BMC Medical Imaging

Analysis of MRI imaging characteristics in 10 cases of adult granulosa cell tumor with normal estrogen levels

This study investigates the MRI characteristics of primary and metastatic adult granulosa cell tumor with normal estrogen levels (AGCT-NEL) to enhance clinical understanding and diagnostic accuracy of this disease. We collected clinical data from 10 patients with AGCT-NEL, confirmed by pathology, treated at our hospital from January 2016 to January 2024. We retrospectively analyzed the MRI features of primary and metastatic lesions from aspects such as shape, edge characteristics, MRI signal, and enhancement features. A total of 10 AGCT-NEL patients were included in this study, aged 28 to 81 years, with an average age of 54 ± 16 years. The primary tumors primarily presented as unilocular cystic, solid, and cystic-solid types. The solid components showed isointense to slightly hypointense signals on T1-weighted imaging (T The MRI characteristics of primary and metastatic lesions in AGCT-NEL possess specific features, such as signs of hemorrhage, absence of wall nodules in the cystic portions of the tumors, and distinctive honeycomb and Swiss cheese signs, with metastatic lesions being cystic. Understanding these features can aid in improving preoperative diagnostic capabilities and reducing misdiagnosis.

Comparison of the diagnostic efficiency between the O-RADS US risk stratification system and doctors’ subjective judgment

Abstract Background This study aimed to compare the diagnostic efficiency of Ovarian-Adnexal Reporting and Data System (O-RADS) and doctors’ subjective judgment in diagnosing the malignancy risk of adnexal masses. Methods This was an analysis of 616 adnexal masses between 2017 and 2020. The clinical findings, preoperative ultrasound images, and pathological diagnosis were recorded. Each adnexal mass was evaluated by doctors’ subjective judgment and O-RADS by two senior doctors and two junior doctors. A mass with an O-RADS grade of 1 to 3 was a benign tumor, and a mass with an O-RADS grade of 4–5 was a malignant tumor. All outcomes were compared with the pathological diagnosis. Results Of the 616 adnexal masses, 469 (76.1%) were benign, and 147 (23.9%) were malignant. There was no difference between the area under the curve of O-RADS and the subjective judgment for junior doctors (0.83 (95% CI: 0.79–0.87) vs. 0.79 (95% CI: 0.76–0.83), p = 0.0888). The areas under the curve of O-RADS and subjective judgment were equal for senior doctors (0.86 (95% CI: 0.83–0.89) vs. 0.86 (95% CI: 0.83–0.90), p = 0.8904). O-RADS had much higher sensitivity than the subjective judgment in detecting malignant tumors for junior doctors (84.4% vs. 70.1%) and senior doctors (91.2% vs. 81.0%). In the subgroup analysis for detecting the main benign lesions of the mature cystic teratoma and ovarian endometriosic cyst, the junior doctors’ diagnostic accuracy was obviously worse than the senior doctors’ on using O-RADS. Conclusions O-RADS had excellent performance in predicting malignant adnexal masses. It could compensate for the lack of experience of junior doctors to a certain extent. Better performance in discriminating various benign lesions should be expected with some complement.

Findings on conventional ultrasonography and contrast-enhanced ultrasonography in different histopathological subtypes of ovarian thecoma-fibroma group

Ovarian thecoma-fibroma group (OTFG) is an unusual type of ovarian cancer with three histopathologic subtypes, but their features on ultrasonography are still poorly understood. This study evaluated the features of different histopathological subtypes of OTFG on conventional ultrasonography and contrast-enhanced ultrasonography (CEUS). This retrospective study enrolled sixty-nine women with pathologically confirmed OTFG who underwent preoperative CEUS. The characteristics of OTFG on conventional ultrasonography and CEUS, clinical manifestations, and laboratory findings were compared among subtypes. Fourteen patients were diagnosed with fibroma, fifty-one with thecofibroma, and four with thecoma. Although 69% of patients were post-menopausal, thecoma patients were significantly younger than those in other two groups. Laboratory examination revealed 21.7% (15/69) of patients had high carbohydrate antigen 125 (CA-125) level. On conventional ultrasonography, 72.5% (50/69) masses showed solid type, 24.6% (17/69) showed mixed cystic-solid type, and only 2.9% (2/69) showed cystic type. On CEUS, 50% (2/4) of thecoma lesions were rapid enhancement, 58.8% (30/51) of thecofibroma lesions and 78.6% (11/14) of fibroma lesions showed slow enhancement, 75% (3/4) of thecoma lesions showed isoenhancement during the descent process, and only 13.75% (7/51) of thecofibroma lesions and 7.1% (1/14) of fibroma lesions showed isoenhancement during the descent. they varied significantly among different histopathological subtypes. The majority of OTFG is solid-like on conventional ultrasonography. Menopause is an important factor related to the subtype of OTFG. In postmenopausal patients with solid adnexal masses, slow hypoenhancement on CEUS is an important feature of fibroma. In premenopausal patients with solid or mixed cystic-solid adnexal masses, thecoma may be considered when rapid hyperenhancement, and isoenhancement or hypoenhancement during descent are observed on CEUS. Not applicable.

Diagnostic utility of apparent diffusion coefficient in preoperative assessment of endometrial cancer: are we ready for the 2023 FIGO staging?

Abstract Background Although endometrial cancer (EC) is staged surgically, magnetic resonance imaging (MRI) plays a critical role in assessing and selecting the most appropriate treatment planning. We aimed to assess the diagnostic performance of quantitative analysis of diffusion-weighted imaging (DWI) in preoperative assessment of EC. Methods Prospective analysis was done for sixty-eight patients with pathology-proven endometrial cancer who underwent MRI and DWI. Apparent diffusion coefficient (ADC) values were measured by two independent radiologists and compared with the postoperative pathological results. Results There was excellent inter-observer reliability in measuring ADCmean values. There were statistically significant lower ADCmean values in patients with deep myometrial invasion (MI), cervical stromal invasion (CSI), type II EC, and lympho-vascular space involvement (LVSI) (AUC = 0.717, 0.816, 0.999, and 0.735 respectively) with optimal cut-off values of ≤ 0.84, ≤ 0.84, ≤ 0.78 and ≤ 0.82 mm2/s respectively. Also, there was a statistically significant negative correlation between ADC values and the updated 2023 FIGO stage and tumor grade (strong association), and the 2009 FIGO stage (medium association). Conclusions The preoperative ADCmean values of EC were significantly correlated with main prognostic factors including depth of MI, CSI, EC type, grade, nodal involvement, and LVSI.

Breast MRI texture analysis for prediction of BRCA-associated genetic risk

Abstract Background BRCA1/2 deleterious variants account for most of the hereditary breast and ovarian cancer cases. Prediction models and guidelines for the assessment of genetic risk rely heavily on criteria with high variability such as family cancer history. Here we investigated the efficacy of MRI (magnetic resonance imaging) texture features as a predictor for BRCA mutation status. Methods A total of 41 female breast cancer individuals at high genetic risk, sixteen with a BRCA1/2 pathogenic variant and twenty five controls were included. From each MRI 4225 computer-extracted voxels were analyzed. Non-imaging features including clinical, family cancer history variables and triple negative receptor status (TNBC) were complementarily used. Lasso-principal component regression (L-PCR) analysis was implemented to compare the predictive performance, assessed as area under the curve (AUC), when imaging features were used, and lasso logistic regression or conventional logistic regression for the remaining analyses. Results Lasso-selected imaging principal components showed the highest predictive value (AUC 0.86), surpassing family cancer history. Clinical variables comprising age at disease onset and bilateral breast cancer yielded a relatively poor AUC (~ 0.56). Combination of imaging with the non-imaging variables led to an improvement of predictive performance in all analyses, with TNBC along with the imaging components yielding the highest AUC (0.94). Replacing family history variables with imaging components yielded an improvement of classification performance of ~ 4%, suggesting that imaging compensates the predictive information arising from family cancer structure. Conclusions The L-PCR model uncovered evidence for the utility of MRI texture features in distinguishing between BRCA1/2 positive and negative high-risk breast cancer individuals, which may suggest value to diagnostic routine. Integration of computer-extracted texture analysis from MRI modalities in prediction models and inclusion criteria might play a role in reducing false positives or missed cases especially when established risk variables such as family history are missing.

Ultrasound-based radiomics for predicting different pathological subtypes of epithelial ovarian cancer before surgery

Abstract Objective To evaluate the value of ultrasound-based radiomics in the preoperative prediction of type I and type II epithelial ovarian cancer. Methods A total of 154 patients with epithelial ovarian cancer were enrolled retrospectively. There were 102 unilateral lesions and 52 bilateral lesions among a total of 206 lesions. The data for the 206 lesions were randomly divided into a training set (53 type I + 71 type II) and a test set (36 type I + 46 type II) by random sampling. ITK-SNAP software was used to manually outline the boundary of the tumor, that is, the region of interest, and 4976 features were extracted. The quantitative expression values of the radiomics features were normalized by the Z-score method, and the 7 features with the most differences were screened by using the Lasso regression tenfold cross-validation method. The radiomics model was established by logistic regression. The training set was used to construct the model, and the test set was used to evaluate the predictive efficiency of the model. On the basis of multifactor logistic regression analysis, combined with the radiomics score of each patient, a comprehensive prediction model was established, the nomogram was drawn, and the prediction effect was evaluated by analyzing the area under the receiver operating characteristic curve (AUC), calibration curve and decision curve. Results The AUCs of the training set and test set in the radiomics model and comprehensive model were 0.817 and 0.731 and 0.982 and 0.886, respectively. The calibration curve showed that the two models were in good agreement. The clinical decision curve showed that both methods had good clinical practicability. Conclusion The radiomics model based on ultrasound images has a good predictive effect for the preoperative differential diagnosis of type I and type II epithelial ovarian cancer. The comprehensive model has higher prediction efficiency.

