Sparse Bayesian Modeling of Hierarchical Independent Component Analysis: Reliable Estimation of Individual Differences in Brain Networks

• Activity Number: 155 - Section on Statistics in Imaging Student Paper Award Winners
• Type: Topic-Contributed
• Date/Time: Tuesday, August 10, 2021 : 10:00 AM to 11:50 AM
• Sponsor: Section on Statistics in Imaging
• Author(s): Joshua Lukemire* and Ying Guo
• Companies: Emory University and Emory University
• Keywords: ICA; Brain Networks; Covariates; Functional Connectivity

Abstract

Independent Component Analysis (ICA) is one of the leading approaches for studying brain functional networks. There has been an increasing interest in neuroscience studies to investigate individual differences in brain networks and their association with demographic characteristics and clinical outcomes. In this work, we develop a sparse Bayesian group hierarchical ICA model that offers significant improvements over existing ICA techniques for identifying covariate effects on the brain network. Specifically, we model the population-level ICA source signals for brain networks using a Dirichlet process mixture. To reliably capture individual differences on brain networks, we propose sparse estimation of the covariate effects in the hierarchical ICA model via a horseshoe prior. Effect discovery under our method can be carried out by examining credible intervals. Through extensive simulation studies, we show our approach has considerably improved performance in detecting covariate effects in comparison with the current leading group ICA methods. We then use it to perform an ICA decomposition of a motivating Zen meditation resting-state study.