Medical image reconstruction with multi-level deep learning denoiser and tight frame regularization

doi:10.1016/j.amc.2024.128795

	Medical image reconstruction with multi-level deep learning denoiser and tight frame regularization
	Wu, Tingting 1; Huang, Chaoyan 4; Jia, Shilong 2; Li, Wei 1; Chan, Raymond 3; Zeng, Tieyong 4; Zhou, S. Kevin 5,6
	2024-09-15
发表期刊	APPLIED MATHEMATICS AND COMPUTATION
ISSN	0096-3003
卷号	477 页码:19
摘要	As a fundamental task, medical image reconstruction has attracted growing attention in clinical diagnosis. Aiming at promising performance, it is critical to deeply understand and effectively design advanced model for image reconstruction. Indeed, one possible solution is to integrate the deep learning methods with the variational approaches to absorb benefits from both parts. In this paper, to protect more details and a better balance between the computational burden and the numerical performance, we carefully choose the multi -level wavelet convolutional neural network (MWCNN) for this issue. As the tight frame regularizer has the capability of maintaining edge information in image, we combine the MWCNN with the tight frame regularizer to reconstruct images. The proposed model can be solved by the celebrated proximal alternating minimization (PAM) algorithm. Furthermore, our method is a noise -adaptive framework as it can also handle real -world images. To prove the robustness of our strategy, we address two important medical image reconstruction tasks: Magnetic Resonance Imaging (MRI) and Positron Emission Tomography (PET). Extensive numerical experiments show clearly that our approach achieves better performance over several state-of-the-art methods.
关键词	Medical image reconstruction Multi-level wavelet convolutional neural network Tight frame Proximal alternating minimization Magnetic resonance imaging Positron emission tomography
DOI	10.1016/j.amc.2024.128795
收录类别	SCI
语种	英语
资助项目	1311 Talent Plan of NUPT[61971234] ; 1311 Talent Plan of NUPT[11671002] ; 1311 Talent Plan of NUPT[12126340] ; 1311 Talent Plan of NUPT[12126304] ; QingLan Project for Colleges and Univer-sities of Jiangsu Province ; STITP[XZD2020122] ; Nanjing University of Posts and Telecommunications Project ; [NY223008]
WOS研究方向	Mathematics
WOS类目	Mathematics, Applied
WOS记录号	WOS:001241682900001
出版者	ELSEVIER SCIENCE INC
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/40039
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zeng, Tieyong
作者单位	1.Nanjing Univ Posts & Telecommun, Sch Sci, Nanjing, Peoples R China 2.Nanjing Univ Posts & Telecommun, Sch Comp Sci, Nanjing, Peoples R China 3.City Univ Hong Kong, Dept Math, Hong Kong, Peoples R China 4.Chinese Univ Hong Kong, Dept Math, Shatin, Hong Kong, Peoples R China 5.Chinese Acad Sci, Key Lab Intelligent Informat Proc CAS, MIRACLE Grp, ICT, Beijing 100190, Peoples R China 6.Univ Chinese Acad Sci UCAS, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Wu, Tingting,Huang, Chaoyan,Jia, Shilong,et al. Medical image reconstruction with multi-level deep learning denoiser and tight frame regularization[J]. APPLIED MATHEMATICS AND COMPUTATION,2024,477:19.
APA	Wu, Tingting.,Huang, Chaoyan.,Jia, Shilong.,Li, Wei.,Chan, Raymond.,...&Zhou, S. Kevin.(2024).Medical image reconstruction with multi-level deep learning denoiser and tight frame regularization.APPLIED MATHEMATICS AND COMPUTATION,477,19.
MLA	Wu, Tingting,et al."Medical image reconstruction with multi-level deep learning denoiser and tight frame regularization".APPLIED MATHEMATICS AND COMPUTATION 477(2024):19.