Potentialities of multi-b-values diffusion-weighted imaging for predicting efficacy of concurrent chemoradiotherapy in cervical cancer patients

Abstract Background To testify whether multi-b-values diffusion-weighted imaging (DWI) can be used to ultra-early predict treatment response of concurrent chemoradiotherapy (CCRT) in cervical cancer patients and to assess the predictive ability of concerning parameters. Methods Fifty-three patients with biopsy proved cervical cancer were retrospectively recruited in this study. All patients underwent pelvic multi-b-values DWI before and at the 3rd day during treatment. The apparent diffusion coefficient (ADC), true diffusion coefficient (D slow ), perfusion-related pseudo-diffusion coefficient (D fast ), perfusion fraction (f), distributed diffusion coefficient (DDC) and intravoxel diffusion heterogeneity index(α) were generated by mono-exponential, bi-exponential and stretched exponential models. Treatment response was assessed based on Response Evaluation Criteria in Solid Tumors (RECIST v1.1) at 1 month after the completion of whole CCRT. Parameters were compared using independent t test or Mann-Whitney U test as appropriate. Receiver operating characteristic (ROC) curves was used for statistical evaluations. Results ADC-T0 ( p  = 0.02), D slow -T0 ( p  <  0.01), DDC-T0 ( p  = 0.03), ADC-T1 ( p  <  0.01), D slow -T1 ( p  <  0.01), ΔADC ( p  = 0.04) and Δα ( p  <  0.01) were significant lower in non-CR group patients. ROC analyses showed that ADC-T1 and Δα exhibited high prediction value, with area under the curves of 0.880 and 0.869, respectively. Conclusions Multi-b-values DWI can be used as a noninvasive technique to assess and predict treatment response in cervical cancer patients at the 3rd day of CCRT. ADC-T1 and Δα can be used to differentiate good responders from poor responders.

Ultrasound-based deep learning radiomics model for differentiating benign, borderline, and malignant ovarian tumours: a multi-class classification exploratory study

Abstract Background Accurate preoperative identification of ovarian tumour subtypes is imperative for patients as it enables physicians to custom-tailor precise and individualized management strategies. So, we have developed an ultrasound (US)-based multiclass prediction algorithm for differentiating between benign, borderline, and malignant ovarian tumours. Methods We randomised data from 849 patients with ovarian tumours into training and testing sets in a ratio of 8:2. The regions of interest on the US images were segmented and handcrafted radiomics features were extracted and screened. We applied the one-versus-rest method in multiclass classification. We inputted the best features into machine learning (ML) models and constructed a radiomic signature (Rad_Sig). US images of the maximum trimmed ovarian tumour sections were inputted into a pre-trained convolutional neural network (CNN) model. After internal enhancement and complex algorithms, each sample’s predicted probability, known as the deep transfer learning signature (DTL_Sig), was generated. Clinical baseline data were analysed. Statistically significant clinical parameters and US semantic features in the training set were used to construct clinical signatures (Clinic_Sig). The prediction results of Rad_Sig, DTL_Sig, and Clinic_Sig for each sample were fused as new feature sets, to build the combined model, namely, the deep learning radiomic signature (DLR_Sig). We used the receiver operating characteristic (ROC) curve and the area under the ROC curve (AUC) to estimate the performance of the multiclass classification model. Results The training set included 440 benign, 44 borderline, and 196 malignant ovarian tumours. The testing set included 109 benign, 11 borderline, and 49 malignant ovarian tumours. DLR_Sig three-class prediction model had the best overall and class-specific classification performance, with micro- and macro-average AUC of 0.90 and 0.84, respectively, on the testing set. Categories of identification AUC were 0.84, 0.85, and 0.83 for benign, borderline, and malignant ovarian tumours, respectively. In the confusion matrix, the classifier models of Clinic_Sig and Rad_Sig could not recognise borderline ovarian tumours. However, the proportions of borderline and malignant ovarian tumours identified by DLR_Sig were the highest at 54.55% and 63.27%, respectively. Conclusions The three-class prediction model of US-based DLR_Sig can discriminate between benign, borderline, and malignant ovarian tumours. Therefore, it may guide clinicians in determining the differential management of patients with ovarian tumours.

Diagnostic value of computed tomography and magnetic resonance imaging in ovarian malignant mesothelioma

Abstract Objective To investigate the diagnostic value of computed tomography (CT) and magnetic resonance imaging (MRI) in ovarian malignant mesothelioma (OMM). Methods The clinical and imaging data of 10 pathologically-confirmed OMM patients were analyzed retrospectively. Result (1) The patients were 27 years to 70 years old, with an average age of 57.2 ± 15.4 years. Seven patients reported abdominal distension and pain, 1 reported lower abdominal discomfort and decreased appetite, and 2 patients had no symptoms. (2) Two cases of localized OMM with incomplete semi-annular “capsule” observed around the localized OMM tumors were reported while 8 cases had diffuse OMM in which the tumor parenchyma showed isointense or slightly hypointense on T1WI, inhomogeneous hyperintense on T2WI, and obviously hyperintense on DWI, with obvious inhomogeneous enhancement after enhancement. Diffuse OMM was not mainly composed of ovarian masses and was mainly characterized by mild ovarian enlargement, nodular and irregular thickening of the peritoneum, cloudy omentum, unclear fat gap, and reticular or irregular thickening, which can fuse into a “cake-shape”. (3) All 10 patients underwent surgery, while 9 patients underwent systemic chemotherapy or immunotherapy after surgery. All patients with localized OMM survived. Out of the 8 diffuse-type patients, 5 died, 1 was lost to follow-up, and 2 survived. Conclusion OMM has certain clinical and imaging characteristics. There is no liquefaction, calcification, or partition in the tumor. The ovarian enlargement in the diffuse lesion is not significant. The diffuse thickening of the peritoneum and omentum with early appearance of mural nodules and ascites in the upper abdomen, help the diagnosis of OMM.

An integrated radiomics and deep learning model on multisequence MRI for preoperative prediction of lymphovascular space invasion in endometrial cancer

To develop and validate a multimodal model that integrates radiomics features (RFs) and deep learning features (DFs) derived from preoperative multisequence magnetic resonance imaging (MRI) for the prediction of lymphovascular space invasion (LVSI) in patients with endometrial cancer (EC). This multicenter, retrospective study enrolled 892 patients with postoperative pathologically confirmed EC. Preoperative MRI comprised T2-weighted imaging, contrast-enhanced T1-weighted imaging, and apparent diffusion coefficient maps, were analyzed. Regions of interest (ROIs) were manually delineated for 2D and 3D analyses. RFs were extracted using PyRadiomics, and DFs were obtained using pretrained VGG 11, ResNet 101, and DenseNet 121 architectures. Five single-modality models (2D-RF, 3D-RF, VGG11-DF, ResNet101-DF, and DenseNet121-DF) were developed. In addition, the integration of RFs and DFs were explored to construct combined models. Models were trained in a training cohort (n = 378) and evaluated in both internal (n = 160) and external (n = 354) validation cohorts. Model performance was evaluated by the area under the receiver operating characteristic curve (AUC). In the training cohort, the 2D-RF and 3D-RF models showed comparable performance for LVSI prediction (AUC: 0.775 vs. 0.772, P = 0.89). Among the deep learning models, DenseNet121-DF achieved the highest AUC (0.757), which was significantly higher than ResNet-101-DF (AUC: 0.671; P = 0.01) and not statistically different from VGG11-DF (AUC: 0.720, P = 0.20). The optimal combined model, integrating features from 2D-RF and DenseNet121-DF, yielded the highest performance in the training cohort (AUC: 0.796). These findings were confirmed in both the internal and external validation cohorts. A multimodal MRI-based model integrating both RFs and DFs achieved superior performance for noninvasive prediction of LVSI in patients with EC. This approach holds potential to enhance preoperative risk stratification and guide personalized treatment planning.

Ultrasound-based machine learning model to predict the risk of endometrial cancer among postmenopausal women

Current ultrasound-based screening for endometrial cancer (EC) primarily relies on endometrial thickness (ET) and morphological evaluation, which suffer from low specificity and high interobserver variability. This study aimed to develop and validate an artificial intelligence (AI)-driven diagnostic model to improve diagnostic accuracy and reduce variability. A total of 1,861 consecutive postmenopausal women were enrolled from two centers between April 2021 and April 2024. Super-resolution (SR) technique was applied to enhance image quality before feature extraction. Radiomics features were extracted using Pyradiomics, and deep learning features were derived from convolutional neural network (CNN). Three models were developed: (1) R model: radiomics-based machine learning (ML) algorithms; (2) CNN model: image-based CNN algorithms; (3) DLR model: a hybrid model combining radiomics and deep learning features with ML algorithms. Using endometrium-level regions of interest (ROI), the DLR model achieved the best diagnostic performance, with an area under the receiver operating characteristic curve (AUROC) of 0.893 (95% CI: 0.847-0.932), sensitivity of 0.847 (95% CI: 0.692-0.944), and specificity of 0.810 (95% CI: 0.717-0.910) in the internal testing dataset. Consistent performance was observed in the external testing dataset (AUROC 0.871, sensitivity 0.792, specificity 0.829). The DLR model consistently outperformed both the R and CNN models. Moreover, endometrium-level ROIs yielded better results than uterine-corpus-level ROIs. This study demonstrates the feasibility and clinical value of AI-enhanced ultrasound analysis for EC detection. By integrating radiomics and deep learning features with SR-based image preprocessing, our model improves diagnostic specificity, reduces false positives, and mitigates operator-dependent variability. This non-invasive approach offers a more accurate and reliable tool for EC screening in postmenopausal women. Not applicable.

