Correction of image distortion in large-field ssEM stitching by an unsupervised intermediate-space solving network

doi:10.1093/bioinformatics/btac566

	Correction of image distortion in large-field ssEM stitching by an unsupervised intermediate-space solving network
	He, Bintao 1,2; Zhang, Yan 3; Zhang, Fa 4; Han, Renmin 1
	2022-10-14
发表期刊	BIOINFORMATICS
ISSN	1367-4803
卷号	38 期号:20 页码:4797-4805
摘要	Motivation: Serial-section electron microscopy (ssEM) is a powerful technique for cellular visualization, especially for large-scale specimens. Limited by the field of view, a megapixel image of whole-specimen is regularly captured by stitching several overlapping images. However, suffering from distortion by manual operations, lens distortion or electron impact, simple rigid transformations are not adequate for perfect mosaic generation. Non-linear deformation usually causes 'ghosting' phenomenon, especially with high magnification. To date, existing microscope image processing tools provide mature rigid stitching methods but have no idea with local distortion correction. Results: In this article, following the development of unsupervised deep learning, we present a multi-scale network to predict the dense deformation fields of image pairs in ssEM and blend these images into a clear and seamless montage. The model is composed of two pyramidal backbones, sharing parameters and interacting with a set of registration modules, in which the pyramidal architecture could effectively capture large deformation according to multi-scale decomposition. A novel 'intermediate-space solving' paradigm is adopted in our model to treat inputted images equally and ensure nearly perfect stitching of the overlapping regions. Combining with the existing rigid transformation method, our model further improves the accuracy of sequential image stitching. Extensive experimental results well demonstrate the superiority of our method over the other traditional methods.
DOI	10.1093/bioinformatics/btac566
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2021YFF0704300] ; National Key Research and Development Program of China[2020YFA0712401] ; National Natural Science Foundation of China[62072280] ; National Natural Science Foundation of China[61932018] ; National Natural Science Foundation of China[62072441] ; National Natural Science Foundation of China[31730023] ; National Natural Science Foundation of China[31521002] ; National Natural Science Foundation of China[31925026] ; Chinese Academy of Sciences (CAS)[XDB37010100] ; National Laboratory of Biomacromolecules of China[2019KF07]
WOS研究方向	Biochemistry & Molecular Biology ; Biotechnology & Applied Microbiology ; Computer Science ; Mathematical & Computational Biology ; Mathematics
WOS类目	Biochemical Research Methods ; Biotechnology & Applied Microbiology ; Computer Science, Interdisciplinary Applications ; Mathematical & Computational Biology ; Statistics & Probability
WOS记录号	WOS:000857451900001
出版者	OXFORD UNIV PRESS
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19821
专题	中国科学院计算技术研究所期刊论文
通讯作者	Zhang, Fa; Han, Renmin
作者单位	1.Shandong Univ, Res Ctr Math & Interdisciplinary Sci, Frontiers Sci Ctr Nonlinear Expectat, Minist Educ, Jinan 266000, Shandong, Peoples R China 2.BioMap Inc, Beijing 100086, Peoples R China 3.Chinese Acad Sci, Ctr Biol Imaging, Inst Biophys, Beijing 100190, Peoples R China 4.Chinese Acad Sci, High Performance Comp Res Ctr, Inst Comp Technol, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	He, Bintao,Zhang, Yan,Zhang, Fa,et al. Correction of image distortion in large-field ssEM stitching by an unsupervised intermediate-space solving network[J]. BIOINFORMATICS,2022,38(20):4797-4805.
APA	He, Bintao,Zhang, Yan,Zhang, Fa,&Han, Renmin.(2022).Correction of image distortion in large-field ssEM stitching by an unsupervised intermediate-space solving network.BIOINFORMATICS,38(20),4797-4805.
MLA	He, Bintao,et al."Correction of image distortion in large-field ssEM stitching by an unsupervised intermediate-space solving network".BIOINFORMATICS 38.20(2022):4797-4805.