weighted images (CE-T1). Filtration histogram-based texture analysis was used to generate six first-order statistical parameters [mean intensity, standard deviation (SD), mean of positive pixels (MPP), entropy, skewness, and kurtosis] at five spatial scaling factors (SSFs, 2-6 mm) as well as from unfiltered images. Cox proportional hazard models and time-dependent receiver operating characteristic analyses were used to evaluate the associations between parameters and recurrence-free survival (RFS). During a median follow-up of 36 months, tumor recurrence was found in 26 patients (22.6%). Multivariate analysis demonstrated that CE-T1 MPP and T2 kurtosis at SSF3-5, CE-T1 MPP at SSF6, and CE-T1 SD at unfiltered images were independent predictors of RFS (p  optimal cutoff values demonstrated significantly worse survival than those with ≤ optimal cutoff values (p < 0.05). Preoperative MRTA may be useful for predicting postoperative outcome in patients with cervical cancer.

Clinical outcomes of uterine arterial chemoembolization with drug-eluting beads for advanced-stage or recurrent cervical cancer

To study the clinical efficacy and safety of transarterial chemoembolization with drug-eluting beads (DEB-TACE) among women with advanced-stage or recurrent cervical cancer. This retrospective cohort study enrolled women with cervical cancer who were treated by DEB-TACE between April 3, 2017 and July 12, 2021. Inclusion criteria were pathologic diagnosis of cervical cancer, II-IVa period, being aged 18 to 80 years, patient's inclination of treatment with DEB-TACE, and complete clinicopathologic data. Direct medical cost, hospital stay, resection frequency, treatment responses, adverse events, overall survival, and progression-free survival were investigated. A total of 16 women with cervical cancer were treated by DEB-TACE. DEB-TACE was successfully performed in all patients, with no major complications or adverse events. A total of 10 minor complications were observed in 9 women (56.3%) after the procedure. Seven (43.8%) women experienced mild to moderate post-embolization pain. The tumors decreased 3 and 6 months after the treatment. The frequency of complete response, partial response, stable disease, and progressive disease was 1 (40%), 3 (40%), 12 (15%), and 0 (0%), respectively, resulting in an objective response rate of 25.0% and a disease control rate of 100.0% after 1 month. The median hospital stay was 9.5 days, and the direct medical cost was 5.9 × 10 DEB-TACE with diamminedichloroplatinum-preloaded beads may be an effective and safe treatment for women with advanced-stage or recurrent cervical cancer.

MR imaging findings of ovarian lymphoma: differentiation from other solid ovarian tumors

To evaluate magnetic resonance imaging (MRI) findings for distinguishing ovarian lymphomas from other solid ovarian tumors. This retrospective multicenter study included 14 women (median age, 46.5 years; range, 26-81 years) with surgically proven ovarian lymphoma and 28 women with solid ovarian tumors other than lymphoma. We conducted a subjective image analysis of factors including laterality, shape, composition, T2 signal intensity (SI), heterogeneity, diffusion restriction, enhancement, and presence of peripheral follicles. A generalized estimating equation was used to identify MRI findings that could be used to distinguish ovarian lymphomas from other solid ovarian tumors. Diagnostic performance of the identified MRI findings was assessed using the area under the receiver-operating characteristic curve (AUC). Ovarian lymphoma more frequently showed homogeneous high SI on T2-weighted imaging (81.8% vs. 19.4%, P 0.05 for all). Homogeneous high SI on T2-weighted imaging was the only independent MRI finding (OR = 15.19; 95% CI 3.15-73.33; P = 0.001) in the multivariable analysis. Homogeneous high SI on T2-weighted imaging yielded an AUC of 0.82 with a sensitivity of 81.8% and specificity of 80.6% in distinguishing ovarian lymphomas from other solid ovarian tumors. Homogeneous high signal intensity on T2-weighted imaging was helpful in distinguishing ovarian lymphomas from other solid ovarian tumors. Peripheral ovarian follicles might be an additional clue that suggests a diagnosis of ovarian lymphoma.

Comparison of contrast-enhanced ultrasonography and magnetic resonance imaging in the evaluation of tumor size and local invasion of surgically treated cervical cancer

This retrospective study aimed to compare the performance of contrast-enhanced ultrasound (CEUS) and magnetic resonance imaging (MRI) in staging surgically treated early-stage cervical cancer. Patients with surgically treated cervical carcinoma confirmed by post-operative pathological findings were included between December 2016 and December 2018. All included patients underwent both CEUS and MRI examinations before the surgery. Post-operative pathology was used as the gold standard. The κ values were calculated to assess the agreements of CEUS and MRI in staging cervical carcinoma in comparison with post-operative pathology. Complete data were available for 39 patients. CEUS showed great inter-observer reproducibility in tumor measurement [Intra-class Correlation Coefficient (ICC) 0.831] and moderate inter-observer reproducibility in the evaluation of vaginal infiltration and parametrial invasion (Cohen's κ 0.692 and 0.624). Tumor size was comparable as measured by CEUS and MRI (ICC 0.769). Both CEUS and MRI presented good concordance with post-operative pathology in staging cervical cancer (weighted κ 0.732 and 0.761). CEUS was comparable to MRI in staging surgically treated cervical cancer and might be considered in the pre-treatment work-up for cervical cancer.

Unveiling the mille-feuille sign: a key to diagnosing ovarian carcinosarcoma in addition to ovarian metastasis from colorectal carcinoma on MRI

To clarify the diagnostic utility and formation of the Mille-feuille sign for ovarian carcinosarcoma (OCS) on MRI, and to evaluate the other MRI findings and serum markers compared to ovarian metastases from colorectal carcinoma (OMCRC). Three blinded radiologists retrospectively reviewed MR images of 12 patients with OCS, 18 with OMCRC, and 40 with primary ovarian carcinoma (POC) identified by the electronic database of radiology reports. The interobserver agreement was analyzed using Fleiss' kappa test. Their MRI characteristics and tumor markers were compared using Fisher's exact test and Mann-Whitney's U test. Receiver operating characteristic curve analyses were used to determine the cutoff points for the ADC value. This study was approved by the institutional ethics committee. Interobserver agreement analysis was moderate or higher for all MRI characteristics. The frequency of Mille-feuille sign was comparable for both OCS and OMCRC groups, and predominantly higher than that of the POC group (p < 0.001, p < 0.001), respectively. Pathologically, the Mille-feuille sign in OCS reflected alternating layers of tumor cells with stroma and necrosis or intraluminal necrotic debris. Compared to OMCRC, intratumoral hemorrhage (p = 0.02), margin irregularity (p = 0.048), unilateral adnexal mass (p = 0.02), and low ADC values (p < 0.01) were more frequently observed and serum CEA levels was significantly lower (p = 0.007) in the OCS group. Under setting of the cutoff value of ADC at 0.871 × 10 The Mille-feuille sign was seen in both OCS and OMCRC. MR findings of intratumoral hemorrhage, margin irregularity, unilateral adnexal mass, low ADC values, and low serum CEA levels can be useful in differentiating OCS from OMCRC.

Salient magnetic resonance imaging findings in the differential diagnosis of benign, borderline and malignant ovarian mucinous tumors

In mucinous ovarian tumors, preoperative prediction of histological subgroup is important for treatment approach. Therefore, we aimed to determine salient magnetic resonance imaging (MRI) findings and estimate optimal cut off values for quantitative features in differential diagnosis of benign, borderline and malignant mucinous ovarian tumors. Between January 2011 and December 2021, preoperative MRI scans of 50 patients with mucinous ovarian tumors (n = 54) were evaluated retrospectively. MRI findings [size, signal intensity, contrast pattern, features of loculation, wall, septa and mural nodule (MN), diffusion restriction] were investigated. There were benign, borderline, and malignant groups based on histopathological results. The relationship between radiological and histopathological results was analyzed by performing Kruskal Wallis test, Pearson's chi-squared test, receiver operating characteristic analysis. In our study, there were 54 mucinous ovarian tumors in 50 patients. Of 54, 33 were benign, 13 borderline and eight malignant tumors. In comparison of three groups, tumor size, number of loculation, number and frequency of MN were higher and apparent diffusion coefficient (ADC) value were lower in malignant group (p < 0.05). Septa thickness was lower with optimal cut off value of 2.45 mm in benign group compared to borderline and malignant groups [sensitivity: 79%, specificity: 75%, AUC (Area under the curve): 0.861] (p < 0.05). T2-weighted (T2-w) signal intensity ratio (SIR) of MN was higher in borderline compared to malignant group, with a cut-off value of 3.9 (sensitivity: 85%, specificity: 83%, AUC: 0.943) (p < 0.05). Ascites was also significant in malignant group (p < 0.05). T2-w SIR of MN with a cut off value of 3.9 is beneficial for differential diagnosis. By awareness of some salient MRI findings (size, septa thickness, number of loculation, number and T2-w SIR of MN, ADC value and ascites), preoperative prediction of histological subgroup of mucinous tumors for appropriate treatment planning is possible.

Comparison of 68Ga-FAPI-04 and 18F-FDG PET/CT in diagnosing ovarian cancer

This study assesses the diagnostic performance of Seventy-nine ovarian cancer patients who performed Among all patients, 6 were assessed for initial assessment and 73 for recurrence and metastasis detection. For all lesions,

CT-based radiomic analysis for categorization of ovarian sex cord-stromal tumors and epithelial ovarian cancers

To evaluate the diagnostic potential of radiomic analyses based on machine learning that rely on contrast-enhanced computerized tomography (CT) for categorizing ovarian sex cord-stromal tumors (SCSTs) and epithelial ovarian cancers (EOCs). We included a total of 225 patients with 230 tumors, who were randomly divided into training and test cohorts with a ratio of 8:2. Radiomic features were extracted from each tumor and dimensionally reduced using LASSO. We used univariate and multivariate analyses to identify independent predictors from clinical features and conventional CT parameters. Clinic-radiological model, radiomics model and mixed model were constructed respectively. We evaluated model performance via analysis of the receiver operating characteristic (ROC) curve and area under ROC curves (AUCs), and compared it across models using the Delong test. We selected a support vector machine as the best classifier. Both radiomic and mixed model achieved good classification accuracy with AUC values of 0.923/0.930 in the training cohort, and 0.879/0.909 in the test cohort. The mixed model performed significantly better than the model based on clinical radiological information, with AUC values of 0.930 versus 0.826 (p = 0.000) in the training cohort and 0.905 versus 0.788 (p = 0.042) in the test cohort. Radiomic analysis based on CT images is a reliable and noninvasive tool for identifying SCSTs and EOCs, outperforming experience radiologists.

