Normative Modeling of Brain Morphometry Across the Lifespan using CentileBrain: Algorithm Benchmarking and Model Optimization

Ruiyang Ge; Yuetong Yu; Yi Xuan Qi; Yunan Vera Fan; Shiyu Chen; Chuntong Gao; Shalaila S. Haas; Amirhossein Modabbernia; Faye New; Ingrid Agartz; Philip J. Asherson; Rosa Ayesa‐Arriola; Nerisa Banaj; Tobias Banaschewski; Sarah Baumeister; Alessandro Bertolino; Dorret Irene Boomsma; Stefan Borgwardt; Josiane Bourque; Daniel Brandeis; Alan F. Breier; Henry Brodaty; Rachel M. Brouwer; Randy L. Buckner; Jan K. Buitelaar; Dara M. Cannon; Xavier Caseras; Simon Červenka; Patricia Conrod; Benedicto Crespo‐Facorro

doi:10.1101/2023.01.30.523509

BioinformaticsbioRxivJan 30, 2023

Preprint

Normative Modeling of Brain Morphometry Across the Lifespan using CentileBrain: Algorithm Benchmarking and Model Optimization

Ruiyang Ge iD, Yuetong Yu iD, Yi Xuan Qi, Yunan Vera Fan, Shiyu Chen iD, Chuntong Gao, Shalaila S. Haas iD, Amirhossein Modabbernia iD, Faye New, Ingrid Agartz iD, Philip J. Asherson iD, Rosa Ayesa‐Arriola iD, Nerisa Banaj iD, Tobias Banaschewski iD, Sarah Baumeister iD, Alessandro Bertolino iD, Dorret Irene Boomsma iD, Stefan Borgwardt iD, Josiane Bourque iD, Daniel Brandeis, Alan F. Breier, Henry Brodaty iD, Rachel M. Brouwer iD, Randy L. Buckner iD, Jan K. Buitelaar iD, , Bernd Weber iD

Abstract

We present an empirically benchmarked framework for sex-specific normative modeling of brain morphometry that can inform about the biological and behavioral significance of deviations from typical age-related neuroanatomical changes and support future study designs. This framework was developed using regional morphometric data from 37,407 healthy individuals (53% female; aged 3-90 years) following a comparative evaluation of eight algorithms and multiple covariate combinations pertaining to image acquisition and quality, parcellation software versions, global neuroimaging measures, and longitudinal stability. The Multivariate Factorial Polynomial Regression (MFPR) emerged as the preferred algorithm optimized using nonlinear polynomials for age and linear effects of global measures as covariates. The MFPR models showed excellent accuracy across the lifespan and within distinct age-bins, and longitudinal stability over a 2-year period. The performance of all MFPR models plateaued at sample sizes exceeding 3,000 study participants. The model and scripts described here are freely available through CentileBrain (https://centilebrain.org/).

PDF DOI