Understanding the heterogeneity in atrophy changes from Alzheimer's disease (AD) can be an important factor to develop effective drugs and improve patients' outcomes [7]. In this study, we propose a deep learning approach to identify AD subtypes based on T1w magnetic resonance images (MRI). Experimental results show that the proposed method can accurately identify four AD subtypes exhibiting a distinctive cortical atrophy pattern.
This abstract and the presentation materials are available to members only; a login is required.