BrainRiem: Riemannian Prototype Learning for Source-Free Cross-Site Brain Network Diagnosis

2026-06-28

AI Summary

This study addresses domain shift in multi-site fMRI research caused by variations in scanners, populations, and acquisition protocols. The authors propose the first framework that integrates Riemannian geometry with source-free domain adaptation, preserving clinical data privacy while avoiding geometric distortions inherent in Euclidean treatments of brain networks residing on the symmetric positive definite (SPD) manifold. Leveraging the Log-Euclidean metric, the method employs bi-level optimization to learn compact, anonymized brain network prototypes directly on the SPD manifold and incorporates Dirichlet energy spectrum calibration to enhance biological interpretability. Experiments on the ABIDE and REST-meta-MDD datasets demonstrate that the proposed approach significantly outperforms existing methods, yielding prototypes that are both neuroscientifically interpretable and offer stronger privacy guarantees.

Abstract

Multi-site functional MRI (fMRI) studies are essential for robust neuropsychiatric diagnosis yet suffer severe domain shifts from scanner heterogeneity, demographics, and site-specific acquisition protocols. Traditional domain adaptation requires concurrent source and target data access, violating clinical privacy regulations. Moreover, functional connectivity matrices lie on the Symmetric Positive Definite (SPD) manifold, where Euclidean operations cause geometric distortions corrupting diagnostic patterns. We propose BrainRiem, a source-free domain adaptation framework learning compact Riemannian brain prototypes via manifold-aware bi-level optimization. It employs the Log-Euclidean Metric to ensure prototypes remain valid SPD matrices, while Dirichlet Energy spectral calibration aligns their frequency characteristics with real brain networks. Only anonymized prototypes are transmitted to target sites, serving as stable anchors for training local models without source data access and reducing leakage under the evaluated attacks. Comprehensive experiments on ABIDE and REST-meta-MDD show BrainRiem consistently outperforms state-of-the-art source-free, traditional, and graph domain adaptation methods across diverse scanners and demographics. Notably, learned prototypes exhibit biologically interpretable connectivity patterns aligning with established neuroscience findings, validating the necessity of Riemannian geometry for brain network analysis.

Problem

• domain shift
• source-free domain adaptation
• functional connectivity
• Symmetric Positive Definite manifold
• clinical privacy

Innovation

• Riemannian geometry
• source-free domain adaptation
• SPD manifold
• brain network prototype
• functional connectivity