Graph Neural Network for Interpreting Task-fMRI Biomarkers
Authors:
- 10 October 2019
- book chapter
- Published by Springer Nature
- Vol. 11768, 485-493
Abstract
Finding the biomarkers associated with ASD is helpful for understanding the underlying roots of the disorder and can lead to earlier diagnosis and more targeted treatment. A promising approach to identify biomarkers is using Graph Neural Networks (GNNs), which can be used to analyze graph structured data, i.e. brain networks constructed by fMRI. One way to interpret important features is through looking at how the classification probability changes if the features are occluded or replaced. The major limitation of this approach is that replacing values may change the distribution of the data and lead to serious errors. Therefore, we develop a 2-stage pipeline to eliminate the need to replace features for reliable biomarker interpretation. Specifically, we propose an inductive GNN to embed the graphs containing different properties of task-fMRI for identifying ASD and then discover the brain regions/sub-graphs used as evidence for the GNN classifier. We first show GNN can achieve high accuracy in identifying ASD. Next, we calculate the feature importance scores using GNN and compare the interpretation ability with Random Forest. Finally, we run with different atlases and parameters, proving the robustness of the proposed method. The detected biomarkers reveal their association with social behaviors and are consistent with those reported in the literature. We also show the potential of discovering new informative biomarkers. Our pipeline can be generalized to other graph feature importance interpretation problems.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- Distance Metric Learning Using Graph Convolutional Networks: Application to Functional Brain Networks2017
- Brain responses to biological motion predict treatment outcome in young children with autismTranslational Psychiatry, 2016
- Comparison of communities detection algorithms for multiplexPhysica A: Statistical Mechanics and its Applications, 2015
- Biomarkers in AutismFrontiers in Psychiatry, 2014
- Large-scale automated synthesis of human functional neuroimaging dataNature Methods, 2011
- Neural signatures of autismProceedings of the National Academy of Sciences, 2010
- Automatic parcellation of human cortical gyri and sulci using standard anatomical nomenclatureNeuroImage, 2010
- An automated labeling system for subdividing the human cerebral cortex on MRI scans into gyral based regions of interestNeuroImage, 2006
- Analysis of Individual Differences in Multidimensional Scaling Via an N-way Generalization of “Eckart-Young” DecompositionPsychometrika, 1970