The value of diffusion-weighted imaging and semi-quantitative dynamic contrast-enhanced MRI in predicting the efficacy of medroxyprogesterone acetate treatment for atypical endometrial hyperplasia and endometrial carcinoma

It will be important to noninvasively evaluate the efficacy of treatment for patients with atypical endometrial hyperplasia (AEH) and endometrial carcinoma (EC) who wish to have children. The study aimed to explore the feasibility of diffusion-weighted imaging (DWI) and semi-quantitative dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in predicting the efficacy of medroxyprogesterone acetate treatment for AEH and EC. A retrospective analysis was conducted on the clinical-pathological data of 6 patients with AEH and 6 patients with EC. The treatment effects of medroxyprogesterone acetate were pathologically evaluated. Additionally, MRI examination was conducted at each follow-up at the 3rd and 6th month after treatment. Repeated measures variance analysis was used to compare statistically significant differences in the apparent diffusion coefficient (ADC) values and maximum signal difference (MSD) of the lesion and corresponding endometrial site before treatment, and at the 3rd and 6th month after treatment. Endometrial thickness was analyzed utilizing the Friedman test. Furthermore, Fisher's exact probability method was used to determine if there was a significant difference in the time-intensity curve (TIC). There was a statistically significant difference in endometrial thickness before treatment, and at the 3rd and 6th month after treatment for EC and AEH (P  0.05). No significant differences were noted in the ADC values, and type of TIC curve before and after treatment for AEH (P > 0.05). Endometrial thickness can be imaging markers for predicting complete remission of EC and AEH with medroxyprogesterone acetate treatment. ADC values and TIC curve types can be imaging markers for predicting complete remission of EC.

Multimodal MRI-based radiomics models for the preoperative prediction of lymphovascular space invasion of endometrial carcinoma

To evaluate the predictive capabilities of MRI-based radiomics for detecting lymphovascular space invasion (LVSI) in patients diagnosed with endometrial carcinoma (EC). A retrospective analysis was conducted on 160 female patients diagnosed with EC. The radiomics model including T2-weighted and dynamic contrast-enhanced MRI (DCE-MRI) images was established. Additionally, a conventional MRI model, which incorporated MRI-reported FIGO stage, deep myometrial infiltration (DMI), adnexal involvement, and vaginal/parametrial involvement, was established. Finally, a combined model was created by integrating the radiomics signature and conventional MRI characteristics. The predictive performance was validated by the area under the curve (AUC) of the receiver operating characteristic (ROC) curves. A stratified analysis was conducted to compare the differences between the three models by Delong test. In predicting LVSI, the radiomics model outperformed the clinical model in the training cohort (AUC: 0.899 vs. 0.8862) but not in the test cohort (AUC: 0.812 vs. 0.8758). The combined model demonstrated superior performance in both the training and test cohorts (training cohort: AUC = 0.934, 95% CI: 0.8807-0.9873; testing cohort: AUC = 0.905, 95% CI: 0.7679-1). The combined model exhibited utility in preoperatively predicting LVSI in patients with EC, offering potential benefits for clinical decision-making.

Whole-lesion apparent diffusion coefficient (ADC) histogram as a quantitative biomarker to preoperatively differentiate stage IA endometrial carcinoma from benign endometrial lesions

Abstract Background To assess the value of whole-lesion apparent diffusion coefficient (ADC) histogram analysis in differentiating stage IA endometrial carcinoma (EC) from benign endometrial lesions (BELs) and characterizing histopathologic features of stage IA EC preoperatively. Methods One hundred and six BEL and 126 stage IA EC patients were retrospectively enrolled. Eighteen volumetric histogram parameters were extracted from the ADC map of each lesion. The Mann–Whitney U or Student’s t-test was used to compare the differences between the two groups. Models based on clinical parameters and histogram features were established using multivariate logistic regression. Receiver operating characteristic (ROC) analysis and calibration curves were used to assess the models. Results Stage IA EC showed lower ADC10th, ADC90th, ADCmin, ADCmax, ADCmean, ADCmedian, interquartile range, mean absolute deviation, robust mean absolute deviation (rMAD), root mean squared, energy, total energy, entropy, variance, and higher skewness, kurtosis and uniformity than BELs (all p < 0.05). ADCmedian yielded the highest area under the ROC curve (AUC) of 0.928 (95% confidence interval [CI] 0.895–0.960; cut-off value = 1.161 × 10−3 mm2/s) for differentiating stage IA EC from BELs. Moreover, multivariate analysis demonstrated that ADC-score (ADC10th + skewness + rMAD + total energy) was the only significant independent predictor (OR = 2.641, 95% CI 2.045–3.411; p < 0.001) for stage IA EC when considering clinical parameters. This ADC histogram model (ADC-score) achieved an AUC of 0.941 and a bias-corrected AUC of 0.937 after bootstrap resampling. The model performed well for both premenopausal (accuracy = 0.871) and postmenopausal (accuracy = 0.905) patients. Besides, ADCmin and ADC10th were significantly lower in Grade 3 than in Grade 1/2 stage IA EC (p = 0.022 and 0.047). At the same time, no correlation was found between ADC histogram parameters and the expression of Ki-67 in stage IA EC (all p > 0.05). Conclusions Whole-lesion ADC histogram analysis could serve as an imaging biomarker for differentiating stage IA EC from BELs and assisting in tumor grading of stage IA EC, thus facilitating personalized clinical management for premenopausal and postmenopausal patients.

Magnetic resonance spectroscopy associations with clinicopathologic features of estrogen-dependent endometrial cancer

Abstract Background We studied the magnetic resonance spectroscopy (MRS) associations with clinicopathologic features of estrogen-dependent endometrial cancer (type I EC). Methods Totally 45 patients with type I EC who underwent preoperative multi-voxel MRS at 3.0 T were enrolled. The mean ratio of the Cho peak integral to the unsuppressed water peak integral (Cho/water) of the tumor was calculated. The Cho/water and apparent diffusion coefficient (ADC) of type I EC with and without local invasion, as well as with different levels of Ki-67 staining index (SI) (≤ 40% and > 40%), were compared. Correlation test was used to examine the relationship of Cho/water, as well as mean ADC, with Ki-67 SI, tumor stage, and tumor grade. Results The mean Cho/water of EC with Ki-67 SI ≤ 40% (2.28 ± 0.93) × 10−3 was lower than that with Ki-67 SI > 40% (4.08 ± 1.00) × 10−3 (P < 0.001). The mean Cho/water of EC with deep and superficial myometrial invasion was (3.41 ± 1.26) × 10−3 and (2.43 ± 1.11) × 10−3, respectively (P = 0.011). There was no significant difference in Cho/water between type I EC with and without cervical invasioin ([2.68 ± 1.00] × 10−3 and [2.77 ± 1.28] × 10−3, P = 0.866). The mean Cho/water of type I EC with and without lymph node metastasis was (4.02 ± 1.90) × 10−3 and (2.60 ± 1.06) × 10−3, respectively (P = 0.014). The Cho/water was positively correlated with the Ki-67 SI (r = 0.701, P < 0.001). There were no significant differences in ADC among groups (all P > 0.05). Conclusion MRS is helpful for preoperative assessment of clinicopathological features of type I EC.

The efficacy of deep learning models in the diagnosis of endometrial cancer using MRI: a comparison with radiologists

Abstract Purpose To compare the diagnostic performance of deep learning models using convolutional neural networks (CNN) with that of radiologists in diagnosing endometrial cancer and to verify suitable imaging conditions. Methods This retrospective study included patients with endometrial cancer or non-cancerous lesions who underwent MRI between 2015 and 2020. In Experiment 1, single and combined image sets of several sequences from 204 patients with cancer and 184 patients with non-cancerous lesions were used to train CNNs. Subsequently, testing was performed using 97 images from 51 patients with cancer and 46 patients with non-cancerous lesions. The test image sets were independently interpreted by three blinded radiologists. Experiment 2 investigated whether the addition of different types of images for training using the single image sets improved the diagnostic performance of CNNs. Results The AUC of the CNNs pertaining to the single and combined image sets were 0.88–0.95 and 0.87–0.93, respectively, indicating non-inferior diagnostic performance than the radiologists. The AUC of the CNNs trained with the addition of other types of single images to the single image sets was 0.88–0.95. Conclusion CNNs demonstrated high diagnostic performance for the diagnosis of endometrial cancer using MRI. Although there were no significant differences, adding other types of images improved the diagnostic performance for some single image sets.

