Self-Supervised Coordinate Projection Network for Sparse-View Computed Tomography

doi:10.1109/TCI.2023.3281196

	Self-Supervised Coordinate Projection Network for Sparse-View Computed Tomography
	Wu, Qing1,2,3 ; Feng, Ruimin 4,5; Wei, Hongjiang 4,5; Yu, Jingyi1 ; Zhang, Yuyao1,6
	2023
发表期刊	IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING (IF:4.2[JCR-2023],4.7[5-Year])
ISSN	2573-0436
EISSN	2333-9403
卷号	9 页码:517-529
发表状态	已发表
DOI	10.1109/TCI.2023.3281196
摘要	Sparse-view Computed Tomography (SVCT) has great potential for decreasing patient radiation exposure dose during scanning. In this work, we propose a Self-supervised COordinate Projection nEtwork (SCOPE) to reconstruct the artifact-free CT image from the acquired SV sinogram by solving the inverse problem of tomography imaging. To solve the under-determined inverse imaging problem, we first introduce an implicit neural representation (INR) network to constrain the solution space via image continuity prior. And inspired by the relationship between linear algebra and inverse problems, we propose a novel re-projection strategy to generate a dense view sinogram from the initial solution, which significantly improves the rank of the linear equation system and produces a more stable CT image solution space. Specially, the desired CT image is represented as an implicit function of the two-dimensional spatial coordinate to directly approximate the SV sinogram through the CT imaging forward model. Then, a dense-view sinogram is generated from the fine-trained INR network. The final CT reconstruction is reconstructed by applying Filtered Back Projection (FBP) to the generated dense-view sinogram. Additionally, we integrate the recent hash encoding into our SCOPE model, which efficiently accelerates the model training process. We evaluate SCOPE in parallel and fan X-ray beam SVCT reconstruction tasks. Our experiment results demonstrate that the re-projection strategy significantly improves the image reconstruction quality (+3 dB for PSNR at least). The proposed SCOPE model provides state-of-the-art reconstruction results compared to two latest INR-based methods and two well-popular supervised DL methods for the SV CT image reconstruction.
关键词	Computed tomography Image reconstruction Mathematical models X-ray imaging Training Inverse problems Image coding Sparse-view computed tomography inverse imaging problem self-supervised learning implicit neural representation
URL	查看原文
收录类别	SCI ; EI
语种	英语
资助项目	National Natural Science Foundation of China["62071299","61901256","91949120"]
WOS研究方向	Engineering ; Imaging Science & Photographic Technology
WOS类目	Engineering, Electrical & Electronic ; Imaging Science & Photographic Technology
WOS记录号	WOS:001004182700003
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
EI入藏号	20232414219599
EI主题词	Inverse problems
EI分类号	723.5 Computer Applications ; 921.1 Algebra ; 921.2 Calculus
原始文献类型	Journal article (JA)
来源库	IEEE
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/312306
专题	信息科学与技术学院 iHuman研究所信息科学与技术学院_PI研究组_虞晶怡组信息科学与技术学院_博士生信息科学与技术学院_PI研究组_张玉瑶组
通讯作者	Zhang, Yuyao
作者单位	1.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai 201210, Peoples R China 2.Chinese Acad Sci, Shanghai Adv Res Inst, Shanghai 201210, Peoples R China 3.Univ Chinese Acad Sci, Beijing 101408, Peoples R China 4.Shanghai Jiao Tong Univ, Inst Med Robot, Shanghai 200127, Peoples R China 5.Shanghai Jiao Tong Univ, Inst Med Robot, Shanghai 200127, Peoples R China 6.ShanghaiTech Univ, iHuman Inst, Shanghai 201210, Peoples R China
第一作者单位	信息科学与技术学院
通讯作者单位	信息科学与技术学院; iHuman研究所
第一作者的第一单位	信息科学与技术学院
推荐引用方式 GB/T 7714	Wu, Qing,Feng, Ruimin,Wei, Hongjiang,et al. Self-Supervised Coordinate Projection Network for Sparse-View Computed Tomography[J]. IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING,2023,9:517-529.
APA	Wu, Qing,Feng, Ruimin,Wei, Hongjiang,Yu, Jingyi,&Zhang, Yuyao.(2023).Self-Supervised Coordinate Projection Network for Sparse-View Computed Tomography.IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING,9,517-529.
MLA	Wu, Qing,et al."Self-Supervised Coordinate Projection Network for Sparse-View Computed Tomography".IEEE TRANSACTIONS ON COMPUTATIONAL IMAGING 9(2023):517-529.