Interpretable Cross-Network Attention for Resting-State fMRI Representation Learning
This work addresses the problem of limited mechanistic insight in neuroimaging for researchers studying neurodegeneration, offering an interpretable method to analyze brain network interactions, though it is incremental as it builds on existing self-supervised models.
The paper tackled the challenge of interpreting functional brain network reorganization in cognitive decline by proposing BrainInterNet, a self-supervised framework using masked reconstruction with cross-attention, which revealed systematic alterations in network interactions under Alzheimer's disease and supported accurate classification and tracking of disease severity.
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.