Plug-and-Play ADMM for MRI Reconstruction With Convex Nonconvex Sparse Regularization

Traditional <inline-formula> <tex-math notation="LaTeX">$\ell _{1}$ </tex-math></inline-formula>-regularized compressed sensing magnetic resonance imaging (CS-MRI) model tends to underestimate the fine textures and edges of the MR image, which play important roles i...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jincheng Li, Jinlan Li, Zhaoyang Xie, Jian Zou
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Plug-and-play method ADMM convex nonconvex sparse regularization compressed sensing MRI reconstruction Electrical engineering. Electronics. Nuclear engineering TK1-9971
Acceso en línea:	https://doaj.org/article/94148e7094c340a1a2dbec9f09b9027a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:94148e7094c340a1a2dbec9f09b9027a
record_format	dspace
spelling	oai:doaj.org-article:94148e7094c340a1a2dbec9f09b9027a2021-11-18T00:10:55ZPlug-and-Play ADMM for MRI Reconstruction With Convex Nonconvex Sparse Regularization2169-353610.1109/ACCESS.2021.3124600https://doaj.org/article/94148e7094c340a1a2dbec9f09b9027a2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9597555/https://doaj.org/toc/2169-3536Traditional <inline-formula> <tex-math notation="LaTeX">$\ell _{1}$ </tex-math></inline-formula>-regularized compressed sensing magnetic resonance imaging (CS-MRI) model tends to underestimate the fine textures and edges of the MR image, which play important roles in clinical diagnosis. In contrast, the convex nonconvex (CNC) strategy allows the use of nonconvex regularization while maintaining the convexity of the total objective function. Plug-and-play (PnP) algorithm is a powerful framework for sparse regularization problems, which plug any advanced denoiser into traditional proximal algorithms. In this paper, we propose a PnP-ADMM algorithm for CS-MRI reconstruction with CNC sparse regularization. We first obtain the proximal operator for CNC sparse regularization. Then we present PnP-ADMM algorithm by replacing the proximal operator of ADMM with properly pre-trained denoisers. Furthermore, we conduct comparison experiments using various denoisers under different sampling templates for different images. The experimental results verify the effectiveness of the proposed algorithm with both numerical criteria and visual effects.Jincheng LiJinlan LiZhaoyang XieJian ZouIEEEarticlePlug-and-play methodADMMconvex nonconvex sparse regularizationcompressed sensingMRI reconstructionElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 148315-148324 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Plug-and-play method ADMM convex nonconvex sparse regularization compressed sensing MRI reconstruction Electrical engineering. Electronics. Nuclear engineering TK1-9971
spellingShingle	Plug-and-play method ADMM convex nonconvex sparse regularization compressed sensing MRI reconstruction Electrical engineering. Electronics. Nuclear engineering TK1-9971 Jincheng Li Jinlan Li Zhaoyang Xie Jian Zou Plug-and-Play ADMM for MRI Reconstruction With Convex Nonconvex Sparse Regularization
description	Traditional <inline-formula> <tex-math notation="LaTeX">$\ell _{1}$ </tex-math></inline-formula>-regularized compressed sensing magnetic resonance imaging (CS-MRI) model tends to underestimate the fine textures and edges of the MR image, which play important roles in clinical diagnosis. In contrast, the convex nonconvex (CNC) strategy allows the use of nonconvex regularization while maintaining the convexity of the total objective function. Plug-and-play (PnP) algorithm is a powerful framework for sparse regularization problems, which plug any advanced denoiser into traditional proximal algorithms. In this paper, we propose a PnP-ADMM algorithm for CS-MRI reconstruction with CNC sparse regularization. We first obtain the proximal operator for CNC sparse regularization. Then we present PnP-ADMM algorithm by replacing the proximal operator of ADMM with properly pre-trained denoisers. Furthermore, we conduct comparison experiments using various denoisers under different sampling templates for different images. The experimental results verify the effectiveness of the proposed algorithm with both numerical criteria and visual effects.
format	article
author	Jincheng Li Jinlan Li Zhaoyang Xie Jian Zou
author_facet	Jincheng Li Jinlan Li Zhaoyang Xie Jian Zou
author_sort	Jincheng Li
title	Plug-and-Play ADMM for MRI Reconstruction With Convex Nonconvex Sparse Regularization
title_short	Plug-and-Play ADMM for MRI Reconstruction With Convex Nonconvex Sparse Regularization
title_full	Plug-and-Play ADMM for MRI Reconstruction With Convex Nonconvex Sparse Regularization
title_fullStr	Plug-and-Play ADMM for MRI Reconstruction With Convex Nonconvex Sparse Regularization
title_full_unstemmed	Plug-and-Play ADMM for MRI Reconstruction With Convex Nonconvex Sparse Regularization
title_sort	plug-and-play admm for mri reconstruction with convex nonconvex sparse regularization
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/94148e7094c340a1a2dbec9f09b9027a
work_keys_str_mv	AT jinchengli plugandplayadmmformrireconstructionwithconvexnonconvexsparseregularization AT jinlanli plugandplayadmmformrireconstructionwithconvexnonconvexsparseregularization AT zhaoyangxie plugandplayadmmformrireconstructionwithconvexnonconvexsparseregularization AT jianzou plugandplayadmmformrireconstructionwithconvexnonconvexsparseregularization
_version_	1718425178830012416

Plug-and-Play ADMM for MRI Reconstruction With Convex Nonconvex Sparse Regularization

Ejemplares similares