中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 中国科学院分子影像重点实验室
Nonconvex Laplacian Manifold Joint Method for Morphological Reconstruction of Fluorescence Molecular Tomography

文献类型：期刊论文

作者He, Xuelei2,3; Meng, Hui3; He, Xiaowei2; Wang, Kun3; Song, Xiaolei2; Tian, Jie1,3,4,5,6,7
刊名MOLECULAR IMAGING AND BIOLOGY
出版日期2021-01-07
页码13
关键词Fluorescence molecular tomography Reconstruction Nonconvex Laplacian manifold In vivo imaging Morphology
ISSN号1536-1632
DOI10.1007/s11307-020-01568-8
通讯作者Tian, Jie(jie.tian@ia.ac.cn)
英文摘要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.
WOS关键词TOTAL VARIATION REGULARIZATION ; DIFFUSE OPTICAL TOMOGRAPHY ; SPARSE RECONSTRUCTION ; MAXIMIZATION ; PERFORMANCE ; MICROSCOPY ; RECEPTOR ; PURSUIT ; SYSTEM ; CANCER
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]
WOS研究方向Radiology, Nuclear Medicine & Medical Imaging
语种英语
WOS记录号WOS:000605858900001
出版者SPRINGER
资助机构Ministry of Science and Technology of China ; National Natural Science Foundation of China ; Chinese Academy of Sciences ; Innovative Talents Promotion Plan of Shananxi
源URL[http://ir.ia.ac.cn/handle/173211/42572]  
专题自动化研究所_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.Jinan Univ, Zhuhai Precis Med Ctr, Zhuhai Peoples Hosp, Zhuhai 519000, Peoples R China
2.Northwest Univ, Sch Informat Sci & Technol, Xian 710127, Peoples R China
3.Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing 100190, Peoples R China
4.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100190, Peoples R China
5.Beihang Univ, Beijing Adv Innovat Ctr Big Data Based Precis Med, Beijing 100191, Peoples R China
6.Beihang Univ, Minist Ind & Informat Technol, Key Lab Big Data Based Precis Med, Beijing 100191, Peoples R China
7.Xidian Univ, Sch Life Sci & Technol, Engn Res Ctr Mol & Neuro Imaging, Minist Educ, Xian 710127, Peoples R China
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.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。