Multi-scale UDCT dictionary learning based highly undersampled MR image reconstruction using patch-based constraint splitting augmented Lagrangian shrinkage algorithm*

Yuan Min; Yang Bing-xin; Ma Yi-de; Zhang Jiu-wen; Lu Fu-xiang; Zhang Tong-feng

doi:10.1631/FITEE.1400423

Your Location：

Home >

Browse articles >

Multi-scale UDCT dictionary learning based highly undersampled MR image reconstruction using patch-based constraint splitting augmented Lagrangian shrinkage algorithm*

Electronic Engineering | Updated：2022-06-06

- Multi-scale UDCT dictionary learning based highly undersampled MR image reconstruction using patch-based constraint splitting augmented Lagrangian shrinkage algorithm*
- 基于多尺度UDCT域字典学习及分块约束型分裂增广拉格朗日收缩算法的高度欠采样磁共振图像重构
- Frontiers of Information Technology & Electronic Engineering Vol. 16, Issue 12, Pages: 1069-1087(2015)
- Affiliations：
  
  School of Information Science & Engineering, Lanzhou University, Lanzhou 730000, China
- Author bio：
  
  ‡Corresponding Author
- Funds：
- DOI：10.1631/FITEE.1400423
  CLC：
- Received：08 December 2014，
  
  Revised：2015-10-12，
  
  Accepted：09 October 2015，
  
  Published：2015-12
- Accepted：
Scan QR Code
Yuan Min, Yang Bing-xin, Ma Yi-de, et al. Multi-scale UDCT dictionary learning based highly undersampled MR image reconstruction using patch-based constraint splitting augmented Lagrangian shrinkage algorithm*[J]. Frontiers of Information Technology & Electronic Engineering, 2015, 16(12): 1069-1087.
DOI：

Yuan Min, Yang Bing-xin, Ma Yi-de, et al. Multi-scale UDCT dictionary learning based highly undersampled MR image reconstruction using patch-based constraint splitting augmented Lagrangian shrinkage algorithm*[J]. Frontiers of Information Technology & Electronic Engineering, 2015, 16(12): 1069-1087. DOI： 10.1631/FITEE.1400423.

摘要

目的

针对现有预定义分析型变换和图像域单尺度字典在稀疏表示中存在的不足，从寻求最优的稀疏先验信息和探索重构最优化问题的有效数值求解算法以适用于相应稀疏化结构两个方面，基于CS理论开展通过欠采样

空间数据重构高质量MR图像的研究，提出改进方法，从而达到改善重构图像质量的目的。

创新点

改进了基本的字典学习模型，提出了一种基于均匀离散Curvelet变换(Uniform Discrete Curvelet Transform

UDCT)域多尺度字典学习的稀疏化模型，并应用于CS-MRI重构。为适应多尺度分层和分块稀疏化结构，进一步扩展约束型分裂增广拉格朗日收缩方法，并用于模型的数值求解。

方法

文中图2为提出的UDCT域多尺度字典学习的CS-MRI重构方法的流程框图。如算法2中描述，整个UDPC方法包含两个阶段：多尺度字典学习阶段和PBC-SALSA重构阶段。在UDCT域多尺度字典学习阶段，提出的模型通过在UDCT的多尺度结构上训练过完备字典来构建。构造的UDCT域多尺度字典融合了多分辨率特性与字典学习的自适应数据匹配能力。在重构问题的求解过程中，将训练字典的稀疏先验信息引入到重构模型中，对分块约束型分裂增广拉格朗日算法进一步扩展以适应于多尺度字典结构。该算法能够稳定快速地收敛，从而重构出高质量的MR图像。

结论

相比于仅使用预定义的分析型变换和图像域单尺度字典稀疏先验，该稀疏化模型能够用更少的稀疏系数自适应地匹配图像在多尺度多方向的各种结构成分，有利于保留MR图像不同分辨率的精细特征和重构的快速收敛。提出的方法显著改善了高度欠采样情况下重构图像的质量，充分体现了UDCT域多尺度字典学习稀疏化模型的优势以及扩展的数值求解算法的有效性和稳定性。

