A Constrained, Weighted-L1 Minimization Approach for Joint Discovery of Heterogeneous Neural Connectivity Graphs

TL;DR

This paper introduces W-SIMULE, a novel weighted-L1 multi-task graphical model that incorporates neuroscience priors and extends Gaussian assumptions, significantly improving the estimation of brain connectivity from neuroimaging data.

Contribution

The paper presents W-SIMULE, a flexible, parallelizable model that effectively integrates domain-specific priors and extends Gaussian models for better brain connectivity inference.

Findings

W-SIMULE outperforms previous models in log-likelihood and edge detection.

Achieved 58.6% accuracy in classifying autism spectrum disorder groups.

Successfully links key neural areas associated with autism.

Abstract

Determining functional brain connectivity is crucial to understanding the brain and neural differences underlying disorders such as autism. Recent studies have used Gaussian graphical models to learn brain connectivity via statistical dependencies across brain regions from neuroimaging. However, previous studies often fail to properly incorporate priors tailored to neuroscience, such as preferring shorter connections. To remedy this problem, the paper here introduces a novel, weighted-$\ell_1$, multi-task graphical model (W-SIMULE). This model elegantly incorporates a flexible prior, along with a parallelizable formulation. Additionally, W-SIMULE extends the often-used Gaussian assumption, leading to considerable performance increases. Here, applications to fMRI data show that W-SIMULE succeeds in determining functional connectivity in terms of (1) log-likelihood, (2) finding edges that differentiate groups, and (3) classifying different groups based on their connectivity, achieving 58.6\% accuracy on the ABIDE dataset. Having established W-SIMULE's effectiveness, it links four key areas to autism, all of which are consistent with the literature. Due to its elegant domain adaptivity, W-SIMULE can be readily applied to various data types to effectively estimate connectivity.