Predicting brain amyloid-&beta; PET phenotypes with graph convolutional networks based on functional MRI and multi-level functional connectivity

doi:10.1101/2021.08.26.21262325

	Predicting brain amyloid-β PET phenotypes with graph convolutional networks based on functional MRI and multi-level functional connectivity
	Li, C.1,2 ; Liu, M.2; Xia, J.3; Mei, L.2 ; Yang, Q.3; Shi, F.4; Zhang, H.3,5; Shen, D.2,4,6
	2021-08-29
状态	已发表
摘要	The detection of amyloid-{beta} (A{beta}) deposition in the brain provides crucial evidence in the clinical diagnosis of Alzheimers disease (AD). However, the efficiency of the current PET-based brain A{beta} examination suffers from both coarse, visual inspection-based bi-class stratification and high scanning cost and risks. In this work, we explored the feasibility of using non-invasive functional magnetic resonance imaging (fMRI) to predict A{beta}-PET phenotypes in the AD continuum with graph learning on brain networks. First, three whole-brain A{beta}-PET phenotypes were identified through clustering and their association with clinical phenotypes were investigated. Second, both conventional and high-order functional connectivity (FC) networks were constructed using resting-state fMRI and the network topological architectures were learned with graph convolutional networks (GCNs) to predict such A{beta}-PET phenotypes. The experiment of A{beta}-PET phenotype prediction on 258 samples from the AD continuum showed that our algorithm achieved a high fMRI-to-PET prediction accuracy (78.8%). The results demonstrated the existence of distinguishable brain A{beta} deposition phenotypes in the AD continuum and the feasibility of using artificial intelligence and non-invasive brain imaging technique to approximate PET-based evaluations. It can be a promising technique for high-throughput screening of AD with less costs and restrictions.
关键词	Functional connectivity brain network amyloid β PET graph convolutional network
语种	英语
DOI	10.1101/2021.08.26.21262325
相关网址	查看原文
出处	medRxiv
收录类别	PPRN.PPRN
WOS记录号	PPRN:8246834
WOS类目	Geriatrics & Gerontology
资助项目	Guangzhou Science and Technology["202102010495","82027808","ZJ2018-ZD-012"]
文献类型	预印本
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/348430
专题	生物医学工程学院物质科学与技术学院_硕士生信息科学与技术学院_硕士生生命科学与技术学院_PI研究组_窦坤组
通讯作者	Zhang, H.; Shen, D.
作者单位	1.Guangzhou Univ, Expt Ctr, Guangzhou, Peoples R China 2.ShanghaiTech Univ, Sch Biomed Engn, Shanghai, Peoples R China 3.Inst Brain Intelligence Technol, Zhangjiang Lab, Shanghai, Peoples R China 4.United Imaging Intelligence Co Ltd, Dept Res & Dev, Shanghai, Peoples R China 5.Inst Brain Intelligence Technol, Zhangjiang Lab, Shanghai 201204, Peoples R China 6.Shanghai Tech Univ, Sch Biomed Engn, Shanghai 201210, Peoples R China
推荐引用方式 GB/T 7714	Li, C.,Liu, M.,Xia, J.,et al. Predicting brain amyloid-β PET phenotypes with graph convolutional networks based on functional MRI and multi-level functional connectivity. 2021.