Abstract

Recently

dictionary learning (DL) based methods have been introduced to compressed sensing magnetic resonance imaging (CS-MRI)

which outperforms pre-defined analytic sparse priors. However

single-scale trained dictionary directly from image patches is incapable of representing image features from multi-scale

multi-directional perspective

which influences the reconstruction performance. In this paper

incorporating the superior multi-scale properties of uniform discrete curvelet transform (UDCT) with the data matching adaptability of trained dictionaries

we propose a flexible sparsity framework to allow sparser representation and prominent hierarchical essential features capture for magnetic resonance (MR) images. Multi-scale decomposition is implemented by using UDCT due to its prominent properties of lower redundancy ratio

hierarchical data structure

and ease of implementation. Each sub-dictionary of different sub-bands is trained independently to form the multi-scale dictionaries. Corresponding to this brand-new sparsity model

we modify the constraint splitting augmented Lagrangian shrinkage algorithm (C-SALSA) as patch-based C-SALSA (PB C-SALSA) to solve the constraint optimization problem of regularized image reconstruction. Experimental results demonstrate that the trained sub-dictionaries at different scales

enforcing sparsity at multiple scales

can then be efficiently used for MRI reconstruction to obtain satisfactory results with further reduced undersampling rate. Multi-scale UDCT dictionaries potentially outperform both single-scale trained dictionaries and multi-scale analytic transforms. Our proposed sparsity model achieves sparser representation for reconstructed data

which results in fast convergence of reconstruction exploiting PB C-SALSA. Simulation results demonstrate that the proposed method outperforms conventional CS-MRI methods in maintaining intrinsic properties

eliminating aliasing

reducing unexpected artifacts

and removing noise. It can achieve comparable performance of reconstruction with the state-of-the-art methods even under substantially high undersampling factors.

关键词

Keywords

references

MV Afonso , JM Bioucas-Dias , MAT Figueiredo . An augmented Lagrangian approach to the constrained optimization formulation of imaging inverse problems . IEEE Trans Image Process , 2011 . 20 ( 3 ): 681 - 695 . DOI: 10.1109/TIP.2010.2076294 http://doi.org/10.1109/TIP.2010.2076294 .

M Aharon , M Elad , A Bruckstein . K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation . IEEE Trans Signal Process , 2006 . 54 ( 11 ): 4311 - 4322 . DOI: 10.1109/TSP.2006.881199 http://doi.org/10.1109/TSP.2006.881199 .

R Baraniuk . Compressive sensing . IEEE Signal Process Mag , 2007 . 24 ( 4 ): 118 - 121 . DOI: 10.1109/MSP.2007.4286571 http://doi.org/10.1109/MSP.2007.4286571 .

EJ Candes , DL Donoho . New tight frames of curvelets and optimal representations of objects with piecewise C 2 singularities . Commun Pure Appl Math , 2004 . 57 ( 2 ): 219 - 266 . DOI: 10.1002/cpa.10116 http://doi.org/10.1002/cpa.10116 .

EJ Candes , J Romberg , T Tao . Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information . IEEE Trans Inform Theory , 2006 . 52 ( 2 ): 489 - 509 . DOI: 10.1109/TIT.2005.862083 http://doi.org/10.1109/TIT.2005.862083 .

EJ Candes , JK Romberg , T Tao . Stable signal rcovery from incomplete and inaccurate measurements . Commun Pure Appl Math , 2006 . 59 ( 8 ): 1207 - 1223 . DOI: 10.1002/cpa.20124 http://doi.org/10.1002/cpa.20124 .

A Chambolle . An algorithm for total variation minimization and applications . J Math Imag Vis , 2004 . 20 ( 1-2 ): 89 - 97 . DOI: 10.1023/B:JMIV.0000011325.36760.1e http://doi.org/10.1023/B:JMIV.0000011325.36760.1e .

C Chen , J Huang . The benefit of tree sparsity in accelerated MRI . Med Image Anal , 2014 . 18 ( 6 ): 834 - 842 . DOI: 10.1016/j.media.2013.12.004 http://doi.org/10.1016/j.media.2013.12.004 .

PL Combettes , VR Wajs . Signal recovery by proximal forward-backward splitting . Multiscale Model Simul , 2005 . 4 ( 4 ): 1168 - 1200 . DOI: 10.1137/050626090 http://doi.org/10.1137/050626090 .

J Dahl , PC Hansen , SH Jensen , 等 . Algorithms and software for total variation image reconstruction via first-order methods . Numer Algor , 2010 . 53 ( 1 ): 67 - 92 . DOI: 10.1007/s11075-009-9310-3 http://doi.org/10.1007/s11075-009-9310-3 .

DL Donoho . Sparse components of images and optimal atomic decompositions . Constr Approx , 2001 . 17 ( 3 ): 353 - 382 . DOI: 10.1007/s003650010032 http://doi.org/10.1007/s003650010032 .