MRI-based radiomics model for predicting endometrial cancer with high tumor mutation burden

To evaluate the performance of MRI-based radiomics in predicting endometrial cancer (EC) with a high tumor mutation burden (TMB-H). A total of 122 patients with pathologically confirmed EC (40 TMB-H, 82 non-TMB-H) were included in this retrospective study. Patients were randomly divided into training and testing cohorts in a ratio of 7:3. Radiomics features were extracted from sagittal T2-weighted images and contrast-enhanced T1-weighted images. Then, the logistic regression (LR), random forest (RF), and support vector machine (SVM) algorithms were used to construct radiomics models. The area under the receiver operating characteristic curve (AUC) was calculated to evaluate the diagnostic performance of each model, and decision curve analysis was used to determine their clinical application value. Four radiomics features were selected to build the radiomics models. The three models had similar performance, achieving 0.771 (LR), 0.892 (RF), and 0.738 (SVM) in the training cohort, and 0.787 (LR), 0.798 (RF), and 0.777 (SVM) in the testing cohort. The decision curve demonstrated the good clinical application value of the LR model. The MRI-based radiomics models demonstrated moderate predictive ability for TMB-H EC and thus may be a tool for preoperative, noninvasive prediction of TMB-H EC.

Multiparametric MRI-based radiomics nomogram for identifying cervix-corpus junction cervical adenocarcinoma from endometrioid adenocarcinoma

To developed a magnetic resonance imaging (MRI) radiomics nomogram to identify adenocarcinoma at the cervix-corpus junction originating from the endometrium or cervix in order to better guide clinical treatment. Between February 2011 and September 2021, the clinicopathological data and MRI in 143 patients with histopathologically confirmed cervical adenocarcinoma (CAC, n = 86) and endometrioid adenocarcinoma (EAC, n = 57) were retrospectively analyzed at the cervix-corpus junction. Radiomics features were extracted from fat-suppressed T2-weighted imaging (FS-T2WI), diffusion-weighted imaging (DWI), apparent diffusion coefficient (ADC) maps, and delayed phase contrast-enhanced T1-weighted imaging (CE-T1WI) sequences. A radiomics nomogram was developed integrating radscore with independent clinical risk factors. The area under the curve (AUC) was used to evaluate the diagnostic efficacy of the radscore, nomogram and two different experienced radiologists in differentiating CAC from EAC at the cervix-corpus junction, and Delong test was applied to compare the differences of their diagnostic performance. In the training cohort, the AUC was 0.93 for radscore; 0.97 for radiomics nomograms; 0.85 and 0.86 for radiologists 1 and 2, respectively. Delong test showed that the differential efficacy of nomogram was significant better than those of radiologists in the training cohort (both P < 0.05). The nomogram based on radscore and clinical risk factors could better differentiate CAC from EAC at the cervix-corpus junction than radiologists, and preoperatively and non-invasively identify the origin of adenocarcinoma at the cervix-corpus junction, which facilitates clinicians to make individualized treatment decision.

Role of magnetic resonance imaging to differentiate between borderline and malignant serous epithelial ovarian tumors

We aimed to differentiate serous borderline ovarian tumors (SBOT) from serous epithelial ovarian carcinomas (SEOC) using morphological and functional MRI findings, to improve the patient management. We retrospectively investigated 24 ovarian lesions diagnosed with SBOT and 64 ovarian lesions diagnosed with SEOC. Additional to the demographic and morphological findings T2W signal intensity ratio, mean apparent diffusion coefficient (ADC Bilaterality, pelvic free fluid presence, serum CA-125 level (U/mL), presence of pelvic peritoneal implant were in favor of SEOC. Lower maximum size of solid component and solid size to maximum size ratio, dominantly cystic and solid-cystic appearance, exophytic growth pattern, presence of papiller projection and papillary architecture and internal branching pattern, higher T2W signal intensity ratio, ADC Our study revealed that morphological and functional imaging findings were valuable in differentiating BSOT from SEOC.

Updated endometrial cancer FIGO staging: the role of MRI in determining newly included histopathological criteria

Endometrial cancer (EC) is among the prevalent malignancies in gynecology, showing an increasing occurrence and mortality rate. The updated 2023 FIGO staging integrates both histopathological and molecular analyses, which significantly impact the prognosis and treatment approaches. This research aims to examine the effectiveness of MRI in identifying essential histopathological tumor features, including histological subtype, grade, and lymphovascular space invasion. A total of 106 patients diagnosed with EC from February 2018 to December 2023 underwent preoperative pelvic MRI. Surgical procedures followed ESMO guidelines, with histopathological assessments using FIGO 2009 criteria. Two radiologists independently evaluated MRI images, measuring maximum tumor size, minimum tumor ADC value (using a free-hand ROI technique), and ADC tumor/myometrium ratio. MRI findings were compared with histopathological data. Peritoneal implant presence and tumor size exhibited significant differences between endometrioid adenocarcinoma (EAC) and non-endometrioid endometrial carcinoma (NEEC), with p values of < 0.001 and 0.003, respectively. Significant differences in age, tumor size, ADC tumor, and ADC tumor/myometrium between low-grade and high-grade tumors were observed, with p values of < 0.001, 0.004, 0.006, and 0.011, respectively. Increased tumor size, reduced ADC tumor, ADC tumor/myometrium, and pelvic peritoneal implant presence were significantly associated with LVSI, with p values of < 0.001, 0.001, 0.002, and 0.001, respectively. The AUC values for tumor size, ADC tumor, and ADC tumor/myometrium were 0.842, 0.781 and 0.747, respectively, in distinguishing between low and high-grade endometrial tumors. Similarly, obtained AUC values for predicting LVSI were 0.836, 0.719, and 0.696, respectively. Our study emphasizes MRI's role in predicting tumor characteristics such as histological subtype, grade, and LVSI based on updated FIGO criteria. By highlighting the potential of MRI, this research contributes to our comprehension of improving diagnostic and clinical management for EC. Further multicenter studies are warranted to validate these findings and establish MRI's role in EC management.

Both intra- and peri-tumoral radiomics signatures can be used to predict lymphatic vascular space invasion and lymphatic metastasis positive status from endometrial cancer MR imaging

To identify lymphatic vascular space invasion (LVSI) and lymphatic node metastasis (LNM) status of endometrial cancer (EC) patients, using radiomics based on MRI images. Five hundred and ninety-eight EC patients between January 2015 and September 2020 from two institutions were retrospectively included. Tumoral regions on DWI, T1CE, and T2W images were manually outlined. Radiomics features were extracted from tumor region and peri-tumor region of different thicknesses. We established sub-models to select features from each smaller category. Using this method, we separately constructed radiomic signatures for intra-tumoral and peri-tumoral images using different sequences. We constructed intra-tumoral and peri-tumoral models by combining their features, and a multi-sequence model by combining logits. Models were trained with 397 patients and validated with 170 internal and 31 external patients. For LVSI positive/LNM positive status identification, the multi-parameter MRI radiomics model achieved the area under curve (AUC) values of 0.771 (95%CI: [0.692-0.849])/0.801 (95%CI: [0.704, 0.898]) and 0.864 (95%CI: [0.728-1.000])/0.976 (95%CI: [0.919, 1.000]) in internal and external test cohorts, respectively. Intra-tumoral and peri-tumoral radiomics signatures based on mpMRI can both be used to identify LVSI or LNM status in EC patients non-invasively. Further studies on LVSI and LNM should pay attention to both of them.

Impact of the 2023 FIGO staging revision on MRI diagnostic accuracy in FIGO 2009 stage I endometrial cancer

This study aimed to evaluate the diagnostic performance of Magnetic Resonance Imaging (MRI) for staging patients with International Federation of Gynecology and Obstetrics (FIGO) stage I endometrial cancer, by comparing the original 2009 system with the revised 2023 system. This retrospective study included 432 patients (mean age, 54.9 years) with histopathologically confirmed FIGO 2009 stage I endometrial cancer who underwent preoperative MRI. The patients were categorized into non-aggressive (n = 364; low-grade endometrioid histology) and aggressive (n = 68; grade 3 endometrioid or non-endometrioid histology, including serous, clear cell carcinoma, and carcinosarcoma) tumor groups. Preoperative MRI-based assessment of myometrial invasion was compared with histopathological results to assess the myometrial invasion depth, which was classified as no invasion, superficial invasion (< 50%), and deep invasion (≥ 50%). Diagnostic accuracy, sensitivity, specificity, and agreement of preoperative MRI-based staging determination were calculated for both FIGO 2009 and 2023 systems. In non-aggressive tumors, the 2009 FIGO staging demonstrated superior accuracy (kappa 0.82, 95% CI 0.74-0.89) compared to the 2023 staging (kappa 0.66, 95% CI 0.59-0.74), with a statistically significant difference (p = 0.0029). MRI performance varied across invasion depths, with excellent diagnostic accuracy for deep myometrial invasion (sensitivity, 87.0%; specificity, 95.9%). For aggressive tumors, no significant difference was observed between the two staging systems (p = 0.160). Subgroup analysis demonstrated that the presence of lymphovascular space invasion did not result in statistically significant differences in diagnostic agreement between MRI and pathological staging (p = 0.452). This study provides evidence that 2023 FIGO staging revisions present measurable challenges for MRI-based staging accuracy, particularly in the assessment of non-aggressive endometrial tumors confined to the uterus. Despite these challenges, MRI maintains reliable diagnostic performance for detecting deep myometrial invasion in uterus-confined disease, supporting its continued utility in preoperative staging protocols. KEY TAKE‑HOME: Radiologists should recognize the statistically significant reduction in diagnostic accuracy for detecting the absence of myometrial invasion under FIGO 2023 criteria, particularly in non-aggressive endometrioid tumors, and consider integrating complementary quantitative imaging parameters or molecular biomarkers to enhance the preoperative staging precision.

Biological characteristics prediction of endometrial cancer based on deep convolutional neural network and multiparametric MRI radiomics

The exploration of deep learning techniques for predicting various biological characteristics of endometrial cancer (EC) is of significant importance. The objective of this study was to develop an optimized radiomics scheme combining multiparametric magnetic resonance imaging (MRI), deep learning, and machine learning to predict biological features including myometrial invasion (MI), lymph-vascular space invasion (LVSI), histologic grade (HG), and estrogen receptor (ER). This retrospective study involved 201 EC patients, who were divided into four groups according to the specific tasks. The proposed radiomics scheme extracted quantitative imaging features and multidimensional deep learning features from multiparametric MRI. Several classifiers were employed to predict biological features. Model performance and interpretability were assessed using traditional classification metrics, Gradient-weighted Class Activation Mapping (Grad-CAM), and SHapley Additive exPlanation (SHAP) techniques. In the deep MI (DMI) prediction task, the proposed protocol achieved an area under the curve (AUC) value of 0.960 (95% CI 0.9005-1.0000) in the test cohort. In the LVSI prediction task, the AUC of the proposed scheme in the test cohort was 0.924 (95% CI 0.7760-1.0000). In the HG prediction task, the AUC value of the proposed scheme in the test cohort was 0.937 (95% CI 0.8561-1.0000). In the ER prediction task, the AUC value of the proposed scheme in the test cohort was 0.929 (95% CI 0.7991-1.0000). The proposed radiomics scheme outperformed the comparative scheme and effectively extracted imaging features related to the expression of EC biological characteristics, providing potential clinical significance for accurate diagnosis and treatment decision-making.

