Transformer-Based Deep Learning Integrating Multi-Regional MRI and Clinical Features for Predicting Biochemical Recurrence After Radical Prostatectomy: A Multicenter Study.
4 affiliations
- 1Department of Radiology, The Third Affiliated Hospital, Southern Medical University, Guangzhou, Guangdong, China.
- 2Department of Ultrasound, Huizhou Central People's Hospital, Huizhou, Guangdong, China.
- 3Department of Statistics and Actuarial Science, School of Computing and Data Science, The University of Hong Kong, Hong Kong, China.
- 4Department of Radiology, Zhujiang Hospital of Southern Medical University, Guangzhou, Guangdong, China.
Abstract
Background
Existing deep learning models for predicting biochemical recurrence (BCR) after radical prostatectomy often ignore the biological context beyond the tumor. This study aims to develop and validate a transformer-based model combining multi-regional magnetic resonance imaging (MRI) features and clinical data to improve BCR prediction after radical prostatectomy in prostate cancer (PCa).Methods
We enrolled 232 Pca patients from three medical centers between 2013 and 2020. Multi-parametric MRI sequences, including T2-weighted fat-suppressed and diffusion-weighted imaging, were collected before surgery. Patients from centers 1 and 2 were assigned to a discovery cohort (training: n = 146; internal validation: n = 36), and patients from center 3 (n = 50) formed an external test cohort. A transformer-based deep learning (DL) model was developed using imaging features from intratumoral, peritumoral, and periprostatic regions, combined with clinical variables. Model performance was evaluated using the area under the curve (AUC), accuracy, sensitivity, and specificity with 95% confidence intervals (CI), and prognostic value was assessed via Kaplan-Meier (K-M) survival analysis.Results
The combined three-region MRI-based model demonstrated superior predictive performance for BCR risk across all sets, with an AUC of 0.801 (0.663-0.920) on the external test set and an AUC of 0.799 (0.715-0.872) on the validation set. Notably, the integrated DL model, which combined MRI data with clinical characteristics, outperformed the MRI-based and clinical models. The three-region with clinical combined model improved AUCs from 0.801 (95% CI: 0.663-0.920) to 0.863 (95% CI: 0.697-0.975) on the external test set and from 0.799 (95% CI: 0.715-0.872) to 0.832 (95% CI: 0.746-0.904) on the validation set. K-M curve analysis revealed that the integrated model provided significantly better predictions than the MRI-based and clinical models (p < 0.0001).Conclusion
By combining intratumoral, peritumoral, and periprostatic regions from multi-parametric MRI with clinical data, the transformer-based DL model provides a multimodal approach for predicting BCR in PCa patients.
Related
- Interpretable Machine Learning Prognostic Model Integrating Inflammatory-Nutritional Biomarkers for Post-Prostatectomy Biochemical Recurrence: Development, Internal Validation, and Translational Target Exploration.
- Pathomic Texture Composites from H&E, and Immunohistochemistry of Prostatectomy Specimens for Exploratory Modeling of Time to Biochemical Recurrence
- A nomogram integrating YTHDC2 expression and clinicopathological parameters for predicting endometrial cancer recurrence: a multicenter retrospective study
- A multimodal deep learning radiomics nomogram integrating clinicopathological features for predicting pathological complete response after neoadjuvant therapy in triple-negative breast cancer: a multicenter retrospective study
- Performance and Clinical Utility of the Memorial Sloan Kettering Cancer Center Nomogram for Predicting Lymph Node Invasion in Patients Undergoing Radical Prostatectomy
BibTeX
@article{zhou2026transformerbased,
title = {{Transformer-Based Deep Learning Integrating Multi-Regional MRI and Clinical Features for Predicting Biochemical Recurrence After Radical Prostatectomy: A Multicenter Study.}},
author = {Mengting Zhou and Kang Lu and Yuhua Liu and Zhuoyao Xie and Bomiao Lin and Qinmei Yang and Rui Chen and Lequan Yu and Yinghua Zhao},
journal = {Cancer medicine},
year = {2026},
month = oct,
doi = {10.1002/cam4.72342},
url = {https://europepmc.org/article/MED/42910549},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Transformer-Based Deep Learning Integrating Multi-Regional MRI and Clinical Features for Predicting Biochemical Recurrence After Radical Prostatectomy: A Multicenter Study.
AU - Mengting Zhou
AU - Kang Lu
AU - Yuhua Liu
AU - Zhuoyao Xie
AU - Bomiao Lin
AU - Qinmei Yang
AU - Rui Chen
AU - Lequan Yu
AU - Yinghua Zhao
PY - 2026
DA - 2026/10/01
JO - Cancer medicine
DO - 10.1002/cam4.72342
UR - https://europepmc.org/article/MED/42910549
AB - Background Existing deep learning models for predicting biochemical recurrence (BCR) after radical prostatectomy often ignore the biological context beyond the tumor. This study aims to develop and validate a transformer-based model combining multi-regional magnetic resonance imaging (MRI) features and clinical data to improve BCR prediction after radical prostatectomy in prostate cancer (PCa).Methods We enrolled 232 Pca patients from three medical centers between 2013 and 2020. Multi-parametric MRI sequences, including T2-weighted fat-suppressed and diffusion-weighted imaging, were collected before surgery. Patients from centers 1 and 2 were assigned to a discovery cohort (training: n = 146; internal validation: n = 36), and patients from center 3 (n = 50) formed an external test cohort. A transformer-based deep learning (DL) model was developed using imaging features from intratumoral, peritumoral, and periprostatic regions, combined with clinical variables. Model performance was evaluated using the area under the curve (AUC), accuracy, sensitivity, and specificity with 95% confidence intervals (CI), and prognostic value was assessed via Kaplan-Meier (K-M) survival analysis.Results The combined three-region MRI-based model demonstrated superior predictive performance for BCR risk across all sets, with an AUC of 0.801 (0.663-0.920) on the external test set and an AUC of 0.799 (0.715-0.872) on the validation set. Notably, the integrated DL model, which combined MRI data with clinical characteristics, outperformed the MRI-based and clinical models. The three-region with clinical combined model improved AUCs from 0.801 (95% CI: 0.663-0.920) to 0.863 (95% CI: 0.697-0.975) on the external test set and from 0.799 (95% CI: 0.715-0.872) to 0.832 (95% CI: 0.746-0.904) on the validation set. K-M curve analysis revealed that the integrated model provided significantly better predictions than the MRI-based and clinical models (p < 0.0001).Conclusion By combining intratumoral, peritumoral, and periprostatic regions from multi-parametric MRI with clinical data, the transformer-based DL model provides a multimodal approach for predicting BCR in PCa patients.
SN - 2045-7634
ER -