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

TL;DR

This paper introduces BrainInterNet, a self-supervised, interpretable model using cross-attention to analyze inter-network dependencies in resting-state fMRI, revealing brain network changes in Alzheimer's disease.

Contribution

The paper presents BrainInterNet, a novel network-aware self-supervised framework that explicitly models and interprets inter-network dependencies in rs-fMRI data.

Findings

Reveals systematic alterations in brain network interactions in AD.

Supports accurate Alzheimer's classification with learned representations.

Provides a compact marker tracking disease severity longitudinally.

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.