Endometrial carcinoma: association between mutational status, sites of metastasis, recurrence, and correlation with overall survival

To investigate the association between sites of endometrial carcinoma (EC) recurrence and metastases, mutational status, race, and overall survival (OS). This single-center retrospective study evaluated patients with biopsy-proven EC that underwent genomic molecular testing between January 2015 and July 2021. Association between genomic profile and sites of metastases or recurrence was performed using Pearson's chi-squared or Fisher exact test. Survival curves for ethnicity and race, mutations, sites of metastases or recurrence were estimated using the Kaplan-Meier method. Univariable and multivariable Cox proportional hazard regression models were used. The study included 133 women [median age 64 years (IQR 57-69)]. The most common mutation was TP53 (65/105 patients, 62%). The most common site of metastasis was the peritoneum (35/43, 81%). The most common recurrence was in lymph nodes (34/75, 45%). Mutations of TP53 and PTEN were significantly associated with Black women (p = 0.048, p = 0.004, respectively). In the univariable Cox regression analyses, TP53 mutation and presence of recurrence or metastases to the peritoneum were associated with lower OS (HR 2.1; 95% CI 1.1, 4.3; p = 0.03/ HR 2.9; 95% CI 1.6, 5.4; p = 0.0004; respectively). On multivariable Cox proportional hazards model ER expression (HR 0.4; 95% CI 0.22, 0.91; p = 0.03), peritoneal recurrence or metastases (HR 3.55; 95% CI 1.67, 7.57; p = 0.001), and Black race (HR 2.2; 95% CI 1.1, 4.6; p = 0.03) were significant independent predictors of OS. The integration of EC mutational status and clinicopathological risk assessment demonstrated potential implications on the patterns of metastasis, recurrence, and OS.

Dynamic contrast-enhanced MR imaging of uterine endometrial carcinoma with/without squamous differentiation

Endometrial carcinoma with strong enhancement on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) is suggestive of high-grade type II endometrial carcinoma. However, low-grade type I endometrial carcinoma may also sometimes show strong enhancement. We hypothesized that squamous differentiation would contribute to the strong enhancement at the early phase on DCE-MRI-like uterine cervical squamous cell carcinoma and compared the DCE-MRI findings of endometrial carcinoma with and without squamous differentiation. DCE-MRI of endometrial carcinoma including 41 low-grade type I endometrial carcinomas without squamous differentiation (LG), 39 low-grade type I endometrial carcinomas with squamous differentiation (LGSD), and 20 high-grade type II endometrial carcinomas (HG) was retrospectively evaluated. Significant difference in the time-intensity curves was found between LG and HG and LG and LGSD, whereas no significant difference was seen between HG and LGSD. Curve type 3 (initial signal rise which is steeper than that of the myometrium) was more frequent in HG (60%) and LGSD (77%) than in LG (34%). It should be recognized as a pitfall that high-grade type II endometrial carcinoma and low-grade type I endometrial carcinoma with squamous differentiation may show similar early strong enhancement on DCE-MRI.

Whole-tumor ADC histogram analysis for differentiating endometriosis-related tumors: seromucinous borderline tumor, clear cell carcinoma and endometrioid carcinoma

To investigate the feasibility of whole-tumor apparent diffusion coefficient (ADC) histogram analysis for improving the differentiation of endometriosis-related tumors: seromucinous borderline tumor (SMBT), clear cell carcinoma (CCC) and endometrioid carcinoma (EC). Clinical features, solid component ADC (ADC A significantly higher ADC Whole-tumor ADC histogram analysis was valuable for differentiating endometriosis-related tumors, and the 90th percentile ADC was optimal in differentiating CCC from EC.

Uterine fibroid-like tumors: spectrum of MR imaging findings and their differential diagnosis

Uterine leiomyoma, also known as uterine fibroid, is the most common gynecological tumor, affecting almost 80% of women at some point during their lives. In the same time, other fibroid-like tumors have similar clinical presentations and about 0.5% of resected tumors of which were presumed benign fibroids in the preoperative diagnosis revealed as malignant sarcomas in the final histopathological examination. Amid the emergence of nonsurgical or minimally invasive procedures for symptomatic benign uterine fibroids, such as uterine artery embolization, high-intensity-focused ultrasound, or laparoscopic myomectomy, the preoperative diagnosis of uterine tumors through imaging becomes all the more relevant. Preoperative tissue sampling is challenging because of the variable location of the myometrial mass; thus, the preoperative evaluation of size and location is increasingly performed through magnetic resonance imaging. Features in images might also be useful for examining the full spectrum of such growths, from benign fibroids to neoplasms of uncertain behavior and malignant sarcomas. Benign fibroids include usual-type leiomyomas, myomas with degeneration, and mitotically active leiomyomas. Neoplasms of uncertain behavior include smooth muscle tumors of uncertain malignant potential, leiomyomas with bizarre nuclei, and cellular leiomyomas. Malignant sarcomas comprise leiomyosarcomas, endometrial stromal sarcomas, adenosarcomas, and carcinosarcomas. The purpose of this article is to review the spectrum of MRI findings of uterine fibroid-like tumors, from benign variants, uncertain behavior to malignant sarcomas, and update the advanced imaging modalities, including diffusion-weighted imaging, positron emission tomography/computed tomography, combining texture analysis and radiomics, to tackle this important issue.

MR Imaging of uterine sarcomas: a comprehensive review with radiologic-pathologic correlation

The aim of this article is to summarize the MRI features of each sarcoma subtype and to correlate them with its pathological findings. Literature review through PubMed/Medline database to identify relevant articles on uterine sarcomas, with a special emphasis on their MRI findings and pathological features. While several, more generalistic, MRI findings of a uterine tumour should raise suspicion for malignancy (including irregular contour, intra-tumoral necrosis/hemorrhage and low ADC values), some particular features may suggest their specific histological subtype such as the gross lymphovascular invasion associated with endometrial stromal sarcomas, the "bag of worms" appearance of the low-grade endometrial stromal sarcoma and the "lattice-like" aspect of adenosarcomas which results from the mixed composition of solid and multiseptated cystic components. Knowledge of the different histological uterine sarcoma subtypes, their specific MRI features and comprehension of their pathological background allows for a more confident diagnosis and may indicate the correct histological subtype.

Quantitative imaging of uterine cancers with diffusion-weighted MRI and 18-fluorodeoxyglucose PET/CT

Imaging plays an important role in the diagnosis and treatment of women with uterine cervical and endometrial cancers. Quantitative imaging, through MRI, PET/CT, and hybrid PET/MRI, allows for characterization of primary tumors beyond anatomic and qualitative descriptors. MRI diffusion-weighted imaging (DWI) yields an apparent diffusion coefficient (ADC), which can be applied in both the pre-and post-treatment assessment of uterine tumors. PET/CT assesses metabolic activity, and measurement of tumor standardized uptake value (SUV) is a useful metric in the staging of uterine malignancies. Hybrid PET/MRI is an emerging modality that combines the soft tissue contrast of MRI with the molecular imaging capability of PET. This review provides an overview of these quantitative imaging modalities, and their current and potential roles in the assessment of uterine cervical and cancer.

Endometrial cancer from early to advanced-stage disease: an update for radiologists

The purpose of this article is to review the current molecular classification of endometrial cancer, the imaging findings in early and advanced disease, and the current management strategies, focusing on the new systemic therapies for advanced EC. In recent years, the management of endometrial cancer has significantly changed. The molecular characterization of endometrial cancer has shed new light into the biologic behavior of this disease, the International Federation of Gynecology and Obstetrics staging system was recently revised, and imaging was formally incorporated in the management of endometrial cancer. Recent genomic analysis of endometrial cancer led to the approval of new molecular-targeted therapies and immune checkpoint inhibitors. Imaging allows assessment of myometrial invasion, cervical stromal extension, lymph node involvement and distant metastases, and has a crucial role for treatment planning. Treatment strategies, which include surgery, radiation and systemic therapies are based on accurate staging and risk stratification.

Multiparametric magnetic resonance imaging facilitates the selection of patients prior to fertility-sparing management of endometrial cancer

To compare the diagnostic performance of biparametric magnetic resonance imaging (bpMRI) versus multiparametric MRI (mpMRI) for the staging of well-differentiated endometrioid endometrial cancer (EC) in potential candidates for fertility-sparing management. This multi-center retrospective study included 48 potential candidates for fertility-sparing management (age <46 years, grade 1 endometroid EC) who did not wish to undergo fertility-sparing management and thus underwent definitive surgery. Two readers (R1, R2) independently reviewed bpMRI (T1, T2, and diffusion-weighted imaging) and mpMRI (bpMRI and dynamic contrast-enhanced imaging, DCE) during two separate sessions spaced one month apart for the presence of myometrial invasion (MI), cervical stromal involvement (CSI), malignant adnexal disease (mAD), and pelvic lymphadenopathy (pLNM). Each reader also recorded maximum tumor diameter, tumor volume, and tumor-to-uterine volume ratio (TVR) on T2-weighted imaging. The diagnostic performance of bpMRI and mpMRI was determined for each reader with surgical pathology serving as a gold standard. The area under the receiver operating curve (AUC) for bpMRI versus mpMRI was 0.76/0.78 (R1/R2) versus 0.84/0.83 for MI, 0.79/0.76 versus 0.99/0.80 for CSI, 0.84/0.84 versus 0.84/0.80 for mAD, and 0.82/0.82 for pLMN. The sensitivity and specificity of MRI for detecting tumor spread beyond the endometrium were 71%/77% and 71%/65% for bpMRI (R1/R2) vs. 84%/90% and 71%/65% for mpMRI (R1/R2), respectively. The AUC of maximum tumor diameter, tumor volume, and TVR for MI was 0.71/0.61, 0.73/0.75, and 0.75/0.77 for R1/R2, respectively. MRI had moderate diagnostic performance across potential candidates for fertility-sparing treatment of EC. mpMRI outperformed bpMRI for detecting EC spreading beyond the endometrium.

