A multicenter deep learning framework integrating radiomics and vision transformers for comprehensive ovarian tumor analysis from ultrasound imaging.
Authors
Affiliations (3)
Affiliations (3)
- Department of Gynecology, First Hospital of Shanxi Medical University, No.85, Jiefang South Road, Taiyuan, 030000, Shanxi Province, China.
- Department of Pathology, First Hospital of Shanxi Medical University, No.85, Jiefang South Road, Taiyuan, 030000, Shanxi Province, China.
- Department of Interventional Ultrasound, First Hospital of Shanxi Medical University, No.85, Jiefang South Road, Taiyuan, 030000, Shanxi Province, China. [email protected].
Abstract
This study aimed to develop and validate a robust multicenter deep learning pipeline that integrates radiomic descriptors with deep feature embeddings to enable comprehensive ovarian tumor analysis from ultrasound imaging, encompassing segmentation, multi-class classification, and prognostic prediction. Ultrasound data from 3156 patients across eight centers were retrospectively analyzed. Five segmentation networks (UNETR, nnU-Net, Swin-UNet, SegNet, UNet) were trained to delineate tumors. From segmented regions, handcrafted radiomic features and deep features (ResNet, Vision Transformer (ViT)) were extracted. After reproducibility filtering (intraclass correlation coefficient (ICC)āā„ā0.75) and dimensionality reduction (PCA, RFE, ANOVA), three classifiers (TabTransformer, MLP, XGBoost) were trained for six-class categorization. Progression-free survival (PFS) was predicted using regression models. External validation was performed on 756 patients. UNETR achieved the best segmentation performance (DSC: 96.2%). For classification, the combined feature model with RFE and TabTransformer reached the highest accuracy (training AUC: 98.0%; external AUC: 95.8%; accuracy: 94.0%). For prognosis, TabTransformer achieved the best performance (C-index: 0.847), with consistent generalization across centers. Kaplan-Meier analysis confirmed significant survival group separation (pā<ā0.001). The proposed framework shows strong potential to reduce inter-operator variability and support personalized clinical decision-making in ovarian cancer care.