RT Journal Article
SR Electronic
T1 Modelling neuroanatomical variation due to age and sex during childhood and adolescence
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 126441
DO 10.1101/126441
A1 Gareth Ball
A1 Chris Adamson
A1 Richard Beare
A1 Marc L. Seal
YR 2017
UL http://biorxiv.org/content/early/2017/04/11/126441.abstract
AB Brain development is a dynamic process that follows a choreographed trajectory during childhood and adolescence with tissue-specific alterations that reflect complex and ongoing biological processes. Accurate identification and modelling of these anatomical processes in vivo with MRI may provide clinically useful imaging markers of individual variability in development. In this study, we build a model of age- and sex-related anatomical variation using multimodal imaging measures and manifold learning.Using publicly-available data from two large, independent developmental cohorts (n=768 and 862), we apply a multimodal machine learning approach combining measures of tissue volume, cortical area and cortical thickness into a low-dimensional data representation.We find that neuroanatomical variation due to age and sex can be captured by two orthogonal patterns of brain development and we use this model to predict age with a mean error of 1.6-2 years and sex with an accuracy of 80-84%.We present a framework for modelling anatomical development during childhood using low-dimensional data representations. This model accurately predicts age and sex based on image-derived markers of cerebral morphology and generalises well to independent populations.