Neuroanatomical morphometric characterization of sex differences in youth using statistical learning

Abstract

Exploring neuroanatomical sex differences using a multivariate statistical learning approach can yield insights that cannot be derived with univariate analysis. While gross differences in total brain volume are well-established, uncovering the more subtle, regional sex-related differences in neuroanatomy requires a multivariate approach that can accurately model spatial complexity as well as the interactions between neuroanatomical features. Here, we developed a multivariate statistical learning model using a support vector machine (SVM) classifier to predict sex from MRI-derived regional neuroanatomical features from a single-site study of 967 healthy youth from the Philadelphia Neurodevelopmental Cohort (PNC). Then, we validated the multivariate model on an independent dataset of 682 healthy youth from the multi-site Pediatric Imaging, Neurocognition and Genetics (PING) cohort study. The trained model exhibited an 83% cross-validated prediction accuracy, and correctly predicted the sex of 77% of the subjects from the independent multi-site dataset. Results showed that cortical thickness of the middle occipital lobes and the angular gyri are major predictors of sex. Results also demonstrated the inferential benefits of going beyond classical regression approaches to capture the interactions among brain features in order to better characterize sex differences in male and female youths. We also identified specific cortical morphological measures and parcellation techniques, such as cortical thickness as derived from the Destrieux atlas, that are better able to discriminate between males and females in comparison to other brain atlases (Desikan-Killiany, Brodmann and subcortical atlases).

Gender Identification of Human Cortical 3-D Morphology Using Hierarchical Sparsity

“…Recently, gender difference in surface-based morphology such as cortical thickness, surface area, cortical curvature and cortical volume has attracted much attention. Im et al (2006) indicated that women showed more significant localized cortical thickening in the frontal, parietal and occipital lobes, which were also reported of significant gender-related difference by Lv et al (2010) using graph theoretical approaches; Sowell et al (2007) found women had thicker cortices in posterior temporal and right inferior parietal regions, while men showed larger brain in all locations, especially in the frontal and occipital poles of both hemispheres; Sepehrband et al (2018) developed a multivariate statistical learning model to predict gender from regional neuroanatomical features on different brain atlases, and they got an 83% cross-validated prediction accuracy and found the middle occipital lobes and the angular gyri the major predictors of gender.…”

Blood–brain barrier breakdown is an early biomarker of human cognitive dysfunction

“…The technical details of this procedure are described in previous publications 54,55 . Data processing was performed using the Laboratory of Neuro Imaging (LONI) pipeline system (http://pipeline.loni.usc.edu) 56,57 .…”

Alteration of perivascular spaces in early cognitive decline

“…Similar processing to Amyloid PET was performed to measure Tau PET SUVR. ADNI-3 Tau PET includes a broad set of regional MRI preprocessing and brain parcellation T1w preprocessing and parcellation was done using the FreeSurfer (v5.3.0) software package, which is freely available [45], and data processing using the Laboratory of Neuro Imaging (LONI) pipeline system (http://pipeline.loni.usc.edu) [46][47][48][49], similar to [50,51]. Brain volume and white matter mask were derived from the Desikan-Killiany atlas [52].…”