A Deep Graph Neural Network Architecture for Modelling Spatio-temporal Dynamics in resting-state functional MRI Data
Preprint
Abstract
Resting-state functional magnetic resonance imaging (rs-fMRI) has been successfully employed to understand the organisation of the human brain. For rs-fMRI analysis, the brain is typically parcellated into regions of interest (ROIs) and modelled as a graph where each ROI is a node and pairwise correlation between ROI blood-oxygen-level-dependent (BOLD) time series are edges. Recently, graph neural networks (GNNs) have seen a surge in popularity due to their successes in modelling unstructured relational data. The latest developments with GNNs, however, have not yet been fully exploited for the analysis of rs-fMRI data, particularly with regards to its spatio-temporal dynamics. Herein we present a novel deep neural network architecture, combining both GNNs and temporal convolutional networks (TCNs), which is able to learn from the spatial and temporal components of rs-fMRI data in an end-to-end fashion. In particular, this corresponds to intra-feature learning (i.e., learning temporal dynamics with TCNs) as well as inter-feature learning (i.e., leveraging spatial interactions between ROIs with GNNs). We evaluate our model with an ablation study using 35,159 samples from the UK Biobank rs-fMRI database. We also demonstrate explainability features of our architecture which map to realistic neurobiological insights. We hope our model could lay the groundwork for future deep learning architectures focused on leveraging the inherently and inextricably spatio-temporal nature of rs-fMRI data.Keywords
All Related Versions
- Published version: Medical Image Analysis, 79, 102471.
This publication has 33 references indexed in Scilit:
- The significance of negative correlations in brain connectivityJournal of Comparative Neurology, 2017
- The (in)stability of functional brain network measures across thresholdsNeuroImage, 2015
- The connectomics of brain disordersNature Reviews Neuroscience, 2015
- Automatic denoising of functional MRI data: Combining independent component analysis and hierarchical fusion of classifiersNeuroImage, 2014
- The minimal preprocessing pipelines for the Human Connectome ProjectNeuroImage, 2013
- Simulation physiologischer Regelkreise mit der objektorientierten Modellbibliothek “HumanLib”at - Automatisierungstechnik, 2011
- A Hierarchy of Time-Scales and the BrainPLOS Computational Biology, 2008
- The Human Central Nervous System2008
- An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interestNeuroImage, 2006
- Investigations into resting-state connectivity using independent component analysisPhilosophical Transactions of the Royal Society B: Biological Sciences, 2005