A benchmark of individual auto-regressive models in a massive fMRI dataset

Abstract

Dense functional magnetic resonance imaging datasets open new avenues to create auto-regressive models of brain activity. Individual idiosyncrasies are obscured by group models, but can be captured by purely individual models given sufficient amounts of training data. In this study, we compared several deep and shallow individual models on the auto-regression of BOLD time series recorded during a natural video watching task. The best performing models were then analyzed in terms of their data requirements and scaling, subject specificity and the space-time structure of their predicted dynamics.We found the Chebnets, a type of graph convolutional neural network, to be best suited for BOLD auto-regression, closely followed by linear models. Chebnets demonstrated an increase in performance with increasing amounts of data, with no complete saturation at 9 h of training data. Significant subject specificity was found at short prediction time lags. The Chebnets were found to capture lower frequencies at longer prediction time lags, and the spatial correlations in predicted dynamics were found to match traditional functional connectivity networks.Overall, these results demonstrate that large individual fMRI datasets can be used to efficiently train purely individual auto-regressive models of brain activity, and that massive amounts of individual data are required to do so. The excellent performance of the Chebnets likely reflects their ability to combine spatial and temporal interactions on large time scales at a low complexity cost. Individual auto-regressive models have the potential to improve our understanding of the functional interactions in the human brain. This study is based on a massive, publicly-available dataset, which can serve for future benchmarks of individual auto-regressive modeling.