Riemannian geometry meets fMRI: the advantages of modeling correlation manifolds and eigenvector subspaces

TL;DR

This paper introduces a scalable Riemannian geometric framework for analyzing correlation matrices in fMRI data, improving sensitivity and predictive accuracy in clinical and aging studies.

Contribution

The authors develop a novel Off-log metric and Grassmannian subspace method that enable closed-form operations and better discrimination in correlation-based brain network analysis.

Findings

Off-log metric increased sensitivity in permutation tests.

Grassmannian method outperformed Euclidean baselines in classification.

Riemannian metrics showed superior performance in some cohorts.

Abstract

Correlation matrices are fundamental summaries of functional brain networks, yet standard analyses often treat entries independently, ignoring the curved geometry of correlation space. Existing geometric methods frequently lack closed-form operations or depend on arbitrary region ordering, limiting scalability. We introduce a scalable geometric framework with two components: (i) the Off-log metric, a smooth transformation mapping correlation matrices to symmetric zero-diagonal matrices. This enables closed-form expressions for distances, Frechet means, and linear models, allowing standard statistical modeling without complex manifold optimization. (ii) Grassmannian subspace discrimination, which compares subjects via principal-angle distances between eigenvector subspaces, resolving inherent sign and basis ambiguities. Both components integrate into standard machine-learning workflows for inference, regression, and classification. Validated across two clinical cohorts (Parkinson's and psychosis) and three ageing fMRI datasets, the Off-log metric increased sensitivity in permutation tests and matched or exceeded Riemannian and Euclidean baselines in classification. Brain-age prediction performance was comparable, with Riemannian metrics excelling in two of three cohorts. The Grassmannian method consistently outperformed Euclidean baselines, highlighting disease-relevant networks. Overall, geometry-aware representations improve sensitivity and predictive performance while remaining straightforward to deploy at scale.