An Iterative Method With Enhanced Laplacian- Scaled Thresholding for Noise-Robust Compressive Sensing Magnetic Resonance Image Reconstruction
Compressive sensing (CS) has proven to be an efficient technique for accelerating magnetic resonance imaging (MRI) acquisition through breaking the Nyquist sampling limit. However, CS measurements are often corrupted by noise in the sensing process, which greatly reduces the quality of reconstructed...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9207943/ |
id |
doaj-412a72755fe84e9095458d188a197dbb |
---|---|
record_format |
Article |
spelling |
doaj-412a72755fe84e9095458d188a197dbb2021-03-30T04:48:29ZengIEEEIEEE Access2169-35362020-01-01817702117704010.1109/ACCESS.2020.30273139207943An Iterative Method With Enhanced Laplacian- Scaled Thresholding for Noise-Robust Compressive Sensing Magnetic Resonance Image ReconstructionZhong-Hua Xie0https://orcid.org/0000-0001-6625-3949Ling-Jun Liu1Xiao-Ye Wang2https://orcid.org/0000-0003-1851-6884Cui Yang3School of Computer Science and Engineering, Huizhou University, Huizhou, ChinaSchool of Computer Science and Engineering, Huizhou University, Huizhou, ChinaSchool of Computer Science and Engineering, Huizhou University, Huizhou, ChinaSchool of Electronic and Information Engineering, South China University of Technology, Guangzhou, ChinaCompressive sensing (CS) has proven to be an efficient technique for accelerating magnetic resonance imaging (MRI) acquisition through breaking the Nyquist sampling limit. However, CS measurements are often corrupted by noise in the sensing process, which greatly reduces the quality of reconstructed images and deteriorates the performance of follow-up diagnosis tasks. In this paper, we propose a novel iterative shrinkage-thresholding (IST) method based on enhanced Laplacian-scaled shrinkage operation for robust CS-MRI reconstruction. Differing to existing nonlocal Laplacian-scaled based methods that easily cause biased estimation in the presence of external noise, we design a side information-aided Laplacian-scaled sparse representation model to adapt to spatially varying image structures. Reference information obtained by performing Block-Matching 3D (BM3D) thresholding on the noisy observation is incorporated into the Laplacian-scaled thresholding operator for enhancing the accuracy of sparse coding. Furthermore, we build connections between IST algorithm and approximate message passing (AMP) algorithm and consider an approximation of the divergence of thresholding, leading to an AMP-like iterative method. Experiments validate the effectiveness of leveraging a combination of Laplacian-scaled and BM3D thresholding, and demonstrate the superior robustness of the proposed method both quantitatively and visually as compared with state-of-the-art methods.https://ieeexplore.ieee.org/document/9207943/Compressive sensing (CS)magnetic resonance imaging (MRI)Laplacian-scaled thresholdingBM3Diterative shrinkage-thresholding (IST)approximate message passing (AMP) |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Zhong-Hua Xie Ling-Jun Liu Xiao-Ye Wang Cui Yang |
spellingShingle |
Zhong-Hua Xie Ling-Jun Liu Xiao-Ye Wang Cui Yang An Iterative Method With Enhanced Laplacian- Scaled Thresholding for Noise-Robust Compressive Sensing Magnetic Resonance Image Reconstruction IEEE Access Compressive sensing (CS) magnetic resonance imaging (MRI) Laplacian-scaled thresholding BM3D iterative shrinkage-thresholding (IST) approximate message passing (AMP) |
author_facet |
Zhong-Hua Xie Ling-Jun Liu Xiao-Ye Wang Cui Yang |
author_sort |
Zhong-Hua Xie |
title |
An Iterative Method With Enhanced Laplacian- Scaled Thresholding for Noise-Robust Compressive Sensing Magnetic Resonance Image Reconstruction |
title_short |
An Iterative Method With Enhanced Laplacian- Scaled Thresholding for Noise-Robust Compressive Sensing Magnetic Resonance Image Reconstruction |
title_full |
An Iterative Method With Enhanced Laplacian- Scaled Thresholding for Noise-Robust Compressive Sensing Magnetic Resonance Image Reconstruction |
title_fullStr |
An Iterative Method With Enhanced Laplacian- Scaled Thresholding for Noise-Robust Compressive Sensing Magnetic Resonance Image Reconstruction |
title_full_unstemmed |
An Iterative Method With Enhanced Laplacian- Scaled Thresholding for Noise-Robust Compressive Sensing Magnetic Resonance Image Reconstruction |
title_sort |
iterative method with enhanced laplacian- scaled thresholding for noise-robust compressive sensing magnetic resonance image reconstruction |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
Compressive sensing (CS) has proven to be an efficient technique for accelerating magnetic resonance imaging (MRI) acquisition through breaking the Nyquist sampling limit. However, CS measurements are often corrupted by noise in the sensing process, which greatly reduces the quality of reconstructed images and deteriorates the performance of follow-up diagnosis tasks. In this paper, we propose a novel iterative shrinkage-thresholding (IST) method based on enhanced Laplacian-scaled shrinkage operation for robust CS-MRI reconstruction. Differing to existing nonlocal Laplacian-scaled based methods that easily cause biased estimation in the presence of external noise, we design a side information-aided Laplacian-scaled sparse representation model to adapt to spatially varying image structures. Reference information obtained by performing Block-Matching 3D (BM3D) thresholding on the noisy observation is incorporated into the Laplacian-scaled thresholding operator for enhancing the accuracy of sparse coding. Furthermore, we build connections between IST algorithm and approximate message passing (AMP) algorithm and consider an approximation of the divergence of thresholding, leading to an AMP-like iterative method. Experiments validate the effectiveness of leveraging a combination of Laplacian-scaled and BM3D thresholding, and demonstrate the superior robustness of the proposed method both quantitatively and visually as compared with state-of-the-art methods. |
topic |
Compressive sensing (CS) magnetic resonance imaging (MRI) Laplacian-scaled thresholding BM3D iterative shrinkage-thresholding (IST) approximate message passing (AMP) |
url |
https://ieeexplore.ieee.org/document/9207943/ |
work_keys_str_mv |
AT zhonghuaxie aniterativemethodwithenhancedlaplacianscaledthresholdingfornoiserobustcompressivesensingmagneticresonanceimagereconstruction AT lingjunliu aniterativemethodwithenhancedlaplacianscaledthresholdingfornoiserobustcompressivesensingmagneticresonanceimagereconstruction AT xiaoyewang aniterativemethodwithenhancedlaplacianscaledthresholdingfornoiserobustcompressivesensingmagneticresonanceimagereconstruction AT cuiyang aniterativemethodwithenhancedlaplacianscaledthresholdingfornoiserobustcompressivesensingmagneticresonanceimagereconstruction AT zhonghuaxie iterativemethodwithenhancedlaplacianscaledthresholdingfornoiserobustcompressivesensingmagneticresonanceimagereconstruction AT lingjunliu iterativemethodwithenhancedlaplacianscaledthresholdingfornoiserobustcompressivesensingmagneticresonanceimagereconstruction AT xiaoyewang iterativemethodwithenhancedlaplacianscaledthresholdingfornoiserobustcompressivesensingmagneticresonanceimagereconstruction AT cuiyang iterativemethodwithenhancedlaplacianscaledthresholdingfornoiserobustcompressivesensingmagneticresonanceimagereconstruction |
_version_ |
1724181206315040768 |