A0698
Title: Whole brain connectivity estimation by GPU-enhanced Gaussian process
Authors: Minjee Kim - Vanderbilt University (United States)
Yuting Mei - Vanderbilt University (United States)
Ilwoo Lyu - POSTECH (Korea, South)
Alisa Zoltowski - Vanderbilt University (United States)
Chris Fonnesbeck - Vanderbilt University Medical Center (United States)
Carissa Cascio - Vanderbilt University Medical Center (United States)
Hakmook Kang - Vanderbilt University (United States) [presenting]
Abstract: The previous Bayesian spatiotemporal model approach has been expanded to significantly reduce the computation burden by employing GPU (graphics processing unit) computing and the Gaussian process to model the intra-voxel spatial correlation in each ROI (region of interest). A Bayesian double-fusion technique is used for enhancing the estimation of whole brain resting state functional connectivity (FC) based on functional magnetic resonance imaging (fMRI) data between brain regions by using structural connectivity (SC) based on diffusion tensor imaging (DTI) data. Concurrently acquired two imaging data are simultaneously used for FC estimation, which allows precise investigation of the relationship between FC and SC or alterations in white matter microstructural integrity. This enhanced modeling approach is applied to investigate the nuances of functional network connectivity in individuals with autism, potentially uncovering significant insights into the neural underpinnings of the disorder.
