|
Activity Number:
|
249
- Multivariate Methods for Neuroimaging Data
|
|
Type:
|
Contributed
|
|
Date/Time:
|
Tuesday, August 9, 2022 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Statistics in Imaging
|
|
Abstract #323329
|
|
|
Title:
|
A General Framework for Repeated Measures Sparse Bayesian Independent Component Analysis with Applications to Multi-Center and Longitudinal Imaging Studies
|
|
Author(s):
|
Joshua Lukemire* and Ying Guo
|
|
Companies:
|
Emory University and Emory University
|
|
Keywords:
|
Multi-center;
Longitudinal;
fMRI;
ICA;
Brain Networks;
Covariates
|
|
Abstract:
|
We introduce a general framework of repeated measures Sparse Bayesian ICA (RM-SparseBayes ICA). This general method provides a rigorous and much needed tool for investigating brain networks and their differences in imaging studies with complex study designs including longitudinal and/or multi-center studies. Our approach incorporates random and fixed effects corresponding to data collection sites, allowing us to include information such as scanner type and field strength. Moreover, our approach incorporates sparsity assumptions to reliably estimate differences in brain networks due to covariates and center attributes. Additionally our approach uses subject-specific random effects to accommodate within-subject repeated measures such as those from longitudinal studies. Through simulations, we show that the proposed method has considerably improved performance as compared to other potential approaches. We apply the RM-SparseBayes ICA to investigate brain network changes using longitudinal multi-center data from a resting-state fMRI study.
|
Authors who are presenting talks have a * after their name.