MR diagnosis of SCC arising within ovarian cystic teratomas: analysis of mural nodule characteristics

Abstract Purpose This study aims to evaluate and identify magnetic resonance (MR) findings of mural nodules to detect squamous cell carcinoma arising from ovarian mature cystic teratoma (SCC-MCT). Methods This retrospective study examined 135 patients (SCC-MCTs, n = 12; and benign MCTs, n = 123) with confirmed diagnoses across five different institutions between January 2010 and June 2022. Preoperative MR images for each patient were independently assessed by two experienced radiologists and analyzed following previously reported findings (PRFs): age, tumor size, presence of mural nodules, size of mural nodule, and the angle between mural nodule and cyst wall (acute or obtuse). Furthermore, this study evaluated four mural nodule features—diffusion restriction, fat intensity, Palm tree appearance, and calcification—and the presence of transmural extension. Results There were significant differences between the SCC-MCT and benign MCT groups in terms of all PRFs and all mural nodule findings (p &lt; 0.01). Among the PRFs, “tumor size” demonstrated the highest diagnostic performance, with a sensitivity of 83.3% and a specificity of 88.6%. A combination of the aforementioned four mural nodule findings showed a sensitivity and specificity of 83.3% and 97.6%, respectively, for the diagnosis of SCC-MCT. Regarding diagnosis based on a combination of four mural nodule findings, the specificity was significantly higher than the diagnosis based on tumor size (p = 0.021). Based on these mural nodule findings, three SCC-MCT patients without transmural invasion could be diagnosed. Conclusion Mural nodule MR findings had a higher diagnostic performance than PRFs for SCC-MCT and can potentially allow early detection of SCC-MCTs. Graphical abstract

Combining multimodal diffusion-weighted imaging and morphological parameters for detecting lymph node metastasis in cervical cancer

Accurate detection of lymph node metastasis (LNM) is crucial for determining the tumor stage, selecting optimal treatment, and estimating the prognosis for cervical cancer. This study aimed to assess the diagnostic efficacy of multimodal diffusion-weighted imaging (DWI) and morphological parameters alone or in combination, for detecting LNM in cervical cancer. In this prospective study, we enrolled consecutive cervical cancer patients who received multimodal DWI (conventional DWI, intravoxel incoherent motion DWI, and diffusion kurtosis imaging) before treatment from June 2022 to June 2023. The largest lymph node (LN) observed on each side on imaging was matched with that detected on pathology to improve the accuracy of LN matching. Comparison of the diffusion and morphological parameters of LNs and the primary tumor between the positive and negative LN groups. A combined diagnostic model was constructed using multivariate logistic regression, and the diagnostic performance was evaluated using receiver operating characteristic curves. A total of 93 cervical cancer patients were enrolled: 35 with LNM (48 positive LNs were collected), and 58 without LNM (116 negative LNs were collected). The area under the curve (AUC) values for the apparent diffusion coefficient, diffusion coefficient, mean diffusivity, mean kurtosis, long-axis diameter, short-axis diameter of LNs, and the largest primary tumor diameter were 0.716, 0.720, 0.716, 0.723, 0.726, 0.798, and 0.744, respectively. Independent risk factors included the diffusion coefficient, mean kurtosis, short-axis diameter of LNs, and the largest primary tumor diameter. The AUC value of the combined model based on the independent risk factors was 0.920, superior to the AUC values of all the parameters mentioned above. Combining multimodal DWI and morphological parameters improved the diagnostic efficacy for detecting cervical cancer LNM than using either alone.

Diagnostic value of serum CA125 combined with PET/CT in ovarian cancer and tuberculous peritonitis in female patients

To evaluate the diagnostic value of serum CA125 combined with A total of 86 female patients (64 OC and 22 TBP) were included in this study. Serum CA125, PET/CT maximal intensity projection (MIP), maximal standardized uptake value, ovarian mass, ascites volume, and other indicators were analyzed and a diagnostic scoring system was established according to the weights of statistically significant indicators. Univariate analysis showed that serum CA125 in OC and TBP patients were 2079.9 ± 1651.3 U/mL and 448.3 ± 349.5 U/mL (P < 0.001). In MIP images, abdominal lesions were focal distribution in 92.2% (59/64) of OC patients and diffuse distribution in 95.5% (21/22) of TBP patients (P < 0.001). Ovarian masses could be observed in 82.8% (53/64) OC patients and 31.8% (7/22) TBP patients (P <0.001). The other indicators were not statistically significant. Logistic regression analysis showed that serum CA125 and MIP were independent risk factors for diagnosis. A diagnostic scoring system could be established based on serum CA125, MIP and ovarian mass, and the diagnostic sensitivity, specificity, accuracy, positive predictive value, and negative predictive value were 98.4% (63/64), 95.5% (21/22), 97.7% (84/86), 98.4% (63/64), and 95.5% (21/22), respectively. Serum CA125 combined with PET/CT is of great value in the diagnosis of OC and TBP. A simple and efficient diagnostic scoring system can be established using serum CA125, MIP image feature, and ovarian mass.

Integrated pretreatment diffusion kurtosis imaging and serum squamous cell carcinoma antigen levels: a biomarker strategy for early assessment of radiotherapy outcomes in cervical cancer

This study aims to explore the utility of pretreatment DKI parameters and serum SCC-Ag in evaluating the early therapeutic response of cervical cancer to radiotherapy. A total of 33 patients diagnosed with cervical cancer, including 31 cases of cervical squamous cell carcinoma and two cases of adenosquamous carcinoma, participated in the study. All patients underwent conventional MRI and DKI scans on a 3T magnetic resonance scanner before radiotherapy and after ten sessions of radiotherapy. The therapeutic response was evaluated based on the Response Evaluation Criteria in Solid Tumors (RECIST) version 1.1. Patients were categorized into a response group (RG), comprising Complete Remission (CR) and Partial Remission (PR), and a non-response group (NRG), comprising Stable Disease (SD) and Progressive Disease (PD). LASSO was employed to select pretreatment DKI parameters, and ROC curves were generated for the selected parameters and serum SCC-Ag. Significant differences were observed in pretreatment MD, Da, Dr, MK, Ka, Kr, and SCC-Ag between the RG and NRG groups (P < 0.01). However, no significant differences were noted for FA and FAK (P = 0.441&0.928). The two selected parameters (MD and MK) demonstrated area under the curve (AUC), sensitivity, and specificity of 0.810, 0.769, 0.850 and 0.827, 0.846, 0.750, respectively. The combination of MD and MK exhibited an improved AUC of 0.901, sensitivity of 0.692, and specificity of 1.000, with a higher Youden index compared to the individual parameters. Conversely, the AUC, sensitivity, and specificity of the combination of MD, MK, and SCC-Ag were 0.852, 0.615, and 1.000, with a Youden index of 0.615. Pretreatment MD, MK, and SCC-Ag demonstrate potential clinical utility, with the combined application of MD and MK showing enhanced efficacy in assessing the early therapeutic response of cervical cancer to radiotherapy. The addition of SCC-Ag did not contribute further to the assessment efficacy.

Radiomics combined with clinical and MRI features may provide preoperative evaluation of suboptimal debulking surgery for serous ovarian carcinoma

Abstract Purpose To develop and validate a model for predicting suboptimal debulking surgery (SDS) of serous ovarian carcinoma (SOC) using radiomics method, clinical and MRI features. Methods 228 patients eligible from institution A (randomly divided into the training and internal validation cohorts) and 45 patients from institution B (external validation cohort) were collected and retrospectively analyzed. All patients underwent abdominal pelvic enhanced MRI scan, including T2-weighted imaging fat-suppressed fast spin-echo (T2FSE), T1-weighted dual-echo magnetic resonance imaging (T1DEI), diffusion weighted imaging (DWI), and T1 with contrast enhancement (T1CE). We extracted, selected and eliminated highly correlated radiomic features for each sequence. Then, Radiomic models were made by each single sequence, dual-sequence (T1CE + T2FSE), and all-sequence, respectively. Univariate and multivariate analyses were performed to screen the clinical and MRI independent predictors. The radiomic model with the highest area under the curve (AUC) was used to combine the independent predictors as a combined model. Results The optimal radiomic model was based on dual sequences (T2FSE + T1CE) among the five radiomic models (AUC = 0.720, P &lt; 0.05). Serum carbohydrate antigen 125, the relationship between sigmoid colon/rectum and ovarian mass or mass implanted in Douglas’ pouch, diaphragm nodules, and peritoneum/mesentery nodules were considered independent predictors. The AUC of the radiomic–clinical–radiological model was higher than either the optimal radiomic model or the clinical–radiological model in the training cohort (AUC = 0.908 vs. 0.720/0.854). Conclusions The radiomic–clinical–radiological model has an overall algorithm reproducibility and may help create individualized treatment programs and improve the prognosis of patients with SOC. Graphical abstract

Preoperative risk assessment of endometrial cancer using histogram analysis of weighted and quantitative MRI images

Abstract Objective The aim of this study was to evaluate the capability of histogram analysis of weighted and quantitative MRI images to improve preoperative endometrial cancer (EC) risk stratification by providing information about the histological properties of the tumours. Methods In this prospective study, 94 patients with biopsy verified endometrial carcinoma underwent a preoperative MRI examination performed according to the European Society of Urogenital Radiology (ESUR) guidelines with addition of synthetic MRI, dynamic contrast enhancement and diffusion weighted imaging (DWI) with high b-values. Quantitative relaxation maps, perfusion maps and diffusion kurtosis imaging (DKI) maps were generated from the additional sequences. Tumours were segmented on three adjacent slices and histogram properties were compared between tumours with low and high histological risk. Results Significant differences were found between tumours with low and high histological risk in the histogram properties for the DKI derived apparent diffusion maps (D app ): mean (p = 0.048), median (p = 0.025), skewness (p &lt; 0.001) and kurtosis (p = 0.003). No significant differences between the groups were observed in histogram properties of quantitative relaxation maps, acquired by synthetic MRI. Conclusion Histogram analysis of DKI shows better potential to discriminate between EC histological risk groups and histologically determined endometrioid tumour grades than regular DWI, relaxation maps from synthetic MR, perfusion maps and T1 or T2 weighted images.

The updated 2023 staging of endometrial cancer: tips for MRI interpretation

Abstract Purpose This study aims to highlight the major modifications introduced in the FIGO 2023 staging system for endometrial cancer (EC) and their implications for MRI interpretation. Methods This pictorial essay was based on a retrospective review of 27 histologically confirmed cases of endometrial cancer (EC) imaged between 2009 and 2023 at our institution. Cases were selected to represent a broad spectrum of FIGO 2009 and FIGO 2023 stages, emphasizing features with updated staging implications. Inclusion criteria were availability of preoperative pelvic MRI and complete histopathological data, including molecular classification when available. Exclusion criteria included suboptimal image quality or incomplete clinical records. MRI assessments were performed by two radiologists with 25 years of experience in gynecological imaging, respectively. In illustrative examples where inter-reader differences arose, consensus was reached after joint review; however, no formal inter-reader agreement statistics (e.g., kappa values) were calculated, given the descriptive nature of the study. Results The revised FIGO 2023 staging incorporates molecular subtypes, refines classification criteria, and improves the prognostic significance of MRI findings in EC staging. Conclusion The integration of histopathology, molecular markers, and MRI features enhances diagnostic accuracy and treatment planning.

