Abstract:
Functional magnetic resonance imaging (fMRI) enables recording the brain’s neural activity spatiotemporally and is the center of much cutting-edge psychology and neurosci...Show MoreMetadata
Abstract:
Functional magnetic resonance imaging (fMRI) enables recording the brain’s neural activity spatiotemporally and is the center of much cutting-edge psychology and neuroscience research. Many methods are proposed to process the 4-dimensional data the fMRI scans provide. The most common approach for classification tasks is to analyze functional connectivity, where brain volume is parcelled to regions, and the correlation between their time series is calculated. Such an approach is very suitable for graphical neural networks, a popular deep learning method for graphical data analysis. A graph is constructed by formulating the parcelled brain regions as the graph nodes, while their features and edges are constructed from the correlations. However, in many studies, the correlations are calculated from simple methods that do not take account of the lagged relations between the node time-series. This paper addresses this issue by proposing a new graphical neural network layer. This layer accounts for lagged relationships between the nodes and learns reacher features rather than simple zero-lag correlations. We show that our graphical layer can be used in front of a known graphical model and increase its performance for two different downstream tasks in a large fMRI dataset.
Date of Conference: 15-18 May 2022
Date Added to IEEE Xplore: 29 August 2022
ISBN Information:
Print on Demand(PoD) ISSN: 2165-0608