DynFS-MoE: Dynamic Functional-Structural Mixture-of-Experts for Post-Traumatic Epilepsy Diagnosis
2026-06-15 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors developed a new method to better detect epilepsy that happens after a brain injury by using two types of brain scans (functional and structural MRI) together. Their method smartly combines information over time and assigns tasks to different specialized parts of the model. They tested it on several classification problems and found it worked better than older methods that combined data in a simpler way. The approach also helps explain which brain areas interact differently depending on the epilepsy risk, making it useful for diagnosis and risk assessment.
post-traumatic epilepsytraumatic brain injuryfunctional MRIstructural MRIMixture-of-Expertstime-aware encodingclassificationrisk stratificationregion-of-interest (ROI)dynamic multimodal fusion
Authors
Jun-En Ding, Spencer Chen, Henry Noren, Daniel Valdivia, Christine Yohn, Suhina Patel, Taylor Zink, Hai Sun, Feng Liu
Abstract
Post-traumatic epilepsy (PTE) is a severe complication of traumatic brain injury (TBI), yet early identification remains challenging due to the complex structural and functional alterations it induces in the brain. To address this, we propose a dynamic multimodal Mixture-of-Experts (MoE) framework that integrates functional and structural MRI through time-aware functional-structural encoding and class-conditioned expert routing. Within this framework, modality-specific and cross-modal experts learn complementary representations, while a Modality-Class MoE (MCoE) module dynamically dispatches expert weights according to each classification objective. Experimental results across three binary classification tasks demonstrate that the framework consistently outperforms static fusion baselines, and high-interpretability analyses further reveal meaningful region-of-interest (ROI) interactions. This dynamic multimodal expert framework effectively captures class-dependent brain interaction patterns and provides an interpretable approach for PTE diagnosis and risk stratification.