CoHyFuse: Condition-wise Hypergraph Fusion with Global Connectome in Task-fMRI

2026-10-05

AI Summary

This study addresses the limitation of conventional methods that aggregate multi-task conditions into static graphs, thereby obscuring state-dependent neural reconfiguration signals across multiple regions of interest (ROIs). To this end, we propose a condition-aware ROI-centric hypergraph framework. Specifically, it models state-resolved ROI set structures through adaptive neighborhood-adjusted hyperedge scaling, generates task-specific association matrices, and integrates functional connectivity profiles to achieve dual-view feature fusion. The proposed framework demonstrates leading performance in cognitive and age prediction tasks, attaining a classification accuracy of 74.2% for attention-deficit/hyperactivity disorder (ADHD) identification. Overall, this work delivers both superior predictive capability and enhanced interpretability for analyzing dynamic brain organization across diverse cognitive states.

Abstract

Task-fMRI connectomes reveal state-dependent neural reconfigurations, yet conventional methods marginalize these signals by aggregating distinct conditions into static pairwise graphs, thereby obscuring condition-specific multi-ROI organization. We introduce CoHyFuse, a condition-aware ROI-centered hypergraph framework that constructs a task-state-specific incidence matrix from condition-wise functional connectivity (FC)-profile embeddings, allowing the same ROI to form different multi-ROI hyperedges across task phases. Condition-specific neighborhood sizes $K_q$ further adapt the hyperedge scale to each task state, and the resulting condition embeddings are fused with a complementary whole-session FC branch for prediction. In the AABC cohort (N=1,074), CoHyFuse achieved the best mean out-of-fold predictive performance among evaluated baselines on FACENAME Fluid Cognition Composite (FCC) prediction (7.83$\pm$0.10 MAE, 0.439$\pm$0.026 \(R^2\)) and VISMOTOR age prediction (7.52$\pm$0.37 MAE, 0.592$\pm$0.022 \(R^2\)). In an auxiliary CMI-HBN attention-deficit/hyperactivity disorder (ADHD) classification benchmark (N=223), CoHyFuse obtained 72.0$\pm$2.1\% macro-AUC and 74.2$\pm$2.9\% accuracy. Ablation studies support the contributions of condition-wise incidence construction and dual-view fusion, suggesting that state-resolved ROI-set structure provides complementary predictive information beyond whole-session FC alone. Occlusion analysis identifies the Distraction condition as the primary driver of model prediction, pointing toward the Salience/Ventral Attention Network (SAN)--FrontoParietal Network (FPN) and within-SAN hyperedge-defined ROI-set motifs as candidate model-relevant patterns. This framework provides an interpretable, state-resolved view of the connectome for downstream cohort analysis.

Problem

• task-fMRI
• connectome
• hypergraph
• condition-specific
• multi-ROI organization

Innovation

• Hypergraph Fusion
• Task-fMRI Connectome
• Condition-wise Incidence Matrix
• Dual-view Fusion
• Interpretable Framework