DL Donoho . Compressed sensing . IEEE Trans Inform Theory , 2006 . 52 ( 4 ): 1289 - 1306 . DOI: 10.1109/TIT.2006.871582 http://doi.org/10.1109/TIT.2006.871582 .

J Eckstein , DP Bertsekas . On the Douglas-Rachford splitting method and the proximal point algorithm for maximal monotone operators . Math Program , 1992 . 55 ( 1 ): 293 - 318 . DOI: 10.1007/BF01581204 http://doi.org/10.1007/BF01581204 .

M Elad . Sparse and Redundant Representations: from Theory to Applications in Signal and Image Processing , 2010 . Springer, New York, USA , DOI: 10.1007/978-1-4419-7011-4 http://doi.org/10.1007/978-1-4419-7011-4 .

M Elad , M Aharon . Image denoising via sparse and redundant representations over learned dictionaries . IEEE Trans Image Process , 2006 . 15 ( 12 ): 3736 - 3745 . DOI: 10.1109/TIP.2006.881969 http://doi.org/10.1109/TIP.2006.881969 .

D Gabay , B Mercier . A dual algorithm for the solution of nonlinear variational problems via finite element approximation . Comput Math Appl , 1976 . 2 ( 1 ): 17 - 40 . DOI: 10.1016/0898-1221(76)90003-1 http://doi.org/10.1016/0898-1221(76)90003-1 .

SM Gho , Y Nam , SY Zho , 等 . Three dimension double inversion recovery gray matter imaging using compressed sensing . Magn Reson Imag , 2010 . 28 ( 10 ): 1395 - 1402 . DOI: 10.1016/j.mri.2010.06.029 http://doi.org/10.1016/j.mri.2010.06.029 .

J Huang , S Zhang , D Metaxas . Efficient MR image reconstruction for compressed MR imaging . Med Image Anal , 2011 . 15 ( 5 ): 670 - 679 . DOI: 10.1016/j.media.2011.06.001 http://doi.org/10.1016/j.media.2011.06.001 .

Y Kim , MI Altbach , TP Trouard , 等 . Compressed sensing using dual-tree complex wavelet transform . 2009 . Proc. Int. Soc. Mag. Reson. Med . 2814 .

Y Kim , MS Nadar , A Bilgin . Wavelet-based compressed sensing using a Gaussian scale mixture model . IEEE Trans Image Process , 2012 . 21 ( 6 ): 3102 - 3108 . DOI: 10.1109/TIP.2012.2188807 http://doi.org/10.1109/TIP.2012.2188807 .

MS Lewicki , TJ Sejnowski . Learning overcomplete representations . Neur Comput , 2000 . 12 ( 2 ): 337 - 365 . DOI: 10.1162/089976600300015826 http://doi.org/10.1162/089976600300015826 .

L Lin . A concordance correlation coefficient to evaluate reproducibility . Biometrics , 1989 . 45 ( 1 ): 255 - 268 . DOI: 10.2307/2532051 http://doi.org/10.2307/2532051 .

Y Liu , J Cai , Z Zhan , 等 . Balanced sparse model for tight frames in compressed sensing magnetic resonance imaging . PLoS ONE , 2015 . 10 ( 4 ): e0119584.1 - e011958419 . DOI: 10.1371/journal.pone.0119584 http://doi.org/10.1371/journal.pone.0119584 .

M Lustig , D Donoho , JM Pauly . Sparse MRI: the application of compressed sensing for rapid MR imaging . Magn Reson Med , 2007 . 58 ( 6 ): 1182 - 1195 . DOI: 10.1002/mrm.21391 http://doi.org/10.1002/mrm.21391 .

M Lustig , DL Donoho , JM Santos , 等 . Compressed sensing MRI . IEEE Signal Process Mag , 2008 . 25 ( 2 ): 72 - 82 . DOI: 10.1109/MSP.2007.914728 http://doi.org/10.1109/MSP.2007.914728 .

S Mallat . A Wavelet Tour of Signal Processing: the Sparse Way (3rd Ed , 2008 . ). Academic Press, USA , .

TT Nguyen , H Chauris . Uniform discrete curvelet transform . IEEE Trans Signal Process , 2010 . 58 ( 7 ): 3618 - 3634 . DOI: 10.1109/TSP.2010.2047666 http://doi.org/10.1109/TSP.2010.2047666 .

