Elastic shape analysis of brain structures for predictive modeling of PTSD

• Type of Material: Article
• Authors: Yuexuan Wu, Florida State University; Suprateek Kundu, Emory University; Jennifer Stevens, Emory University; Negar Fani, Emory University; Anuj Srivastava, Florida State University
• Language: English
• Date: 2022-09-01
• Publisher: FRONTIERS MEDIA SA
• Publication Version: Final Published Version
• Copyright Statement: © 2022 Wu, Kundu, Stevens, Fani and Srivastava.
• License: Creative Commons Attribution 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.3389/fnins.2022.954055
• Title of Journal or Parent Work: FRONTIERS IN NEUROSCIENCE
• Volume: 16
• Start Page: 954055
• End Page: 954055
• Grant/Funding Information: This research was conducted in part with support from NIH R01 MH120299 and NSF DMS 1953087.
• Keywords: VOLUME; Neurosciences & Neurology; statistical regression models; COMORBIDITY; computational anatomy; POSTTRAUMATIC-STRESS-DISORDER; elastic shape analysis; Science & Technology; Neurosciences; SEGMENTATION; PTSD diagnosis; Life Sciences & Biomedicine; shape PCA; RISK-FACTORS
• Research Categories: Biology, Biostatistics; Statistics

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 via PCs and in conjunction with auxiliary exposure variables. We apply our method to data from the Grady Trauma Project (GTP), where the goal is to predict clinical measures of PTSD. The framework seamlessly integrates accurate morphological features and other clinical covariates to yield superior predictive performance when modeling PTSD outcomes. Compared to vertex-wise analysis and other widely applied shape analysis methods, the elastic shape analysis approach results in considerably higher reconstruction accuracy for the brain shape and reveals significantly greater predictive power. It also helps identify local deformations in brain shapes associated with PTSD severity.