Preoperative prediction of positive surgical margins in prostate cancer using multimodal deep learning model: a multicenter study.
Authors
Affiliations (13)
Affiliations (13)
- School of Engineering Medicine, Beihang University, Beijing, China.
- Key Laboratory of Big Data-Based Precision Medicine (Beihang University), Ministry of Industry and Information Technology of China, Beijing, China.
- Department of Radiology, First Affiliated Hospital of Soochow University, Suzhou, China.
- Department of Radiology, Second Affiliated Hospital of Soochow University, Suzhou, China.
- Department of Radiology, Affiliated Zhangjiagang Hospital of Soochow University, Zhangjiagang, China.
- Department of Radiology, The People's Hospital of Taizhou, Taizhou, China.
- Department of Radiology, Changshu No.1 People's Hospital, Changshu, China.
- Department of Radiology, Suzhou Kowloon Hospital, Shanghai Jiaotong University School of Medicine, Suzhou, China.
- Department of Urology, Peking University Third Hospital, Beijing, China. [email protected].
- Department of Radiology, First Affiliated Hospital of Soochow University, Suzhou, China. [email protected].
- Department of Radiology, Suzhou Kowloon Hospital, Shanghai Jiaotong University School of Medicine, Suzhou, China. [email protected].
- School of Engineering Medicine, Beihang University, Beijing, China. [email protected].
- Key Laboratory of Big Data-Based Precision Medicine (Beihang University), Ministry of Industry and Information Technology of China, Beijing, China. [email protected].
Abstract
This study aimed to develop a deep learning model based on magnetic resonance imaging (MRI) and clinical features for predicting PSM risk after radical prostatectomy (RP). This retrospective multicenter study included 1177 prostate cancer patients who underwent preoperative MRI and RP across eight institutions. A total of 1022 patients from two institutions were used for model training, while 155 patients from six independent centers formed the external validation cohort. A feature disentanglement-based deep learning model (DESM) was developed to isolate disease-specific features from hospital-specific variations. A multimodal fusion model (MDESM) was further constructed by integrating the DESM-derived imaging signature with clinical variables to enhance prediction accuracy and generalizability. Gradient-weighted class activation mapping was applied to provide interpretability by highlighting model attention regions. In the external validation cohort, MDESM achieved an area under the receiver operating characteristic curve of 0.843 (95% CI, 0.770-0.911), significantly outperforming the DESM (0.711, 95% CI, 0.607-0.800, p = 0.003, Z = 2.936) and the clinical-only model (0.676, 95% CI, 0.577-0.770, p < 0.001, Z = 3.420). Decision curve analysis demonstrated the highest net benefit for MDESM across a range of threshold probabilities. The MDESM model, based on a feature disentanglement and multimodal fusion strategy, demonstrates the potential to effectively combine MRI and clinical data to achieve accurate PSM prediction. This approach offers a promising tool for preoperative risk stratification and surgical planning in prostate cancer.