DynFS-MoE: Dynamic Functional-Structural Mixture-of-Experts for Post-Traumatic Epilepsy Diagnosis

• URL: http://arxiv.org/abs/2606.16203v2
• Date: Tue, 16 Jun 2026 16:02:53 GMT
• Title: DynFS-MoE: Dynamic Functional-Structural Mixture-of-Experts for Post-Traumatic Epilepsy Diagnosis
• Abstract summary: Post-traumatic epilepsy (PTE) is a severe complication of traumatic brain injury (TBI)<n>MoE framework integrates functional and structural MRI through time-aware functional-structural encoding and class-structural expert routing.
• Score: 4.520124850961863
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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.

Related papers

• Optimize Surgical Triplet Recognition: A Knowledge-Driven Mixture-of-Experts Solution [52.149337961205624]
  We propose a Mixture-of-Experts-guided Co-Optimization framework powered by knowledge-driven learning.<n>We develop a coordinated gradient learning strategy to handle category-level conflicts.<n> Notably, inspired by surgical domain expertise, we introduce a knowledge-driven mixture-of-experts mechanism.
  arXiv  Detail & Related papers  (2026-08-24T08:32:53Z)
• NeuroAlign: Hierarchical Multimodal Fusion of Dynamic and Structural Neuroimaging for MCI Analysis [31.200243008831578]
  We propose textitNeuroAlign, a hierarchical framework for structured multimodal fusion.<n>NeuroAlign achieves competitive MCI/SCD detection and preliminary cross-dataset transferability.
  arXiv  Detail & Related papers  (2026-05-31T14:01:15Z)
• PathMoE: Interpretable Multimodal Interaction Experts for Pediatric Brain Tumor Classification [30.58342408480846]
  PathMoE is an interpretable multimodal framework that integrates H&E slides, pathology reports, and nuclei-level cell graphs.<n>We evaluate our framework on two dataset-specific classification tasks on an internal pediatric brain tumor dataset and external TCGA datasets.
  arXiv  Detail & Related papers  (2026-03-02T07:17:44Z)
• MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learning [53.37068897861388]
  MedSAM-Agent is a framework that reformulates interactive segmentation as a multi-step autonomous decision-making process.<n>We develop a two-stage training pipeline that integrates multi-turn, end-to-end outcome verification.<n>Experiments across 6 medical modalities and 21 datasets demonstrate that MedSAM-Agent achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-03T09:47:49Z)
• Beyond Benchmarks: Understanding Mixture-of-Experts Models through Internal Mechanisms [55.1784306456972]
  Mixture-of-Experts (MoE) architectures have emerged as a promising direction, offering efficiency and scalability by activating only a subset of parameters during inference.<n>We use an internal metric to investigate the mechanisms of MoE architecture by explicitly incorporating routing mechanisms and analyzing expert-level behaviors.<n>We uncover several findings: (1) neuron utilization decreases as models evolve, reflecting stronger generalization; (2) training exhibits a dynamic trajectory, where benchmark performance alone provides limited signal; (3) task completion emerges from collaborative contributions of multiple experts, with shared experts driving concentration; and (4) activation patterns at the neuron level provide a fine-grained proxy for data diversity.
  arXiv  Detail & Related papers  (2025-09-28T15:13:38Z)
• Foundation Model for Skeleton-Based Human Action Understanding [56.89025287217221]
  This paper presents a Unified Skeleton-based Dense Representation Learning framework.<n>USDRL consists of a Transformer-based Dense Spatio-Temporal (DSTE), Multi-Grained Feature Decorrelation (MG-FD), and Multi-Perspective Consistency Training (MPCT)
  arXiv  Detail & Related papers  (2025-08-18T02:42:16Z)
• Unified Cross-Modal Attention-Mixer Based Structural-Functional Connectomics Fusion for Neuropsychiatric Disorder Diagnosis [17.40353435750778]
  ConneX is a multimodal fusion method that integrates cross-attention mechanism and multilayer perceptron (MLP)-Mixer for refined feature fusion.<n>We show improved performance on two distinct clinical datasets, highlighting the robustness of our proposed framework.
  arXiv  Detail & Related papers  (2025-05-21T05:49:13Z)
• MIRROR: Multi-Modal Pathological Self-Supervised Representation Learning via Modality Alignment and Retention [57.044719143401664]
  Histopathology and transcriptomics are fundamental modalities in oncology, encapsulating the morphological and molecular aspects of the disease.<n>We present MIRROR, a novel multi-modal representation learning method designed to foster both modality alignment and retention.<n>Extensive evaluations on TCGA cohorts for cancer subtyping and survival analysis highlight MIRROR's superior performance.
  arXiv  Detail & Related papers  (2025-03-01T07:02:30Z)
• Interpretable Spatio-Temporal Embedding for Brain Structural-Effective Network with Ordinary Differential Equation [56.34634121544929]
  In this study, we first construct the brain-effective network via the dynamic causal model. We then introduce an interpretable graph learning framework termed Spatio-Temporal Embedding ODE (STE-ODE) This framework incorporates specifically designed directed node embedding layers, aiming at capturing the dynamic interplay between structural and effective networks.
  arXiv  Detail & Related papers  (2024-05-21T20:37:07Z)
• An Interpretable Cross-Attentive Multi-modal MRI Fusion Framework for Schizophrenia Diagnosis [46.58592655409785]
  We propose a novel Cross-Attentive Multi-modal Fusion framework (CAMF) to capture both intra-modal and inter-modal relationships between fMRI and sMRI. Our approach significantly improves classification accuracy, as demonstrated by our evaluations on two extensive multi-modal brain imaging datasets. The gradient-guided Score-CAM is applied to interpret critical functional networks and brain regions involved in schizophrenia.
  arXiv  Detail & Related papers  (2024-03-29T20:32:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.