干旱区生态环境知识资源中心(Arid): Predicting Brain Amyloid-β PET Grades with Graph Convolutional Networks Based on Functional MRI and Multi-Level Functional Connectivity

Arid

DOI	10.3233/JAD-215497
	Predicting Brain Amyloid-β PET Grades with Graph Convolutional Networks Based on Functional MRI and Multi-Level Functional Connectivity
	Li, Chaolin; Liu, Mianxin; Xia, Jing; Mei, Lang; Yang, Qing; Shi, Feng; Zhang, Han; Shen, Dinggang
通讯作者	Zhang, H ; Shen, DG
来源期刊	JOURNAL OF ALZHEIMERS DISEASE
ISSN	1387-2877
EISSN	1875-8908
出版年	2022
卷号	86 期号:4 页码:1679-1693
英文摘要	Background: The detection of amyloid-beta (A beta) deposition in the brain provides crucial evidence in the clinical diagnosis of Alzheimer's disease (AD). However, the current positron emission tomography (PET)-based brain A beta examination suffers from the problems of coarse visual inspection (in many cases, with 2-class stratification) and high scanning cost. Objective: 1) To characterize the non-binary A beta deposition levels in the AD continuum based on clustering of PET data, and 2) to explore the feasibility of predicting individual A beta deposition grades with non-invasive functional magnetic resonance imaging (fMRI). Methods: 1) Individual whole-brain A beta-PET images from the OASIS-3 dataset (N= 258) were grouped into three clusters (grades) with t-SNE and k-means. The demographical data as well as global and regional standard uptake value ratios (SUVRs) were compared among the three clusters with Chi-square tests or ANOVA tests. 2) From resting-state fMRI, both conventional functional connectivity (FC) and high-order FC networks were constructed and the topological architectures of the two networks were jointly learned with graph convolutional networks (GCNs) to predict the A beta-PET grades for each individual. Results: We found three clearly separated clusters, indicating three A beta-PET grades. There were significant differences in gender, age, cognitive ability, APOE type, as well as global and regional SUVRs among the three grades we found. The prediction of A beta-PET grades with GCNs on FC for the 258 samples in the AD continuum reached a satisfactory averaged accuracy (78.8%) in the two-class classification tasks. Conclusion: The results demonstrated the feasibility of using deep learning on a non-invasive brain functional imaging technique to approximate PET-based A beta deposition grading.
英文关键词	Amyloid-beta brain network functional connectivity graph convolutional neural network positron emission tomography
类型	Article
语种	英语
开放获取类型	Green Submitted
收录类别	SCI-E
WOS记录号	WOS:000784452600014
WOS关键词	ALZHEIMERS ASSOCIATION WORKGROUPS ; DIAGNOSTIC GUIDELINES ; NATIONAL INSTITUTE ; DISEASE ; RECOMMENDATIONS ; INDIVIDUALS ; PATTERNS ; AGE
WOS类目	Neurosciences
WOS研究方向	Neurosciences & Neurology
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/393277
推荐引用方式 GB/T 7714	Li, Chaolin,Liu, Mianxin,Xia, Jing,et al. Predicting Brain Amyloid-β PET Grades with Graph Convolutional Networks Based on Functional MRI and Multi-Level Functional Connectivity[J],2022,86(4):1679-1693.
APA	Li, Chaolin.,Liu, Mianxin.,Xia, Jing.,Mei, Lang.,Yang, Qing.,...&Shen, Dinggang.(2022).Predicting Brain Amyloid-β PET Grades with Graph Convolutional Networks Based on Functional MRI and Multi-Level Functional Connectivity.JOURNAL OF ALZHEIMERS DISEASE,86(4),1679-1693.
MLA	Li, Chaolin,et al."Predicting Brain Amyloid-β PET Grades with Graph Convolutional Networks Based on Functional MRI and Multi-Level Functional Connectivity".JOURNAL OF ALZHEIMERS DISEASE 86.4(2022):1679-1693.