B Ning , X Qu , D Guo , 等 . Magnetic resonance image reconstruction using trained geometric directions in 2D redundant wavelets domain and non-convex optimization . Magn Reson Imag , 2013 . 31 ( 9 ): 1611 - 1622 . DOI: 10.1016/j.mri.2013.07.010 http://doi.org/10.1016/j.mri.2013.07.010 .

B Ophir , M Lustig , M Elad . Multi-scale dictionary learning using wavelets . IEEE J Sel Topics Signal Process , 2011 . 5 ( 5 ): 1014 - 1024 . DOI: 10.1109/JSTSP.2011.2155032 http://doi.org/10.1109/JSTSP.2011.2155032 .

G Qu , D Zhang , P Yan . Information measure for performance of image fusion . Electron Lett , 2002 . 38 ( 7 ): 313 - 315 . DOI: 10.1049/el:20020212 http://doi.org/10.1049/el:20020212 .

X Qu , W Zhang , D Guo , 等 . Iterative thresholding compressed sensing MRI based on contourlet transform . Inv Probl Sci Eng , 2010 . 18 ( 6 ): 737 - 758 . DOI: 10.1080/17415977.2010.492509 http://doi.org/10.1080/17415977.2010.492509 .

X Qu , D Guo , B Ning , 等 . Undersampled MRI reconstruction with patch-based directional wavelets . Magn Reson Imag , 2012 . 30 ( 7 ): 964 - 977 . DOI: 10.1016/j.mri.2012.02.019 http://doi.org/10.1016/j.mri.2012.02.019 .

X Qu , Y Hou , F Lam , 等 . Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator . Med Image Anal , 2014 . 18 ( 6 ): 843 - 856 . DOI: 10.1016/j.media.2013.09.007 http://doi.org/10.1016/j.media.2013.09.007 .

H Rauhut , K Schnass , P Vandergheynst . Compressed sensing and redundant dictionaries . IEEE Trans Inform Theory , 2008 . 54 ( 5 ): 2210 - 2219 . DOI: 10.1109/TIT.2008.920190 http://doi.org/10.1109/TIT.2008.920190 .

S Ravishankar , Y Bresler . MR image reconstruction from highly undersampled k -space data by dictionary learning . IEEE Trans Med Imag , 2011 . 30 ( 5 ): 1028 - 1041 . DOI: 10.1109/TMI.2010.2090538 http://doi.org/10.1109/TMI.2010.2090538 .

R Rubinstein , M Zibulevsky , M Elad . Double sparsity: learning sparse dictionaries for sparse signal approximation . IEEE Trans Signal Process , 2010 . 58 ( 3 ): 1553 - 1564 . DOI: 10.1109/TSP.2009.2036477 http://doi.org/10.1109/TSP.2009.2036477 .

LI Rudin , S Osher , E Fatemi . Nonlinear total variation based noise removal algorithms . Phys D , 1992 . 60 ( 1-4 ): 259 - 268 . DOI: 10.1016/0167-2789(92)90242-F http://doi.org/10.1016/0167-2789(92)90242-F .

J Trzasko , A Manduca . Highly undersampled magnetic resonance image reconstruction via homotopic l 0 -minimization . IEEE Trans Med Imag , 2009 . 28 ( 1 ): 106 - 121 . DOI: 10.1109/TMI.2008.927346 http://doi.org/10.1109/TMI.2008.927346 .

Z Wang , AC Bovik , HR Sheikh , 等 . Image quality assessment: from error visibility to structural similarity . IEEE Trans Image Process , 2004 . 13 ( 4 ): 600 - 612 . DOI: 10.1109/TIP.2003.819861 http://doi.org/10.1109/TIP.2003.819861 .

CS Xydeas , V Petrović . Objective image fusion performance measure . Electron Lett , 2000 . 36 ( 4 ): 308 - 309 . DOI: 10.1049/el:20000267 http://doi.org/10.1049/el:20000267 .

Z Zhu , K Wahid , P Babyn , 等 . Compressed sensing-based MRI reconstruction using complex double-density dual-tree DWT . Int J Biomed Imag , 2013 . 2013 907501.1 - 90750112 . DOI: 10.1155/2013/907501 http://doi.org/10.1155/2013/907501 .

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

Chat

Address：Zhejiang University Press, 148 Tianmushan Road, Hangzhou, China Postal code：310028
Tel：+86-571-88273162 Email：fitee@zju.edu.cn
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