We propose a new framework for estimating neuroimaging-derived “brain-age” at a local level within the brain, using deep learning. The local approach, contrary to existing global methods, provides spatial anatomical information on patterns of brain ageing. We trained a U-Net model on brain MRI scans from n=3463 healthy people to produce individualised 3D maps of brain-predicted age. Testing on n=692 healthy people resulted in a median (across subject) mean absolute error (within subject) of 9.0 years. Performance was more accurate (MAE around 7 years) in the prefrontal cortex and periventricular areas. We also introduce a new voxelwise method to reduce the age-bias when predicting local brain-age “gaps”. To validate local brain-age predictions, we tested the model in people with mild cognitive impairment or dementia using data from OASIS3 (n=267). Different local brain-age patterns were clearly evident between healthy controls and people with mild cognitive impairment or dementia, particularly in subcortical regions, with the accumbens, putamen, pallidum, hippocampus and amygdala. Comparing groups based on mean local brain-age over regions-of-interest resulted in large effects sizes, with Cohen’s d values >1.5, for example when comparing people with stable and progressive mild cognitive impairment.
bioRxiv Subject Collection: Neuroscience