Interpretable Cross-Network Attention for Resting-State fMRI Representation Learning

2026-02-28

AI Summary

This study addresses the unclear mechanisms of brain network reorganization in cognitive decline and the limited interpretability of existing self-supervised models by proposing BrainInterNet, a novel framework that explicitly models interactions among predefined functional networks in resting-state fMRI. BrainInterNet uniquely integrates network-guided masked self-supervised learning with a cross-network attention mechanism to directly quantify and interpret inter-network dependencies. Evaluated across multiple cohorts (ABCD, HCP, ADNI), the method reveals systematic interaction abnormalities among the default mode, limbic, and attention networks in Alzheimer’s disease. The learned representations not only enable high-accuracy disease classification but also yield compact, interpretable biomarkers capable of tracking disease progression.

Technology Category

• Machine Learning: Unsupervised & Self-Supervised Learning
• Humans and AI: Brain-Sensing and Analysis
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Understanding how large-scale functional brain networks reorganize during cognitive decline remains a central challenge in neuroimaging. While recent self-supervised models have shown promise for learning representations from resting-state fMRI, their internal mechanisms are difficult to interpret, limiting mechanistic insight. We propose BrainInterNet, a network-aware self-supervised framework based on masked reconstruction with cross-attention that explicitly models inter-network dependencies in rs-fMRI. By selectively masking predefined functional networks and reconstructing them from remaining context, our approach enables direct quantification of network predictability and interpretable analysis of cross-network interactions. We train BrainInterNet on multi-cohort fMRI data (from the ABCD, HCP Development, HCP Young Adults, and HCP Aging datasets) and evaluate on the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset, in total comprising 5,582 recordings. Our method reveals systematic alterations in the brain's network interactions under AD, including in the default mode, limbic, and attention networks. In parallel, the learned representations support accurate Alzheimer's-spectrum classification and yield a compact summary marker that tracks disease severity longitudinally. Together, these results demonstrate that network-guided masked modeling with cross-attention provides an interpretable and effective framework for characterizing functional reorganization in neurodegeneration.

Problem

• resting-state fMRI
• functional brain networks
• cognitive decline
• Alzheimer's disease
• network reorganization

Innovation

• cross-attention
• masked reconstruction
• interpretable representation learning
• functional brain networks
• self-supervised learning