An Invertible Dynamic Graph Convolutional Network for Multi-Center ASD Classification

Yueying Chen; Aiping Liu; Xueyang Fu; Jie Wen; Xun Chen

doi:10.3389/fnins.2021.828512

An Invertible Dynamic Graph Convolutional Network for Multi-Center ASD Classification

Front Neurosci. 2022 Feb 4:15:828512. doi: 10.3389/fnins.2021.828512. eCollection 2021.

Authors

Yueying Chen^{1

2}, Aiping Liu^{1

2}, Xueyang Fu^{1

2}, Jie Wen³, Xun Chen^{1

2}

Affiliations

¹ School of Information Science and Technology, University of Science and Technology of China, Hefei, China.
² USTC IAT-Huami Joint Laboratory for Brain-Machine Intelligence, Institute of Advanced Technology, University of Science and Technology of China, Hefei, China.
³ Division of Life Sciences and Medicine, Department of Radiology, The First Affiliated Hospital of USTC (Anhui Provincial Hospital), University of Science and Technology of China, Hefei, China.

Abstract

Autism Spectrum Disorder (ASD) is one common developmental disorder with great variations in symptoms and severity, making the diagnosis of ASD a challenging task. Existing deep learning models using brain connectivity features to classify ASD still suffer from degraded performance for multi-center data due to limited feature representation ability and insufficient interpretability. Given that Graph Convolutional Network (GCN) has demonstrated superiority in learning discriminative representations of brain connectivity networks, in this paper, we propose an invertible dynamic GCN model to identify ASD and investigate the alterations of connectivity patterns associated with the disease. In order to select explainable features from the model, invertible blocks are introduced in the whole network, and we are able to reconstruct the input dynamic features from the network's output. A pre-screening of connectivity features is adopted to reduce the redundancy of the input information, and a fully-connected layer is added to perform classification. The experimental results on 867 subjects show that our proposed method achieves superior disease classification performance. It provides an interpretable deep learning model for brain connectivity analysis and is of great potential in studying brain-related disorders.

Keywords: autism spectrum disorder; brain connectivity networks; disease classification; fMRI; graph convolutional networks; invertible networks.