基于非下采样轮廓波的MRI图像的压缩感知重构

doi:10.11896/j.issn.1002-137X.2015.11.061

摘要/Abstract

摘要： 压缩感知是一种全新的信息采集与处理的理论框架,借助信号内在的稀疏性或可压缩性,可从小规模的线性、非自适应的测量值中通过非线性优化的方法精确重构信号。压缩感知以远低于奈奎斯特频率的采样频率,在压缩成像系统、医学图像处理等领域有着广阔的应用前景。提出算法采用非下采样轮廓波变换稀疏表达原始图像,通过傅立叶矩阵进行测量,最后采用迭代软阈值算法实现医学MRI图像的压缩感知重构。以峰值信噪比、互信息、伪影功率为评价指标,比较小波变换、频率局部化轮廓波变换以及非下采样轮廓波变换三者的压缩感知重构效果。实验结果表明,无论采样率设置如何变化,提出算法在峰值信噪比、原始信息保留比例以及重构精度等方面均具有明显优势,在快速医学成像领域具有广阔的应用前景。

关键词: 压缩感知,非下采样轮廓波变换,图像重构,医学图像,MRI

Abstract: Compressed sensing is a newly developed theoretical framework for information acquisition and processing.Using the non-linear optimization methods,the signals can be recovered accurately from fewer linear and non-adaptive measurements by taking advantages of the sparsity or compressibility inherent in real world signals.Compressed sensing represents compressible signals at a sampling rate significantly below the Nyquist rate,and it has been applied in compressive imaging and medical image processing.The flow chart of our algorithm is as follows.The nonsubsampled con-tourlet transform is applied to sparsely represent the original image,then the iterative soft-thresholding algorithm is used to reconstruct the medical MRI images based on Fourier matrix as the measurement matrix.The peak signal to noise rate (PSNR),mutual information (MI) and artifacts power (AP) are used to compare the reconstruction effects of wavelet transform(WT),sharp frequency localization contourlet transform (SFLCT) and nonsubsampled contourlet transform (NSCT).Experimental results demonstrate that our method is superior to the other two methods in PSNR,remained proportion of original information and reconstruction precision.Our algorithm can be extended and widely used in rapid medical imaging technology.

Key words: Compressed sensing,Nonsubsampled contourlet transform,Image reconstruction,Medical image,MRI

陈秀梅,王敬时,王伟,赵扬,汤敏. 基于非下采样轮廓波的MRI图像的压缩感知重构[J]. 计算机科学, 2015, 42(11): 299-304. https://doi.org/10.11896/j.issn.1002-137X.2015.11.061

CHEN Xiu-mei, WANG Jing-shi, WANG Wei, ZHAO Yang and TANG Min. Compressed Sensing Reconstruction of MRI Images Based on Nonsubsampled Contourlet Transform[J]. Computer Science, 2015, 42(11): 299-304. https://doi.org/10.11896/j.issn.1002-137X.2015.11.061

