Predicting Recurrence Risk of Glioblastoma Based on Preoperative-Postoperative Longitudinal MRI: A Multicenter Study

Glioblastoma has a high recurrence rate, yet conventional single-time-point imaging fails to capture the dynamic tumor evolution before and after surgery. This study aims to develop a deep learning model based on preoperative and postoperative longitudinal MRI to predict postoperative recurrence risk by capturing imaging dynamics. We propose MambaDiff-Net, which employs a dual-stream encoder to extract multi-scale features from preoperative and postoperative T2WI. It also includes a feature discrepancy computation module to model longitudinal imaging changes, outputting individualized recurrence risk probabilities. We included 139 patients with glioblastoma (59 training, 40 internal validation, 40 external test), with recurrence within 6 months post-surgery as the prediction target. Performance was evaluated using AUC, accuracy, and F1. MambaDiff-Net achieved AUCs of 0.887 and 0.762 in internal and external validation, respectively, significantly outperforming single-time-point models. Kaplan-Meier analysis demonstrated effective risk stratification, and decision curve analysis confirmed superior clinical net benefit. Grad-CAM visualization showed the model's focus shifting from preoperative tumor parenchyma to postoperative resection cavity margins, consistent with clinical knowledge. A deep learning model based on preoperative-postoperative longitudinal MRI can accurately predict postoperative recurrence risk in glioblastoma. By modeling dynamic imaging changes before and after surgery, it supports individualized treatment decisions.