Multiparametric MRI-Based Interpretable Machine Learning Radiomics Model for Predicting Neoadjuvant Chemotherapy Sensitivity and Recurrence-Free Survival in Breast Cancer.
Authors
Affiliations (5)
Affiliations (5)
- Ganzhou Institute of Medical Imaging, Ganzhou KeyLaboratory of Medical Imaging and Artificial Intelligence, Medical Imaging Center, The Affiliated Ganzhou Hospital,Jiangxi Medical College, Nanchang University, Ganzhou Hospital-Nanfang Hospital, Southern Medical University (Ganzhou People's Hospital), No. 16, MeiGuan Avenue, Ganzhou, Jiangxi Province 341000, China (X.Z., J.P.).
- The First Affiliated Hospital of Nanchang University, Nanchang, Jiangxi Province, China (X.Z.).
- Ganzhou Cancer Hospital, Ganzhou, Jiangxi Province, China (X.T.).
- Heyou International Hospital, Foshan, Guangdong Province, China (J.X.).
- Ganzhou Institute of Medical Imaging, Ganzhou KeyLaboratory of Medical Imaging and Artificial Intelligence, Medical Imaging Center, The Affiliated Ganzhou Hospital,Jiangxi Medical College, Nanchang University, Ganzhou Hospital-Nanfang Hospital, Southern Medical University (Ganzhou People's Hospital), No. 16, MeiGuan Avenue, Ganzhou, Jiangxi Province 341000, China (X.Z., J.P.). Electronic address: [email protected].
Abstract
This study aimed to develop and validate an interpretable model using pretreatment multiparametric magnetic resonance imaging (mpMRI) radiomics and clinical data to predict neoadjuvant chemotherapy (NAC) sensitivity and recurrence-free survival (RFS) in breast cancer. The model was interpreted using the SHapley Additive exPlanations (SHAP) framework to enhance clinical transparency and support individualized treatment planning. In this multicenter retrospective study, 373 patients with pretreatment mpMRI (T2, dynamic contrast-enhanced, diffusion-weighted imaging) were enrolled. Patients were classified as NAC-insensitive (Miller-Payne grades 1-3) or sensitive (grades 4-5). Radiomic features from manual segmentations were integrated with clinical variables. A combined model was built using random forest and interpreted via SHapley Additive exPlanations (SHAP). A nomogram score from the model was assessed for RFS using Cox regression. The combined model achieved an AUC of 0.859 (95% CI: 0.764-0.954) in the internal validation set, outperforming the clinical (AUC 0.643) and radiomics (AUC 0.844) models, with similar performance in external validation (AUC 0.862). SHAP analysis identified sigma_5_0_mm_3D_glcm_DifferenceEntropy_T2 as the most influential feature. A nomogram score ≥95 predicted high sensitivity probability. Lower nomogram scores were independently associated with worse RFS. The interpretable radiomics-clinical model based on pretreatment mpMRI effectively predicts NAC sensitivity and RFS, offering potential to aid personalized treatment decisions. By providing transparent, individualized predictions via SHAP, this tool shows potential for optimizing personalized treatment strategies and reducing unnecessary toxicity.