Interpretable Spatio-Temporal Embedding for Brain Structural-Effective Network with Ordinary Differential Equation
This work addresses the challenge of interpreting brain network dynamics for clinical applications, representing an incremental improvement by combining existing techniques like dynamic causal modeling with novel embedding layers.
The study tackled the problem of capturing directional influences and temporal dynamics in brain networks from MRI data by introducing an interpretable graph learning framework called STE-ODE, which uses an ODE model to integrate structural and effective networks, and demonstrated advantages over state-of-the-art methods on clinical phenotype prediction tasks using HCP and OASIS datasets.
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.