Exploring interpretable graph convolutional networks for autism spectrum disorder diagnosis

• Published in: International journal for computer assisted radiology and surgery Vol. 18; no. 4; pp. 663 - 673
• Main Authors: Li, Lanting, Wen, Guangqi, Cao, Peng, Liu, Xiaoli, R. Zaiane, Osmar, Yang, Jinzhu
• Format: Journal Article
• Language: English
• Published: Cham Springer International Publishing 01-04-2023; Springer Nature B.V
• Subjects: Artificial neural networks; Autism; Autism Spectrum Disorder - diagnosis; Biomarkers; Brain; Brain - diagnostic imaging; Classification; Computer Imaging; Computer Science; Diagnosis; Graphical representations; Health Informatics; Humans; Imaging; Learning; Machine learning; Medicine; Medicine & Public Health; Nodes; Original Article; Pattern Recognition and Graphics; Radiology; Surgery; Vision; Graph convolutional networks; Brain network; Biomarker identification; Autism spectrum disorder; Attention
• ISSN: 1861-6429; 1861-6410; 1861-6429
• DOI: 10.1007/s11548-022-02780-3

Purpose
Finding the biomarkers associated with autism spectrum disorder (ASD) is helpful for understanding the underlying roots of the disorder and can lead to earlier diagnosis and more targeted treatments. In essence, we are faced with two challenges (
i
) how to learn a node representation and a clean graph structure from original graph data with high dimensionality and (
ii
) how to jointly model the procedure of node representation learning, structure learning and graph classification.
Methods
We propose FSL-BrainNet, an interpretable graph convolution network (GCN) model for jointly Learning of node Features and clean Structures in brain networks for automatic brain network classification and interpretation. We formulate an end-to-end trainable and interpretable framework for graph classification and biomarkers (salient brain regions and potential subnetworks) identification.
Results
The experimental results on the ABIDE dataset show that our proposed methods not only achieve improved prediction performance compared with the state-of-the-art methods, but also find a compact set of highly suggestive biomarkers including relevant brain regions and subnetworks to ASD.
Conclusion
Through node feature learning and structure learning, our model can simultaneously select important brain regions and identify subnetworks.