Cargando…
An Invertible Dynamic Graph Convolutional Network for Multi-Center ASD Classification
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...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8854990/ https://www.ncbi.nlm.nih.gov/pubmed/35185454 http://dx.doi.org/10.3389/fnins.2021.828512 |
_version_ | 1784653556533428224 |
---|---|
author | Chen, Yueying Liu, Aiping Fu, Xueyang Wen, Jie Chen, Xun |
author_facet | Chen, Yueying Liu, Aiping Fu, Xueyang Wen, Jie Chen, Xun |
author_sort | Chen, Yueying |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-8854990 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-88549902022-02-19 An Invertible Dynamic Graph Convolutional Network for Multi-Center ASD Classification Chen, Yueying Liu, Aiping Fu, Xueyang Wen, Jie Chen, Xun Front Neurosci Neuroscience 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. Frontiers Media S.A. 2022-02-04 /pmc/articles/PMC8854990/ /pubmed/35185454 http://dx.doi.org/10.3389/fnins.2021.828512 Text en Copyright © 2022 Chen, Liu, Fu, Wen and Chen. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Neuroscience Chen, Yueying Liu, Aiping Fu, Xueyang Wen, Jie Chen, Xun An Invertible Dynamic Graph Convolutional Network for Multi-Center ASD Classification |
title | An Invertible Dynamic Graph Convolutional Network for Multi-Center ASD Classification |
title_full | An Invertible Dynamic Graph Convolutional Network for Multi-Center ASD Classification |
title_fullStr | An Invertible Dynamic Graph Convolutional Network for Multi-Center ASD Classification |
title_full_unstemmed | An Invertible Dynamic Graph Convolutional Network for Multi-Center ASD Classification |
title_short | An Invertible Dynamic Graph Convolutional Network for Multi-Center ASD Classification |
title_sort | invertible dynamic graph convolutional network for multi-center asd classification |
topic | Neuroscience |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8854990/ https://www.ncbi.nlm.nih.gov/pubmed/35185454 http://dx.doi.org/10.3389/fnins.2021.828512 |
work_keys_str_mv | AT chenyueying aninvertibledynamicgraphconvolutionalnetworkformulticenterasdclassification AT liuaiping aninvertibledynamicgraphconvolutionalnetworkformulticenterasdclassification AT fuxueyang aninvertibledynamicgraphconvolutionalnetworkformulticenterasdclassification AT wenjie aninvertibledynamicgraphconvolutionalnetworkformulticenterasdclassification AT chenxun aninvertibledynamicgraphconvolutionalnetworkformulticenterasdclassification AT chenyueying invertibledynamicgraphconvolutionalnetworkformulticenterasdclassification AT liuaiping invertibledynamicgraphconvolutionalnetworkformulticenterasdclassification AT fuxueyang invertibledynamicgraphconvolutionalnetworkformulticenterasdclassification AT wenjie invertibledynamicgraphconvolutionalnetworkformulticenterasdclassification AT chenxun invertibledynamicgraphconvolutionalnetworkformulticenterasdclassification |