DS-GCNs: Connectome Classification using Dynamic Spectral Graph Convolution Networks with Assistant Task Training

doi:10.1093/cercor/bhaa292

	DS-GCNs: Connectome Classification using Dynamic Spectral Graph Convolution Networks with Assistant Task Training
	Xing, Xiaodan 1,2; Li, Qingfeng 3; Yuan, Mengya 3; Wei, Hao 1,4; Xue, Zhong 1; Wang, Tao 3; Shi, Feng 1; Shen, Dinggang1,5,6
	2021-02
发表期刊	CEREBRAL CORTEX (IF:2.9[JCR-2023],3.7[5-Year])
ISSN	1047-3211
EISSN	1460-2199
卷号	31 期号:2 页码:1259-1269
DOI	10.1093/cercor/bhaa292
摘要	Functional connectivity (FC) matrices measure the regional interactions in the brain and have been widely used in neurological brain disease classification. A brain network, also named as connectome, could form a graph structure naturally, the nodes of which are brain regions and the edges are interregional connectivity. Thus, in this study, we proposed novel graph convolutional networks (GCNs) to extract efficient disease-related features from FC matrices. Considering the time-dependent nature of brain activity, we computed dynamic FC matrices with sliding windows and implemented a graph convolution-based LSTM (long short-term memory) layer to process dynamic graphs. Moreover, the demographics of patients were also used as additional outputs to guide the classification. In this paper, we proposed to utilize the demographic information as extra outputs and to share parameters among three networks predicting subject status, gender, and age, which serve as assistant tasks. We tested the performance of the proposed architecture in ADNI II dataset to classify Alzheimer's disease patients from normal controls. The classification accuracy, sensitivity, and specificity reach 90.0%, 91.7%, and 88.6%, respectively, on ADNI II dataset.
关键词	Connectome fMRI GCN
URL	查看原文
收录类别	SCIE
语种	英语
WOS研究方向	Neurosciences & Neurology
WOS类目	Neurosciences
WOS记录号	WOS:000646868100036
出版者	OXFORD UNIV PRESS INC
原始文献类型	Article
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/126543
专题	生物医学工程学院_PI研究组_沈定刚组
通讯作者	Wang, Tao; Shi, Feng; Shen, Dinggang
作者单位	1.United Imaging Intelligence Co Ltd, Shanghai 201210, Peoples R China; 2.Shanghai Adv Res Inst, Shanghai 201210, Peoples R China; 3.Shanghai Jiao Tong Univ, Shanghai Mental Hlth Ctr, Sch Med, Shanghai 201108, Peoples R China; 4.Cent South Univ, Sch Comp Sci & Engn, Changsha 410083, Hunan, Peoples R China; 5.ShanghaiTech Univ, Sch Biomed Engn, Shanghai 201210, Peoples R China; 6.Korea Univ, Dept Artificial Intelligence, Seoul 02841, South Korea
通讯作者单位	生物医学工程学院
推荐引用方式 GB/T 7714	Xing, Xiaodan,Li, Qingfeng,Yuan, Mengya,et al. DS-GCNs: Connectome Classification using Dynamic Spectral Graph Convolution Networks with Assistant Task Training[J]. CEREBRAL CORTEX,2021,31(2):1259-1269.
APA	Xing, Xiaodan.,Li, Qingfeng.,Yuan, Mengya.,Wei, Hao.,Xue, Zhong.,...&Shen, Dinggang.(2021).DS-GCNs: Connectome Classification using Dynamic Spectral Graph Convolution Networks with Assistant Task Training.CEREBRAL CORTEX,31(2),1259-1269.
MLA	Xing, Xiaodan,et al."DS-GCNs: Connectome Classification using Dynamic Spectral Graph Convolution Networks with Assistant Task Training".CEREBRAL CORTEX 31.2(2021):1259-1269.