NeuroTree: Hierarchical Functional Brain Pathway Decoding for Mental Health Disorders

2025/02/26 by Jun-En Ding, Ding, Jun-En, Dongsheng Luo +7
Computer Science · Neuroscience · Psychology · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #FOS: Biological sciences #FOS: Computer and information sciences #Functional Brain Connectivity Studies #Mental Health Research Topics #Neural and Evolutionary Computing (cs.NE) #Neurons and Cognition (q-bio.NC)

paper · doi:10.48550/arxiv.2502.18786

openalex publication_date 2025/02/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

-hop AGE-GCN with neural ordinary differential equations (ODEs) and contrastive masked functional connectivity (CMFC) to enhance similarities and dissimilarities of brain region distance. Furthermore, NeuroTree effectively decodes fMRI network features into tree structures, which improves the capture of high-order brain regional pathway features and enables the identification of hierarchical neural behavioral patterns essential for understanding disease-related brain subnetworks. Our empirical evaluations demonstrate that NeuroTree achieves state-of-the-art performance across two distinct mental disorder datasets. It provides valuable insights into age-related deterioration patterns, elucidating their underlying neural mechanisms. The code and datasets are available at https://github.com/Ding1119/NeuroTree.

Related

• Exploring General Intelligence via Gated Graph Transformer in Functional Connectivity Studies
• Joint Embedding of Structural and Functional Brain Networks with Graph Neural Networks for Mental Illness Diagnosis
• Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysis
• NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomics
• Graph Neural Networks for Brain Graph Learning: A Survey