Nonconvex Laplacian Manifold Joint Method for Morphological Reconstruction of Fluorescence Molecular Tomography

doi:10.1007/s11307-020-01568-8

	Nonconvex Laplacian Manifold Joint Method for Morphological Reconstruction of Fluorescence Molecular Tomography
	He, Xuelei 1,2; Meng, Hui2 ; He, Xiaowei 1; Wang, Kun2 ; Song, Xiaolei 1; Tian, Jie 2,3,4,5,6,7
发表期刊	MOLECULAR IMAGING AND BIOLOGY
ISSN	1536-1632
	2021-01-07
页码	13
通讯作者	Tian, Jie(jie.tian@ia.ac.cn)
摘要	Purpose: Fluorescence molecular tomography (FMT) is a promising technique for three-dimensional (3D) visualization of biomarkers in small animals. Morphological reconstruction is valuable and necessary for further applications of FMT owing to its innate requirement for knowledge of the molecular probe distributions. Procedures: In this study, a Laplacian manifold regularization joint l(1/2)-norm model is proposed for morphological reconstruction and solved by a nonconvex algorithm commonly referred to as the half-threshold algorithm. The model is combined with the structural and sparsity priors to achieve the location and structure of the target. In addition, two improvement forms (truncated and hybrid truncated forms) are proposed for better morphological reconstruction. The truncated form is proposed for balancing the sharpness and smoothness of the boundary of reconstruction. A hybrid truncated form is proposed for more structural priors. To evaluate the proposed methods, three simulation studies (morphological, robust, and double target analyses) and an in vivo experiment were performed. Results: The proposed methods demonstrated morphological accuracy, location accuracy, and reconstruction robustness in glioma simulation studies. An in vivo experiment with an orthotopic glioma mouse model confirmed the advantages of the proposed methods. The proposed methods always yielded the best intersection of union (IoU) in simulations and in vivo experiments (mean of 0.80 IoU). Conclusions: Simulation studies and in vivo experiments demonstrate that the proposed half-threshold hybrid truncated Laplacian algorithm had an improved performance compared with the comparative algorithm in terms of morphology.
关键词	Fluorescence molecular tomography Reconstruction Nonconvex Laplacian manifold In vivo imaging Morphology
DOI	10.1007/s11307-020-01568-8
关键词[WOS]	TOTAL VARIATION REGULARIZATION ; DIFFUSE OPTICAL TOMOGRAPHY ; SPARSE RECONSTRUCTION ; MAXIMIZATION ; PERFORMANCE ; MICROSCOPY ; RECEPTOR ; PURSUIT ; SYSTEM ; CANCER
收录类别	SCI
语种	英语
资助项目	Ministry of Science and Technology of China[2017YFA0205200] ; National Natural Science Foundation of China[81227901] ; National Natural Science Foundation of China[81527805] ; National Natural Science Foundation of China[81930053] ; National Natural Science Foundation of China[61671449] ; Chinese Academy of Sciences[KFJ-STS-ZDTP-059] ; Chinese Academy of Sciences[YJKYYQ20180048] ; Chinese Academy of Sciences[QYZDJ-SSW-JSC005] ; Innovative Talents Promotion Plan of Shananxi[2017SR5024]
项目资助者	Ministry of Science and Technology of China ; National Natural Science Foundation of China ; Chinese Academy of Sciences ; Innovative Talents Promotion Plan of Shananxi
WOS研究方向	Radiology, Nuclear Medicine & Medical Imaging
WOS类目	Radiology, Nuclear Medicine & Medical Imaging
WOS记录号	WOS:000605858900001
出版者	SPRINGER
七大方向——子方向分类	医学影像处理与分析
引用统计	被引频次：7[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/42573
专题	中国科学院分子影像重点实验室
通讯作者	Tian, Jie
作者单位	1.Northwest Univ, Sch Informat Sci & Technol, Xian 710127, Peoples R China 2.Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China 4.Beihang Univ, Beijing Adv Innovat Ctr Big Data Based Precis Med, Beijing 100191, Peoples R China 5.Beihang Univ, Minist Ind & Informat Technol, Key Lab Big Data Based Precis Med, Beijing 100191, Peoples R China 6.Xidian Univ, Sch Life Sci & Technol, Engn Res Ctr Mol & Neuro Imaging, Minist Educ, Xian 710127, Peoples R China 7.Jinan Univ, Zhuhai Precis Med Ctr, Zhuhai Peoples Hosp, Zhuhai 519000, Peoples R China
第一作者单位	中国科学院分子影像重点实验室
通讯作者单位	中国科学院分子影像重点实验室
推荐引用方式 GB/T 7714	He, Xuelei,Meng, Hui,He, Xiaowei,et al. Nonconvex Laplacian Manifold Joint Method for Morphological Reconstruction of Fluorescence Molecular Tomography[J]. MOLECULAR IMAGING AND BIOLOGY,2021:13.
APA	He, Xuelei,Meng, Hui,He, Xiaowei,Wang, Kun,Song, Xiaolei,&Tian, Jie.(2021).Nonconvex Laplacian Manifold Joint Method for Morphological Reconstruction of Fluorescence Molecular Tomography.MOLECULAR IMAGING AND BIOLOGY,13.
MLA	He, Xuelei,et al."Nonconvex Laplacian Manifold Joint Method for Morphological Reconstruction of Fluorescence Molecular Tomography".MOLECULAR IMAGING AND BIOLOGY (2021):13.