When Brain Networks Travel: Learning Beyond Site

TL;DR

This paper introduces CORE, a novel framework for brain network analysis that enhances cross-site generalization in fMRI data by decoupling confounders, modeling transient dynamics, and leveraging population priors.

Contribution

CORE is the first unified approach combining confounder decoupling, transient pathway profiling, and adaptive gating for robust cross-site brain network learning.

Findings

CORE outperforms state-of-the-art methods with up to 6.7% accuracy gain.

CORE maintains performance across different brain parcellation schemes.

The framework demonstrates robustness in leave-one-site-out evaluations on multiple datasets.

Abstract

Graph-based learning on functional magnetic resonance imaging (fMRI) has shown strong potential for brain network analysis. However, existing methods degrade under cross-site out-of-distribution (OOD) settings because site-conditioned confounders induce non-pathological shortcuts, while functional connectivity constructed by temporal averaging obscures transient neurodynamics, limiting generalization to unseen sites. In this paper, we propose Cross-site OOD Robust brain nEtwork (CORE), a unified framework for brain network learning across unseen sites. CORE first performs site-aware confounder decoupling to mitigate site-conditioned bias and extract a cross-site population scaffold of reproducible diagnostic connectivity edges. It then profiles transient pathway dynamics over this scaffold using lightweight temporal descriptors and organizes scaffold edges into a line graph for transferable pathway-level modeling. Finally, CORE introduces a prior-guided subject-adaptive gating mechanism that leverages scaffold-derived population priors while preserving subject-specific connectivity variability. Extensive experiments under leave-one-site-out evaluation on real-world datasets (ABIDE, REST-meta-MDD, SRPBS, and ABCD) show that CORE consistently outperforms state-of-the-art baselines, with up to 6.7% relative gain. Furthermore, CORE remains robust to atlas variations, maintaining performance gains across different brain parcellation schemes.