CT-based radiomics model for noninvasive prediction of progression-free survival in high-grade serous ovarian carcinoma: a multicenter study incorporating preoperative and postoperative clinical factors

To investigate the potential of combining radiomics with clinicoradiological features in predicting progression-free survival (PFS) after the surgery of high-grade serous ovarian carcinoma (HGSOC). In this retrospective multicenter study, a total of 195 patients with pathologically confirmed HGSOC who underwent cytoreductive surgery followed by platinum-based chemotherapy were included from two institutions (train cohort, n = 134; test cohort, n = 61). From the train cohort, univariate and multivariate Cox proportional hazards regression analyses systematically evaluated associations between clinicoradiological features and PFS, culminating in a clinical prediction model for stratifying progression risk. Radiomics features were extracted and utilized to build the radiomics model through univariate Cox regression and least absolute shrinkage and selection operator Cox regression. A combined model integrating both clinicoradiological and radiomics features was subsequently developed. The concordance index (C-index) was used to assess the predictive performance of different models in 1-, 3-, and 5-year PFS evens among HGSOC patients. Model performance was assessed using time-dependent receiver operating characteristic curves, with area under the curve (AUC) values calculated at various time points. as well as calibration curves and Brier scores to evaluate prediction accuracy and model reliability. Kaplan-Meier analysis was employed to evaluate the clinical utility of each model in predicting PFS. Five clinicoradiologicall features, including supradiaphragmatic lymphadenopathy, CA125 level, HE4 level, residual tumor status, and FIGO stage, were included in the clinical model.The combined model achieved strong predictive performance with a C-index of 0.758 (95% CI: 0.685-0.830) in the train cohort and 0.707 (95% CI: 0.593-0.821) in the test cohort, outperforming both the clinical and radiomics models independently. The combined model demonstrated superior performance for 1-year prediction, with the highest accuracy (0.822), AUC (0.864), and lowest Brier score (0.132) in the train cohort, and the highest balanced accuracy (0.806), AUC (0.787), and lowest Brier score (0.159) in the test cohort. For 3-year survival, the radiomics model showed the best performance, with a balanced accuracy of 0.760, AUC of 0.838, and Brier score of 0.168 in train cohort, and a balanced accuracy of 0.813, AUC of 0.785, and Brier score of 0.198 in test cohort. Similarly, the radiomics model overall outperformed the other models for 5-year survival, with a balanced accuracy of 0.813, AUC of 0.887, and Brier score of 0.164 in train cohort, and a balanced accuracy of 0.813, AUC of 0.767, and Brier score of 0.207 in test cohort. The combined model excels in 1-year PFS prediction and overall risk stratification, while the radiomics model performs better for 3- and 5-year fixed-time PFS predictions. Not applicable.

MRI cytometry imaging for cervical cancer differential diagnosis: a preliminary study

Precise noninvasive detection and differentiation of pathological subtypes in cervical cancer remains challenging. Diffusion MRI (dMRI)-based cytometry, an imaging technique quantifying tumor microenvironments, shows diagnostic potential but requires clinical validation. 74 patients with cervical cancer and 44 healthy volunteers underwent diffusion-weighted imaging using oscillating gradient spin-echo (OGSE) and pulsed gradient spin-echo (PGSE) sequences at 3T. Three radiologists independently scored image quality on a 5-point scale. Time-dependent apparent diffusion coefficients (ADCs) as well as information from 'imaging microstructural parameters using limited spectrally edited diffusion' (IMPULSED) alone or incorporating transcytolemmal water exchange (JOINT) were used to distinguish cancerous from normal tissues and identify tumor subtypes. The microstructural parameters included intracellular volume fraction ([Formula: see text]), cell diameter ([Formula: see text]), extracellular diffusivity ([Formula: see text]), and water exchange rate constant ([Formula: see text]). Receiver operating characteristic (ROC) curves were used to assess the effectiveness. Kendall's W statistics showed strong inter-reader reliability for assessing OGSE and PGSE images (W = 0.819, P < 0.0001). Microstructural parameters can effectively distinguish cervical cancer from normal tissues, with higher [Formula: see text] (P < 0.01), lower [Formula: see text] (P < 0.0001), and higher [Formula: see text] (P < 0.0001) values for tumors. Additionally, squamous carcinomas were characterized by lower [Formula: see text] and [Formula: see text] values (P < 0.01 and P < 0.05). The area under ROC curve of the combined regression model can reach up to 0.967 and 0.853 for diagnosing cervical cancer and differentiating the subtypes, respectively. MRI cytometry-derived microstructural parameters can reliably detect cervical cancer and further differentiate its pathological subtypes. This improves the accuracy of noninvasive preoperative assessment and shows considerable clinical potential.

Outlier data in volume calculations of uterine fibroids comparing ellipsoid formula and voxel-based segmentation

Abstract Background The ellipsoidal formula is the most common method used to determine the volume of fibroids on MR images. Labor-intensive manual segmentation provides the opportunity to measure the volume of a given lesion on a voxel basis. The aim of this study is to compare the volume of the uterine fibroid calculated using voxel-based segmentation and the ellipsoid formula. Methods In this study, pretreatment MRI scans of patients who underwent uterine artery embolization due to symptomatic fibroids were retrospectively collected between 2016 and 2022. The volume data of the largest fibroids was determined by segmentation (group S) as the reference standard. In addition, the largest diameters of the fibroids in three planes (D1/D2/D3) were also measured and the volumes were also estimated by using the ellipsoidal formula (D1*D2*D3*0.5233) (group E). The interobserver reproducibility of the diameter measurements was tested. The volume values (median, IQR) were compared; in addition, the differences between the segmented and ellipsoidal volumes were recorded. Statistical analysis was performed using the Kruskal-Wallis test, Wilcoxon’s two-sided signed rank test, intraclass correlation (ICC) analysis, and Bland-Altman plots. Results Pretreatment MRI scans of 113 patients were identified. Fibroids where the interobserver difference of diameter-based ellipsoidal volumes reached 30% were excluded resulting in 99 patients in the final dataset. The volumes of group S and group E showed no significant differences with 134.1 (257.3) cm3 and 133.5 (269.1) cm3, respectively, with an average difference of 3.47 cm3 (0.25%; p = 0.377). The agreement between the two methods was excellent (ICC = 0.979), without difference across fibroid locations. In 46 cases (46.5%), group S values were larger, and in 53 fibroids (53.5%), group E volume values were larger. However, volume difference was outside the ± 20% range in 21 cases (21.2%) and outside the ± 30% range in 10 cases (10.1%); the largest difference was approximately 56.5% (156.5 cm3). Conclusions The ellipsoid formula-based and the voxel-based volume calculation showed no significant difference for the group as a whole. However, there was a difference of &gt; 20% in 21.2% of cases and &gt; 30% in 10.1% of cases. In the era of personalized medicine, it is not only the average difference between the two methods that need to be considered but also cases where there is a 20% or 30% difference in results should be highlighted, as these may change the treatment plan in individual cases. This methodology should also be tested for other tumor-type volume calculations.

Value of a combined magnetic resonance-enhanced and diffusion-weighted imaging dual-sequence radiomics model in predicting the efficacy of high-intensity focused ultrasound ablation for uterine fibroids

To establish a joint radiomics model based on T1 contrast-enhanced (T1C) imaging and diffusion-weighted imaging (DWI), and investigate its value in predicting the efficacy of high-intensity focused ultrasound (HIFU) in ablating uterine fibroids. This multicenter retrospective study included 195 patients with uterine fibroids. Their data were divided into training (n = 120), internal test (n = 30), and external test (n = 45) sets. The radiomic features were extracted from T1C and DWI sequences. Logistic regression was used to develop the T1C, DWI, integration, and joint models, and receiver operating characteristic curves were used to assess model performance. The Delong test was used to compare the predictive efficacies of different models, and the best model was used for external validation and development of the nomogram. Eight T1C features, six DWI features, and three imaging features were retained for the modeling. The areas under the curve were 0.852 and 0.769 for the integrated model on the training and internal test sets, respectively; 0.857 and 0.824 for the joint model on the training and internal test sets, respectively, which were higher than those of the single-sequence model; and 0.857 for the joint model on the external test set. A joint radiomics model based on T1C and DWI data can effectively predict the efficacy of HIFU for ablating uterine fibroids and guide the development of individualized clinical treatment plans.

Systemic immune-related spleen radiomics predict progression-free survival in patients with locally advanced cervical cancer underwent definitive chemoradiotherapy

Systemic immunity is essential for driving therapeutically induced antitumor immune responses, and the spleen may reflect alterations in systemic immunity. This study aimed to evaluate the predictive value of contrast-enhanced CT-based spleen radiomics for progression-free survival (PFS) in patients with locally advanced cervical cancer (LACC) who underwent definitive chemoradiotherapy (dCRT). Additionally, we investigated the role of spleen radiomics features and changes in spleen volume in assessing systemic immunity. This retrospective study included 257 patients with LACC who underwent dCRT. The patients were randomly divided into training and validation groups in a 7:3 ratio. Radiomic features were extracted from CT images obtained before and after dCRT. Radiomic scores (Radscore) were calculated using features selected through least absolute shrinkage and selection operator (LASSO) Cox regression. The percentage change in spleen volume was determined from measurements taken before and after treatment. Independent prognostic factors for PFS were identified through multivariate Cox regression analyses. Model performance was evaluated with the receiver operating characteristic (ROC) curve and the C-index. The Radscore cut-off value, determined from the ROC curve, was used to stratify patients into high- and low-risk survival groups. The Wilcoxon test was used to analyze differences in hematological parameters between different survival risk groups and between different spleen volume change groups. Spearman correlation analysis was used to explore the relationship between spleen volume change and hematological parameters. Independent prognostic factors included FIGO stage, pre-treatment neutrophil-to-lymphocyte ratio (pre-NLR), spleen volume change, and Radscore. The radiomics-combined model demonstrated the best predictive performance for PFS in both the training group (AUC: 0.923, C-index: 0.884) and the validation group (AUC: 0.895, C-index: 0.834). Compared to the low-risk group, the high-risk group had higher pre-NLR (p = 0.0054) and post-NLR (p = 0.038). Additionally, compared to the decreased spleen volume group, the increased spleen volume group had lower post-NLR (p = 0.0059) and post-treatment platelet-to-lymphocyte ratio (p < 0.001). Spleen radiomics combined with clinical features can effectively predict PFS in patients with LACC after dCRT. Furthermore, spleen radiomics features and changes in spleen volume can reflect alterations in systemic immunity.

