Log-Euclidean Frameworks for Smooth Brain Connectivity Trajectories

TL;DR

This paper introduces a Log-Euclidean Riemannian framework for modeling smooth, interpretable trajectories of brain connectivity from fMRI data, ensuring geometric validity and computational efficiency.

Contribution

It presents a novel application of Log-Euclidean diffeomorphisms to approximate dynamic functional connectivity trajectories as smooth curves in Euclidean space.

Findings

Framework maintains valid correlation matrices throughout

Demonstrates geometric consistency in brain connectivity modeling

Shows improved computational efficiency over existing methods

Abstract

The brain is often studied from a network perspective, where functional activity is assessed using functional Magnetic Resonance Imaging (fMRI) to estimate connectivity between predefined neuronal regions. Functional connectivity can be represented by correlation matrices computed over time, where each matrix captures the Pearson correlation between the mean fMRI signals of different regions within a sliding window. We introduce several Log-Euclidean Riemannian framework for constructing smooth approximations of functional brain connectivity trajectories. Representing dynamic functional connectivity as time series of full-rank correlation matrices, we leverage recent theoretical Log-Euclidean diffeomorphisms to map these trajectories in practice into Euclidean spaces where polynomial regression becomes feasible. Pulling back the regressed curve ensures that each estimated point remains a valid correlation matrix, enabling a smooth, interpretable, and geometrically consistent approximation of the original brain connectivity dynamics. Experiments on fMRI-derived connectivity trajectories demonstrate the geometric consistency and computational efficiency of our approach.