ShockLab

AUTHORS

D. Taylor, J.P Shock, D. Moodley, J. Ipser, M. Treder

DATE PUBLISHED

01 January 2022

Abstract

Brain Age (BA) estimation via Deep Learning has become a strong and reliable bio-marker for brain health, but the black-box nature of Neural Networks does not easily allow insight into the features of brain ageing. We trained a ResNet model as a BA regressor on T1 structural MRI volumes from a small cross-sectional cohort of 524 individuals. Using Layer-wise Relevance Propagation (LRP), we analysed the trained model to determine the most revealing structures over the course of brain ageing for the network. We show the change in attribution of relevance to different brain regions through the course of ageing. A tripartite pattern of relevance attribution to brain regions emerges. Some regions increase in relevance with age (e.g. the right Transverse Temporal Gyrus); some decrease in relevance with age (e.g. the right Fourth Ventricle); and others remained consistently relevant across ages. We also examine the effect of Brain Age Gap (BAG) on the distribution of LRP-assigned relevance within the brain volume. It is hoped that these findings will provide clinically relevant region-wise trajectories for normal brain ageing, and a baseline against which to compare brain ageing trajectories.