In vitro detection of cancer cells using a novel fluorescent choline derivative

The treatment of preinvasive lesions is more effective than treating invasive disease, hence detecting cancer at its early stages is crucial. However, currently, available screening methods show various limitations in terms of sensitivity, specificity, and practicality, thus novel markers complementing traditional cyto/histopathological assessments are needed. Alteration in choline metabolism is a hallmark of many malignancies, including cervical and breast cancers. Choline radiotracers are widely used for imaging purposes, even though many risks are associated with their radioactivity. Therefore, this work aimed to synthesise and characterise a non-radioactive choline tracer based on a fluorinated acridine scaffold (CFA) for the in vitro detection of cervical and breast cancer cells by fluorescence imaging. CFA was fully characterised and tested for its cytotoxicity on breast (MCF-7), cervical (HeLa), glioblastoma (U-87 MG) and hepatoblastoma (HepG2) cancer cell lines and in normal cell lines (epithelial, HEK-293 and human dermal fibroblasts, HDFs). The cellular uptake of CFA was investigated by a confocal microscope and its accumulation was quantified over time. The specificity of CFA over mesenchymal origin cells (HDFs), as a model of cancer-associated fibroblasts was investigated by fluorescence microscopy. CFA was toxic at much higher concentrations (HeLa IC The results showed that CFA preferentially accumulated in cancer cells rather than in normal cells. These findings suggest that CFA may be a potential diagnostic probe for discriminating healthy tissues from malignant tissues due to its specific and highly sensitive features; CFA may also represent a useful tool for in vitro/ex vivo investigations of choline metabolism in patients with cervical and breast cancers.

Utilizing CT imaging for evaluating late gastrointestinal tract side effects of radiotherapy in uterine cervical cancer: a risk regression analysis

Abstract Background Radiotherapy (RT) is effective for cervical cancer but causes late side effects (SE) to nearby organs. These late SE occur more than 3 months after RT and are rated by clinical findings to determine their severity. While imaging studies describe late gastrointestinal (GI) SE, none demonstrate the correlation between the findings and the toxicity grading. In this study, we demonstrated the late GI toxicity prevalence, CT findings, and their correlation. Methods We retrospectively studied uterine cervical cancer patients treated with RT between 2015 and 2018. Patient characteristics and treatment(s) were obtained from the hospital’s databases. Late RTOG/EORTC GI SE and CT images were obtained during the follow-up. Post-RT GI changes were reviewed from CT images using pre-defined criteria. Risk ratios (RR) were calculated for CT findings, and multivariable log binomial regression determined adjusted RRs. Results This study included 153 patients, with a median age of 57 years (IQR 49–65). The prevalence of ≥ grade 2 RTOG/EORTC late GI SE was 33 (27.5%). CT findings showed 91 patients (59.48%) with enhanced bowel wall (BW) thickening, 3 (1.96%) with bowel obstruction, 7 (4.58%) with bowel perforation, 6 (3.92%) with fistula, 0 (0%) with bowel ischemia, and 0 (0%) with GI bleeding. Adjusted RRs showed that enhanced BW thickening (RR 9.77, 95% CI 2.64–36.07, p = 0.001), bowel obstruction (RR 5.05, 95% CI 2.30–11.09, p &lt; 0.001), and bowel perforation (RR 3.82, 95% CI 1.96–7.44, p &lt; 0.001) associated with higher late GI toxicity grades. Conclusions Our study shows CT findings correlate with grade 2–4 late GI toxicity. Future research should validate and refine these findings with different imaging and toxicity grading systems to assess their potential predictive value.

nnU-Net based segmentation and 3D reconstruction of uterine fibroids with MRI images for HIFU surgery planning

High-Intensity Focused Ultrasound (HIFU) ablation represents a rapidly advancing non-invasive treatment modality that has achieved considerable success in addressing uterine fibroids, which constitute over 50% of benign gynecological tumors. Preoperative Magnetic Resonance Imaging (MRI) plays a pivotal role in the planning and guidance of HIFU surgery for uterine fibroids, wherein the segmentation of tumors holds critical significance. The segmentation process was previously manually executed by medical experts, entailing a time-consuming and labor-intensive procedure heavily reliant on clinical expertise. This study introduced deep learning-based nnU-Net models, offering a cost-effective approach for their application in the segmentation of uterine fibroids utilizing preoperative MRI images. Furthermore, 3D reconstruction of the segmented targets was implemented to guide HIFU surgery. The evaluation of segmentation and 3D reconstruction performance was conducted with a focus on enhancing the safety and effectiveness of HIFU surgery. Results demonstrated the nnU-Net's commendable performance in the segmentation of uterine fibroids and their surrounding organs. Specifically, 3D nnU-Net achieved Dice Similarity Coefficients (DSC) of 92.55% for the uterus, 95.63% for fibroids, 92.69% for the spine, 89.63% for the endometrium, 97.75% for the bladder, and 90.45% for the urethral orifice. Compared to other state-of-the-art methods such as HIFUNet, U-Net, R2U-Net, ConvUNeXt and 2D nnU-Net, 3D nnU-Net demonstrated significantly higher DSC values, highlighting its superior accuracy and robustness. In conclusion, the efficacy of the 3D nnU-Net model for automated segmentation of the uterus and its surrounding organs was robustly validated. When integrated with intra-operative ultrasound imaging, this segmentation method and 3D reconstruction hold substantial potential to enhance the safety and efficiency of HIFU surgery in the clinical treatment of uterine fibroids.

Deep learning based uterine fibroid detection in ultrasound images

Uterine fibroids are common benign tumors originating from the uterus's smooth muscle layer, often leading to symptoms such as pelvic pain, and reproductive issues. Early detection is crucial to prevent complications such as infertility or the need for invasive treatments like hysterectomy. One of the main challenges in diagnosing uterine fibroids is the lack of specific symptoms, which can mimic other gynecological conditions. This often leads to under-diagnosis or misdiagnosis, delaying appropriate management. In this research, an attention based fine-tuned EfficientNetB0 model is proposed for the classification of uterine fibroids from ultrasound images. Attention mechanisms, permit the model to focus on particular parts of an image and move forward the model's execution by empowering it to specifically go to imperative highlights whereas overlooking irrelevant ones. The proposed approach has used a total of 1990 images divided into two classes: Non-uterine fibroid and uterine fibroid. The data augmentation methods have been connected to improve generalization and strength by exposing it to a wider range of varieties within the training data. The proposed model has obtained the value of accuracy as 0.99. Future research should focus on improving the accuracy and efficiency of diagnostic techniques, as well as evaluating their effectiveness in diverse populations with higher sensitivity and specificity for the detection of uterine fibroids, as well as biomarkers to aid in diagnosis.

Multiparametric mri-based radiomics nomogram for predicting lymph-vascular space invasion in cervical cancer

Abstract Purpose To develop and validate a multiparametric magnetic resonance imaging (mpMRI)-based radiomics model for predicting lymph-vascular space invasion (LVSI) of cervical cancer (CC). Methods The data of 177 CC patients were retrospectively collected and randomly divided into the training cohort (n=123) and testing cohort (n = 54). All patients received preoperative MRI. Feature selection and radiomics model construction were performed using max-relevance and min-redundancy (mRMR) and the least absolute shrinkage and selection operator (LASSO) on the training cohort. The models were established based on the extracted features. The optimal model was selected and combined with clinical independent risk factors to establish the radiomics fusion model and the nomogram. The diagnostic performance of the model was assessed by the area under the curve. Results Feature selection extracted the thirteen most important features for model construction. These radiomics features and one clinical characteristic were selected showed favorable discrimination between LVSI and non-LVSI groups. The AUCs of the radiomics nomogram and the mpMRI radiomics model were 0.838 and 0.835 in the training cohort, and 0.837 and 0.817 in the testing cohort. Conclusion The nomogram model based on mpMRI radiomics has high diagnostic performance for preoperative prediction of LVSI in patients with CC.

Performance of node reporting and data system (node-RADS): a preliminary study in cervical cancer

Abstract Background Node Reporting and Data System (Node-RADS) was proposed and can be applied to lymph nodes (LNs) across all anatomical sites. This study aimed to investigate the diagnostic performance of Node-RADS in cervical cancer patients. Methods A total of 81 cervical cancer patients treated with radical hysterectomy and LN dissection were retrospectively enrolled. Node-RADS evaluations were performed by two radiologists on preoperative MRI scans for all patients, both at the LN level and patient level. Chi-square and Fisher’s exact tests were employed to evaluate the distribution differences in size and configuration between patients with and without LN metastasis (LNM) in various regions. The receiver operating characteristic (ROC) and the area under the curve (AUC) were used to explore the diagnostic performance of the Node-RADS score for LNM. Results The rates of LNM in the para-aortic, common iliac, internal iliac, external iliac, and inguinal regions were 7.4%, 9.3%, 19.8%, 21.0%, and 2.5%, respectively. At the patient level, as the NODE-RADS score increased, the rate of LNM also increased, with rates of 26.1%, 29.2%, 42.9%, 80.0%, and 90.9% for Node-RADS scores 1, 2, 3, 4, and 5, respectively. At the patient level, the AUCs for Node-RADS scores &gt; 1, &gt;2, &gt; 3, and &gt; 4 were 0.632, 0.752, 0.763, and 0.726, respectively. Both at the patient level and LN level, a Node-RADS score &gt; 3 could be considered the optimal cut-off value with the best AUC and accuracy. Conclusions Node-RADS is effective in predicting LNM for scores 4 to 5. However, the proportions of LNM were more than 25% at the patient level for scores 1 and 2, which does not align with the expected very low and low probability of LNM for these scores.

T1 mapping as a quantitative imaging biomarker for diagnosing cervical cancer: a comparison with diffusion kurtosis imaging

Abstract Background T1 mapping can potentially quantitatively assess the intrinsic properties of tumors. This study was conducted to explore the ability of T1 mapping in distinguishing cervical cancer type, grade, and stage and compare the diagnostic performance of T1 mapping with diffusion kurtosis imaging (DKI). Methods One hundred fifty-seven patients with pathologically confirmed cervical cancer were enrolled in this prospectively study. T1 mapping and DKI were performed. The native T1, difference between native and postcontrast T1 (T1diff), mean kurtosis (MK), mean diffusivity (MD), and apparent diffusion coefficient (ADC) were calculated. Cervical squamous cell carcinoma (CSCC) and adenocarcinoma (CAC), low- and high-grade carcinomas, and early- and advanced-stage groups were compared using area under the receiver operating characteristic (AUROC) curves. Results The native T1 and MK were higher, and the MD and ADC were lower for CSCC than for CAC (all p &lt; 0.05). Compared with low-grade CSCC, high-grade CSCC had decreased T1diff, MD, ADC, and increased MK (p &lt; 0.05). Compared with low-grade CAC, high-grade CAC had decreased T1diff and increased MK (p &lt; 0.05). Native T1 was significantly higher in the advanced-stage group than in the early-stage group (p &lt; 0.05). The AUROC curves of native T1, MK, ADC and MD were 0,772, 0.731, 0.715, and 0.627, respectively, for distinguishing CSCC from CAC. The AUROC values were 0.762 between high- and low-grade CSCC and 0.835 between high- and low-grade CAC, with T1diff and MK showing the best discriminative values, respectively. For distinguishing between advanced-stage and early-stage cervical cancer, only the AUROC of native T1 was statistically significant (AUROC = 0.651, p = 0.002). Conclusions Compared with DKI-derived parameters, native T1 exhibits better efficacy for identifying cervical cancer subtype and stage, and T1diff exhibits comparable discriminative value for cervical cancer grade.

Clinical and multiparametric MRI features for differentiating uterine carcinosarcoma from endometrioid adenocarcinoma

Abstract Introduction The purpose of our study was to differentiate uterine carcinosarcoma (UCS) from endometrioid adenocarcinoma (EAC) by the multiparametric magnetic resonance imaging (MRI) features. Methods We retrospectively evaluated clinical and MRI findings in 17 patients with UCS and 34 patients with EAC proven by histologically. The following clinical and pathological features were evaluated: post- or pre-menopausal, clinical presentation, invasion depth, FIGO stage, lymphaticmetastasis. The following MRI features were evaluated: tumor dimension, cystic degeneration or necrosis, hemorrhage, signal intensity (SI) on T2-weighted images (T2WI), relative SI of lesion to myometrium on T2WI, T1WI, DWI, ADCmax, ADCmin, ADCmean (RSI-T2, RSI-T1, RSI-DWI, RSI-ADCmax, RSI-ADCmin, RSI-ADCmean), ADCmax, ADCmin, ADCmean, the maximum, minimum and mean relative enhancement (RE) of lesion to myometrium on the arterial and venous phases (REAmax, REAmin, REAmean, REVmax, REVmin, REVmean). Receiver operating characteristic (ROC) analysis and the area under the curve (AUC) were used to evaluate prediction ability. Results The mean age of UCS was higher than EAC. UCS occurred more often in the postmenopausal patients. UCS and EAC did not significantly differ in depth of myometrial invasion, FIGO stage and lymphatic metastasis. The anterior-posterior and transverse dimensions were significantly larger in UCS than EAC. Cystic degeneration or necrosis and hemorrhage were more likely occurred in UCS. The SI of tumor on T2WI was more heterogeneous in UCS. The RSI-T2, ADCmax, ADCmean, RSI-ADCmax and RSI-ADCmean of UCS were significantly higher than EAC. The REAmax, REAmin, REAmean, REVmax, REVmin and REVmean of UCS were all higher than EAC. The AUCs were 0.72, 0.71, 0.86, 0.96, 0.89, 0.84, 0.73, 0.97, 0.88, 0.94, 0.91, 0.69 and 0.80 for the anterior-posterior dimension, transverse dimension, RSI-T2, ADCmax, ADCmean, RSI-ADCmax, RSI-ADCmean, REAmax, REAmin, REAmean, REVmax, REVmin and REVmean, respectively. The AUC was 0.997 of the combined of ADCmax, REAmax and REVmax. Our study showed that ADCmax threshold value of 789.05 (10 –3 mm 2 /s) can differentiate UCS from EAC with 100% sensitivity, 76.5% specificity, and 0.76 AUC, REAmax threshold value of 0.45 can differentiate UCS from EAC with 88.2% sensitivity, 100% specificity, and 0.88 AUC. Conclusion Multiparametric MRI features may be utilized as a biomarker to distinguish UCS from EAC.

Preoperative prediction of cervical cancer survival using a high-resolution MRI-based radiomics nomogram

Abstract Background Cervical cancer patients receiving radiotherapy and chemotherapy require accurate survival prediction methods. The objective of this study was to develop a prognostic analysis model based on a radiomics score to predict overall survival (OS) in cervical cancer patients. Methods Predictive models were developed using data from 62 cervical cancer patients who underwent radical hysterectomy between June 2020 and June 2021. Radiological features were extracted from T2-weighted (T2W), T1-weighted (T1W), and diffusion-weighted (DW) magnetic resonance images prior to treatment. We obtained the radiomics score (rad-score) using least absolute shrinkage and selection operator (LASSO) regression and Cox’s proportional hazard model. We divided the patients into low- and high-risk groups according to the critical rad-score value, and generated a nomogram incorporating radiological features. We evaluated the model’s prediction performance using area under the receiver operating characteristic (ROC) curve (AUC) and classified the participants into high- and low-risk groups based on radiological characteristics. Results The 62 patients were divided into high-risk ( n  = 43) and low-risk ( n  = 19) groups based on the rad-score. Four feature parameters were selected via dimensionality reduction, and the scores were calculated after modeling. The AUC values of ROC curves for prediction of 3- and 5-year OS using the model were 0.84 and 0.93, respectively. Conclusion Our nomogram incorporating a combination of radiological features demonstrated good performance in predicting cervical cancer OS. This study highlights the potential of radiomics analysis in improving survival prediction for cervical cancer patients. However, further studies on a larger scale and external validation cohorts are necessary to validate its potential clinical utility.

Automated cervical cell segmentation using deep ensemble learning

Abstract Background Cervical cell segmentation is a fundamental step in automated cervical cancer cytology screening. The aim of this study was to develop and evaluate a deep ensemble model for cervical cell segmentation including both cytoplasm and nucleus segmentation. Methods The Cx22 dataset was used to develop the automated cervical cell segmentation algorithm. The U-Net, U-Net +  + , DeepLabV3, DeepLabV3Plus, Transunet, and Segformer were used as candidate model architectures, and each of the first four architectures adopted two different encoders choosing from resnet34, resnet50 and denseNet121. Models were trained under two settings: trained from scratch, encoders initialized from ImageNet pre-trained models and then all layers were fine-tuned. For every segmentation task, four models were chosen as base models, and Unweighted average was adopted as the model ensemble method. Results U-Net and U-Net +  + with resnet34 and denseNet121 encoders trained using transfer learning consistently performed better than other models, so they were chosen as base models. The ensemble model obtained the Dice similarity coefficient, sensitivity, specificity of 0.9535 (95% CI:0.9534–0.9536), 0.9621 (0.9619–0.9622),0.9835 (0.9834–0.9836) and 0.7863 (0.7851–0.7876), 0.9581 (0.9573–0.959), 0.9961 (0.9961–0.9962) on cytoplasm segmentation and nucleus segmentation, respectively. The Dice, sensitivity, specificity of baseline models for cytoplasm segmentation and nucleus segmentation were 0.948, 0.954, 0.9823 and 0.750, 0.713, 0.9988, respectively. Except for the specificity of cytoplasm segmentation, all metrics outperformed the best baseline models ( P  &lt; 0.05) with a moderate margin. Conclusions The proposed algorithm achieved better performances on cervical cell segmentation than baseline models. It can be potentially used in automated cervical cancer cytology screening system.

Multimodal magnetic resonance imaging in the diagnosis of cervical cancer and its correlation with the differentiation process of cervical cancer

Abstract Purpose This study seeks to evaluate the value of MRI (Magnetic resonance imaging) diffusion weighted images (DWI), diffusion kurtosis imaging (DKI) and intravoxel incoherent motion (IVIM) in the diagnosis of cervical carcinoma. Methods Seventy-nine cases of cervical cancer (CC group) (39 cases of squamous carcinoma (SCC group) and 40 cases of adenocarcinoma (ACC group)) and 30 cases of healthy controls (HC group) were included in this study. All the subjects were informed of the purpose of this study. The study was approved by the Ethics Committee of Beihua University Hospital, Jinlin, China. In this study, images were acquired based on a 3T MR scanner (Ingenia; Philips, Best, the Netherlands) and measured the imaging parameters by DWI, IVIM and DKI techniques. The parameters were obtained by Philips post-processing workstation, DKE and IVIM. These ROIs (region of interest) were manually drawn on each parameter mapping image by MRI physicians. Finally, SPSS 23.0 statistical software was used for data analysis. Results The ADC (apparent diffusion coefficient) value of M group was lower than that of N group, and the difference was statistically significant ( P  &lt; 0.05). The D (true diffusion coefficient) value, D*(pseudo diffusion coefficient) value, f (perfusion fraction) value, MD (mean diffusivity) value, and ADC value in the SCC group were lower than those in the ACC group with statistically significant differences ( P  &lt; 0.05). The MK (mean kurtosis) value was higher than that of the ACC group, and the difference was statistically significant ( P  &lt; 0.05). Compared with the HC group, the ADC values, D values, MD values of group CC group were lower, and the D* values, f values, MK values were higher; all the parameters were statistically significant ( P  &lt; 0.05). The higher the differentiation degree of cervical cancer, the higher ADC values, D values, MD values, and the smaller D* values, f values, MK values. The difference of ADC values, D values and MK values was statistically significant ( P  &lt; 0.05). MK value had the best diagnostic efficiency in the differential diagnosis of cervical cancer with low and medium differentiation, high and low differentiation ( P  &lt; 0.05). There was no significant difference in the f value between high and low differentiation cervical cancer ( P  &gt; 0.05). There was no significant difference in the MD value between low and high differentiation cervical cancer ( P  &gt; 0.05). The strongest correlation between MK values ( r = 0.796) and the degree of pathological differentiation of cervical cancer is positively correlated. The D values, MD values, and ADC values are negatively correlated with the degree of pathological differentiation of cervical cancer. Conclusion The ADC value of DWI parameters has important diagnostic value for different menstrual states of cervical cancer. The parameter values of DWI, IVIM, and DKI can be used to differentiate cervical cancer from normal cervical tissue, and thus have important diagnostic value for differentiating pathological types of cervical cancer. This means that these parameter values may have great significance in the differential diagnosis of cervical cancer with different degrees of pathological differentiation. The pathological differentiation degree of cervical cancer is significantly positively correlated with the MK value in the parameter values of DWI, IVIM, and DKI, while negatively correlated with the D value, MD value, and ADC value.

Prediction of lymph node status in patients with early-stage cervical cancer based on radiomic features of magnetic resonance imaging (MRI) images

Abstract Background Lymph node metastasis is an important factor affecting the treatment and prognosis of patients with cervical cancer. However, the comparison of different algorithms and features to predict lymph node metastasis is not well understood. This study aimed to construct a non-invasive model for predicting lymph node metastasis in patients with cervical cancer based on clinical features combined with the radiomic features of magnetic resonance imaging (MRI) images. Methods A total of 180 cervical cancer patients were divided into the training set (n = 126) and testing set (n = 54). In this cross-sectional study, radiomic features of MRI images and clinical features of patients were collected. The least absolute shrinkage and selection operator (LASSO) regression was used to filter the features. Seven machine learning methods, including eXtreme Gradient Boosting (XGBoost), Logistic Regression, Multinomial Naive Bayes (MNB), Support Vector Machine (SVM), Decision Tree, Random Forest, and Gradient Boosting Decision Tree (GBDT) are used to build the models. Receiver operating characteristics (ROC) curve and area under the curve (AUC), accuracy, sensitivity, and specificity were calculated to assess the performance of the models. Results Of these 180 patients, 49 (27.22%) patients had lymph node metastases. Five of the 122 radiomic features and 3 clinical features were used to build predictive models. Compared with other models, the MNB model was the most robust, with its AUC, specificity, and accuracy on the testing set of 0.745 (95%CI: 0.740–0.750), 0.900 (95%CI: 0.807–0.993), and 0.778 (95%CI: 0.667–0.889), respectively. Furthermore, the AUCs of the MNB models with clinical features only, radiomic features only, and combined features were 0.698 (95%CI: 0.692–0.704), 0.632 (95%CI: 0.627–0.637), and 0.745 (95%CI: 0.740–0.750), respectively. Conclusion The MNB model, which combines the radiomic features of MRI images with the clinical features of the patient, can be used as a non-invasive tool for the preoperative assessment of lymph node metastasis.

Prediction of BRCA gene mutation status in epithelial ovarian cancer by radiomics models based on 2D and 3D CT images

Abstract Background The objective of this study is to explore the value of two-dimensional (2D) and three-dimensional (3D) radiomics models based on enhanced computed tomography (CT) images in predicting BRCA gene mutations in patients with epithelial ovarian cancer. Methods The clinical and imaging data of 106 patients with ovarian cancer confirmed by surgery and pathology were retrospectively analyzed and genetic testing was performed. Radiomics features extracted from the 2D and 3D regions of interest of the patients’ primary tumor lesions were selected in the training set using the maximum correlation and minimum redundancy method. Then, the best features were selected through Lasso tenfold cross-validation. Feature subsets were employed to establish a radiomics model. The model’s performance was evaluated via area under the receiver operating characteristic curve analysis and its clinical validity was assessed by using the model’s decision curve. Results On the validation set, the area under the curve values of the 2D, 3D, and 2D + 3D combined models were 0.78 (0.61–0.96), 0.75 (0.55–0.92), and 0.82 (0.61–0.96), respectively. However, the DeLong test P values between the three pairs of models were all &gt; 0.05. The decision curve analysis showed that the radiomics model had a high net benefit across all high-risk threshold probabilities. Conclusions The three radiomics models can predict the BRCA gene mutation in ovarian cancer, and there were no statistically significant differences between the prediction performance of the three models.

RESOLVE-DWI-based deep learning nomogram for prediction of normal-sized lymph node metastasis in cervical cancer: a preliminary study

Abstract Background It is difficult to predict normal-sized lymph node metastasis (LNM) in cervical cancer clinically. We aimed to investigate the feasibility of using deep learning (DL) nomogram based on readout segmentation of long variable echo-trains diffusion weighted imaging (RESOLVE-DWI) and related patient information to preoperatively predict normal-sized LNM in patients with cervical cancer. Methods A dataset of MR images [RESOLVE-DWI and apparent diffusion coefficient (ADC)] and patient information (age, tumor size, International Federation of Gynecology and Obstetrics stage, ADC value and squamous cell carcinoma antigen level) of 169 patients with cervical cancer between November 2013 and January 2022 were retrospectively collected. The LNM status was determined by final histopathology. The collected studies were randomly divided into a development cohort (n = 126) and a test cohort (n = 43). A single-channel convolutional neural network (CNN) and a multi-channel CNN based on ResNeSt architectures were proposed for predicting normal-sized LNM from single or multi modalities of MR images, respectively. A DL nomogram was constructed by incorporating the clinical information and the multi-channel CNN. These models’ performance was analyzed by the receiver operating characteristic analysis in the test cohort. Results Compared to the single-channel CNN model using RESOLVE-DWI and ADC respectively, the multi-channel CNN model that integrating both two MR modalities showed improved performance in development cohort [AUC 0.848; 95% confidence interval (CI) 0.774–0.906] and test cohort (AUC 0.767; 95% CI 0.613–0.882). The DL nomogram showed the best performance in development cohort (AUC 0.890; 95% CI 0.821–0.938) and test cohort (AUC 0.844; 95% CI 0.701–0.936). Conclusion The DL nomogram incorporating RESOLVE-DWI and clinical information has the potential to preoperatively predict normal-sized LNM of cervical cancer.

3cDe-Net: a cervical cancer cell detection network based on an improved backbone network and multiscale feature fusion

Abstract Background Cervical cancer cell detection is an essential means of cervical cancer screening. However, for thin-prep cytology test (TCT)-based images, the detection accuracies of traditional computer-aided detection algorithms are typically low due to the overlapping of cells with blurred cytoplasmic boundaries. Some typical deep learning-based detection methods, e.g., ResNets and Inception-V3, are not always efficient for cervical images due to the differences between cervical cancer cell images and natural images. As a result, these traditional networks are difficult to directly apply to the clinical practice of cervical cancer screening. Method We propose a cervical cancer cell detection network (3cDe-Net) based on an improved backbone network and multiscale feature fusion; the proposed network consists of the backbone network and a detection head. In the backbone network, a dilated convolution and a group convolution are introduced to improve the resolution and expression ability of the model. In the detection head, multiscale features are obtained based on a feature pyramid fusion network to ensure the accurate capture of small cells; then, based on the Faster region-based convolutional neural network (R-CNN), adaptive cervical cancer cell anchors are generated via unsupervised clustering. Furthermore, a new balanced L1-based loss function is defined, which reduces the unbalanced sample contribution loss. Result Baselines including ResNet-50, ResNet-101, Inception-v3, ResNet-152 and the feature concatenation network are used on two different datasets (the Data-T and Herlev datasets), and the final quantitative results show the effectiveness of the proposed dilated convolution ResNet (DC-ResNet) backbone network. Furthermore, experiments conducted on both datasets show that the proposed 3cDe-Net, based on the optimal anchors, the defined new loss function, and DC-ResNet, outperforms existing methods and achieves a mean average precision (mAP) of 50.4%. By performing a horizontal comparison of the cells on an image, the category and location information of cancer cells can be obtained concurrently. Conclusion The proposed 3cDe-Net can detect cancer cells and their locations on multicell pictures. The model directly processes and analyses samples at the picture level rather than at the cellular level, which is more efficient. In clinical settings, the mechanical workloads of doctors can be reduced, and their focus can be placed on higher-level review work.

Clinical evaluation of deep learning–based clinical target volume three-channel auto-segmentation algorithm for adaptive radiotherapy in cervical cancer

Abstract Objectives Accurate contouring of the clinical target volume (CTV) is a key element of radiotherapy in cervical cancer. We validated a novel deep learning (DL)-based auto-segmentation algorithm for CTVs in cervical cancer called the three-channel adaptive auto-segmentation network (TCAS). Methods A total of 107 cases were collected and contoured by senior radiation oncologists (ROs). Each case consisted of the following: (1) contrast-enhanced CT scan for positioning, (2) the related CTV, (3) multiple plain CT scans during treatment and (4) the related CTV. After registration between (1) and (3) for the same patient, the aligned image and CTV were generated. Method 1 is rigid registration, method 2 is deformable registration, and the aligned CTV is seen as the result. Method 3 is rigid registration and TCAS, method 4 is deformable registration and TCAS, and the result is generated by a DL-based method. Results From the 107 cases, 15 pairs were selected as the test set. The dice similarity coefficient (DSC) of method 1 was 0.8155 ± 0.0368; the DSC of method 2 was 0.8277 ± 0.0315; the DSCs of method 3 and 4 were 0.8914 ± 0.0294 and 0.8921 ± 0.0231, respectively. The mean surface distance and Hausdorff distance of methods 3 and 4 were markedly better than those of method 1 and 2. Conclusions The TCAS achieved comparable accuracy to the manual delineation performed by senior ROs and was significantly better than direct registration.

Predicting preoperative lymph node metastasis in patients with high-grade serous ovarian cancer by using intratumoral and peritumoral radiomics: a retrospective cohort study

Ovarian cancer (OC) carries the worst prognosis among gynecologic cancers, with high-grade serous ovarian cancer (HGSOC) as its most common subtype. Cytoreductive surgery (tumor resection) is the cornerstone of OC treatment. However, controversy remains regarding whether lymphadenectomy should be performed during surgery; more than 30% of patients with OC undergo unnecessary lymphadenectomy, increasing surgical risks and prolonging postoperative recovery. By analyzing multidimensional imaging features, such as tumor morphology, texture, and density, radiomics can accurately quantify the biological characteristics of tumors. However, its application in OC needs to be explored further. This study aimed to explore radiomics' role in predicting lymph node metastasis risk in HGSOC. This retrospective cohort analysis involved 273 participants from Qingdao University Affiliated Hospital and Rizhao People's Hospital, and they were categorized into the training, testing, and external validation groups. Imaging characteristics were derived from the tumor region of interest and its surrounding areas (1-5 mm), and radiomics scores were calculated for each region. This approach was employed for assessing the diagnostic performance of different regions and identify the optimal one. We constructed a risk prediction model that integrated imaging features of the optimal region with independent clinical risk factors. The radiomic features of the tumor and its surrounding 3-mm extension region yielded area under the curve (AUC) values of 0.957 and 0.793 in the training and testing sets, respectively. After integrating the radiomic features of the tumor and its surrounding 3-mm extension region with clinical features, the AUC values in the training set, testing set, and external validation set were 0.971, 0.811, and 0.869, respectively, demonstrating strong predictive ability. This study developed a model to assess lymph node metastasis likelihood in HGSOC patients. In the test and external validation cohorts, the model demonstrated excellent predictive performance. We believe the model can assist clinicians in identifying patients who are suitable for lymph node resection, thereby optimizing treatment decisions. Not applicable.

O-RADS US versus IOTA simple rules in the diagnosis of benign and malignant adnexal masses: a prospective study

Although many studies have validated the diagnostic performance of Ovarian-Adnexal Reporting and Data Systems ultrasound (O-‎RADS US), most have been observed by experienced sonologists, and relatively few by junior sonologists. The purpose of this study was to compare the diagnostic performance of the O-RADS US and the International Ovarian Tumor Analysis (IOTA) Simple Rules (SRs) in senior and junior sonologists to determine a more suitable assessment model for general clinical use. We prospectively recruited 228 patients diagnosed with adnexal masses (AMs). Two senior sonologists acquired images and evaluated them following the O-RADS US and IOTA guidelines, and two junior sonologists reviewed and analyzed images and evaluated them following the same guidelines. In this research, pathological findings were used as the reference standard. Comparisons of categorical variables were made using the chi-square test, and comparisons of continuous variables were made using the two independent-samples t-test. The diagnostic performance of the models was compared by analyzing the receiver operating characteristic (ROC) curve. The kappa value (κ) was used to compare the interobserver agreement between the senior and junior sonologists and the agreement between each ultrasound method and the reference standard. Of 228 AMs, 176 were benign and 52 malignant. The junior adjusted O-RADS US (> O-RADS 4a represents malignancy) had the highest diagnostic validity, with a sensitivity, specificity, and accuracy of 94.23%, 87.5%, and 89.04%, respectively, and ROC curve of 0.959 (95% CI, 0.924-0.980). Both junior unadjusted (> O-RADS 3 represents malignancy) and adjusted O-RADS US had significantly higher diagnostic performance than the junior SRs (AUC 0.951 and 0.959 vs. 0.840, P = 0.0003, 0.0001, respectively). Interobserver agreement between senior and junior sonologists using O-RADS US was moderate (κ = 0.465), and interobserver agreement between senior and junior sonologists using SRs, unadjusted, and adjusted O-RADS US was good (κ = 0.618, 0.657, and 0.718, respectively). The junior unadjusted O-RADS US, adjusted O-RADS US, and SRs showed good agreement with the pathological results (κ = 0.648, 0.724, 0.716, respectively). When assisting sonologists in AM diagnosis, the O-RADS US, especially the adjusted O-RADS US, had higher diagnostic performance than the SRs, and it would be more suitable for general clinical application.

Ultrasound-based radiomics for predicting the five major histological subtypes of epithelial ovarian cancer

Computational approaches have been proposed using radiomics in order to assess tumour heterogeneity, which is motivated by the concept that biomedical images may contain underlying pathophysiology information and has the potential to quantitatively measure the heterogeneity of intra- and intertumours. Ovarian cancer has the highest mortality among malignant tumours of female reproductive system and can be further divided into many subtypes with different management strategies and prognosis. The purpose of our study is to develop and validate ultrasound-based radiomics models to distinguish the five major histological subtypes of epithelial ovarian cancer. From January 2018 to August 2022, 1209 eligible ovarian cancer patients were enrolled. There were two subjects in this study: all patients (n = 1209) and patients with the five major histological subtypes (n = 1039). After image segmentation manually, radiomics features were extracted and some clinical characteristics were added. Nine feature selection methods were used to select the optimal predictive features. Seven classifiers were carried out to construct models. Choose the combination with the best predictive performance as the final result. As for low-grade serous carcinoma, endometrioid carcinoma, and clear cell carcinoma, the models yields AUCs below 0.80 in the 10-fold cross-validation in the two groups. As for mucinous carcinoma, the AUCs were 0.83(95%CI, 0.74-0.93) and 0.89(95%CI, 0.83-0.95) in the validation cohorts and 0.80(95%CI, 0.73-0.87) and 0.86(95%CI, 0.78-0.94) in the 10-fold cross-validation in the two groups, respectively. As for high-grade serous carcinoma (HGSC), the models showed AUCs of 0.87(95%CI, 0.83-0.91) and 0.85(95%CI, 0.81-0.89) in the validation cohorts and 0.87(95%CI, 0.85-0.89) and 0.84(95%CI, 0.81-0.87) in the 10-fold cross-validation in the two groups, respectively, and exhibited high consistency between the predicted results and the actual outcomes, and brought great net benefits for patients. The ultrasound-based radiomics models in discriminating HGSC and non-HGSC showed good predictive performance, as well as high consistency between the predicted results and the actual outcomes, and brought significant net benefits for patients.

The predictive value of nomogram for adnexal cystic-solid masses based on O-RADS US, clinical and laboratory indicators

Ovarian cancer remains a leading cause of death among women, largely due to its asymptomatic early stages and high mortality when diagnosed late. Early detection significantly improves survival rates, and the Ovarian-Adnexal Reporting and Data System Ultrasound (O-RADS US) is currently the most commonly used method, but has limitations in specificity and accuracy. While O-RADS US has standardized reporting, its sensitivity can lead to the misdiagnosis of benign masses as malignant, resulting in overtreatment. This study aimed to construct a nomogram model based on the O-RADS US and clinical and laboratory indicators to predict the malignancy risk of adnexal cystic-solid masses. This retrospective study collected data from patients with adnexal cystic-solid masses who underwent ultrasonography and were pathologically confirmed between January 2021 and December 2023 at the First Affiliated Hospital of Shenzhen University. They were categorized into benign and malignant groups according to pathological findings. Least absolute shrinkage and selection operator (LASSO) regression analysis was used to select the most relevant predictors of ovarian cancer. A nomogram model was constructed, and its diagnostic performance was calculated. We bootstrapped the data 500 times to perform internal verification, drew a calibration curve to verify the prediction ability, and performed a decision curve analysis to assess clinical usefulness. A total of 399 patients with adnexal cystic-solid masses were included in this study: 327 in the benign group and 72 in the malignant group. Five predictors associated with the risk of malignancy of adnexal cystic-solid masses were selected using LASSO regression: O-RADS, acoustic shadowing, postmenopausal status, CA125, and HE4. The area under the curve, sensitivity, specificity, accuracy, positive and negative predictive values of the nomogram were 0.909, 83.3%, 82.9%, 83.0%, 51.7%, and 95.8%, respectively. The calibration curve of the nomogram showed good consistency between the predicted and actual probabilities, and the decision curve showed good clinical usefulness. The nomogram model based on O-RADS US and clinical and laboratory indicators can be used to predict the risk of malignancy in adnexal cystic-solid masses, with high predictive performance, good calibration, and clinical usefulness.