Establishing group-level brain structural connectivity incorporating anatomical knowledge under latent space modeling

TL;DR

This paper introduces a novel Bayesian latent space model for group-level brain structural connectivity that incorporates anatomical knowledge, providing interpretable, statistically robust summaries and identifying sex-specific neuromarkers in Alzheimer's disease.

Contribution

The paper proposes the ABC model, a latent space-based generative approach that integrates anatomical attributes and offers improved interpretability and predictive power over existing methods.

Findings

Superior predictive accuracy on out-of-sample data

Identification of meaningful sex-specific neuromarkers for AD

Incorporation of anatomical attributes enhances model interpretability

Abstract

Brain structural connectivity, capturing the white matter fiber tracts among brain regions inferred by diffusion MRI (dMRI), provides a unique characterization of brain anatomical organization. One fundamental question to address with structural connectivity is how to properly summarize and perform statistical inference for a group-level connectivity architecture, for instance, under different sex groups, or disease cohorts. Existing analyses commonly summarize group-level brain connectivity by a simple entry-wise sample mean or median across individual brain connectivity matrices. However, such a heuristic approach fully ignores the associations among structural connections and the topological properties of brain networks. In this project, we propose a latent space-based generative network model to estimate group-level brain connectivity. We name our method the attributes-informed brain connectivity (ABC) model, which compared with existing group-level connectivity estimations, (1) offers an interpretable latent space representation of the group-level connectivity, (2) incorporates the anatomical knowledge of nodes and tests its co-varying relationship with connectivity and (3) quantifies the uncertainty and evaluates the likelihood of the estimated group-level effects against chance. We devise a novel Bayesian MCMC algorithm to estimate the model. By applying the ABC model to study brain structural connectivity stratified by sex among Alzheimer's Disease (AD) subjects and healthy controls incorporating the anatomical attributes (volume, thickness and area) on nodes, our method shows superior predictive power on out-of-sample structural connectivity and identifies meaningful sex-specific network neuromarkers for AD.