Characterization of complex renal cysts in hereditary leiomyomatosis and renal cell cancerUsing magnetic resonance based qualitative features

Abstract Purpose Hereditary Leiomyomatosis and Renal Cell Cancer (HLRCC) is a hereditary cancer syndrome associated with germline pathogenic variants of the fumarate hydratase (FH) are at risk for the development of benign renal cysts as well as an aggressive form of renal cell carcinoma which can occur inside the cysts. This study was conducted in order to assess the role of MR imaging characteristics of HLRCC-associated cystic lesions for distinguishing benign from malignant complex renal cysts in this patient population. Methods This IRB-approved retrospective study included 42 HLRCC patients (mean age, 46 ± 14 years; men: women, 22:20) with a pathogenic FH germline variant with renal cysts on abdominal MRI. Between June 2002 and May 2022 these patients underwent partial or radical nephrectomy for surgical removal of 76 renal lesions suspicious for renal carcinomas. Two abdominal radiologists independently reviewed the MRI images of all lesions while blinded to the surgical pathology. The lesion characteristics, including location, 3D dimensions, internal composition, characteristics of the cyst wall, nodules, septations, enhancement patterns in different series and restricted diffusion on ADC, and b-2000 series were recorded. Results Out of the 76 histologically characterized renal lesions, 44 (58%) were found to be benign and 32 (42%) were malignant. Malignant cystic lesions had a significantly larger mean diameter (4.0 ± 3.4 cm) compared to benign lesions (1.8 ± 2.1 cm, p = 0.002). Inter-reader agreement analysis identified 12 imaging features with moderate agreement (κ &gt;0.4). Univariate analysis identified 8 significant predictors of malignancy: “combined areas of enhancement on T1-weighted images during the nephrogenic phase (the nephrogenic phase, occurring approximately 70 seconds after intravenous contrast injection)”, “endophytic/exophytic mass”, “presence of a nodule”, and “nodule enhancement on T1 nephrogenic phase.” The final multivariable model for Reader 1 achieved an AUC of 0.86 and for reader 2 with an AUC of 0.91, indicating high diagnostic accuracy. At a predicted‐probability threshold of 0.17 (point = 60), the nomogram identified all malignant lesions and would have spared 57% of patients with benign cysts from unnecessary surgery. Conclusion Qualitative MRI features, including nodule presence, enhancement patterns, and lesion size, effectively differentiate between benign and malignant renal complex cysts in patients with HLRCC. The final multivariable model achieved high diagnostic, highlighting the potential of MRI in guiding clinical decision-making and improving management of cystic renal lesions in this high-risk population. Graphical abstract Created in BioRender. Sheikhy, A. (2025) https://BioRender.com/w45f229

Ultrasound-guided percutaneous microwave ablation assisted by a three-dimensional visualization treatment platform (3DVOPS) for large uterine fibroids

This study aims to evaluate the efficacy of a three-dimensional visualization operative planning system (3DVOPS) in ultrasound-guided percutaneous microwave ablation (US-PMWA) for the treatment of large uterine fibroids. From October 2020 to December 2023, a total of 30 patients with symptomatic uterine fibroids (≥ 7 cm) who underwent US-PMWA with the assistance of a 3D visualization operative planning system were included in this retrospective study. A control group of 60 patients who underwent US-PMWA using conventional 2D image operative planning methods was also studied. Assessment endpoints included technical efficacy and complications. The ablation time and energy consumption in the 3D group were significantly lower than those in the 2D group (45.2 ± 7.5 min vs. 56.6 ± 8.9 min and 77.5 ± 19.3 kJ vs. 100.9 ± 36.7 kJ, respectively; P < 0.05). There was no significant difference in the ablation rate between the two groups. The incidence of vaginal discharge after ablation was lower in the 3D group compared to the 2D group (6.6% vs. 13.3%, P < 0.05). No severe complications were reported during the follow-up period. The 3DVOPS can reduce ablation time and microwave energy requirements for the treatment of large uterine fibroids via US-PMWA, while also enhancing the accuracy of ablation.

A radiomic nomogram based on arterial phase of CT for differential diagnosis of ovarian cancer

Abstract Purpose To develop and validate a radiomic nomogram based on arterial phase of CT to discriminate the primary ovarian cancers (POCs) and secondary ovarian cancers (SOCs). Methods A total of 110 ovarian cancer patients in our hospital were reviewed from January 2010 to December 2018. Radiomic features based on the arterial phase of CT were extracted by Artificial Intelligence Kit software (A.K. software). The least absolute shrinkage and selection operation regression (LASSO) was employed to select features and construct the radiomics score (Rad-score) for further radiomics signature calculation. Multivariable logistic regression analysis was used to develop the predicting model. The predictive nomogram model was composed of rad-score and clinical data. Nomogram discrimination and calibration were evaluated. Results Two radiomic features were selected to build the radiomics signature. The radiomics nomogram that incorporated 2 radiomics signature and 2 clinical factors (CA125 and CEA) showed good discrimination in training cohort (AUC 0.854), yielding the sensitivity of 78.8% and specificity of 90.7%, which outperformed the prediction model based on radiomics signature or clinical data alone. A visualized differential nomogram based on the radiomic score, CEA, and CA125 level was established. The calibration curve demonstrated the clinical usefulness of the proposed nomogram. Conclusion The presented nomogram, which incorporated radiomic features of arterial phase of CT with clinical features, could be useful for differentiating the primary and secondary ovarian cancers.

The feasibility of high-resolution organ-axial T2-weighted MRI when combined with federation of gynecology and obstetrics (FIGO) classification of uterine fibroid patients

Correctly classifying uterine fibroids is essential for treatment planning. The objective of this study was to assess the accuracy and reliability of the FIGO classification system in categorizing uterine fibroids via organ-axial T2WI and to further investigate the factors associated with uterine compression. A total of 130 patients with ultrasound-confirmed fibroids were prospectively enrolled between March 2023 and May 2024. These patients underwent MR examinations, including body-axial T2W (sagittal and axial) and organ-axial T2W (high resolution with oblique coronal and double oblique axial). For postprocessing, the interobserver agreements between two radiologists and the interagreements between two MR examinations and operational descriptions were evaluated via kappa statistics. The accuracy of axial and organ-axial T2W assessments in the FIGO classification of uterine fibroids was compared when surgical outcomes were used as the gold standard. The Kruskal‒Wallis test was used to compare the differences in cavity deformation across various FIGO classifications. Spearman's rank correlation test was used to analyze the correlation between the FIGO classification and the parameters of uterine cavity deformation. In total, 170 fibroids from 130 patients were included. Compared with body-axial T2WI, organ-axial T2WI showed better interobserver agreement and greater interagreements with operational descriptions, with kappa values of 0.877 (P = 0.04) and 0.932 (P = 0.037), respectively. The accuracy of the organ-axial T2WI assessment in determining the FIGO classification of uterine fibroids was greater than that of the body-axial T2WI assessment, with an accuracy of 92.9% (P < 0.01). Thirty-two (38.1%) fibroids showed cavity deformation according to organ-axial T2WI, including fibroids with FIGO types 0-7 and 2-5. Among these factors, the size of the fibroids (S), base width (B), depth of compression (D), D/B, D/S, and compression angle (A) significantly differed among the different FIGO types of fibroids (P < 0.05). Compression angle exhibited a linear correlation with the FIGO type (P < 0.001). Compared with body-axial T2WI, organ-axial T2WI provides greater accuracy on the basis of the FIGO classification, which is more consistent with surgical outcomes. Given the excellent reliability and accuracy of the preoperative FIGO classification, organ-axial T2WI can contribute to treatment planning.

The Poké Ball sign in mature ovarian cystic teratoma

Distribution of prostate specific membrane antigen (PSMA) on PET-MRI in patients with and without ovarian cancer

Ovarian cancer is the most lethal cancer and future research needs to focus on the early detection and exploration of new therapeutic agents. The objectives of this proof-of-concept study are to assess the feasibility of PSMA 18F-DCFPyl PET/MR imaging for detecting ovarian cancer and to evaluate the PSMA distribution in patients with and without ovarian cancer. This prospective pilot proof-of-concept study in patients with and without ovarian cancers occurred between October 2017 and January 2020. Patients were recruited from gynecologic oncology or hereditary ovarian cancer clinics, and underwent surgical removal of the uterus and ovaries for gynecologic indications. PSMA 18F-DCFPyl PET/MRI was obtained prior to standard of care surgery. Fourteen patients were scanned: four patients with normal ovaries, six patients with benign ovarian lesions, and four patients with malignant ovarian lesions. Tracer uptake in normal ovaries (SUVmax = 2.8 ± 0.4) was greater than blood pool (SUVmax = 1.8 ± 0.5, p < 0.0001). Tracer uptake in benign ovarian lesions (2.2 ± 1.0) did not differ significantly from blood pool (p = 0.331). Tracer uptake in ovarian cancer (SUVmax = 7.8 ± 3.8) was greater than blood pool (p < 0.0001), normal ovaries (p = 0.0014), and benign ovarian lesions (p = 0.005). PET/MR imaging detected PSMA uptake in ovarian cancer, with little to no uptake in benign ovarian findings. These results are encouraging and further studies in a larger patient cohort would be useful to help determine the extent and heterogeneity of PSMA uptake in ovarian cancer patients.

Role of radiomics as a predictor of disease recurrence in ovarian cancer: a systematic review

AbstractOvarian cancer is associated with high cancer-related mortality rate attributed to late-stage diagnosis, limited treatment options, and frequent disease recurrence. As a result, careful patient selection is important especially in setting of radical surgery. Radiomics is an emerging field in medical imaging, which may help provide vital prognostic evaluation and help patient selection for radical treatment strategies. This systematic review aims to assess the role of radiomics as a predictor of disease recurrence in ovarian cancer. A systematic search was conducted in Medline, EMBASE, and Web of Science databases. Studies meeting inclusion criteria investigating the use of radiomics to predict post-operative recurrence in ovarian cancer were included in our qualitative analysis. Study quality was assessed using the QUADAS-2 and Radiomics Quality Score tools. Six retrospective studies met the inclusion criteria, involving a total of 952 participants. Radiomic-based signatures demonstrated consistent performance in predicting disease recurrence, as evidenced by satisfactory area under the receiver operating characteristic curve values (AUC range 0.77–0.89). Radiomic-based signatures appear to good prognosticators of disease recurrence in ovarian cancer as estimated by AUC. The reviewed studies consistently reported the potential of radiomic features to enhance risk stratification and personalise treatment decisions in this complex cohort of patients. Further research is warranted to address limitations related to feature reliability, workflow heterogeneity, and the need for prospective validation studies.

Prediction of recurrence risk factors in patients with early-stage cervical cancers by nomogram based on MRI handcrafted radiomics features and deep learning features: a dual-center study

To establish and validate a deep learning radiomics nomogram (DLRN) based on intratumoral and peritumoral regions of MR images and clinical characteristics to predict recurrence risk factors in early-stage cervical cancer and to clarify whether DLRN could be applied for risk stratification. Two hundred and twenty five pathologically confirmed early-stage cervical cancers were enrolled and made up the training cohort and internal validation cohort, and 40 patients from another center were enrolled into the external validation cohort. On the basis of region of interest (ROI) of intratumoral and different peritumoral regions, two sets of features representing deep learning and handcrafted radiomics features were created using combined images of T2-weighted MRI (T2WI) and diffusion-weighted imaging (DWI). The signature subset with the best discriminant features was chosen, and deep learning and handcrafted signatures were created using logistic regression. Integrated with independent clinical factors, a DLRN was built. The discrimination and calibration of DLNR were applied to assess its therapeutic utility. The DLRN demonstrated satisfactory performance for predicting recurrence risk factors, with AUCs of 0.944 (95% confidence interval 0.896-0.992) and 0.885 (95% confidence interval 0.834-0.937) in the internal and external validation cohorts. Furthermore, decision curve analysis revealed that the DLRN outperformed the clinical model, deep learning signature, and radiomics signature in terms of net benefit. A DLRN based on intratumoral and peritumoral regions had the potential to predict and stratify recurrence risk factors for early-stage cervical cancers and enhance the value of individualized precision treatment.