参考文献

[1] 石光明,刘丹华,高大化,等.压缩感知理论及其研究进展[J].电子学报,2009,37(5):1070-1081 Shi Guang-ming,Liu Dan-hua,Gao Da-hua,et al.Advances in Theory and Applicantion of Compressed Sensing[J].Acta Electronic Sinica,2009,37(5):1070-1081
[2] 戴琼海,付长军,季向阳.压缩感知研究[J].计算机学报,2011,34(3):425-434 Dai Qiong-hai,Fu Chang-jun,Ji Xiang-yang.Research on Compressed Sensing[J].Chinese Journal of Computers,2011,34(3):425-434
[3] Donoho David L.Compressed sensing[J].IEEE Transactions on Information Theory,2006,52(4):1289-1306
[4] 李树涛,魏丹.压缩传感综述[J].自动化学报,2009,35(11):1369-1377 Li Shu-tao,Wei Dan.A Survey on Compressed Sensing[J].Acta Automatica Sinica,2009,35(11):1369-1377
[5] 刘芳,武娇,杨淑媛,等.结构化压缩感知研究进展[J].自动化学报,2013,39(12):1980-1995 Liu Fang,Wu Jiao,Yang Shu-yuan,et al.Research Advances on Structured Compressive Sensing[J].Acta Automatica Sinica,2013,39(12):1980-1995
[6] 焦鹏飞,李亮,赵骥.压缩感知在医学图像重建中的最新进展[J].CT理论与应用研究,2012,21(1):133-147 Jiao Peng-fei,Li Liang,Zhao Ji.New advances of compressed sensing in medical image reconstruction[J].CT Theory and Applications,2012,21(1):133-147
[7] Lustig M,Donoho D,Pauly J M.Sparse MRI:The application of compressed sensing for rapid MR imaging[J].Magnetic Resonance in Medicine,2007,58(6):1182-1195
[8] Zhu Zan-gen,Yang Ran,Zhang Jing-xin,et al.Compressed sensing MRI by two-dimensional wavelet filter banks[C]∥2011 7th International Workshop on Multidimensional (nD) Systems (nDs).IEEE,2011:1-6
[9] Wang Hui-yuan,Vieira J.2-D wavelet transforms in the form of matrices and application in compressed sensing[C]∥2010 8th World Congress on Intelligent Control and Automation (WCICA).IEEE,2010:35-39
[10] 岑翼刚,陈晓方,岑丽辉,等.基于单层小波变换的压缩感知图像处理 [J].通信学报,2010,31(8):52-55 Cen Yi-gang,Chen Xiao-fang,Cen Li-hui,et al.Compressed sensing based on the single layer wavelet transform for image processing[J].Journal on Communications,2010,31(8):52-55
[11] Zhu Zan-gen,Wahid K,Babyn P,et al.Compressed sensing-based MRI reconstruction using complex double-density dual-tree DWT[J].Journal of Biomedical Imaging,2013,2013:1-12
[12] Liu Jia-feng,Li Hai-yun,Shi Hong-li.MR Image Reconstruction Based on Compressed Sensing[J].International Journal of Digi-tal Content Technology & its Applications,2012,6(8):135-143
[13] 李林,孔令富,练秋生.基于轮廓波维纳滤波的图像压缩传感重构[J].仪器仪表学报,2009,30(10):2051-2056Li Lin,Kong Ling-fu,Lian Qiu-sheng.Image compressed sen-sing reconstruction based on contourlet winner filtering[J].Chinese Journal of Scientific Instrument,2009,30(10):2051-2056
[14] Qu Xiao-bo,Zhang Wei-ru,Guo Di,et al.Iterative thresholding compressed sensing MRI based on contourlet transform[J].Inverse Problems in Science and Engineering,2010,18(6):737-758
[15] Qu Xiao-bo,Guo Di,Chen Zhong,et al.Compressed sensingMRI based on nonsubsampled contourlet transform[C]∥IEEE International Symposium on IT in Medicine and Education,2008(ITME 2008).IEEE,2008:693-696
[16] 汤敏,陈峰.轮廓波及曲波和小波变换用于显微图像消噪的比较[J].中国组织工程研究与临床康复,2011,15(22):4094-4097 Tang Min,Chen Feng.Comparison of microscopy image denoi-sing effects based on contourlet,curvelet and wavelet transform[J].Journal of Clinical Rehabilitative Tissue Engineering Research,2011,15(22):4094-4097
[17] Do M N,Vetterli M.The contourlet transform:an efficient directional multiresolution image representation[J].IEEE Transactions on Image Processing,2005,14(12):2091-2106
[18] 焦李成,侯彪,王爽,等.图像多尺度几何分析理论与应用:后小波分析理论与应用[M].西安:西安电子科技大学出版社,2008:280-289 Jiao Li-cheng,Hou Biao,Wang Shuang,et al.Image multiscale geometric anlysis:theory and applications beyond wavelets[M].Xi’an:Xi’an University of Electronic Science and Technology Press,2008:280-289
[19] Lu Yue,Do M N.A new contourlet transform with sharp frequency localization[C]∥2006 IEEE International Conference on Image Processing.IEEE,2006:1629-1632
[20] 蒋媛.基于多尺度几何分析的SAR图像去噪和融合[D].成都:电子科技大学,2010 Jiang Yuan.SAR Image denoising and fusing based on multiscale geometric anlysis[D].Chengdu:University of Electronic Science and Technology of China,2010
[21] Zhou Jian-ping,Cunha A L,Do M N.Nonsubsampled contourlet transform:construction and application in enhancement[C]∥IEEE International Conference on Image Processing,2005(ICIP 2005).IEEE,2005:469-472
[22] 张宗念,李金徽,黄仁泰.迭代硬阈值压缩感知重构算法——IIHT[J].计算机应用,2011,31(8):2123-2125 Zhang Zong-nian,Li Jin-hui,Huang Ren-tai.IIHT:New improved iterative hard thresholding algorithm for compressive sensing[J].Journal of Computer Applications,2011,31(8):2123-2125
[23] Herrity K K,Gilbert A C,Tropp J A.Sparse approximation via iterative thresholding[C]∥ICASSP 2006 Proceedings of IEEE International Conference on Acoustics,Speech and Signal Processing,2006.IEEE,2006:624-627
[24] 吴巧玲,倪林,何德龙.基于非下采样Contourlet变换的压缩感知图像重建[J].中国科学技术大学学报,2012,42(2):87-91 Wu Qiao-ling,Ni Lin,He De-long.Compressed sensing based on nonsubsampled contourlet transform for image reconstruction[J].Journal of University of Science and Technology of China,2012,42(2):87-91

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed