Multi-hops functional connectivity improves individual prediction of fusiform face activation via a graph neural network

Abstract

Brain connectivity plays an important role in determining the brain regions function. Previous researchers proposed that the brain regions function is characterized by that regions input and output connectivity profiles. Following this proposal, numerous studies have investigated the relationship between connectivity and function. However, based on a preliminary analysis, this proposal is deficient in explaining individual differences in the brain regions function. To overcome this problem, we proposed that a brain regions function is characterized by that regions multi-hops connectivity profile. To test this proposal, we used multi-hops functional connectivity to predict the individual face response of the right fusiform face area (rFFA) via a multi-layers graph neural network and showed that the prediction performance is essentially improved. Results also indicated that the 2-layers graph neural network is the best in characterizing rFFAs face response and revealed a hierarchical network for the face processing of rFFA.