MAGNETIC RESONANCE IMAGE DENOISING BASED ON LAPLACIAN PRIOR SPARSITY CONSTRAINT AND NONCONVEX SECOND-ORDER TV PENALTY

被引:1
作者
Ge, Yumeng [1 ,2 ]
Xue, Wei [1 ,2 ]
Xu, Yun [1 ,2 ]
Huang, Jun [1 ,2 ]
Gu, Xiaolei [3 ]
机构
[1] Anhui Univ Technol, Sch Comp Sci & Technol, Maanshan 243032, Peoples R China
[2] Hefei Comprehens Natl Sci Ctr, Inst Artificial Intelligence, Hefei 230088, Peoples R China
[3] Maanshan Peoples Hosp, Dept Radiol, Maanshan 243099, Peoples R China
关键词
image denoising; Laplacian prior; magnetic resonance imaging; second-order total variation; sparsity constraint; RESTORATION; NOISE; MODEL;
D O I
10.5566/ias.2917
中图分类号
T [工业技术];
学科分类号
08 ;
摘要
Magnetic resonance (MR) imaging is considered as a very powerful imaging modality in clinical examination, but the process of image acquisition and transmission will be affected by noise, resulting in the degradation of imaging quality. In this paper, based on the Laplacian prior sparsity constraint and the nonconvex second -order total variation (TV) penalty, we propose a MR images denoising model which consists of three terms. Specifically, in the first term, we use the L2-norm as the fidelity term to control the proximity between the observed image and the recovered MR image. Then, we introduce the Laplacian sparse prior constraint as the second term to mitigate the staircase artifacts in the recovered image. In the third term, we adopt the nonconvex second-order TV penalty to preserve important textures and edges. Finally, we use the alternating direction method of multipliers to solve the corresponding minimization problem. Comparative experiments on clinical data demonstrate the effectiveness of our approach in terms of PSNR and SSIM values.
引用
收藏
页码:119 / 132
页数:14
相关论文
共 33 条
[1]   Image denoising using combined higher order non-convex total variation with overlapping group sparsity [J].
Adam, Tarmizi ;
Paramesran, Raveendran .
MULTIDIMENSIONAL SYSTEMS AND SIGNAL PROCESSING, 2019, 30 (01) :503-527
[2]  
Al-Shayea T.K., 2020, GLOB COMMUN C, P1
[3]   Medical image denoising using adaptive fusion of curvelet transform and total variation [J].
Bhadauria, H. S. ;
Dewal, M. L. .
COMPUTERS & ELECTRICAL ENGINEERING, 2013, 39 (05) :1451-1460
[4]   Distributed optimization and statistical learning via the alternating direction method of multipliers [J].
Boyd S. ;
Parikh N. ;
Chu E. ;
Peleato B. ;
Eckstein J. .
Foundations and Trends in Machine Learning, 2010, 3 (01) :1-122
[5]   Enhancing Sparsity by Reweighted l1 Minimization [J].
Candes, Emmanuel J. ;
Wakin, Michael B. ;
Boyd, Stephen P. .
JOURNAL OF FOURIER ANALYSIS AND APPLICATIONS, 2008, 14 (5-6) :877-905
[6]   Constrained Total Variation Deblurring Models and Fast Algorithms Based on Alternating Direction Method of Multipliers [J].
Chan, Raymond H. ;
Tao, Min ;
Yuan, Xiaoming .
SIAM JOURNAL ON IMAGING SCIENCES, 2013, 6 (01) :680-697
[7]   Hyper-Laplacian Regularized Unidirectional Low-rank Tensor Recovery for Multispectral Image Denoising [J].
Chang, Yi ;
Yan, Luxin ;
Zhong, Sheng .
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, :5901-5909
[8]   An improved coupled PDE system applied to the inverse image denoising problem [J].
El Hakoume, Abdelmajid ;
Afraites, Lekbir ;
Laghrib, Amine .
ELECTRONIC RESEARCH ARCHIVE, 2022, 30 (07) :2618-2642
[9]   Magnetic resonance image restoration via least absolute deviations measure with isotropic total variation constraint [J].
Gu, Xiaolei ;
Xue, Wei ;
Sun, Yanhong ;
Qi, Xuan ;
Luo, Xiao ;
He, Yongsheng .
MATHEMATICAL BIOSCIENCES AND ENGINEERING, 2023, 20 (06) :10590-10609
[10]   An optimal variable exponent model for Magnetic Resonance Images denoising [J].
Hadri, Aissam ;
Laghrib, Amine ;
Oummi, Hssaine .
PATTERN RECOGNITION LETTERS, 2021, 151 :302-309