Multiparametric MRI-based radiomics and deep learning for differentiating uterine serous carcinoma from endometrioid carcinoma: a multicenter retrospective study

Yi Shen¹Liping Liu²Shuang Ma³Xiaohua Ban⁴Shaoxian Chen¹Zhuozhi Dai¹Shaofan Lin¹Kainan Huang¹Xiaohui Duan³Daiying Lin^1*

• ¹Department of Radiology, Shantou Central Hospital, Shantou, China
• ²Shantou University Medical College Cancer Hospital, Shantou, China
• ³Sun Yat-Sen Memorial Hospital, Guangzhou, China
• ⁴Sun Yat-sen University Cancer Center, Guangzhou, China

Background: Uterine serous carcinoma (USC) and endometrioid endometrial carcinoma (EEC) are distinct subtypes of endometrial cancer with markedly different prognoses and management strategies. Accurate preoperative differentiation between USC and EEC is of great significance for tailoring surgical planning and adjuvant therapy. Purpose: To develop and validate a multiparametric MRI-based radiomics and deep learning (DL) model for preoperative distinguishing USC from EEC. Methods: A total of 210 patients (68 USCs and 142 EECs) from four hospitals who underwent preoperative MRI were enrolled in this retrospective study. Features from radiomics and deep learning were extracted using T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and contrast enhanced MRI (CE-MRI). The least absolute shrinkage and selection operator (LASSO) analysis was employed to identify the most valuable features. Clinical-radiological characteristics, radiomics and DL features were constructed using a support vector machine (SVM) algorithm. The models were evaluated using receiver operating characteristic (ROC) and decision curve analysis (DCA). Results: The all-combined model of clinical-radiological characteristics, radiomics and DL features showed better discrimination ability than either alone. The all-combined model demonstrated superior classification performance, achieving an AUC of 0.957 (95% CI: 0.904– 1.000) on the internal-testing set and an AUC of 0.880 (95% CI: 0.800–0.961) on the external-testing set. The DLR model demonstrated superior predictive performance compared to the clinical-radiological model, although the differences were not statistically significant in both the internal-testing set (AUC = 0.908 vs. 0.861, p = 0.504) and the external-testing set (AUC = 0.767 vs. 0.700, p = 0.499). The DCA revealed that the all-combined model illustrated the best overall net benefit in clinical application. Conclusion: The integrated model, combining multiparametric MRI-based radiomics, deep learning features, and clinical-radiological characteristics, may be utilized for the preoperative differentiation of USC from EEC.