Diagnostic performance of PET/CT and PET/MR in the management of ovarian carcinoma—a literature review

Ovarian cancer is a challenging disease. It often presents at an advanced stage with frequent recurrence despite optimal management. Accurate staging and restaging are critical for improving treatment outcomes and determining the prognosis. Imaging is an indispensable component of ovarian cancer management. Hybrid imaging modalities, including positron emission tomography/computed tomography (PET/CT) and PET/magnetic resonance imaging (MRI), are emerging as potential non-invasive imaging tools for improved management of ovarian cancer. This review article discusses the role of PET/CT and PET/MRI in ovarian cancer.

Preoperative CT image-based assessment for estimating risk of ovarian torsion in women with ovarian lesions and pelvic pain

To define and weight the preoperative CT findings for ovarian torsion and to develop an integrated nomogram for estimating the probability of ovarian torsion in women with ovarian lesion and pelvic pain. This retrospective study included 218 women with surgically resected ovarian lesions who underwent preoperative contrast-enhanced CT for pelvic pain from January 2014 to February 2019. Significant imaging findings for torsion were extracted using regression analyses and a regression coefficient-based nomogram was constructed. The diagnostic performance with sensitivity, specificity, and accuracy of the significant imaging findings and the nomogram were assessed. A total of 255 ovarian lesions (123 lesions with torsion and 132 lesions without torsion) were evaluated. Multivariable regression analysis showed that whirl sign (odds ratio [OR] 11.000; p < 0.001), tubal thickening (OR 4.621; p = 0.001), unusual location of ovarian lesion (OR 2.712; p = 0.020), and hemorrhagic component within adnexal lesion (OR 2.537; p = 0.028) were independent significant parameters predicting ovarian torsion. Tubal thickening showed the highest sensitivity (91.1%) and whirl sign showed the highest specificity (94.7%). When probabilities of ovarian torsion of 0.5 or more in the nomogram were diagnosed as ovarian torsion, sensitivity, specificity, and accuracy of the nomogram were 78.1%, 91.7%, and 85.1%, respectively. The whirl sign, tubal thickening, unusual location of ovarian lesion, and hemorrhagic component within adnexal lesion, and an integrated nomogram derived from these significant findings can be useful for predicting ovarian torsion.

Decoding incidental ovarian lesions: use of texture analysis and machine learning for characterization and detection of malignancy

To compare CT texture features of benign and malignant ovarian lesions and to build a machine learning model to detect malignancy in incidental ovarian lesions. In this IRB-approved, HIPAA-compliant, retrospective study, 427 consecutive patients with incidental ovarian lesions detected on contrast-enhanced CT (348, 81.5% benign and 79, 18.5% malignant) were included. The following CT texture features were analyzed using commercially available software (TexRAD, Feedback Plc, Cambridge, UK): total pixel, mean, standard deviation (SD), entropy, mean value of positive pixels (MPP), skewness, kurtosis and entropy. Three machine learning models were created by combining texture features and patients' age, and performance of these models was assessed using tenfold cross-validation. Receiver operating characteristics (ROC) were constructed to assess sensitivity and specificity. The cutoff value was picked using a cost-weighted method. Total pixels, mean, SD, entropy, MPP, and skewness were significantly different between benign and malignant groups (p < 0.05). With a selected 10 as a cost factor to optimize cutoff value selection, sensitivity 92%, specificity 60% in the random forest (RF) model, sensitivity 91%, specificity 69% in SVM model, and sensitivity 92%, specificity 61% in the logistic regression, respectively. CT texture analysis could provide objective imaging analysis of incidental ovarian lesions and ML models using CT texture features and age demonstrated high sensitivity and moderate specificity for detection of malignant lesions.

Gynecologic tumor board: a radiologist’s guide to vulvar and vaginal malignancies

AbstractPrimary vulvar and vaginal cancers are rare female genital tract malignancies which are staged using the 2009 International Federation of Gynecology and Obstetrics (FIGO) staging. These cancers account for approximately 2,700 deaths annually in the USA. The most common histologic subtype of both vulvar and vaginal cancers is squamous cell carcinoma, with an increasing role of the human papillomavirus (HPV) in a significant number of these tumors. Lymph node involvement is the hallmark of FIGO stage 3 vulvar cancer while pelvic sidewall involvement is the hallmark of FIGO stage 3 vaginal cancer. Imaging techniques include computed tomography (CT), positron emission tomography (PET)-CT, magnetic resonance imaging (MRI), and PET-MRI. MRI is the imaging modality of choice for preoperative clinical staging of nodal and metastatic involvement while PET-CT is helpful with assessing response to neoadjuvant treatment and for guiding patient management. Determining the pretreatment extent of disease has become more important due to modern tailored operative approaches and use of neoadjuvant chemoradiation therapy to reduce surgical morbidity. Moreover, imaging is used to determine the full extent of disease for radiation planning and for evaluating treatment response. Understanding the relevant anatomy of the vulva and vaginal regions and the associated lymphatic pathways is helpful to recognize the potential routes of spread and to correctly identify the appropriate FIGO stage. The purpose of this article is to review the clinical features, pathology, and current treatment strategies for vulvar and vaginal malignancies and to identify multimodality diagnostic imaging features of these gynecologic cancers, in conjunction with its respective 2009 FIGO staging system guidelines.

Predictors of malignancy in incidental adnexal lesions identified on CT in patients with prior non-ovarian cancer

To identify imaging features in incidental adnexal lesions which are associated with malignancy on portal venous phase contrast-enhanced CT in patients with known non-ovarian cancer. This IRB-approved, HIPAA-compliant retrospective study was performed at a tertiary cancer center. Portal venous phase contrast-enhanced CT from January 2010 to December 2015 was reviewed to identify women with non-ovarian malignancy and incidental adnexal lesion, with mean 18 months (range 1-80 months) to definitive diagnosis or last imaging follow-up. Imaging features of adnexal lesions were recorded (size, laterality, shape, attenuation, and composition) and correlated with outcome (benign or malignant) using univariate and multivariate logistic regression analysis. A point-based system was used to predict likelihood of malignancy. Of 276 women (mean age 45 years), 216 (78.3%) had benign lesions, 58 (21.0%) ovarian metastasis, and 2 (0.7%) had primary ovarian malignancy. On logistic regression model, lesion size > 5 cm (p-value, OR, 95% CI 0.01, 9.11, 1.70-48.87), bilaterality (< 0.0001, 28.34, 7.46-107.67), irregular shape (0.01, 12.31, 1.61-94.05), higher-than-simple-fluid attenuation (< 0.0001, 28.27, 5.65-141.59), and heterogeneous composition (0.0017, 10.75, 2.45-47.23) were associated with malignant outcome (AUC 0.97). A point-based system incorporating these five features (possible 0-5 points) had AUC of 0.97. Rate of malignancy was 0% (0/147) if none of the features of malignancy were present, 12.7% (8/63) if one feature was present, 51.7% (15/29) if two features were present, and 100% (37/37) if three or more features present. Risk of malignancy of incidental adnexal lesions in women with prior non-ovarian cancer can be estimated based on lesion features seen on portal venous phase contrast-enhanced CT.

MR findings for differentiating decidualized endometriomas from seromucinous borderline tumors of the ovary

Decidualized endometriomas (DEs) and seromucinous borderline tumors (SMBTs) exhibit similar MR findings including markedly hyperintense mural nodules within endometriotic cysts on T2-weighted images. The present study aimed to assess the efficacy of MR imaging for differentiating between DEs and SMBTs of the ovary. MR images of 8 DEs and 14 SMBTs were retrospectively assessed and compared according to pathologies. With regard to quantitative assessments of mural nodules, the number and signal intensity ratios (SIRs) on T1-weighted images were significantly greater in DEs than in SMBTs (11.0 ± 8.4 vs. 4.3 ± 4.1, p < 0.05 and 2.36 ± 0.56 vs. 1.49 ± 0.27, p < 0.01, respectively), whereas the height was significantly lower in DEs than in SMBTs (4.5 ± 1.4 mm vs. 21.9 ± 11.4 mm, p < 0.01). However, there were no significant differences between DEs and SMBTs in the SIRs on T2-weighted images, SIRs on diffusion-weighted images, and apparent diffusion coefficient values. With regard to qualitative assessments of mural nodules, the lobulated margin, pedunculated configuration, and T2 hypointense core were significantly more frequent in SMBTs than in DEs (71% vs. 0%, p < 0.01; 86% vs. 0%, p < 0.01; and 43% vs. 0%, p < 0.05, respectively). The number, height, SIRs on T1-weighted images, lobulated margin, pedunculated configuration, and T2 hypointense core of mural nodules within endometriotic cysts were useful MR findings for differentiating DEs from SMBTs.

Computed tomographic enterography (CTE) in evaluating bowel involvement in patients with ovarian cancer

To explore the utility of CTE in the evaluation of bowel invasion in patients with primary ovarian, fallopian tube, and peritoneal cancer. This observational study included 73 patients who received CTE before operation between September 2019 and December 2021. Two radiologists reviewed CTE images, focusing on the sites and depth of bowel involvement. Based on the findings during surgical exploration, we evaluated the diagnostic power, like sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), positive likelihood ratio (+ LR), and negative likelihood ratio (- LR) of CTE. Additionally, the characteristic images of bowel involvement on CTE corresponding to surgical findings were shown in the study. The rate of macroscopic bowel invasion in this cohort was 49.31% (36/73), of which eight patients had small bowel involvement, 17 patients had colon involvement and 27 patients had sigmoid-rectum involvement. CTE detected bowel invasion in the small intestine with a sensitivity, specificity, PPV, NPV, and accuracy of 87.50%, 92.31%, 58.33%, 98.36%, 91.78%; for colon, the statistics were 58.82%, 96.43%, 83.33%, 88.52%, 87.67% and for sigmoid-rectum 62.96%, 82.61%, 68.00%, 79.17%, 75.34%, respectively. CTE appeared a preferable diagnostic power on the small bowel and colon invasion in patients with primary ovarian, fallopian tube, and peritoneal cancer.

MR imaging of benign vulvar lesions: a pictorial essay

Benign vulvar lesions can be difficult to differentiate with few publications on their imaging appearances. While many vulvar lesions may be clinically diagnosed and treated, more are being detected incidentally with the increasing prevalence of magnetic resonance imaging (MRI) of the pelvis. In addition, clinicians may find imaging of benign vulvar lesions helpful for greater anatomical correlation. After reviewing the important MRI sequences for vulvar imaging and the anatomy of the vulva on MRI, this pictorial essay illustrates variety of cystic and solid benign vulvar lesions to familiarize radiologists with their common MRI appearances. Other miscellaneous pelvic lesions that can affect the vulva are also described.

