4.7 Article

A deep graph neural network architecture for modelling spatio-temporal dynamics in resting-state functional MRI data

Journal

MEDICAL IMAGE ANALYSIS
Volume 79, Issue -, Pages -

Publisher

ELSEVIER
DOI: 10.1016/j.media.2022.102471

Keywords

Deep learning; Graph neural networks; UK Biobank; Time series; Temporal convolutional network; Rs-fMRI; Spatio-temporal dynamics

Funding

  1. W. D. Armstrong Trust Fund, University of Cambridge, UK - British Academy Post-Doctoral fellowship [MR/P01271X/1]
  2. NIHR Cambridge Biomedical Research Centre
  3. McDonnell Center for Systems Neuroscience at Washington University
  4. Engineering and Physical Sciences Research Council [MR/P01271X/1]
  5. Science and Technology Facilities Council
  6. W. D. Armstrong Trust Fund, University of Cambridge, UK
  7. British Academy Post-Doctoral fellowship
  8. Autism Research Trust
  9. Guarantors of Brain
  10. Medical Research Council (MRC)
  11. MRC research infrastructure award
  12. Marmaduke Shield Award [MR/P01271X/1]
  13. [MR/M009041/1]
  14. [1U54MH091657]
  15. [EP/P020259/1]

Ask authors/readers for more resources

In this paper, a novel deep neural network architecture is proposed that combines graph neural networks and temporal convolutional networks for learning from both the spatial and temporal components of resting-state functional magnetic resonance imaging (rs-fMRI) data. The model is evaluated using samples from the UK Biobank and Human Connectome Project datasets, showing effectiveness and explainability-related features. This approach lays the groundwork for future deep learning architectures focused on the spatio-temporal nature of rs-fMRI data.
Resting-state functional magnetic resonance imaging (rs-fMRI) has been successfully employed to understand the organisation of the human brain. Typically, the brain is parcellated into regions of interest (ROIs) and modelled as a graph where each ROI represents a node and association measures between ROI-specific blood-oxygen-level-dependent (BOLD) time series are edges. Recently, graph neural networks (GNNs) have seen a surge in popularity due to their success 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. In this paper, we present a novel deep neural network architecture which combines both GNNs and temporal convolutional networks (TCNs) in order to learn from both 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 interactions between ROI-wise dynamics with GNNs). We evaluate our model with an ablation study using 35,159 samples from the UK Biobank rs-fMRI database, as well as in the smaller Human Connectome Project (HCP) dataset, both in a unimodal and in a multi modal fashion. We also demonstrate that out architecture contains explainability-related features which easily map to realistic neurobiological insights. We suggest that this model could lay the groundwork for future deep learning architectures focused on leveraging the inherently and inextricably spatio-temporal nature of rs-fMRI data.(c) 2022 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/ )

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available