Learning the Hierarchical Organization in Brain Network for Brain Disorder Diagnosis

2026-03-10

AI Summary

Current approaches to brain disorder diagnosis rely on predefined functional subnetworks, which struggle to capture higher-order interactions across networks and thus limit model performance. To address this limitation, this work proposes BrainHO, a novel model that forgoes prior subnetwork constraints and instead adaptively learns the intrinsic hierarchical organization of brain networks directly from fMRI data through a hierarchical attention mechanism. The method incorporates orthogonality and hierarchical consistency constraints to enhance structural diversity and stability, while integrating graph semantic augmentation to refine node representations. Evaluated on the ABIDE and REST-meta-MDD datasets, BrainHO achieves state-of-the-art classification performance and successfully identifies clinically meaningful disease-related subnetwork biomarkers.

Technology Category

• Humans and AI: Brain-Sensing and Analysis
• Machine Learning: Graph-based Machine Learning
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding

Abstract

Brain network analysis based on functional Magnetic Resonance Imaging (fMRI) is pivotal for diagnosing brain disorders. Existing approaches typically rely on predefined functional sub-networks to construct sub-network associations. However, we identified many cross-network interaction patterns with high Pearson correlations that this strict, prior-based organization fails to capture. To overcome this limitation, we propose the Brain Hierarchical Organization Learning (BrainHO) to learn inherently hierarchical brain network dependencies based on their intrinsic features rather than predefined sub-network labels. Specifically, we design a hierarchical attention mechanism that allows the model to aggregate nodes into a hierarchical organization, effectively capturing intricate connectivity patterns at the subgraph level. To ensure diverse, complementary, and stable organizations, we incorporate an orthogonality constraint loss, alongside a hierarchical consistency constraint strategy, to refine node-level features using high-level graph semantics. Extensive experiments on the publicly available ABIDE and REST-meta-MDD datasets demonstrate that BrainHO not only achieves state-of-the-art classification performance but also uncovers interpretable, clinically significant biomarkers by precisely localizing disease-related sub-networks.

Problem

• brain network
• functional MRI
• brain disorder diagnosis
• cross-network interaction
• hierarchical organization

Innovation

• hierarchical attention mechanism
• orthogonality constraint
• brain network organization
• cross-network interactions
• interpretable biomarkers