Problem
Research questions and friction points this paper is trying to address.
out-of-distribution generalization
resting-state fMRI
functional connectivity
cross-site
re-estimation
Beyond Site Agreement: Re-estimation for Brain Network Generalization
🤖 AI Summary
This study addresses the limitation in cross-site generalization of resting-state fMRI, where conventional methods rely solely on site consistency while neglecting the stability of functional connectivity (FC) re-estimation. To overcome this, we propose BRIO, a framework that pioneers the incorporation of intra-scan FC re-estimation support into cross-site out-of-distribution learning, moving beyond traditional site-consistency assumptions. Specifically, BRIO leverages connectome factor mapping, task-calibrated support estimation, and prediction-relevance weighting to guide cross-site alignment and optimize feature representations through re-estimation. Evaluated on four real-world datasets, BRIO achieves relative accuracy improvements of up to 3.8% and maintains robust performance gains under alternative brain parcellation schemes. These results demonstrate that integrating FC re-estimation stability enables more reliable and robust brain network generalization across heterogeneous imaging sites.
📝 Abstract
Cross-site out-of-distribution (OOD) generalization in resting-state functional magnetic resonance imaging (rs-fMRI) often relies on learning task-discriminative representations from full-scan functional connectivity (FC) graphs and promoting invariance across source sites. However, FC graphs are estimated from finite, temporally correlated blood-oxygen-level-dependent (BOLD) sequences. Cross-site agreement therefore does not necessarily imply that predictive evidence remains supported under FC re-estimation within the same scan. In this paper, we propose Brain Network Re-estimation-Informed OOD Learning (BRIO), a framework that uses within-scan FC re-estimation to guide cross-site alignment. BRIO maps fullscan graphs and their re-estimates into consistently indexed connectome factors, enabling comparisons of their predictive contributions. It assesses re-estimation support from changes in these contributions relative to within-class subject variability and class separation. For each source-site pair and class, this task-calibrated support from both sites is combined with predictive relevance to form pairwise qualifications, which determine relative factor weights and overall alignment strength. Leave-one-site-out experiments on four real-world datasets (ABIDE, REST-metaMDD, SRPBS, and ABCD) show that BRIO consistently outperforms competitive baselines, with relative improvements of up to 3.8% in accuracy. These gains also persist under an alternative brain parcellation on ABIDE.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Out-of-distribution generalization
Functional connectivity re-estimation
Connectome factors
Cross-site alignment
rs-fMRI
🔎 Similar Papers
No similar papers found.