Differentiating uterine adenosarcoma from endometrial polyps: MRI imaging features

This study was conducted to identify MRI features distinguishing uterine adenosarcoma from endometrial polyps and to predict the presence or absence of sarcomatous overgrowth (SO), a pathological finding linked to poor prognosis. This multicenter retrospective study included 11 cases of uterine adenosarcoma, with 5 showing SO and 6 without, and 20 cases of endometrial polyps measuring 3 cm or greater diameter. Quantitative evaluations (tumor volume, cystic lesion size, diffusion-weighted imaging [DWI] signal ratio, apparent diffusion coefficient [ADC] value, and normalized ADC value) and qualitative evaluations (degree of hemorrhage, signal intensity on T2-weighted imaging and DWI, number of cystic lesions, degree of contrast enhancement, and tumor localization) were performed. The evaluation parameters were compared between uterine adenosarcoma and endometrial polyp groups, and between SO and non-SO subgroups within uterine adenosarcoma. Uterine adenosarcoma had significantly larger tumor volumes (median 192,324 mm³ vs. 15,717 mm³, p < 0.001), larger cystic lesions (median 17.7 mm vs. 6.7 mm, p = 0.0074), and higher DWI signal ratios (median 1.50 vs. 1.08, p = 0.008) along with significantly lower ADC values (median 961.5 × 10 This study identified key imaging features of uterine adenosarcoma, including larger tumor volume, larger cystic lesions, gross intratumoral hemorrhage, higher DWI signal intensity, and lower ADC values. These findings can facilitate preoperative differentiation of uterine adenosarcoma from endometrial polyps.

Imaging the post-treatment pelvis with gynecologic cancers

CT-Based radiomics and deep learning for the preoperative prediction of peritoneal metastasis in ovarian cancers

To develop a CT-based deep learning radiomics nomogram (DLRN) for the preoperative prediction of peritoneal metastasis (PM) in patients with ovarian cancer (OC). A total of 296 patients with OCs were randomly divided into training dataset (N = 207) and test dataset (N = 89). The radiomics features and DL features were extracted from CT images of each patient. Specifically, radiomics features were extracted from the 3D tumor regions, while DL features were extracted from the 2D slice with the largest tumor region of interest (ROI). The least absolute shrinkage and selection operator (LASSO) algorithm was used to select radiomics and DL features, and the radiomics score (Radscore) and DL score (Deepscore) were calculated. Multivariate logistic regression was employed to construct clinical model. The important clinical factors, radiomics and DL features were integrated to build the DLRN. The predictive performance of the models was evaluated using the area under the receiver operating characteristic curve (AUC) and DeLong's test. Nine radiomics features and 10 DL features were selected. Carbohydrate antigen 125 (CA-125) was the independent clinical predictor. In the training dataset, the AUC values of the clinical, radiomics and DL models were 0.618, 0.842, and 0.860, respectively. In the test dataset, the AUC values of these models were 0.591, 0.819 and 0.917, respectively. The DLRN showed better performance than other models in both training and test datasets with AUCs of 0.943 and 0.951, respectively. Decision curve analysis and calibration curve showed that the DLRN provided relatively high clinical benefit in both the training and test datasets. The DLRN demonstrated superior performance in predicting preoperative PM in patients with OC. This model offers a highly accurate and noninvasive tool for preoperative prediction, with substantial clinical potential to provide critical information for individualized treatment planning, thereby enabling more precise and effective management of OC patients.

Diagnostic performance of radiomics models for preoperative prediction of microsatellite instability status in endometrial cancer: a systematic review and meta-analysis

Microsatellite instability (MSI), caused by defects in mismatch repair (MMR) genes, serves as a critical molecular biomarker with therapeutic implications for endometrial cancer (EC). This study aims to assess the diagnostic performance of radiomics as a non-invasive approach for predicting MSI status in EC. A systematic search across PubMed, Scopus, Embase, Web of Science, Cochrane library and Clinical Trials was conducted. Quality assessment was performed using QUADAS-2 and METRICS. Pooled sensitivity, specificity, positive likelihood ratio (PLR), negative likelihood ratio (NLR), diagnostic odds ratio (DOR), and area under the curve (AUC) were computed using a bivariate model. Separate meta-analyses for radiomics and combined models were conducted. Subgroup analysis and sensitivity analysis were conducted to find potential sources of heterogeneity. Likelihood ratio scattergram was used to evaluate the clinical applicability. A total of 9 studies (1650 patients) were included in the systematic review, with seven studies contributing to the meta-analysis of radiomics model and five for combined model. The pooled diagnostic performance of the radiomics model was as follows: sensitivity, 0.66; specificity, 0.89; PLR, 5.48; NLR, 0.43; DOR, 18.56; and AUC, 0.87. For combined model, the pooled sensitivity, specificity, PLR, NLR, DOR, and AUC were 0.58, 0.94, 7.37, 0.50, 16.43, and 0.85, respectively. Subgroup analysis of radiomics models revealed that studies employing non-linear classifiers achieved superior performance compared to those utilizing linear classifiers. Radiomics showed promise as non-invasive tool for MSI prediction in EC, with potential clinical utility in guiding personalized treatments. However, further studies are required to validate these findings.

Radiomics nomogram from multiparametric magnetic resonance imaging for preoperative prediction of substantial lymphovascular space invasion in endometrial cancer

We aimed to develop and validate a radiomics-based machine learning nomogram using multiparametric magnetic resonance imaging to preoperatively predict substantial lymphovascular space invasion in patients with endometrial cancer. This retrospective dual-center study included patients with histologically confirmed endometrial cancer who underwent preoperative magnetic resonance imaging (MRI). The patients were divided into training and test sets. Radiomic features were extracted from multiparametric magnetic resonance imaging to generate radiomic scores using a support vector machine algorithm. Three predictive models were constructed: clinical (Model This study enrolled 283 women (training set: n = 198; test set: n = 85). The lymphovascular space invasion groups (substantial and no/focal) had significantly different radiomic scores (P < 0.05). Model The multiparametric magnetic resonance imaging-based radiomics machine learning nomogram showed moderate diagnostic performance for substantial lymphovascular space invasion in patients with endometrial cancer.

Evaluating the utility of enhanced T1 mapping MR imaging in assessing depth of myometrial invasion and detecting DNA mismatch repair status in endometrial cancer: a pilot study

To evaluate the value of enhanced T1 mapping MR imaging in assessing the depth of myometrial invasion (MI) and in detecting DNA mismatch repair (MMR) status in endometrial cancer (EC) as a non-invasive imaging biomarker. This prospective study enrolled 46 patients with pathologically confirmed EC who underwent pelvic MRI and surgery within two weeks. Each patient underwent multiparametric MRI including T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), dynamic contrast-enhanced imaging (DCE), native T1 mapping and enhanced T1 mapping. Four radiologists (two junior, two senior) independently assessed MI depth of EC using two combinations: T2WI + DWI + DCE and T2WI + DWI + enhanced T1 mapping. Histopathology served as the reference standard. MMR status was determined by immunohistochemistry. Quantitative analysis of native T1, enhanced T1, and Apparent diffusion coefficient (ADC) values was performed, and inter-reader agreement and diagnostic performance were compared. Receiver operating characteristic curve (ROC) analysis was performed. Statistical significance was set at p  0.05). Inter-reader agreement improved with enhanced T1 mapping, particularly for junior readers (κ = 0.898 vs. κ = 0.538). Native T1 values were significantly higher in the proficient MMR group compared to the deficient MMR group (1655.5 ± 131.9 ms vs. 1549.1 ± 125.9 ms, P = 0.047). ROC analysis yielded an Area under the curve (AUC) of 0.729 for differentiating deficient MMR from proficient MMR, with a sensitivity of 87.0% and specificity of 67.7% at a cutoff of 1524.7 ms. Enhanced T1 mapping, when incorporated into routine MR protocols, offers diagnostic performance comparable to DCE for evaluating myometrial invasion in endometrial cancer and significantly improves inter-reader agreement. Native T1 values show promise as a non-invasive biomarker for detecting MMR status in EC.

Effectiveness of T2-weighted and contrast-enhanced T1-weighted multivane sequences in the preoperative evaluation of uterine endometrial cancer

The purpose of this study was to evaluate the clinical effectiveness of MultiVane (MV) sequence, which is a motion correction technique using rotating blades, for patients with uterine endometrial cancer. This study enrolled 42 patients with histopathologically confirmed uterine endometrial cancer, who underwent preoperative MRI including sagittal T2-weighted images (T2WI) and contrast-enhanced T1-weighted images (CE-T1WI) acquired using both turbo spin-echo (TSE) and MV sequences with approximately matched acquisition times. Two experienced radiologists independently evaluated all sagittal images. First, the readers assessed the degree of motion artifacts and measured the signal intensity of the tumor and myometrium to calculate the signal-to-noise ratio (SNR) and tumor-to-myometrium contrast ratio (CR). Second, the readers assessed the depth of myometrial invasion on sagittal T2WI and CE-T1WI acquired using TSE and MV sequences. Image quality and diagnostic performance for assessing myometrial invasion were compared between TSE and MV sequences. Motion artifacts were significantly improved on MV sequence than on TSE sequence (p  0.05). Sensitivities, specificities, accuracies, and area under the curve for the diagnosis of myometrial invasion were slightly increased on MV sequence than on TSE sequence, but these differences were not statistically significant (p > 0.05). MV sequence contributes to the improvement of motion artifacts in the female pelvis without degrading SNR and CR of endometrial cancer and myometrium compared to TSE sequence. MV sequence did not significantly improve the diagnostic performance for assessing myometrial invasion in endometrial cancer, possibly due to the limited imaging plane and small sample size.

Multiparametric MRI radiomics improves preoperative diagnostic performance for local staging in patients with endometrial cancer

To determine whether multiparametric magnetic resonance imaging (MRI) radiomics-based machine learning methods can improve preoperative local staging in patients with endometrial cancer (EC). Data of patients with histologically confirmed EC who underwent preoperative MRI were retrospectively analyzed and divided into a training or test set. Radiomic features extracted from multiparametric MR images were used to train and test the prediction of deep myometrial invasion (DMI) and cervical stromal invasion (CSI). Two radiologists assessed the presence of DMI and CSI on conventional MR images. A combined model incorporating a radiomic signature and conventional MR images was constructed and presented as a nomogram. Performance of the predictive models was assessed using the area under curve (AUC) in the receiver operating curve analysis and pairwise comparison using DeLong's test with Bonferroni correction. This study included 198 women (training set = 138, test set = 60). Conventional MRI achieved AUCs of 0.837 and 0.799 for detecting DMI and 0.825 and 0.858 for detecting CSI in the training and test sets, respectively. The nomogram achieved AUCs of 0.928 and 0.869 for detecting DMI and 0.913 and 0.937 for detecting CSI in the training and test sets, respectively. The ability of the nomogram to detect DMI and CSI in the two sets was superior to that of conventional MRI (adjusted p  0.05). A nomogram incorporating radiomics signature into conventional MRI improved the efficacy of preoperative local staging of EC.

