Academic Radiology

Deep Myometrial Infiltration of Endometrial Cancer on MRI: A Radiomics-Powered Machine Learning Pilot Study

To evaluate an MRI radiomics-powered machine learning (ML) model's performance for the identification of deep myometrial invasion (DMI) in endometrial cancer (EC) patients and explore its clinical applicability. Preoperative MRI scans of EC patients were retrospectively selected. Three radiologists performed whole-lesion segmentation on T2-weighted images for feature extraction. Feature robustness was tested before randomly splitting the population in training and test sets (80/20% proportion). A multistep feature selection was applied to the first, excluding noninformative, low variance features and redundant, highly-intercorrelated ones. A Random Forest wrapper was used to identify the most informative among the remaining. An ensemble of J48 decision trees was tuned and finalized in the training set using 10-fold cross-validation, and then assessed on the test set. A radiologist evaluated all MRI scans without and with the aid of ML to detect the presence of DMI. McNemars's test was employed to compare the two readings. Of the 54 patients included, 17 had DMI. In all, 1132 features were extracted. After feature selection, the Random Forest wrapper identified the three most informative which were used for ML training. The classifier reached an accuracy of 86% and 91% and areas under the Receiver Operating Characteristic curve of 0.92 and 0.94 in the cross-validation and final testing, respectively. The radiologist performance increased from 82% to 100% when using ML (p = 0.48). We proved the feasibility of a radiomics-powered ML model for DMI detection on MR T2-w images that might help radiologists to increase their performance.

The Diagnostic Value of MRI for Preoperative Staging in Patients with Endometrial Cancer: A Meta-Analysis

To assess the diagnostic accuracy of magnetic resonance imaging (MRI) for detecting myometrial invasion, cervical invasion, and lymph node metastases in endometrial cancer. A systematic literature search was performed in PubMed, Embase, Cochrane Library, Web of Science, and Clinical trials. The methodological quality of each study was assessed by using the standard Quality Assessment of Diagnostic Accuracy Studies-2. Statistical analysis included evaluating publication bias, assessing threshold effect, exploring heterogeneity, pooling data, meta-regression, forest plot, and summary receiver-operating characteristics curves construction. Fourteen studies could be analyzed. For detecting deep myometrial invasion, the pooled sensitivity and specificity were 0.79 and 0.81 respectively, and patients younger than 60 years old demonstrated higher sensitivity (0.84) and specificity (0.90). The diagnostic accuracy is highest by jointly using T2-weighted image, dynamic contrast-enhanced MRI, and diffusion weighted imaging to detect the deep myometrial invasion. There were low sensitivity and high specificity for the diagnosis of cervical invasion (0.53, 0.95), cervical stromal invasion (0.50, 0.95), pelvic or/and para-aortic lymph node metastases (0.59, 0.95), and pelvic lymph node metastases (0.65, 0.95). MRI has good diagnostic performance for assessing myometrial invasion in patients with endometrial cancer, especially in patients younger than 60 years old. Dynamic contrast-enhanced MRI and diffusion weighted imaging can help improve sensitivity and specificity for detecting myometrial invasion. MRI shows high specificity for detecting cervical invasion and lymph node metastases in endometrial cancer.

Interpretable Machine Learning Model for Differentiating Uterine Sarcoma From Atypical Leiomyoma Based on Conventional MRI Features and Radiomics

This study aims to develop interpretable machine learning (ML) models by integrating conventional magnetic resonance imaging (MRI) features and radiomics to preoperatively differentiate uterine sarcoma (US) and atypical leiomyoma (ALM). In this retrospective study, 160 patients (47 US, 113 ALM) were randomized into training (n=112) and test (n=48) cohorts. Two blinded radiologists assessed 10 MRI features from pelvic MRI examinations, including tumor border morphology, T2-weighted image (T2WI) signal heterogeneity, uterine endometrial cavity, apparent diffusion coefficient (ADC) value, and other features. Significant MRI features were identified through univariable and multivariable logistic regression analyses. Radiomics features were extracted from axial T2WI and diffusion-weighted imaging (DWI) sequences, with least absolute shrinkage and selection operator regression identifying four discriminative features for radiomic score (radscore) calculation. Five ML models are as follows: logistic regression (LR), random forest (RF), eXtreme gradient boosting (XGBoost), support vector machine (SVM), and Gaussian Naive Bayes (GNB) were trained using significant MRI predictors and radscore. Model performance was evaluated via area under the receiver operating characteristic curve (AUC), calibration curves, and decision curve analysis (DCA). The SHapley Additive exPlanation (SHAP) framework provided interpretable visualizations of feature contributions. Multivariable analysis identified four MRI discriminators as follows: heterogeneous hyperintensity on T2WI (odds ratio [OR]=43.767, P=0.021), ill-defined tumor border (OR=4.887, P=0.038), interrupted uterine cavity (OR=15.947, P=0.003), and low ADC values (OR=0.026, P=0.009). The XGBoost model achieved superior performance, with AUCs of 0.991 (95% confidence interval [CI]: 0.978-1.000) and 0.909 (95% CI: 0.822-0.995) in training and test cohorts, respectively. SHAP analysis highlighted ADC value as the most influential predictor, followed by tumor border, signal intensity on T2WI, radscore, and uterine endometrial cavity. DCA confirmed clinical utility across probability thresholds, and calibration curves demonstrated strong agreement between predicted and observed outcomes. Interpretable ML models integrating MRI biomarkers and radiomics provide a transparent and clinically actionable tool for preoperative differentiation of US and ALM. By quantifying feature contributions through SHAP and providing a transparent SHAP value, this framework bridges the "black-box" gap in ML, fostering clinicians trust and empowering clinicians to formulate precise interventions, such as appropriate surgical planning to avoid the morcellation of suspected US.

Deep Learning Radiomics Nomogram Based on Magnetic Resonance Imaging for Differentiating Type I/II Epithelial Ovarian Cancer

To develop and validate a T2-weighted magnetic resonance imaging (MRI)-based deep learning radiomics nomogram (DLRN) to differentiate between type I and type II epithelial ovarian cancer (EOC). This multicenter study incorporated 437 patients from five centers, divided into training (n = 271), internal validation (n = 68), and external validation (n = 98) sets. The deep learning (DL) model was constructed using the largest orthogonal slices of the tumor area. The extracted radiomics features were employed in building the radiomics model. The clinical model was developed based on clinical characteristics. A DLRN was built by integrating the DL signature, radiomics signature, and independent clinical predictors. Model performances were evaluated through receiver operating characteristic (ROC) analysis, Brier score, calibration curve, and decision curve analysis (DCA). The areas under the ROC curve (AUCs) were compared using the DeLong test. A two-tailed P < 0.05 was considered significantly different. The DLRN exhibited satisfactory discrimination between type I and type II EOC with the AUC of 0.888 (95% confidence interval [CI] 0.810, 0.966) and 0.866 (95% CI 0.786, 0.946) in the internal and external validation sets, respectively. These AUCs significantly exceeded those of the clinical model (P = 0.013 and 0.043, in the internal and external validation sets, respectively). The DLRN demonstrated optimal classification accuracy and clinical application value, according to Brier scores, calibration curves, and DCA. A T2-weighted MRI-based DLRN showed promising potential in differentiating between type I and type II EOC, which could offer assistance in clinical decision-making.

The Predictive Effect of Quantitative Analysis of Signal Intensity Heterogeneity on T2-Weighted MR Images for High-intensity Focused Ultrasound Treatment of Uterine Fibroids

To investigate whether the quantitative index of signal intensity (SI) heterogeneity on T2-weighted (T2W) magnetic resonance images can predict the difficulty and efficacy of high-intensity focused ultrasound (HIFU) ablation for uterine fibroids. The standard deviation (SD) of T2W image (T2WI) SI was used to quantify SI heterogeneity. The correlation between SD and the non-perfused volume ratio (NPVR) in 575 patients undergoing HIFU treatment was retrospectively analyzed, and the efficacy of SD in predicting NPVR was discussed. Three classifications were made based on the SD, and the ablation difficulty and ablation effect of different grades were compared. A total of 65 cases from another center were used as an external validation set to verify the classification performance of SD. The SD of SI was negatively correlated with NPVR (r = -0.460, p < 0.001). The predictive efficiency of SD for the ablation effect was higher than that of the scaled signal intensity (0.767 vs. 0.701, p = 0.006). Univariate and multivariate logistic regression analyses showed that SD was an independent predictor of ablation effect. Based on SD, the three classifications were divided into SD I: SD < 101.0, SD II: 101.0 ≤ SD < 138.7, and SD III: SD≥ 138.7. The treatment time, sonication time, treatment intensity, and total energy of SD I were lower than those of SD II and III (p < 0.05). The heterogeneity of T2WI SI of uterine fibroids is negatively correlated with NPVR. The SD of SI can be used to predict the ablation difficulty and ablation effect of HIFU.

Diffusion Weighted Imaging for the Assessment of Lymph Node Metastases in Women with Cervical Cancer: A Meta-analysis of the Apparent Diffusion Coefficient Values

To assess the diagnostic performance of Diffusion Weighted Imaging (DWI) and provide optimal apparent diffusion coefficient (ADC) cut-off values for differentiating between benign and metastatic lymph nodes in women with uterine cervical cancer. MEDLINE and EMBASE databases were searched. Methodological quality was assessed with QUADAS-2. Data analysis was performed for three subgroups: (1) All studies; (2) Studies with maximum b-values of 800 s/mm², and (3) Studies containing b-values of 1000 s/mm². Receiver-operating characteristics (ROC) curves were constructed and the area under the curve (AUC) was calculated. The maximum Youden index was used to determine optimal ADC cut-off values, following calculations of sensitivity and specificity. 16 articles (1156 patients) were included. Overall, their quality was limited. For all studies combined, the optimum ADC cut-off value was 0.985×10⁻³ mm²/s at maximum Youden Index of 0.77, resulting in sensitivity and specificity of 84%, and 94%, respectively. Studies with b-values up to 800 s/mm², gave an optimum ADC cut-off value of 0.985×10⁻³ mm²/s at maximum Youden Index of 0.62, with a sensitivity and specificity of 62%, and 100%. Studies containing b-values of 1000 s/mm² gave an optimum ADC cut-off value of 0.9435×10⁻³ mm²/s at maximum Youden Index of 0.93, with a sensitivity and specificity of 100%, and 93%, respectively. Studies using DWI including b-values of 1000 s/mm² have higher sensitivity and specificity than those with b-values up to 800 s/mm². At the cut-off value of 0.9435×10⁻³ mm²/s DWI can sufficiently discriminate between benign and metastatic lymph nodes.

Predicting the Prognosis of HIFU Ablation of Uterine Fibroids Using a Deep Learning-Based 3D Super-Resolution DWI Radiomics Model: A Multicenter Study

To assess the feasibility and efficacy of a deep learning-based three-dimensional (3D) super-resolution diffusion-weighted imaging (DWI) radiomics model in predicting the prognosis of high-intensity focused ultrasound (HIFU) ablation of uterine fibroids. This retrospective study included 360 patients with uterine fibroids who received HIFU treatment, including Center A (training set: N = 240; internal testing set: N = 60) and Center B (external testing set: N = 60) and were classified as having a favorable or unfavorable prognosis based on the postoperative non-perfusion volume ratio. A deep transfer learning approach was used to construct super-resolution DWI (SR-DWI) based on conventional high-resolution DWI (HR-DWI), and 1198 radiomics features were extracted from manually segmented regions of interest in both image types. Following data preprocessing and feature selection, radiomics models were constructed for HR-DWI and SR-DWI using Support Vector Machine (SVM), Random Forest (RF), and Light Gradient Boosting Machine (LightGBM) algorithms, with performance evaluated using area under the curve (AUC) and decision curves. All DWI radiomics models demonstrated superior AUC in predicting HIFU ablated uterine fibroids prognosis compared to expert radiologists (AUC: 0.706, 95% CI: 0.647-0.748). When utilizing different machine learning algorithms, the HR-DWI model achieved AUC values of 0.805 (95% CI: 0.679-0.931) with SVM, 0.797 (95% CI: 0.672-0.921) with RF, and 0.770 (95% CI: 0.631-0.908) with LightGBM. Meanwhile, the SR-DWI model outperformed the HR-DWI model (P < 0.05) across all algorithms, with AUC values of 0.868 (95% CI: 0.775-0.960) with SVM, 0.824 (95% CI: 0.715-0.934) with RF, and 0.821 (95% CI: 0.709-0.933) with LightGBM. And decision curve analysis further confirmed the good clinical value of the models. Deep learning-based 3D SR-DWI radiomics model demonstrated favorable feasibility and effectiveness in predicting the prognosis of HIFU ablated uterine fibroids, which was superior to HR-DWI model and assessment by expert radiologists.

Long-term Efficacy of Fibroid Devascularization with Ultrasound-Guided High-Intensity Focused Ultrasound

High-intensity focused ultrasound (HIFU) has been increasingly used for treatment of uterine leiomyoma. The superiority of HIFU therapy targeting uterine leiomyoma blood vessels, however, still needs to be further explored. This study aims to evaluate the long-term efficacy of fibroid devascularization with ultrasound-guided HIFU (USgHIFU) and the effects of treatment on the ovarian reserve and endometrial injury. Fibroid devascularization was assessed with the Adler grade obtained by color Doppler flow imaging and power Doppler imaging (PDI). The targeted vessels were covered and then sonicated by HIFU focal spots. The patients were followed up at 1 month, 3 months, 6 months, 1 year, 2 years and 3 years after treatment. Adverse effects and complications were recorded. The non-perfusion volume rate (NPVR), fibroid volume shrinkage rate (FVSR), Adler Grade, symptom severity score (SSS) and uterine fibroid symptom and quality of life (UFS-QOL) were evaluated. Adverse events (AEs) were recorded. In Center 1, the enrolled patients completed the anti-Müllerian hormone (AMH) test before and at 6 months after treatment. A total of 117 eligible patients were consecutively enrolled to receive interventions and follow-up evaluations of the three centers from January 2019 to May 2023. The 1-month and 6-month NPVRs were 66.60% ± 33.14% and 51.12% ± 39.84%, respectively. The mean FVSRs at 1 month and 6 months after treatment were 38.20% and 43.89%, respectively. No significant difference was observed in AMH levels before and after treatment (p > 0.05). No irreversible endometrial injury was observed in MR images after HIFU treatment. No significant difference was observed in both 1-month and 6-month FVSRs among Center 1, 2 and 3 (p > 0.05). No severe AEs occurred. For long-term outcomes, significant differences were observed in Adler grade, FV, FVSR, SSS, reduction in SSS and UFS-QOL before and after treatment (p  0.05). The SSSs were reduced by 33.42% at 1 year, 42.32% at 2 years and 52.46% at 3 years after treatment. For patients with uterine fibroids, USgHIFU-induced devascularization is a safe and effective treatment option. It has little effect on ovarian function and the endometrial injury is reversible, which could be attractive for patients who plan to become pregnant.

MRI Texture Analysis for Preoperative Prediction of Lymph Node Metastasis in Patients with Nonsquamous Cell Cervical Carcinoma

To preoperatively predict lymph node metastasis (LNM) in patients with cervical nonsquamous cell carcinoma (non-SCC) based on magnetic resonance imaging (MRI) texture analysis. This retrospective study included 104 consecutive patients (mean age of 47.2 ± 11.3 years) with stage IB-IIA cervical non-SCC. According to the ratio of 7:3, 72, and 32 patients were randomly divided into the training and testing cohorts. A total of 272 original features were extracted. In the process of feature selection, features with intraclass correlation coefficients (ICCs) less than 0.8 were eliminated. The Pearson correlation coefficient (PCC) and analysis of variance (ANOVA) were applied to reduce redundancy, overfitting, and selection biases. Further, a support vector machine (SVM) with linear kernel function was applied to select the optimal feature set with a high discrimination power. The T2WI + DWI-based, T2WI + DWI + CE-T1WI-based and T2WI + DWI + LNS-MRI (LN status on MRI)-based SVM models yielded an AUC and accuracy of 0.78 and 0.79; 0.79 and 0.69; 0.79 and 0.81 for predicting LNM in the training cohort, and 0.82 and 0.78; 0.82 and 0.69; 0.79 and 0.72 in the testing cohort. The T2WI + DWI-based, T2WI + DWI + CE-T1WI-based and T2WI + DWI + LNS-MRI-based SVM models performed better than morphologic criteria of LNS-MRI and yield similar discrimination abilities in predicting LNM in the training and testing cohorts (all p-value > 0.05). In addition, the T2WI + DWI-based and T2WI + DWI + LNS-MRI-based SVM models showed robust performance in the AC and ASC subgroups (all p-value > 0.05). The T2WI + DWI-based, T2WI + DWI + CE-T1WI-based and T2WI+DWI+LNS-MRI-based SVM models showed similar good discrimination ability and performed better than the morphologic criteria of LNS-MRI in predicting LNM in patients with cervical non-SCC. The inclusion of the CE-T1WI sequence and morphologic criteria of LNS-MRI did not significantly improve the performance of the T2WI + DWI-based model. The T2WI + DWI-based and T2WI + DWI + LNS-MRI-based SVM models showed robust performance in the subgroup analysis.

Machine Learning-Based Models for Assessing Postoperative Risk Factors in Patients with Cervical Cancer

To investigate the value of machine learning-based radiomics, intravoxel incoherent motion (IVIM) diffusion-weighted imaging and its combined model in predicting the postoperative risk factors of parametrial infiltration (PI), lymph node metastasis (LNM), deep muscle invasion (DMI), lymph-vascular space invasion (LVSI), pathological type (PT), differentiation degree (DD), and Ki-67 expression level in patients with cervical cancer. The data of 180 patients with cervical cancer were retrospectively analyzed and randomized 2:1 into a training and validation group. The IVIM-DWI and radiomics parameters of primary lesions were measured in all patients. Seven machine learning methods were used to calculate the optimal radiomics score (Rad-score), which was combined with IVIM-DWI and clinical parameters to construct nomograms for predicting the risk factors of cervical cancer, with internal and external validation. The diagnostic efficacy of the nomograms based on clinical and imaging parameters was significantly better than MRI assessment alone. The area under the curve (AUC) of nomograms and MRI for the assessment of PI, LNM, and DMI were 0.981 vs 0.868, 0.848 vs 0.639, and 0.896 vs 0.780, respectively. Nomograms also performed well in the assessment of LVSI, PT, DD, and Ki-67 expression levels, with AUC of 0.796, 0.854, 0.806, 0.839 and 0.840, 0.856, 0.810, 0.832 in the training and validation groups. Machine learning-based nomograms can serve as a useful tool for assessing postoperative risk factors in patients with cervical cancer.

Development of a prediction model for gross residual in high-grade serous ovarian cancer by combining preoperative assessments of abdominal and pelvic metastases and multiparametric MRI

To preoperatively predict residual tumor (RT) in patients with high-grade serous ovarian carcinoma (HGSOC) via a radiomic-clinical nomogram. A total of 128 patients with advanced HGSOC were enrolled (training cohort: n=106; validation cohort: n=22). Serum cancer antigen-125 (CA125), serum human epididymis protein 4 (HE-4) level, and neutrophil-to-lymphocyte ratio (NLR) were obtained from the medical records. Metastases in abdomen and pelvis (MAP) of HGSOC patients was evaluated and scored based on preoperative abdominal and pelvic enhanced CT, MRI and/or PET-CT. A volume of interest (VOI) of each tumor was manually contoured along the boundary slice-by-slice. Radiomic features were extracted from the T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) images. Univariate and multivariate analyses were used to determine the independent predictors of RT status. Least absolute shrinkage and selection operator (LASSO) logistic regression was performed to select optimal features and construct radiomic models. A radiomic-clinical nomogram incorporating radiomic signature and clinical parameters was developed and evaluated in training and validation cohorts. MAP score (p = 0.002), HE-4 level (p = 0.001) and NLR (p = 0.008) were independent predictors of RT status. The final radiomic-clinical nomogram showed satisfactory prediction performance in training (AUC = 0.936), cross validation (AUC = 0.906) and separate validation cohorts (AUC = 0.900), and fitted well in calibration curves (p > 0.05). Decision curve further confirmed the clinical application value of the nomogram. The proposed MRI-based radiomic-clinical nomogram achieved excellent preoperative prediction of the RT status in HGSOC.

Prediction of Platinum-based Chemotherapy Response in Advanced High-grade Serous Ovarian Cancer: ADC Histogram Analysis of Primary Tumors

To investigate the feasibility of apparent diffusion coefficient (ADC) histogram analysis of primary advanced high-grade serous ovarian cancer (HGSOC) to predict patient response to platinum-based chemotherapy. A total of 70 patients with 102 advanced stage HGSOCs (International Federation of Gynecology and Obstetrics (FIGO) stages III-IV) who received standard treatment of primary debulking surgery followed by the first line of platinum-based chemotherapy were retrospectively enrolled. Patients were grouped as platinum-resistant and platinum-sensitive according to whether relapse occurred within 6 months. Clinical characteristics, including age, pretherapy CA125 level, International Federation of Gynecology and Obstetrics stage, residual tumor, and histogram parameters derived from whole tumor and solid component such as ADC No significantly different clinical characteristics were observed between platinum-sensitive and platinum-resistant patients. There were no significant differences in any whole-tumor histogram-derived parameters between the two groups. Significantly higher ADC Pretreatment ADC histogram analysis of primary tumors has the potential to allow prediction of response to platinum-based chemotherapy in patients with advanced HGSOC.

Diagnostic Performance of MR Imaging-based Features and Texture Analysis in the Differential Diagnosis of Ovarian Thecomas/Fibrothecomas and Uterine Fibroids in the Adnexal Area

To investigate the value of MRI-based features and texture analysis (TA) in the differential diagnosis between ovarian thecomas/fibrothecomas (OTCA/f-TCAs) and uterine fibroids in the adnexal area (UF-iaas). This retrospective study included 16 OTCA/f-TCA and 37 UF-iaa patients who underwent conventional MRI and DWI between August 2014 and September 2018. Three-dimensional TA was performed with T2-weighted MRI. The clinical, MRI-based and texture features were compared between OTCA/f-TCAs and UF-iaas. Multivariate logistic regression analysis was used for filtering the independent discriminative features and constructing the discriminating model. ROCs were generated to analyse MRI-based features, texture features and their combination for discriminating between the two diseases. Six imaging-based features (ipsilateral ovary detection, arterial period enhancement, lesion components, peripheral cysts, "whorl signs", mean ADCs) and six texture features (Histogram-energy, Histogram-entropy, Histogram-kurtosis, GLCM-energy, GLCM-entropy, and Haralick correlation) were significantly different between OTCA/f-TCAs and UF-iaas (p < 0.05). Multivariate analysis of the MRI-based features revealed that arterial period enhancement (OR = 0.104), peripheral cysts (OR = 16.513), and whorl signs (OR = 0.029) were independent features for discriminating between OTCA/f-TCAs and UF-iaas (p < 0.05). Multivariate analysis of the texture features showed that Histogram-energy and GLCM-energy were independent features for discriminating between OTCA/f-TCAs and UF-iaas (p < 0.05). The area under the curve of imaging-based diagnosis was 0.85, and the combination of imaging-based diagnosis and TA improved the area under the curve to 0.87, with higher accuracy, specificity and sensitivity of 86%, 92%, and 84%, respectively (p < 0.05). MRI-based features can be useful in differentiating OTCA/f-TCAs from UF-iaas. Furthermore, combining imaging-based diagnosis and TA can improve diagnostic performance.

Feasibility of Predicting Pelvic Lymph Node Metastasis Based on IVIM-DWI and Texture Parameters of the Primary Lesion and Lymph Nodes in Patients with Cervical Cancer

To investigate the feasibility and value of intravoxel incoherent motion diffusion weighted imaging (IVIM-DWI) and texture parameters of primary lesions and lymph nodes for predicting pelvic lymph node metastasis in patients with cervical cancer. A total of 143 patients with cervical cancer confirmed by surgical pathology were analyzed retrospectively and 125 patients were enrolled in primary lesions study, 83 patients and 134 lymph nodes were enrolled in lymph nodes study. Patients and lymph nodes were randomly divided into training group and test group at a ratio of 2: 1. The IVIM-DWI parameters and 3D texture features of primary lesions and lymph nodes of all patients were measured. The least absolute shrinkage and selection operator algorithm, spearman's correlation analysis, independent two-sample t-test and Mann-Whitney U-test were used to select texture parameters. Multivariate Logistic regression analysis and receiver operating characteristic curves were used to model and evaluate diagnostic performances. In primary lesions study, model 1 was constructed by combining f value, original_shape_Sphericity and original_firstorder_Mean of primary lesions. In lymph nodes study, model 2 was constructed by combining short diameter, circular enhancement and rough margin of lymph nodes. Model 3 was constructed by combining ADC, f value and original_glszm_Small Area Emphasis of lymph nodes. The areas under curve of model 1, 2 and 3 in training group and test group were 0.882, 0.798, 0.907 and 0.862, 0.771, 0.937 respectively. Models based on IVIM-DWI and texture parameters of primary lesions and lymph nodes both performed well in diagnosing pelvic lymph node metastasis of cervical cancer and were superior to morphological features of lymph nodes. Especially, parameters of lymph nodes showed higher diagnostic efficiency and clinical significance.

A Fusion Model of ResNet and Vision Transformer for Efficacy Prediction of HIFU Treatment of Uterine Fibroids

High-intensity focused ultrasound (HIFU) is a non-invasive technique for treating uterine fibroids, and the accurate prediction of its therapeutic efficacy depends on precise quantification of the intratumoral heterogeneity. However, existing methods still have limitations in characterizing intratumoral heterogeneity, which restricts the accuracy of efficacy prediction. To this end, this study proposes a deep learning model with a parallel architecture of ResNet and ViT (Res-ViT) to verify whether the synergistic characterization of local texture and global spatial features can improve the accuracy of HIFU efficacy prediction. This study enrolled patients with uterine fibroids who underwent HIFU treatment from Center A (training set: N = 272; internal validation set: N = 92) and Center B (external test set: N = 125). Preoperative T2-weighted magnetic resonance images were used to develop the Res-ViT model for predicting immediate post-treatment non-perfused volume ratio (NPVR) ≥ 80%. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC) and compared against independent Radiomics, ResNet-18, and ViT models. The Res-ViT model outperformed all standalone models across both internal (AUC = 0.895, 95% CI: 0.857-0.987) and external (AUC = 0.853, 95% CI: 0.776-0.921) test sets. SHAP analysis identified the ResNet branch as the predominant decision-making component (feature contribution: 55.4%). The visualization of Gradient-weighted Class Activation Mapping (Grad-CAM) shows that the key regions attended by Res-ViT have higher spatial overlap with the postoperative non-ablated fibroid tissue. The proposed Res-ViT model demonstrates that the fusion strategy of local and global features is an effective method for quantifying uterine fibroid heterogeneity, significantly enhancing the accuracy of HIFU efficacy prediction.

Contrast-Enhanced Computed Tomography Radiomics Predicts Colony-Stimulating Factor 3 Expression and Clinical Prognosis in Ovarian Cancer

To develop a radiomics model for non-invasive prediction of colony-stimulating factor 3 (CSF3) expression in ovarian cancer (OC) and evaluate its prognostic value. We acquired clinical data, genetic information, and corresponding computed tomography (CT) scans of OC from The Cancer Genome Atlas and The Cancer Imaging Archive repositories. We assessed the prognostic significance of CSF3 and its association with clinical features through the utilization of Kaplan-Meier analysis, univariate and multivariate Cox regression analysis, along with subgroup analysis. To explore the potential molecular mechanisms associated with CSF3 expression, we utilized gene set enrichment analysis and conducted an analysis on immune-cell infiltration. The max-relevance and min-redundancy and recursive feature elimination (RFE) algorithms were used for feature screening. The CT-based radiomics prediction model was built using support vector machine (SVM) and logistic regression (LR). The expression of CSF3 was found to be decreased in OC, and high expression of CSF3 was associated with poor overall survival. Moreover, it was noted that the expression of CSF3 exhibited a positive correlation with programmed death ligand 1 (PD-L1) and sialic acid-binding Ig-like lectin 15 (SIGLEC15). Patients with high CSF3 expression exhibited a decrease in tumor necrosis factor receptor superfamily member 7 (CD27) expression. The infiltration of neutrophils increased and CD8 +T cells decreased in CSF3 high expression group. The radiomics model, which utilized both LR and SVM methods, demonstrated significant clinical applicability. The expression level of CSF3 was related to the prognosis of OC. Radiomics based on CT can serve as a novel tool for forecasting prognosis.

A Meta-analysis of 68Ga-FAPI PET in Assessment of Ovarian Cancer

The objective of this research is to carry out a systematic review and meta-analysis to detect the diagnostic efficacy of 68Ga-FAPI Positron Emission Tomography (PET) Computed Tomography/Magnetic Resonance (CT/MR) in total of the lesions as well as different aspects of metastasis in individuals with ovarian cancers (OC). The PubMed, Embase, Cochrane library, and Web of Science databases were thoroughly searched until the cut-off date of July 23, 2024. The assessment of 68Ga-FAPI PET CT/MR of OC was presented by the included studies. Bivariate random effects models were utilized to compute the sensitivity and specificity of 68Ga-FAPI PET CT/MR in OC. The I-square index (I The pooled sensitivity as well as specificity for 68Ga-FAPI PET CT/MR in OC were 0.90 (95% CI: 0.84-0.95) as well as 0.95 (95% CI: 0.91-0.97), correspondingly. In the subanalysis for metastatic lesions (lymph node [LN] metastases and peritoneal involvement), the pooled sensitivity and specificity of 68Ga-FAPI PET CT/MR were 0.94 (95% CI: 0.74-0.99) and 0.95 (95% CI: 0.84-0.99) for identifying metastatic LNs as well as 0.93 (95% CI: 0.81-0.97) and 0.96 (95% CI: 0.89-0.99) about peritoneal carcinomatosis evaluation, correspondingly. In the head-to-head comparison with 18F-FDG PET/CT, 68Ga-FAPI PET CT/MR exhibited a better sensitivity in identifying peritoneal metastases (P=.0004). 68Ga-FAPI PET CT/MR displayed a high overall diagnostic effectiveness in OC. When evaluating metastatic peritoneal lesions of OC, 68Ga-FAPI PET CT/MR displayed a superior pooled sensitivity.

Preoperative CECT-Based Multitask Model Predicts Peritoneal Recurrence and Disease-Free Survival in Advanced Ovarian Cancer: A Multicenter Study

Peritoneal recurrence is the predominant pattern of recurrence in advanced ovarian cancer (AOC) and portends a dismal prognosis. Accurate prediction of peritoneal recurrence and disease-free survival (DFS) is crucial to identify patients who might benefit from intensive treatment. We aimed to develop a predictive model for peritoneal recurrence and prognosis in AOC. In this retrospective multi-institution study of 515 patients, an end-to-end multi-task convolutional neural network (MCNN) comprising a segmentation convolutional neural network (CNN) and a classification CNN was developed and tested using preoperative CT images, and MCNN-score was generated to indicate the peritoneal recurrence and DFS status in patients with AOC. We evaluated the accuracy of the model for automatic segmentation and predict prognosis. The MCNN achieved promising segmentation performances with a mean Dice coefficient of 84.3% (range: 78.8%-87.0%). The MCNN was able to predict peritoneal recurrence in the training (AUC 0.87; 95% CI 0.82-0.90), internal test (0.88; 0.85-0.92), and external test set (0.82; 0.78-0.86). Similarly, MCNN demonstrated consistently high accuracy in predicting recurrence, with an AUC of 0.85; 95% CI 0.82-0.88, 0.83; 95% CI 0.80-0.86, and 0.85; 95% CI 0.83-0.88. For patients with a high MCNN-score of recurrence, it was associated with poorer DFS with P < 0.0001 and hazard ratios of 0.1964 (95% CI: 0.1439-0.2680), 0.3249 (95% CI: 0.1896-0.5565), and 0.3458 (95% CI: 0.2582-0.4632). The MCNN approach demonstrated high performance in predicting peritoneal recurrence and DFS in patients with AOC.

CT-Based Radiomics for the Preoperative Prediction of Occult Peritoneal Metastasis in Epithelial Ovarian Cancers

The objective of this study was to develop a comprehensive combined model for predicting occult peritoneal metastasis (OPM) in epithelial ovarian cancers (EOCs) using radiomics features derived from computed tomography (CT) and clinical-radiological predictors. A total of 224 patients with EOCs were randomly divided into training dataset (N = 156) and test dataset (N = 86). Five clinical factors and seven radiological features were collected. The radiomics features were extracted from CT images of each patient. Multivariate logistic regression was employed to construct clinical and radiological models. The correlation analysis and least absolute shrinkage and selection operator algorithm were used to select radiomics features and build radiomics model. The important clinical, radiological factors, and radiomics features were integrated into a combined model by multivariate logistic regression. Receiver operating characteristics curve with area under the curve (AUC) were used to evaluate and compare predictive performance. Carbohydrate antigen 125 (CA-125) and human epididymal protein 4 (HE-4) were independent clinical predictors. Laterality, thickened septa and margin were independent radiological predictors. In the training dataset, the AUCs for the clinical, radiological and radiomics models in evaluating OPM were 0.759, 0.819, and 0.830, respectively. In the test dataset, the AUCs for these models were 0.846, 0.835, and 0.779, respectively. The combined model outperformed other models in both the training and the test datasets with AUCs of 0.901 and 0.912, respectively. Decision curve analysis indicated that the combined model yielded a higher net benefit compared to the other models. The combined model, integrating radiomics features with clinical and radiological predictors exhibited improved accuracy in predicting OPM in EOCs.

The Added Value of ADC-based Nomogram in Assessing the Depth of Myometrial Invasion of Endometrial Endometrioid Adenocarcinoma

To explore the potential value of the apparent diffusion coefficient (ADC)-based nomogram models in preoperatively assessing the depth of myometrial invasion of endometrial endometrioid adenocarcinoma (EEA). Preoperative magnetic resonance imaging (MRI) of 210 EEA patients were retrospectively analyzed. ADC histogram metrics derive from the whole-tumor regions of interest. Univariate and multivariate analyses were used to screen the ADC histogram metrics and clinical characteristics for nomogram model building. The diagnostic sensitivity, specificity, accuracy, positive predictive value (PPV), and negative predictive value (NPV) of two radiologists without and with the assistance of models were calculated and compared. Two nomogram models were developed for predicting no myometrial invasion (NMI) and deep myometrial invasion (DMI) with area under the curves of 0.85 and 0.82, respectively. With the assistance of models, the overall accuracies were significantly improved [radiologist_1, 73.3% vs 86.2% (p = 0.001); radiologist_2, 80.0% vs 91.0% (p = 0.002)]. In determining NMI, the sensitivity and PPV were greatly improved but not significant for radiologist_1 (51.9% vs 77.8% and 46.7% vs 75.0%, p = 0.229 and 0.511), and under/near the significance level for radiologist_2 (59.3% vs 88.9% and 57.1% vs 82.8%, p = 0.041 and 0.065), while the specificity, accuracy, and NPV were significantly improved (all p < 0.001). In determining DMI, all sensitivity, specificity, accuracy, PPV, and NPV were significantly improved (all p < 0.001). The ADC-based nomogram models can improve the diagnostic performance of radiologist in preoperatively assessing the depth of myometrial invasion and facilitate optimizing clinical individualized treatment decisions.

The Value of Contrast-Enhanced CT in the Detection of Residual Disease After Neo-Adjuvant Chemotherapy in Ovarian Cancer

To evaluate the diagnostic performance of contrast-enhanced computed tomography (CT) in predicting residual disease following neo-adjuvant chemotherapy (NACT) in stage III/IV ovarian cancer. This was a retrospective observational cohort study including consecutive patients with primary stage III/IV ovarian cancer who received NACT before interval debulking surgery. CT findings before interval debulking surgerywere correlated with histological/surgical findings. Diagnostic characteristics were calculated on patient-based and lesion-based analyses. False negative results on peritoneal carcinomatosis detection were correlated with lesion size and site. On patient-based analysis, CT (n = 58) had a sensitivity, specificity, positive predictive value, negative predictive value and accuracy of 92.16%, 57.14%, 94.00%, 50.00%, and 87.93%. On lesion-based analysis, the sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 63.01%, 73.47%, 82.51%, 50.00%, and 66.51%. False negative results were associated with lesion size (p < 0.001). The diagnostic performance of CT on the detection of peritoneal carcinomatosis was low at the subdiaphragmatic spaces, bowel serosa and mesentery (p < 0.001). CT had low negative predictive value in determining residual disease following NACT on both patient-based and lesion-based analyses, especially for non-measurable lesions and at the subdiaphragmatic spaces, bowel serosa and mesentery.

Nomogram of Combining CT-Based Body Composition Analyses and Prognostic Inflammation Score: Prediction of Survival in Advanced Epithelial Ovarian Cancer Patients

To investigate the value of body composition changes measured by quantitative computer tomography (QCT) in evaluating the prognosis of advanced epithelial ovarian cancer (AEOC) patients who underwent primary debulking surgery (PDS) and adjuvant platinum-based chemotherapy, and constructed a nomogram model for predicting survival in combination with prognostic inflammation score (PIS). Fifty-seven patients with AEOC between 2012 and 2016 were retrospectively enrolled. Pre- and post-treatment CT images were used to analyze the body composition biomarkers. The subcutaneous adipose tissue (SAT), visceral adipose tissue (VAT), cross-sectional area of paraspinal skeletal muscle area (PMA), skeletal muscle density (SMD), body mineral density (BMD) were measured from two sets of CT images. In multivariate analyses, VFA gain, PMA loss, BMD loss, and PIS were independent risk factors of overall survival (OS) (HR = 3.7, 3.0, 2.8, 1.9, respectively, all p < 0.05). Receiver operating characteristic (ROC) curves showed that the prognostic model combining body composition changes (BCC) and PIS had the highest predictive performance (area under the curve = 0.890). The concordance index (C-index) of the prognostic nomogram was 0.779 (95% CI, 0.673-0.886). Decision curve analysis (DCA) demonstrated the prognostic nomogram had a great distinguishing performance. CT-based body composition analyses and PIS were associated with poor OS for AEOC patients who underwent PDS and adjuvant platinum-based chemotherapy. The prognostic nomogram with a combination of BCC and PIS was dependable in predicting survival for AEOC patients during treatment.

Magnetic Resonance Imaging and Diffusion Weighted Imaging-Based Histogram in Predicting Mesenchymal Transition High-Grade Serous Ovarian Cancer

To investigate the value of magnetic resonance imaging (MRI) including diffusion-weighted imaging (DWI) findings in predicting mesenchymal transition (MT) high-grade serous ovarian cancer (HGSOC). Patients with HGSOC were enrolled from May 2017 to December 2020, who underwent pelvic MRI including DWI (b = 0,1000 s/mm A total of 81 consecutive patients were recruited for pelvic MRI before surgery, including 37 (45.7%) MT patients and 44 (54.3%) non-MT patients. At univariate analysis, the features significantly related to MT HGSOC were identified as absence of discrete primary ovarian mass, pouch of Douglas implants, ovarian mass size, tumor volume, mean, SD, median, and 95th percentile apparent diffusion coefficient (ADC) values (all p < 0.05). At multivariate analysis, the absence of discrete primary ovarian mass {odds ratio (OR): 46.477; p = 0.025}, mean ADC value ≤ 1.105 (OR: 1.023; p = 0.009), and median ADC value ≤ 1.038 (OR: 0.982; p = 0.034) were found to be independent risk factors associated with MT HGSOC. The combination of all independent criteria yielded the largest AUC of 0.82 with a sensitivity of 83.87% and specificity of 66.67%, superior to any of the single predictor alone (p ≤ 0.012). The predictive C-index nomogram performance of the combination was 0.82. The combination of absence of discrete primary ovarian mass, lower mean ADC value, and median ADC value may be helpful for preoperatively predicting MT HGSOC.

Discriminating Between Benign and Malignant Solid Ovarian Tumors Based on Clinical and Radiomic Features of MRI

To develop and validate a combined model integrating clinical and radiomic features to non-invasive discriminate between the benign and malignant solid ovarian tumors. A total of 148 patients with 156 solid ovarian tumors (86 benign and 70 malignant tumors) were included in this study. The dataset was split into the training and the test set with a ratio of 8:2 using stratified random sampling. 12 clinical features and 1612 radiomic features were extracted from each tumor. These features were selected by least absolute shrinkage and selection operator (Lasso). Three classification models were built using extreme gradient boosting (XGB) algorithm: clinical model, radiomic model, combined model. The area under the receiver operating characteristic curve (AUC), accuracy, precision and sensitivity were analyzed to evaluate the performance of these models. All of the three models obtained good performances in differentiating benign with malignant solid ovarian tumors in both training and test sets. The AUC, accuracy, precision, sensitivity of clinical model and radiomic model in test set were 0.847 (95% confidence interval (CI), 0.707-0.986, p <0.01), 0.774, 0.769, 0.714, and 0.807 (95%CI, 0.652-0.961, p <0.05), 0.677, 0.643, 0.643, respectively. Combined model had the best prediction results, the AUC, accuracy, precision and sensitivity were 0.954 (95%CI, 0.862-1.0, p <0.01), 0.839, 0.909 and 0.714 in test set. Radiomics based on machine learning can be helpful for radiologists in differentiating the benign and malignant solid ovarian tumors.

Nomograms Combining Clinical and Imaging Parameters to Predict Recurrence and Disease-free Survival After Concurrent Chemoradiotherapy in Patients With Locally Advanced Cervical Cancer

To investigate the value of nomograms based on clinical prognostic factors (CPF), intravoxel incoherent motion diffusion weighted imaging (IVIM-DWI) and MRI-derived radiomics in predicting recurrence and disease-free survival (DFS) after concurrent chemoradiotherapy (CCRT) for locally advanced cervical cancer (LACC). Retrospective analysis of data from 115 patients with ⅠB-ⅣA cervical cancer who underwent CCRT and had been followed up consistently. All patients were randomized 2:1 into training and validation groups. Pre-treatment IVIM-DWI parameters (ADC-value, D-value, D*-value and f-value) and pre- and post-treatment three-dimensional radiomics parameters (from axial T External beam radiotherapy dose, f-value, pre-treatment and post-treatment Rad-score were independent prognostic factors for recurrence and DFS in patients with cervical cancer, forming Model1 and Model2, with OR values of 0.480, 1.318, 3.071, 3.200 and HR values of 0.322, 3.372, 5.138, 7.204. The area under the curve (AUC) of Model1 for predicting recurrence of cervical cancer was 0.977, with internal and external validation C-indexes of 0.977 and 0.962. The AUC for Model2 predicting disease-free survival (DFS) at 1, 3, and 5 years was 0.895, 0.888 and 0.916 respectively, with internal and external C-indexes of 0.860 and 0.892. The decision curves analysis and clinical impact curves further indicate the high predictive efficiency and stability of nomograms. The nomograms based on clinical, IVIM-DWI and radiomics parameters have high clinical value in predicting recurrence and DFS of patients with LACC after CCRT and can provide a reference for prognostic assessment and individualized treatment of cervical cancer patients.

Radiomics Analysis in Evaluation of Cervical Cancer: A Further Step on the Road

A Multimodal Model Based on Transvaginal Ultrasound-Based Radiomics to Predict the Risk of Peritoneal Metastasis in Ovarian Cancer: A Multicenter Study

This study aimed to develop a predictive model for peritoneal metastasis (PM) in ovarian cancer using a combination radiomics and clinical biomarkers to improve diagnostic accuracy. This retrospective cohort study of 619 ovarian cancer patients involved demographic data, radiomics, O-RADS standardized description, clinical biomarkers, and histological findings. Radiomics features were extracted using 3D Slicer and Pyradiomics, with selective feature extraction using Least Absolute Shrinkage and Selection Operator regression. Model development and validation were carried out using logistic regression and machine learning methods RESULTS: Interobserver agreement was high for radiomics features, with 1049 features initially extracted and 7 features selected through regression analysis. Multi-modal information such as Ascites, Fallopian tube invasion, Greatest diameter, HE4 and D-dimer levels were significant predictors of PM. The developed radiomics nomogram demonstrated strong discriminatory power, with AUC values of 0.912, 0.883, and 0.831 in the training, internal test, and external test sets respectively. The nomogram displayed superior diagnostic performance compared to single-modality models. The integration of multimodal information in a predictive model for PM in ovarian cancer shows promise for enhancing diagnostic accuracy and guiding personalized treatment. This multi-modal approach offers a potential strategy for improving patient outcomes in ovarian cancer management with PM.

Deep Learning Radiomics Nomogram Based on MRI for Differentiating between Borderline Ovarian Tumors and Stage I Ovarian Cancer: A Multicenter Study

To develop and validate a deep learning radiomics nomogram (DLRN) based on T2-weighted MRI to distinguish between borderline ovarian tumors (BOTs) and stage I epithelial ovarian cancer (EOC) preoperatively. This retrospective multicenter study enrolled 279 patients from three centers, divided into a training set (n = 207) and an external test set (n = 72). The intra- and peritumoral radiomics analysis was employed to develop a combined radiomics model. A deep learning model was constructed based on the largest orthogonal slices of the tumor volume, and a clinical model was constructed using independent clinical predictors. The DLRN was then constructed by integrating deep learning, intra- and peritumoral radiomics, and clinical predictors. For comparison, an original radiomics model based solely on tumor volume (excluding the peritumoral area) was also constructed. All models were validated through 10-fold cross-validation and external testing, and their predictive performance was evaluated by the area under the receiver operating characteristic curve (AUC). The DLRN demonstrated superior performance across the 10-fold cross-validation, with the highest AUC of 0.825±0.082. On the external test set, the DLRN significantly outperformed the clinical model and the original radiomics model (AUC = 0.819 vs. 0.708 and 0.670, P = 0.047 and 0.015, respectively). Furthermore, the combined radiomics model performed significantly better than the original radiomics model (AUC = 0.778 vs. 0.670, P = 0.043). The DLRN exhibited promising performance in distinguishing BOTs from stage I EOC preoperatively, thus potentially assisting clinical decision-making.

Leveraging Artificial Intelligence to Revolutionize Ovarian Cancer Diagnosis

Habitat Radiomics Based on MRI for Predicting Platinum Resistance in Patients with High-Grade Serous Ovarian Carcinoma: A Multicenter Study

This study aims to explore the feasibility of MRI-based habitat radiomics for predicting response of platinum-based chemotherapy in patients with high-grade serous ovarian carcinoma (HGSOC), and compared to conventional radiomics and deep learning models. A retrospective study was conducted on HGSOC patients from three hospitals. K-means algorithm was used to perform clustering on T2-weighted images (T2WI), contrast-enhanced T1-weighted images (CE-T1WI), and apparent diffusion coefficient (ADC) maps. After feature extraction and selection, the radiomics model, habitat model, and deep learning model were constructed respectively to identify platinum-resistant and platinum-sensitive patients. A nomogram was developed by integrating the optimal model and clinical independent predictors. The model performance and benefit was assessed using the area under the receiver operating characteristic curve (AUC), net reclassification index (NRI), and integrated discrimination improvement (IDI). A total of 394 eligible patients were incorporated. Three habitats were clustered, a significant difference in habitat 2 (weak enhancement, high ADC values, and moderate T2WI signal) was found between the platinum-resistant and platinum-sensitive groups (P < 0.05). Compared to the radiomics model (0.640) and deep learning model (0.603), the habitat model had a higher AUC (0.710). The nomogram, combining habitat signatures with a clinical independent predictor (neoadjuvant chemotherapy), yielded a highest AUC (0.721) among four models, with positive NRI and IDI. MRI-based habitat radiomics had the potential to predict response of platinum-based chemotherapy in patients with HGSOC. The nomogram combining with habitat signature had a best performance and good model gains for identifying platinum-resistant patients.

A Transvaginal Ultrasound-Based Deep Learning Model for the Noninvasive Diagnosis of Myometrial Invasion in Patients with Endometrial Cancer: Comparison with Radiologists

This study aimed to determine the feasibility of using the deep learning (DL) method to determine the degree (whether myometrial invasion [MI] >50%) of MI in patients with endometrial cancer (EC) based on ultrasound (US) images. From September 2017 to April 2023, 1289 US images of 604 patients with EC who underwent surgical resection at center 1, center 2 or center 3 were obtained and divided into a training set and an internal validation set. Ninety-five patients from center 4 and center 5 were randomly selected as the external testing set according to the same criteria as those for the primary cohort. This study evaluated three DL models trained on the training set and tested them on the validation and testing sets. The models' performance was analyzed based on accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC), and the performance of the models was subsequently compared with that of 15 radiologists. In the final clinical diagnosis of MI in patients with EC, EfficientNet-B6 showed the best performance in the testing set in terms of area under the curve (AUC) [0.814, 95% CI (0.746-0.882]; accuracy [0.802, 95% CI (0.733-0.855]; sensitivity [0.623]; specificity [0.879]; positive likelihood ratio (PLR) [6.750]; and negative likelihood ratio (NLR) [0.389]. The diagnostic efficacy of EfficientNet-B6 was significantly better than that of the 15 radiologists, with an average diagnostic accuracy of 0.681, average AUC of 0.678, AUC of the best performance of 0.739, accuracy of 0.716, sensitivity of 0.806, specificity 0.672, PLR2.457, and NLR 0.289. Based on the preoperative US images of patients with EC, the DL model can accurately determine the degree of endometrial MI; the performance of this model is significantly better than that of radiologists, and it can effectively assist in clinical treatment decisions.

Towards Automated FIGO Staging in Radiology: The Role of LLMs in Cervical and Endometrial Cancer

Staging gynecological malignancies is a complex process, and radiologists should be familiar with the evolution of FIGO staging criteria. Large Language Models (LLMs) offer potential to support radiologists by automating classification tasks from free-text MRI reports. We conducted a retrospective study using two curated datasets of pelvic MRI reports from patients with cervical (n = 261, FIGO 2018) and endometrial cancer (n = 555, FIGO 2023). A general-purpose LLM (Cohere Command-A) was evaluated under three prompting strategies (zero-shot, guided, and chain-of-thought [CoT]), using exact stage accuracy, an ordinal FIGO distance metric, and the rate of severe errors. The Cohere Command-A model was chosen for its long-context reasoning, instruction-following capabilities, reproducible fixed version, and secure handling of sensitive clinical data. While alternative LLMs (eg, GPT-4o, Gemini, Llama-3, DeepSeek) could offer complementary insights, access, resources, and compliance constraints limited broader comparisons. For cervical cancer, CoT prompting achieved the highest accuracy (80.5%) and the lowest FIGO distance, with 23 severe misclassifications (≥2-stage deviation), outperforming guided and zero-shot prompting. For endometrial cancer, all strategies performed appropriately, with CoT again yielding the best results (accuracy, 90.6%) and the lowest number of severe misclassifications (37 cases), compared with guided and zero-shot prompting. In a small subset of cases with no agreement between any prompting strategy and the reference label, manual review showed that only a minority presented potentially suboptimal annotations, suggesting that CoT-based predictions may also help flag doubtful reports. The LLMs used demonstrated strong performance in automatically assigning FIGO stages for cervical and endometrial cancers from MRI reports. Their integration could reduce workload and improve consistency in staging. Further validation is needed before clinical implementation.

Predicting Microsatellite Instability in Endometrial Cancer by Multimodal Magnetic Resonance Radiomics Combined with Clinical Factors

To develop a nomogram integrating clinical and multimodal MRI features for non-invasive prediction of microsatellite instability (MSI) in endometrial cancer (EC), and to evaluate its diagnostic performance. This retrospective multicenter study included 216 EC patients (mean age, 54.68 ± 8.72 years) from two institutions (2017-2023). Patients were classified as MSI (n=59) or microsatellite stable (MSS, n=157) based on immunohistochemistry. Institution A data were randomly split into training (n=132) and testing (n=33) sets (8:2 ratio), while Institution B data (n=51) served as external validation. Eight machine learning algorithms were used to construct models. A nomogram combining radiomics score and clinical predictors was developed. Performance was evaluated via receiver operating characteristic (ROC) curves, calibration, and decision curve analysis (DCA). The T2-weighted imaging (T2WI) radiomics model showed the highest area under the receiver operating characteristic curve (AUC) among single sequences (training set:0.908; test set:0.838). The combined-sequence radiomics model achieved superior performance (AUC: training set=0.983, test set=0.862). The support vector machine (SVM) outperformed other algorithms. The nomogram integrating rad-score and clinical features demonstrated higher predictive efficacy than the clinical model (test set: AUC=0.904 vs. 0.654; p < 0.05) and comparable to the multimodal radiomics model. DCA indicated significant clinical utility for both nomogram and radiomics models. The clinical-radiomics nomogram effectively predicts MSI status in EC, offering a non-invasive tool for guiding immunotherapy decisions.

Intratumoral and Peritumoral Radiomics for Predicting the Prognosis of High-grade Serous Ovarian Cancer Patients Receiving Platinum-Based Chemotherapy

This study aimed to develop a deep learning (DL) prognostic model to evaluate the significance of intra- and peritumoral radiomics in predicting outcomes for high-grade serous ovarian cancer (HGSOC) patients receiving platinum-based chemotherapy. A DL model was trained and validated on retrospectively collected unenhanced computed tomography (CT) scans from 474 patients at two institutions, which were divided into a training set (N = 362), an internal test set (N = 86), and an external test set (N = 26). The model incorporated tumor segmentation and peritumoral region analysis, using various input configurations: original tumor regions of interest (ROIs), ROI subregions, and ROIs expanded by 1 and 3 pixels. Model performance was assessed via hazard ratios (HRs) and receiver operating characteristic (ROC) curves. Patients were stratified into high- and low-risk groups on the basis of the training set's optimal cutoff value. Among the input configurations, the model using an ROI with a 1-pixel peritumoral expansion achieved the highest predictive accuracy. The DL model exhibited robust performance for predicting progression-free survival, with HRs of 3.41 (95% CI: 2.85, 4.08; P < 0.001) in training set, 1.14 (95% CI: 1.03, 1.26; P = 0.012) in internal test set, and 1.32 (95% CI: 1.07, 1.63; P = 0.011) in external test set. KM survival analysis revealed significant differences between the high-risk and low-risk groups (P < 0.05). The DL model effectively predicts survival outcomes in HGSOC patients receiving platinum-based chemotherapy, offering valuable insights for prognostic assessment and personalized treatment planning.

CT-based Machine Learning Radiomics Modeling: Survival Prediction and Mechanism Exploration in Ovarian Cancer Patients

To create a radiomics model based on computed tomography (CT) to predict overall survival in ovarian cancer patients. To combine Rad-score with genomic data to explore the association between gene expression and Rad-score. Imaging and clinical data from 455 patients with ovarian cancer were retrospectively analyzed. Patients were categorized into training cohort, validation cohort and test cohort. Cox regression analysis and the least absolute shrinkage and selection operator (LASSO) methods were utilized to identify characteristics and develop the Rad-score. Radiomics models were developed and evaluated for predictive efficacy and clinical incremental value. Application of genomic data from the cancer genome atlas (TCGA) to reveal differential genes in different Rad-score groups. Screening hub genes and exploring the functions of hub genes through bioinformatics analysis and machine learning. Prognostic models based on FIGO, tumor residual disease and Rad-score were developed. The receiver operating characteristic (ROC) curves showed that the 1, 3, and 5 year area under curves (AUCs) of the model were in the training group (0.816, 0.865 and 0.862, respectively), validation group (0.845, 0.877, 0.869, respectively) and test group (0.899, 0.906 and 0.869, respectively) had good predictive accuracy. Calibration curves showed good agreement between observations and predictions. Decision curve analysis revealed a high net benefit of the clinical-radiomics model. The clinical impact curve (CIC) showed good clinical applicability of the clinical-radiomics model. Analysis of sequencing data from the TCGA database revealed EMP1 as a hub gene for radiomics modeling. It revealed that its biological function may be associated with extracellular matrix organization and focal adhesion. Prognostic models based on FIGO, Tumor residual disease, and Rad-score can effectively predict the overall survival (OS) of ovarian cancer patients. Rad-score may enable prognostic prediction of ovarian cancer patients by revealing the expression level of EMP1 and its biological function.

Predicting Short-term and Long-term Efficacy of HIFU Treatment for Uterine Fibroids Based on Clinical Information and MRI: A Retrospective Study

This study aimed to address the challenge of predicting treatment outcomes for patients with uterine fibroids undergoing high-intensity focused ultrasound (HIFU) ablation. We developed medical-assisted diagnostic models to accurately predict the ablation rates and volume reduction rates, thus assessing both short-term and long-term treatment effects of fibroids. For the ablation rate prediction, our study included 348 fibroids, categorized into 181 fully ablated and 167 inadequately ablated fibroids. Using multimodal MRI sequences and clinical characteristics, coupled with data preprocessing steps such as feature extraction, testing, and screening, we constructed an ensemble model for predicting preoperative ablation rates. In the volume reduction rate study, we analyzed 253 fibroids, divided into 142 high-volume responders and 111 low-volume responders. Based on clinical characteristics and T2-weighted image (T2WI) sequences, along with lesion delineation, feature normalization, and other preprocessing steps, we developed an inter-slice information fusion model for predicting preoperative volume reduction rates. The ensemble model demonstrated an accuracy of 0.800 and an area under the curve (AUC) of 0.830 on the test set, while the inter-slice information fusion model achieved an accuracy of 0.808 and an AUC of 0.891. Both models showed superior predictive performance compared to existing models. The ensemble and inter-slice information fusion models developed in this study exhibit robust predictive capabilities, offering valuable support for clinicians in selecting patients for HIFU treatment. These models hold potential for enhancing patient outcomes through tailored treatment planning.

Voxel-level Radiomics and Deep Learning Based on MRI for Predicting Microsatellite Instability in Endometrial Carcinoma: A Two-center Study

To develop and validate a non-invasive deep learning model that integrates voxel-level radiomics with multi-sequence MRI to predict microsatellite instability (MSI) status in patients with endometrial carcinoma (EC). This two-center retrospective study included 375 patients with pathologically confirmed EC from two medical centers. Patients underwent preoperative multiparametric MRI (T2WI, DWI, CE-T1WI), and MSI status was determined by immunohistochemistry. Tumor regions were manually segmented, and voxel-level radiomics features were extracted following IBSI guidelines. A dual-channel 3D deep neural network based on the Vision-Mamba architecture was constructed to jointly process voxel-wise radiomics feature maps and MR images. The model was trained and internally validated on cohorts from Center I and tested on an external cohort from Center II. Performance was compared with Vision Transformer, 3D-ResNet, and traditional radiomics models. Interpretability was assessed with feature importance ranking and SHAP value visualization. The Vision-Mamba model achieved strong predictive performance across all datasets. In the external test cohort, it yielded an AUC of 0.866, accuracy of 0.875, sensitivity of 0.833, and specificity of 0.900, outperforming other models. Integrating voxel-level radiomics features with MRI enabled the model to better capture both local and global tumor heterogeneity compared to traditional approaches. Interpretability analysis identified glszm_SizeZoneNonUniformityNormalized, ngtdm_Busyness, and glcm_Correlation as top features, with SHAP analysis revealing that tumor parenchyma, regions of enhancement, and diffusion restriction were pivotal for MSI prediction. The proposed voxel-level radiomics and deep learning model provides a robust, non-invasive tool for predicting MSI status in endometrial carcinoma, potentially supporting personalized treatment decision-making.

Construction and Validation of a MRI‑Based Radiomic Nomogram to Predict Overall Survival in Patients with Local Advanced Cervical Cancer: A Multicenter Study

Cervical cancer is the fourth most common cancer among women. Radiomics has emerged as a new approach providing valuable information for cancer management. The aim of this study was to construct a radiomics nomogram to accurately predict survival outcomes in patients with locally advanced cervical cancer. This retrospective study enrolled a total of 582 locally advanced cervical cancer patients from three center (training cohort: n = 228; internal validation cohort: n = 98; external validation cohort: n = 256). Radiomic features were extracted from pretreatment MRI images. Least absolute shrinkage and selection operator logistic regression were applied to select radiomic features and calculated the radiomic scores. Univariate and multivariate Cox proportional hazards regression analyses were used to identify the independent prognostic clinic-radiological factors for cervical cancer, which were incorporated into the nomogram. A total of six radiomic features were found to be associated with overall survival (OS) of locally advanced cervical cancer patients. The AUC of radiomic scores in the training cohort was 0.634-0.708 for the training cohort, 0.725-0.762 for internal validation cohort and 0.788-0.881 for the external validation cohort. Age, parametrial invasion, and radiomic score were the independent prognostic indicators for cervical cancer patients (Age: HR=1.041, 95% CI=1.012-1.071, p = 0.006; Parametrial invasion: HR=4.755, 95% CI=1.493-15.144, p = 0.008; HR=2.324, 95% CI=1.050-5.143, p = 0.037). The nomogram model incorporating these factors showed favorable discrimination in predicting the overall survival rates of cervical cancer patients, with the AUC values of 0.809, 0.808, and 0.862 for 1-, 2-, and 3-year predictions. The decision curve analysis (DCA) indicated that the nomogram model achieved the highest clinical net benefit across the entire range of reasonable threshold probabilities. The nomogram, incorporating clinicopathological factors and radiomic features derived from MRI images, showed satisfactory discrimination in predicting the OS rates of locally advanced cervical cancer patients.

Radiomic Features of T2-weighted Imaging and Diffusion Kurtosis Imaging in Differentiating Clinicopathological Characteristics of Cervical Carcinoma

Clinicopathological characteristics including histological subtypes, tumour grades and International Federation of Gynecology and Obstetrics (FIGO) stages are crucial factors in the clinical decision for cervical carcinoma (CC). The purpose of this study was to evaluate the ability of T2-weighted imaging (T2WI) and diffusion kurtosis imaging (DKI) radiomics in differentiating clinicopathological characteristics of CC. One hundred and seventeen histologically confirmed CC patients (mean age 56.5 ± 14.0 years) with pre-treatment magnetic resonance imaging were retrospectively reviewed. DKI was acquired with 4 b-values (0-1500 s/mm Area under the curves (AUCs) for T2WI-only RF models for discriminating histological subtypes, tumour grades and FIGO stages were 0.762, 0.686, and 0.719. AUCs for DWI-only models were 0.663, 0.645, and 0.868, respectively. AUCs of the combined T2WI and DKI models were 0.823, 0.790, and 0.850, respectively. T2WI and DKI radiomic features could differentiate the clinicopathological characteristics of CC. A combined model showed excellent diagnostic discrimination for histological subtypes, while a DKI-only model presented the best performance in differentiating FIGO stages.

PET/MRI in Endometrial Cancer: Imaging Biomarkers are Associated with Disease Progression and Overall Survival

To evaluate the association between positron emission tomography (PET)/magnetic resonance imaging (MRI) biomarkers and survival outcomes in patients with endometrial cancer. Between April 2014 and April 2016, 88 patients with newly diagnosed endometrial cancer participated this prospective study and underwent [ After a median follow-up of 80 months, 15 (22%) patients had tumor progression and six (9%) patients died. The results of ADC PET/MRI biomarkers, particularly MTV and TLG, are associated with PFS and OS in patients with endometrial cancer. MTV was an independent predictor of PFS.

The Accuracy of Multidetector Computed Tomography and Laparoscopy in the Prediction of Peritoneal Carcinomatosis Index Score in Primary Ovarian Cancer: Terminology Issues

Diffusion Kurtosis Imaging in the Assessment of Cervical Carcinoma

To evaluate the additional value of diffusion kurtosis imaging (DKI) in the characterization of cervical carcinoma. Seventy-five patients (56.9 ± 13.4 years) with histologic-confirmed cervical carcinoma were included. Diffusion-weighted imaging (DWI) was acquired on a 3T MRI with five b values (0, 500, 800, 1000, and 1500 s/mm ROI- and VOI-derived DKI parameters and ADC were all in excellent consistency (intraclass correlation coefficient, ICC > 0.90, respectively). Cervical carcinoma had significantly lower MD, ADC, and higher MK than normal myometrium (p < 0.001). MD and ADC showed significant differences between histologic subtypes and FIGO stages, lower in squamous cell carcinoma than adenocarcinoma and higher in FIGO I-II than FIGO III-IV (p < 0.050), but not with tumor grade. No difference was observed in MK for different clinicopathologic features tested. ROI and VOI analyses were in excellent consistency. MD and ADC were able to distinguish histologic subtypes and separating FIGO stages, MK could not. DKI showed no clear added value over conventional DWI in the characterization of cervical carcinoma.

Diagnostic Accuracies of the Ultrasound and Magnetic Resonance Imaging ADNEX Scoring Systems For Ovarian Adnexal Mass: Systematic Review and Meta-Analysis

We conducted a meta-analysis of IOTA (international ovarian tumor analysis) ADNEX (Assessment of Different NEoplasias in the adneXa) as ultrasound system and MRI (magnetic resonance imaging) ADNEX scoring systems as MR system to assess their diagnostic test accuracy for differentiating benign from malignant adnexal masses of the ovary. We performed an electronic search for relevant publications in the English language up to February 2021 using PubMed, CENTRAL (Cochrane Central Register of Controlled Trials), Web of Science, and Google scholar databases and search engines. We computed the pooled sensitivity, pooled specificity, and summary receiver operating characteristics curve (SROC) using the statistical software STATA (Version 13, College Station, TX, StataCorp LP). Based on 11 studies using IOTA-ADNEX, we observed pooled sensitivity, specificity, area under curve, and diagnostic odds ratio were 96% (95% CI, 94% to 97%), 79% (95% CI, 70% to 86 %), 97% (95% CI, 95% to 98%), and 88 (95% CI, 43 to 180). Based on five studies using MR-ADNEX scoring system the pooled sensitivity, specificity, area under curve and diagnostic odds ratio were 91 % (95% CI, 87% to 94 %), 95% (95% CI, 92% to 97 %), 98% (95% CI, 96% to 99%), and 189 (95% CI, 90 to 396) respectively. Our meta-analysis results demonstrate that the MR-ADNEX scoring system had higher specificity however bit lower sensitivity compared to the IOTA-ADNEX scoring system for discriminating benign from malignant ovarian tumors.

Development and Validation of a Nomogram Based on Multiparametric MRI for Predicting Lymph Node Metastasis in Endometrial Cancer: A Retrospective Cohort Study

To develop a radiomics nomogram based on clinical and magnetic resonance features to predict lymph node metastasis (LNM) in endometrial cancer (EC). We retrospectively collected 308 patients with endometrial cancer (EC) from two centers. These patients were divided into a training set (n=155), a test set (n=67), and an external validation set (n=86). Based on T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and dynamic contrast-enhanced (DCE) arterial phase and equilibrium phase images, radiomics features were extracted. Clinical characteristics were determined using multivariate logistic regression analysis. Subsequently, eight machine learning classification algorithms were employed to construct the radiomics model and clinical models, from which the best algorithm was selected. Ultimately, the radiomics and clinical features were combined to establish the radiomics nomogram. The efficacy of each model was appraised through receiver operating characteristic (ROC), calibration curve, and decision curve analysis (DCA). The LR algorithm demonstrated superior predictive accuracy, with areas under the curve (AUCs) of 0.903 and 0.824 in the test and validation sets, respectively. Radiomics nomograms showed better predictive performance compared to clinical models or radiomics models, the AUCs in the test and external validation set were 0.900 (95% confidence interval [CI]: 0.784-1.000) and 0.858 (95%CI: 0.750-0.966), respectively. The calibration curve and DCA indicated that the nomogram had excellent predictive performance. The nomogram based on radiomics features and clinical parameters could effectively predict LNM in patients with EC, thus providing a basis for clinicians to develop individualized treatment plans preoperatively.

Intratumoral and peritumoral habitat imaging based on multiparametric MRI to predict cervical stromal invasion in early-stage endometrial carcinoma

To evaluate the validity of multiparametric MRI-based intratumoral and peritumoral habitat imaging for predicting cervical stromal invasion (CSI) in patients with early-stage endometrial carcinoma (EC) and to compare the performance of structural and functional habitats. The preoperative MRI and clinical data of 680 patients with early-stage EC from three centers were retrospectively analyzed. Based on cohort-level, gaussian mixture model (GMM) algorithm was used for habitat clustering of MRI images. Structural habitats were clustered using T2-weighted imaging (T2WI) and contrast-enhanced T1-weighted imaging (CE-T1WI), and functional habitats were clustered using apparent diffusion coefficient (ADC) mapping and CE-T1WI. Habitat parameters were extracted from four volumes of interest (VOIs): intratumoral regions (ROI), peritumoral loops of 3 mm dilation (L3), intratumoral regions + peritumoral loops of 3 mm dilation (R3), and peritumoral loops of 3 mm dilation + peritumoral loops of 3 mm erosion (DE3). Clinical-habitat models were constructed by combining clinical independent predictors and optimal habitat models. The model performance was evaluated by the area under the curve (AUC). Deep myometrial invasion (DMI) was an independent predictor. L3 models showed the best performance for both structural and functional habitats, and the L3 functional habitat model had the highest average AUC (0.807) in external test groups, and the average AUC increased to 0.815 when combing with the clinical independent predictor. Multiparametric MRI-based intratumoral and peritumoral habitat imaging provides a noninvasive approach to predict CSI in EC patients. The combination of the clinical predictor with the L3 functional habitat model improved predictive performance.

Prediction of Lymph Node Metastasis in Endometrial Cancer Based on Color Doppler Ultrasound Radiomics

To construct a model using radiomics features based on ultrasound images and evaluate the feasibility of noninvasive assessment of lymph node status in endometrial cancer (EC) patients. In this multicenter retrospective study, a total of 186 EC patients who underwent hysterectomy and lymph node dissection were included, Pathology confirmed the presence or absence of lymph node metastasis (LNM). The study encompassed patients from seven centers, spanning from September 2018 to November 2023, with 93 patients in each group (with or without LNM). Extracted ultrasound radiomics features from transvaginal ultrasound images, used five machine learning (ML) algorithms to establish US radiomics models, screened clinical features through univariate and multivariate logistic regression to establish a clinical model, and combined clinical and radiomics features to establish a nomogram model. The diagnostic ability of the three models for LNM with EC was compared, and the diagnostic performance and accuracy of the three models were evaluated using receiver operating characteristic curve analysis. Among the five ML models, the XGBoost model performed the best, with AUC values of 0.900 (95% CI, 0.847-0.950) and 0.865 (95% CI, 0.763-0.950) for the training and testing sets, respectively. In the final model, the nomogram based on clinical features and the ultrasound radiomics showed good resolution, with AUC values of 0.919 (95% CI, 0.874-0.964) and 0.884 (0.801-0.967) in the training and testing sets, respectively. The decision curve analysis verified the clinical practicality of the nomogram. The ML model based on ultrasound radiomics has potential value in the noninvasive differential diagnosis of LNM in patients with EC. The nomogram constructed by combining ultrasound radiomics and clinical features can provide clinical doctors with more comprehensive and personalized image information, which is highly important for selecting treatment strategies.

Pelvic Recovery After Endometrial Cancer Treatment: Patient-Reported Outcomes and MRI Findings

Most women with endometrial cancer (EC) have an excellent prognosis and may be cured. However, treatment-related pelvic functional impacts may affect long-term quality of life. To better understand these concerns, we explored correlations between patient-reported outcomes and pelvic magnetic resonance imaging (MRI) features in women treated for EC. Women with histologic diagnosis of EC were consented preoperatively and completed the validated Female Sexual Function Index (FSFI) and Pelvic Floor Dysfunction Index (PFDI) questionnaires at preoperative, 6-week, and 6-month follow-up visits. Pelvic MRIs with dynamic pelvic floor sequences were performed at 6 weeks and 6 months. A total of 33 women participated in this prospective pilot study. Only 53.7% had been asked about sexual function by providers while 92.4% thought they should have been. Sexual function became more important to women over time. Baseline FSFI was low, declined at 6 weeks, and climbed above baseline at 6 months. Hyperintense vaginal wall signal on T2-weighted images (10.9 vs. 4.8, p = .002) and intact Kegel function (9.8 vs. 4.8, p = .03) were associated with higher FSFI. PFDI scores trended toward improved pelvic floor function over time. Pelvic adhesions on MRI were associated with better pelvic floor function (23.0 vs. 54.9, p = .003). Urethral hypermobility (48.4 vs. 21.7, p = .01), cystocele (65.6 vs. 24.8, p < .0001), and rectocele (58.8 vs. 18.8, p < .0001) predicted worse pelvic floor function. Use of pelvic MRI to quantify anatomic and tissue changes may facilitate risk stratification and response assessment for pelvic floor and sexual dysfunction. Patients articulated the need for attention to these outcomes during EC treatment.

Evaluation of the Depth of Myometrial Invasion of Endometrial Carcinoma: Comparison of Orthogonal Pelvis-axial Contrast-enhanced and Uterus-axial Dynamic Contrast-enhanced MRI Protocols

To compare the diagnostic performance of orthogonal pelvis-axial (OPA) contrast-enhanced (CE) and orthogonal uterus-axial (OUA) dynamic contrast-enhanced (DCE) magnetic resonance imaging (MRI) protocols in assessing the depth of myometrial invasion (MI) of endometrial carcinoma (EC). Preoperative MRI of 398 consecutive EC patients (197 patients with OPA CE-MRI protocol and 201 patients with OUA DCE-MRI protocol) was analyzed. Two radiologists independently interpreted the depth of MI, with postoperative histopathology as the reference standard. The chi-square test, Fisher's exact test, and receiver operating characteristic curve analysis were used for diagnostic performance comparison. OUA DCE-MRI showed a significantly larger area under the curve than OPA CE-MRI in detecting the presence of MI for radiologist 1 (0.71 versus 0.49, p 0.05). Compared to OPA CE-MRI, OUA DCE-MRI significantly improved the diagnostic accuracy of non-MI and superficial MI (radiologist 1: 45.5% versus 0 and 88.7% versus 86.4%, p = 0.045 and 0.567, respectively; radiologist 2: 45.5% versus 12.5% and 88.7% versus 78.8%, p = 0.177 and 0.027, respectively) and of EC with adenomyosis/submucous myomas, cornual tumor, and antero-posterior diameter ≤ 10 mm (radiologist 1: 86.4% versus 71.4%, 91.2% versus 67.7%, and 90.1% versus 81.1%, p = 0.048, 0.018, and 0.081, respectively; radiologist 2: 86.4% versus 64.3%, 88.2% versus 64.5%, and 87.0% versus 71.6%, p = 0.006, 0.023, and 0.019, respectively). The OUA DCE-MRI protocol was superior to the OPA CE-MRI protocol in assessing the depth of MI of EC.