Identifying Shared Neuroanatomic Architecture between Cognitive Traits through Multiscale Morphometric Correlation Analysis

Med Image Comput Comput Assist Interv MICCAI 2023 Workshops (2023). 2024:14394:227-240. doi: 10.1007/978-3-031-47425-5_21. Epub 2024 Feb 3.

Abstract

We introduce an informative metric, called morphometric correlation, as a measure of shared neuroanatomic similarity between two cognitive traits. Traditional estimates of trait correlations can be confounded by factors beyond brain morphology. To exclude these confounding factors, we adopt a Gaussian kernel to measure the morphological similarity between individuals and compare pure neuroanatomic correlations among cognitive traits. In our empirical study, we employ a multiscale strategy. Given a set of cognitive traits, we first perform morphometric correlation analysis for each pair of traits to reveal their shared neuroanatomic correlation at the whole brain (or global) level. After that, we extend our whole brain concept to regional morphometric correlation and estimate shared neuroanatomic similarity between two cognitive traits at the regional (or local) level. Our results demonstrate that morphometric correlation can provide insights into shared neuroanatomic architecture between cognitive traits. Furthermore, we also estimate the morphometricity of each cognitive trait at both global and local levels, which can be used to better understand how neuroanatomic changes influence individuals' cognitive status.

Keywords: Alzheimer’s Disease; Brain image analysis; Cognitive Traits; Morphometric Correlation; Morphometricity.