Preoperative risk assessment of invasive endometrial cancer using MRI-based radiomics: a systematic review and meta-analysis

Image-derived machine learning (ML) is a robust and growing field in diagnostic imaging systems for both clinicians and radiologists. Accurate preoperative radiological evaluation of the invasive ability of endometrial cancer (EC) can increase the degree of clinical benefit. The present study aimed to investigate the diagnostic performance of magnetic resonance imaging (MRI)-derived artificial intelligence for accurate preoperative assessment of the invasive risk. The PubMed, Embase, Cochrane Library and Web of Science databases were searched, and pertinent English-language papers were collected. The pooled sensitivity, specificity, diagnostic odds ratio (DOR), and positive and negative likelihood ratios (PLR and NLR, respectively) of all the papers were calculated using Stata software. The results were plotted on a summary receiver operating characteristic (SROC) curve, publication bias and threshold effects were evaluated, and meta-regression and subgroup analyses were conducted to explore the possible causes of intratumoral heterogeneity. MRI-based radiomics revealed pooled sensitivity (SEN) and specificity (SPE) values of 0.85 and 0.82 for the prediction of high-grade EC; 0.80 and 0.85 for deep myometrial invasion (DMI); 0.85 and 0.73 for lymphovascular space invasion (LVSI); 0.79 and 0.85 for microsatellite instability (MSI); and 0.90 and 0.72 for lymph node metastasis (LNM), respectively. For LVSI prediction and high-grade histological analysis, meta-regression revealed that the image segmentation and MRI-based radiomics modeling contributed to heterogeneity (p = 0.003 and 0.04). Through a systematic review and meta-analysis of the reported literature, preoperative MRI-derived ML could help clinicians accurately evaluate EC risk factors, potentially guiding individual treatment thereafter.

Assessment of endometrial cancer with microcystic, elongated, and fragmented pattern invasion using multiparametric MRI

To assess the MRI findings of endometrial cancer with microcystic, elongated, and fragmented (MELF) pattern invasion and to evaluate the optimal sequences to detect deep myometrial invasion with MELF. This retrospective single-center case-control study included 85 patients with endometrial cancer, including 17 patients with MELF, between December 2020 and January 2023. Preoperative MRI, including T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and dynamic contrast-enhanced (DCE) with equilibrium phase contrast-enhanced (CE) MRI were reviewed by three radiologists. DWI signal gradation with DWI-CE mismatch (DG-DCM) and tumor-myometrium synchronous early enhancement (TME) were evaluated, as well as the diagnostic performance for deep myometrial invasion, first with T2WI + CE alone and then with the addition of DWI + DCE. Pathology was used as the reference standard. The sensitivity and specificity of DG-DCM were 41.2-76.5% and 89.7-98.5%, and those of TME were 70.7-82.4% and 94.1-95.6%, respectively, for MELF by the three readers. For the diagnosis of deep myometrial invasion with MELF, the addition of DWI + DCE to T2WI + CE significantly improved the sensitivity for two readers (from 16.7 to 91.7% for Reader 1, from 16.7 to 83.3% for Reader 2, p < 0.01) and the accuracy for one reader (from 35.3 to 82.4% for Reader 1, p < 0.01). In contrast, sensitivity, specificity and accuracy did not change with the addition of DWI + DCE in tumors without MELF. Endometrial cancer with MELF may show characteristic MRI findings of DG-DCM and TME. The value of DWI and DCE in detecting deep myometrial invasion may be high for MELF pattern invasion.

Deep learning reconstruction of diffusion-weighted imaging with single-shot echo-planar imaging in endometrial cancer: a comparison with multi-shot echo-planar imaging

To evaluate the efficacy of deep learning reconstruction (DLR) in diffusion-weighted imaging (DWI) with single-shot echo-planar imaging (SSEPI) for endometrial cancer, compared to multiplexed sensitivity-encoding (MUSE) DWI. We retrospectively reviewed 31 women with surgically confirmed endometrial cancer who underwent preoperative pelvic magnetic resonance imaging (MRI) including DWI. Qualitative analysis including overall image quality, susceptibility artifacts, sharpness of the uterine edge, and lesion conspicuity were compared among conventional SSEPI (SSEPI-C), SSEPI with DLR (SSEPI-DL), and MUSE using the Friedman's test. Quantitative analysis including the apparent diffusion coefficient (ADC) values, noise, signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were also compared among three DWI sequences using the Friedman's test. In addition, the diagnostic accuracy for deep myometrial invasion was compared to three DWI sequences using Cochran's Q test. The scores of overall image quality, sharpness of the uterine edge, and lesion conspicuity in SSEPI-DL were higher than SSEPI-C (p  0.05). Noise in SSEPI-DL was lower than SSEPI-C (p  0.05). SNR and CNR in SSEPI-DL were also superior to SSEPI-C (p  0.05). The diagnostic accuracy for detecting deep myometrial invasion showed no significant difference among SSEPI-C, SSEPI-DL and MUSE (p > 0.05). DLR improves the image quality of DWI in endometrial cancer, demonstrating image quality equivalent to that of SSEPI-DL and MUSE. SSEPI-DL can be an alternative to MUSE in female pelvic MRI, with the benefit of significantly shortened scan time.

Preoperative discrimination of absence or presence of myometrial invasion in endometrial cancer with an MRI-based multimodal deep learning radiomics model

Accurate preoperative evaluation of myometrial invasion (MI) is essential for treatment decisions in endometrial cancer (EC). However, the diagnostic accuracy of commonly utilized magnetic resonance imaging (MRI) techniques for this assessment exhibits considerable variability. This study aims to enhance preoperative discrimination of absence or presence of MI by developing and validating a multimodal deep learning radiomics (MDLR) model based on MRI. During March 2010 and February 2023, 1139 EC patients (age 54.771 ± 8.465 years; range 24-89 years) from five independent centers were enrolled retrospectively. We utilized ResNet18 to extract multi-scale deep learning features from T2-weighted imaging followed by feature selection via Mann-Whitney U test. Subsequently, a Deep Learning Signature (DLS) was formulated using Integrated Sparse Bayesian Extreme Learning Machine. Furthermore, we developed Clinical Model (CM) based on clinical characteristics and MDLR model by integrating clinical characteristics with DLS. The area under the curve (AUC) was used for evaluating diagnostic performance of the models. Decision curve analysis (DCA) and integrated discrimination index (IDI) were used to assess the clinical benefit and compare the predictive performance of models. The MDLR model comprised of age, histopathologic grade, subjective MR findings (TMD and Reading for MI status) and DLS demonstrated the best predictive performance. The AUC values for MDLR in training set, internal validation set, external validation set 1, and external validation set 2 were 0.899 (95% CI, 0.866-0.926), 0.874 (95% CI, 0.829-0.912), 0.862 (95% CI, 0.817-0.899) and 0.867 (95% CI, 0.806-0.914) respectively. The IDI and DCA showed higher diagnostic performance and clinical net benefits for the MDLR than for CM or DLS, which revealed MDLR may enhance decision-making support. The MDLR which incorporated clinical characteristics and DLS could improve preoperative accuracy in discriminating absence or presence of MI. This improvement may facilitate individualized treatment decision-making for EC.

ZOOMit diffusion kurtosis imaging combined with diffusion weighted imaging for the assessment of microsatellite instability in endometrial cancer

Detecting microsatellite instability (MSI) plays a key role in the management of endometrial cancer (EC), as it is a critical predictive biomarker for Lynch syndrome or immunotherapy response. A pressing need exists for cost-efficient, broadly accessible tools to aid patient for universal testing. Herein, we investigate the value of ZOOMit diffusion kurtosis imaging (DKI) and diffusion weighted imaging (DWI) based on preoperative pelvic magnetic resonance imaging (MRI) images in assessing MSI in EC. Preoperative MRI examination including ZOOMit DKI and DWI of 81 EC patients were retrospectively analyzed. The apparent diffusion coefficient (ADC), mean kurtosis (MK), mean diffusivity (MD) and the largest tumor size based on MRI images, as well as patients' clinicopathological features were compared and analyzed according to different microsatellite statuses. Of the 81 patients, 59 (72.8%) who were microsatellite stability (MSS) and 22 (27.2%) who were MSI. Interobserver agreement for the quantitative parameter measurements was excellent (ICC 0.78-0.98). The ADC and MD values were significantly lower, while Ki-67 proliferation level and MK values were significantly higher in the MSI group compared to those of the MSS group. The parameters of MD and MK were independent predictors for determining MSI, and their combination showed better diagnostic efficacy with an area under the receiver operating characteristic curve (AUROC) of 0.860 (95% confidence interval, 0.765, 0.927), although there was no significant difference compared to each individual parameter. The microstructural heterogeneity assessment of ZOOMit DKI allowed for characterizing MSI status in EC. Within the current universal MSI testing paradigm, DKI may provide added value as a potential noninvasive imaging biomarker for preoperative assessment of MSI tumors, thereby facilitating clinical decision-making.

Multiparametric MRI-based radiomics combined with 3D deep transfer learning to predict cervical stromal invasion in patients with endometrial carcinoma

To develop and compare various preoperative cervical stromal invasion (CSI) prediction models, including radiomics, three-dimensional (3D) deep transfer learning (DTL), and integrated models, using single-sequence and multiparametric MRI. Data from 466 early-stage endometrial carcinoma (EC) patients from three centers were collected. Radiomics models were constructed based on T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), apparent diffusion coefficient (ADC) mapping, contrast-enhanced T1-weighted imaging (CE-T1WI), and four combined sequences as well as 3D DTL models. Two integrated models were created using ensemble and stacking algorithms based on optimal radiomics and DTL models. Model performance and clinical benefits were assessed using area under the curve (AUC), decision curve analysis (DCA), net reclassification index (NRI), integrated discrimination index (IDI), and the Delong test for model comparisons. Multiparametric MRI models were superior to single-sequence models for radiomics or DTL models. Ensemble and stacking integrated models displayed excellent performance. The stacking model had the highest average AUC (0.908) and accuracy (0.883) in external validation groups 1 and 2 (AUC = 0.965 and 0.851, respectively) and emerged as the best predictive model for CSI. All models significantly outperformed the radiologist (P < 0.05). In terms of net benefits, all models demonstrated favorable outcomes in DCA, NRI, and IDI, with the stacking model yielding the highest net benefit. Multiparametric MRI-based radiomics combined with 3D DTL can be used to noninvasively predict CSI in EC patients with greater diagnostic accuracy than the radiologist. Stacking integrated models showed significant potential utility in predicting CSI. Which helps to provide new treatment strategy for clinicians to treat early-stage EC patients.

Diffusion kurtosis imaging with multiple quantitative parameters for predicting microsatellite instability status of endometrial carcinoma

To explore the value of Diffusion kurtosis imaging (DKI) with multiple quantitative parameters in predicting microsatellite instability (MSI) status in endometrial carcinoma (EC). Data of 38 patients with EC were retrospectively analyzed, including 12 MSI and 26 microsatellite stability (MSS). All patients underwent preoperative 1.5T MR examination. The quantitative values of the DKI sequence in the tumor parenchyma of the two groups, including mean kurtosis (MK), axial kurtosis (Ka), radial kurtosis (Kr), fractional anisotropy (FA), fractional anisotropy of kurtosis (FAk), mean diffusivity (MD), axial diffusivity (Da), and radial diffusivity (Dr) were measured by two observers, respectively. The MK, Ka, Kr, FA, FAk, MD, Da, and Dr values of the MSI group were 1.074 ± 0.162, 1.253 ± 0.229, 0.886 ± 0.205, 0.207 ± 0.041, 0.397 ± 0.129, 0.890 ± 0.158 μm DKI can provide multiple quantitative parameters for predicting the MSI status of EC, and assist gynecologist to optimize the treatment plan for the patients.