Discovering Dynamic Effective Connectome of Brain with Bayesian Dynamic DAG Learning

TL;DR

This paper introduces a Bayesian dynamic DAG learning method called BDyMA for accurately discovering the brain's dynamic effective connectome from fMRI data, addressing high-dimensionality and data quality challenges.

Contribution

The proposed BDyMA method enables more accurate, sparse, and reliable dynamic effective connectome discovery by incorporating prior knowledge and handling feedback loops.

Findings

Outperforms state-of-the-art methods in synthetic and real data

Handles high-dimensional networks effectively

Improves DEC accuracy with DTI prior knowledge

Abstract

Understanding the complex mechanisms of the brain can be unraveled by extracting the Dynamic Effective Connectome (DEC). Recently, score-based Directed Acyclic Graph (DAG) discovery methods have shown significant improvements in extracting the causal structure and inferring effective connectivity. However, learning DEC through these methods still faces two main challenges: one with the fundamental impotence of high-dimensional dynamic DAG discovery methods and the other with the low quality of fMRI data. In this paper, we introduce Bayesian Dynamic DAG learning with M-matrices Acyclicity characterization (BDyMA) method to address the challenges in discovering DEC. The presented dynamic causal model enables us to discover direct feedback loop edges as well. Leveraging an unconstrained framework in the BDyMA method leads to more accurate results in detecting high-dimensional networks, achieving sparser outcomes, making it particularly suitable for extracting DEC. Additionally, the score function of the BDyMA method allows the incorporation of prior knowledge into the process of dynamic causal discovery which further enhances the accuracy of results. Comprehensive simulations on synthetic data and experiments on Human Connectome Project (HCP) data demonstrate that our method can handle both of the two main challenges, yielding more accurate and reliable DEC compared to state-of-the-art and traditional methods. Additionally, we investigate the trustworthiness of DTI data as prior knowledge for DEC discovery and show the improvements in DEC discovery when the DTI data is incorporated into the process.