Elastic Shape Analysis of Brain Structures for Predictive Modeling of PTSD

Authors

Yuexuan Wu
Suprateek Kundu
Jennifer S Stevens
Negar Fani
Anuj Srivastava

Publication Date

1-1-2022

Journal

Frontiers in Neuroscience

DOI

10.3389/fnins.2022.954055

PMID

36117613

PMCID

PMC9475197

PubMedCentral® Posted Date

9-1-2022

PubMedCentral® Full Text Version

Post-print

Abstract

It is well-known that morphological features in the brain undergo changes due to traumatic events and associated disorders such as post-traumatic stress disorder (PTSD). However, existing approaches typically offer group-level comparisons, and there are limited predictive approaches for modeling behavioral outcomes based on brain shape features that can account for heterogeneity in PTSD, which is of paramount interest. We propose a comprehensive shape analysis framework representing brain sub-structures, such as the hippocampus, amygdala, and putamen, as parameterized surfaces and quantifying their shape differences using an elastic shape metric. Under this metric, we compute shape summaries (mean, covariance, PCA) of brain sub-structures and represent individual brain shapes by their principal scores under a shape-PCA basis. These representations are rich enough to allow visualizations of full 3D structures and help understand localized changes. In order to validate the elastic shape analysis, we use the principal components (PCs) to reconstruct the brain structures and perform further evaluation by performing a regression analysis to model PTSD and trauma severity using the brain shapes represented

Keywords

computational anatomy, elastic shape analysis, PTSD diagnosis, statistical regression models, shape PCA

Published Open-Access

yes

Recommended Citation

Wu, Yuexuan; Kundu, Suprateek; Stevens, Jennifer S; et al., "Elastic Shape Analysis of Brain Structures for Predictive Modeling of PTSD" (2022). Faculty, Staff and Student Publications. 4666.
https://digitalcommons.library.tmc.edu/uthgsbs_docs/4666