CASIA OpenIR  > 类脑智能研究中心  > 微观重建与智能分析
Dual Networks for High-Precision and High-Speed Registration of Brain Electron Microscopy Images
Shu, Chang1,2; Xin, Tong1,2; Zhou, Fangxu1,3; Chen, Xi1; Han, Hua3,4,5
Source PublicationBrain Sciences
2020
Volume10Issue:2Pages:86
Corresponding AuthorChen, Xi(xi.chen@ia.ac.cn) ; Han, Hua(hua.han@ia.ac.cn)
Abstract

It remains a mystery as to how neurons are connected and thereby enable us to think, and volume reconstruction from series of microscopy sections of brains is a vital technique in determining this connectivity. Image registration is a key component; the aim of image registration is to estimate the deformation field between two images. Current methods choose to directly regress the deformation field; however, this task is very challenging. It is common to trade off computational complexity with precision when designing complex models for deformation field estimation. This approach is very inefficient, leading to a long inference time. In this paper, we suggest that complex models are not necessary and solve this dilemma by proposing a dual-network architecture. We divide the deformation field prediction problem into two relatively simple subproblems and solve each of them on one branch of the proposed dual network. The two subproblems have completely opposite properties, and we fully utilize these properties to simplify the design of the dual network. These simple architectures enable high-speed image registration. The two branches are able to work together and make up for each other's drawbacks, and no loss of accuracy occurs even when simple architectures are involved. Furthermore, we introduce a series of loss functions to enable the joint training of the two networks in an unsupervised manner without introducing costly manual annotations. The experimental results reveal that our method outperforms state-of-the-art methods in fly brain electron microscopy image registration tasks, and further ablation studies enable us to obtain a comprehensive understanding of each component of our network.

KeywordComputer Vision Image Processing Deep Learning Image Registration Electron Microscopy Image Dual Network Architecture Unsupervised Learning
DOI10.3390/brainsci10020086
WOS KeywordRECONSTRUCTION ; VOLUME
Indexed BySCI
Language英语
Funding ProjectNational Science Foundation of China[61673381] ; National Science Foundation of China[61701497] ; Special Program of Beijing Municipal Science and Technology Commission[Z181100000118002] ; Strategic Priority Research Program of Chinese Academy of Science[XDB32030200] ; Instrument function development innovation program of Chinese Academy of Sciences[282019000057] ; Bureau of International Cooperation, CAS[153D31KYSB20170059]
Funding OrganizationNational Science Foundation of China ; Special Program of Beijing Municipal Science and Technology Commission ; Strategic Priority Research Program of Chinese Academy of Science ; Instrument function development innovation program of Chinese Academy of Sciences ; Bureau of International Cooperation, CAS
WOS Research AreaNeurosciences & Neurology
WOS SubjectNeurosciences
WOS IDWOS:000519243400035
PublisherBrain Sciences
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/38525
Collection类脑智能研究中心_微观重建与智能分析
Corresponding AuthorChen, Xi; Han, Hua
Affiliation1.Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
2.School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China
3.School of Future Technology, University of Chinese Academy of Sciences, Beijing 100049, China
4.The Center for Excellence in Brain Science and Intelligence Technology, CAS, Shanghai 200031, China
5.National Laboratory of Pattern Recognition, CASIA, Beijing 100190, China
First Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Corresponding Author AffilicationInstitute of Automation, Chinese Academy of Sciences
Recommended Citation
GB/T 7714
Shu, Chang,Xin, Tong,Zhou, Fangxu,et al. Dual Networks for High-Precision and High-Speed Registration of Brain Electron Microscopy Images[J]. Brain Sciences,2020,10(2):86.
APA Shu, Chang,Xin, Tong,Zhou, Fangxu,Chen, Xi,&Han, Hua.(2020).Dual Networks for High-Precision and High-Speed Registration of Brain Electron Microscopy Images.Brain Sciences,10(2),86.
MLA Shu, Chang,et al."Dual Networks for High-Precision and High-Speed Registration of Brain Electron Microscopy Images".Brain Sciences 10.2(2020):86.
Files in This Item: Download All
File Name/Size DocType Version Access License
Chang - 2020 - Dual (1388KB)期刊 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Shu, Chang]'s Articles
[Xin, Tong]'s Articles
[Zhou, Fangxu]'s Articles
Baidu academic
Similar articles in Baidu academic
[Shu, Chang]'s Articles
[Xin, Tong]'s Articles
[Zhou, Fangxu]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Shu, Chang]'s Articles
[Xin, Tong]'s Articles
[Zhou, Fangxu]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Chang - 2020 - Dual Networks for High-Precision and High-Speed Registration of Brain Electron Microscopy Images.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.