Yuefei Feng

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.

The registration of preoperative and follow-up brain MRI, which is crucial in illustrating patients’ responses to treatments and providing guidance for postoperative therapy, presents significant challenges. These challenges stem from the considerable deformation of brain tissue and the areas of non-correspondence due to surgical intervention and postoperative changes. We propose a stepwise corrected attention registration network grounded in convolutional neural networks (CNNs). This methodology leverages preoperative and follow-up MRI scans as fixed images and moving images, respectively, and employs a multi-level registration strategy that establishes a precise and holistic correspondence between images, from coarse to fine. Furthermore, our model introduces a corrected attention module into the multi-level registration network that can generate an attention map at the local level through the deformation fields of the upper-level registration network and pathological areas of preoperative images segmented by a mature algorithm in BraTS, serving to strengthen the registration accuracy of non-correspondence areas. A comparison between our scheme and the leading approach identified in the MICCAI’s BraTS-Reg challenge indicates a 7.5% enhancement in the target registration error (TRE) metric and improved visualization of non-correspondence areas. These results illustrate the better performance of our stepwise corrected attention registration network in not only enhancing the registration accuracy but also achieving a more logical representation of non-correspondence areas. Thus, this work contributes significantly to the optimization of the registration of brain MRI between preoperative and follow-up scans.

Deep networks have shown strong performance in glioma grading; however, interpreting their decisions remains challenging due to glioma heterogeneity. To address these challenges, the proposed solution is the Causal Segmentation Framework (CSF). This framework aims to accurately predict high- and low-grade gliomas while simultaneously highlighting key subregions. Our framework utilizes a shrinkage segmentation method to identify subregions containing essential decision information. Moreover, we introduce a glioma grading module that combines deep learning and traditional approaches for precise grading. Our proposed model achieves the best performance among all models, with an AUC of 96.14%, an F1 score of 93.74%, an accuracy of 91.04%, a sensitivity of 91.83%, and a specificity of 88.88%. Additionally, our model exhibits efficient resource utilization, completing predictions within 2.31s and occupying only 0.12 GB of memory during the test phase. Furthermore, our approach provides clear and specific visualizations of key subregions, surpassing other methods in terms of interpretability. In conclusion, the Causal Segmentation Framework (CSF) demonstrates its effectiveness at accurately predicting glioma grades and identifying key subregions. The inclusion of causality in the CSF model enhances the reliability and accuracy of preoperative decision-making for gliomas. The interpretable results provided by the CSF model can assist clinicians in their assessment and treatment planning.