Interpretable Spatio-Temporal Embedding for Brain Structural-Effective Network with Ordinary Differential Equation

TL;DR

This paper introduces STE-ODE, an interpretable graph learning framework using ODEs to model dynamic brain network interactions, improving clinical phenotype prediction from MRI data.

Contribution

It presents a novel interpretable spatio-temporal embedding method with directed node embeddings for brain networks, capturing dynamic influences more effectively.

Findings

Outperforms state-of-the-art methods on clinical prediction tasks

Demonstrates the effectiveness of directed embeddings in modeling brain dynamics

Validates on HCP and OASIS datasets

Abstract

The MRI-derived brain network serves as a pivotal instrument in elucidating both the structural and functional aspects of the brain, encompassing the ramifications of diseases and developmental processes. However, prevailing methodologies, often focusing on synchronous BOLD signals from functional MRI (fMRI), may not capture directional influences among brain regions and rarely tackle temporal functional dynamics. In this study, we first construct the brain-effective network via the dynamic causal model. Subsequently, we introduce an interpretable graph learning framework termed Spatio-Temporal Embedding ODE (STE-ODE). This framework incorporates specifically designed directed node embedding layers, aiming at capturing the dynamic interplay between structural and effective networks via an ordinary differential equation (ODE) model, which characterizes spatial-temporal brain dynamics. Our framework is validated on several clinical phenotype prediction tasks using two independent publicly available datasets (HCP and OASIS). The experimental results clearly demonstrate the advantages of our model compared to several state-of-the-art methods.