SWISTA-Nets: Subband-adaptive wavelet iterative shrinkage thresholding networks for image reconstruction

doi:10.1016/j.compmedimag.2024.102345

	SWISTA-Nets: Subband-adaptive wavelet iterative shrinkage thresholding networks for image reconstruction
	Lu, Binchun 1; Fu, Lidan 2,3; Pan, Yixuan 1; Dong, Yonggui 1
发表期刊	COMPUTERIZED MEDICAL IMAGING AND GRAPHICS
ISSN	0895-6111
	2024-04-01
卷号	113 页码:12
通讯作者	Dong, Yonggui(dongyg@mail.tsinghua.edu.cn)
摘要	Robust and interpretable image reconstruction is central to imageology applications in clinical practice. Prevalent deep networks, with strong learning ability to extract implicit information from data manifold, are still lack of prior knowledge introduced from mathematics or physics, leading to instability, poor structure interpretability and high computation cost. As to this issue, we propose two prior knowledge -driven networks to combine the good interpretability of mathematical methods and the powerful learnability of deep learning methods. Incorporating different kinds of prior knowledge, we propose subband-adaptive wavelet iterative shrinkage thresholding networks (SWISTA-Nets), where almost every network module is in one-to-one correspondence with each step involved in the iterative algorithm. By end -to -end training of proposed SWISTANets, implicit information can be extracted from training data and guide the tuning process of key parameters that possess mathematical definition. The inverse problems associated with two medical imaging modalities, i.e., electromagnetic tomography and X-ray computational tomography are applied to validate the proposed networks. Both visual and quantitative results indicate that the SWISTA-Nets outperform mathematical methods and state-of-the-art prior knowledge -driven networks, especially with fewer training parameters, interpretable network structures and well robustness. We assume that our analysis will support further investigation of prior knowledge -driven networks in the field of ill -posed image reconstruction.
关键词	Image reconstruction Inverse problem Deep learning Iterative shrinkage-thresholding algorithm Electromagnetic tomography Sparse-view CT
DOI	10.1016/j.compmedimag.2024.102345
关键词[WOS]	INVERSE PROBLEMS ; NEURAL-NETWORK ; ALGORITHM ; DOMAIN ; CT
收录类别	SCI
语种	英语
资助项目	National Natural Science Founda-tion of China[62071269]
项目资助者	National Natural Science Founda-tion of China
WOS研究方向	Engineering ; Radiology, Nuclear Medicine & Medical Imaging
WOS类目	Engineering, Biomedical ; Radiology, Nuclear Medicine & Medical Imaging
WOS记录号	WOS:001178669200001
出版者	PERGAMON-ELSEVIER SCIENCE LTD
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/56970
专题	中国科学院分子影像重点实验室
通讯作者	Dong, Yonggui
作者单位	1.Tsinghua Univ, Dept Precis Instrument, Beijing 100084, Peoples R China 2.Chinese Acad Sci, Inst Automat, CAS Key Lab Mol Imaging, Beijing Key Lab Mol Imaging, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Lu, Binchun,Fu, Lidan,Pan, Yixuan,et al. SWISTA-Nets: Subband-adaptive wavelet iterative shrinkage thresholding networks for image reconstruction[J]. COMPUTERIZED MEDICAL IMAGING AND GRAPHICS,2024,113:12.
APA	Lu, Binchun,Fu, Lidan,Pan, Yixuan,&Dong, Yonggui.(2024).SWISTA-Nets: Subband-adaptive wavelet iterative shrinkage thresholding networks for image reconstruction.COMPUTERIZED MEDICAL IMAGING AND GRAPHICS,113,12.
MLA	Lu, Binchun,et al."SWISTA-Nets: Subband-adaptive wavelet iterative shrinkage thresholding networks for image reconstruction".COMPUTERIZED MEDICAL IMAGING AND GRAPHICS 113(2024):12.