Expected affine: A registration method for damaged section in serial sections electron microscopy

doi:10.3389/fninf.2022.944050

CORC > 自动化研究所 > 中国科学院自动化研究所 > 类脑智能研究中心 > 微观重建与智能分析

	Expected affine: A registration method for damaged section in serial sections electron microscopy
	Xin, Tong 2,3; Shen, Lijun 2; Li, Linlin 2; Chen, Xi 2; Han, Hua 1,2,4,5
刊名	FRONTIERS IN NEUROINFORMATICS
	2022-09-02
卷号	16 页码:11
关键词	image registration SSEM broken sections section fold section crack
DOI	10.3389/fninf.2022.944050
通讯作者	Chen, Xi(xi.chen@ia.ac.cn) ; Han, Hua(hua.han@ia.ac.cn)
英文摘要	Registration is essential for the volume reconstruction of biological tissues using serial section electron microscope (ssEM) images. However, due to environmental disturbance in section preparation, damage in long serial sections is inevitable. It is difficult to register the damaged sections with the common serial section registration method, creating significant challenges in subsequent neuron tracking and reconstruction. This paper proposes a general registration method that can be used to register damaged sections. This method first extracts the key points and descriptors of the sections to be registered and matches them via a mutual nearest neighbor matcher. K-means and Random Sample Consensus (RANSAC) are used to cluster the key points and approximate the local affine matrices of those clusters. Then, K-nearest neighbor (KNN) is used to estimate the probability density of each cluster and calculate the expected affine matrix for each coordinate point. In clustering and probability density calculations, instead of the Euclidean distance, the path distance is used to measure the correlation between sampling points. The experimental results on real test images show that this method solves the problem of registering damaged sections and contributes to the 3D reconstruction of electronic microscopic images of biological tissues. The code of this paper is available at .
资助项目	Strategic Priority Research Program of the Chinese Academy of Sciences[XDB32030208] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDA27010403] ; Bureau of International Cooperation, Chinese Academy of Sciences[153D31KYSB20170059] ; Program of Beijing Municipal Science and Technology Commission[Z201100008420004] ; CAS Key Technology Talent Program[292019000126]
WOS关键词	RECONSTRUCTION ; FORMALDEHYDE ; MRI
WOS研究方向	Mathematical & Computational Biology ; Neurosciences & Neurology
语种	英语
出版者	FRONTIERS MEDIA SA
WOS记录号	WOS:000855279100001
资助机构	Strategic Priority Research Program of the Chinese Academy of Sciences ; Bureau of International Cooperation, Chinese Academy of Sciences ; Program of Beijing Municipal Science and Technology Commission ; CAS Key Technology Talent Program
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/50122]
专题	类脑智能研究中心_微观重建与智能分析
通讯作者	Chen, Xi; Han, Hua
作者单位	1.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai, Peoples R China 2.Chinese Acad Sci, Inst Automat, Beijing, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing, Peoples R China 4.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China 5.Univ Chinese Acad Sci, Sch Future Technol, Beijing, Peoples R China
推荐引用方式 GB/T 7714	Xin, Tong,Shen, Lijun,Li, Linlin,et al. Expected affine: A registration method for damaged section in serial sections electron microscopy[J]. FRONTIERS IN NEUROINFORMATICS,2022,16:11.
APA	Xin, Tong,Shen, Lijun,Li, Linlin,Chen, Xi,&Han, Hua.(2022).Expected affine: A registration method for damaged section in serial sections electron microscopy.FRONTIERS IN NEUROINFORMATICS,16,11.
MLA	Xin, Tong,et al."Expected affine: A registration method for damaged section in serial sections electron microscopy".FRONTIERS IN NEUROINFORMATICS 16(2022):11.