Meeting Banner
Abstract #2471

Brain functional fingerprinting predicts individual differences in cognition: An AI-based approach

Morteza Esmaeili1,2 and Alireza Salami3,4,5
1Department of Diagnostic Imaging, Akershus University Hospital, Lørenskog, Norway, 2Department of Electrical Engineering and Computer Science, University of Stavanger, Stavanger, Norway, 3Wallenberg Center for Molecular Medicine (WCMM), Umeå University, Umeå, Sweden, 4Department of Integrative Medical Biology, Umeå University, Umeå, Sweden, 5Aging Research Center, Karolinska Institute and Stockholm University, Solna, Sweden


Machine learning approaches provide convenient autonomous object classification in medical imaging domains. This study examines the utility of convolutional neural networks in predicting individual differences in cognition from the resting-state functional connectome. We observed significant contributions from the subcortical areas (including hippocampus) and their interactions with the cortical default mode network to the training progress. Our results demonstrate that an AI-based model can predict an individual's EM scores.

This abstract and the presentation materials are available to members only; a login is required.

Join Here