[1]朱永成,陈阳,罗立民,等.基于字典学习的低剂量X-ray CT图像去噪[J].东南大学学报(自然科学版),2012,42(5):864-868.[doi:10.3969/j.issn.1001-0505.2012.05.013]
 Zhu Yongcheng,Chen Yang,Luo Limin,et al.Dictionary learning based denoising of low-dose X-ray CT image[J].Journal of Southeast University (Natural Science Edition),2012,42(5):864-868.[doi:10.3969/j.issn.1001-0505.2012.05.013]
点击复制

基于字典学习的低剂量X-ray CT图像去噪()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
42
期数:
2012年第5期
页码:
864-868
栏目:
计算机科学与工程
出版日期:
2012-09-20

文章信息/Info

Title:
Dictionary learning based denoising of low-dose X-ray CT image
作者:
朱永成1 陈阳123 罗立民123 Toumoulin Christine123
1 东南大学影像科学与技术实验室, 南京 210096; 2 中法生物医学信息研究中心, 法国雷恩 35000; 3 法国雷恩大学信号与图像处理实验室, 法国雷恩 35042
Author(s):
Zhu Yongcheng1 Chen Yang123 Luo Limin123 Toumoulin Christine123
1 Laboratory of Image Science and Technology, Southeast University, Nanjing 210096, China
2 Centre de Recherche en Information Biomédicale Sino-Français, Rennes 35000, France
3 Laboratoire Traitement du Signal et de L’Image, Université de Rennes 1, Rennes 35042, France
关键词:
K-SVD算法 低剂量CT 字典学习 稀疏表示
Keywords:
k-means singular value decomposition algorithm low-dose computed-tomography learning dictionary sparse representation
分类号:
TP391.4
DOI:
10.3969/j.issn.1001-0505.2012.05.013
摘要:
介绍了一种基于字典学习的去噪方法,并将其应用于降低低剂量CT图像噪声水平的研究.针对体模图像和病人图像,分别选择低剂量CT图像和正常剂量CT图像作为训练样本,采用K-SVD算法,通过迭代学习构建图像字典; 然后,结合正交匹配跟踪算法,实现图像稀疏表示,稀疏成分对应于图像的有用信息,其他成分对应于图像噪声; 最后,依据图像的稀疏成分重建图像,达到去除噪声的目的.实验结果表明:字典的大小、稀疏表示的约束条件等参数会显著影响所提算法的去噪结果; 相比低剂量CT图像,将正常剂量CT图像作为训练样本可以得到更好的去噪结果; 在相同的噪声水平下,所提算法与传统图像去噪算法相比可以更好地去除图像噪声,且保留了图像的细节信息.
Abstract:
A dictionary learning based denoising method is introduced to eliminate the noise in low-dose computed-tomography(LDCT)image. Aiming at the phantom and patient images, the k-means singular value decomposition(K-SVD)algorithm is adopted to train image dictionary iteratively based on LDCT and normal-dose CT(NDCT)images. Then, based on the orthogonal matching pursuit algorithm, the sparse representation decomposes the noise image into sparse component which is related to image information and remains which are regarded as noise. Finally, noises can be suppressed by reconstructing image only with its sparse components. The experimental results show that the performance of the proposed method is strongly affected by the dictionary size and the constraints for sparsity in dictionary training. The better performance can be achieved when training samples are extracted from NDCT image instead of LDCT image. Under the same noise level, compared with the traditional de-noising methods, the proposed method is more effective in suppressing noise and improving the visual effect while maintaining more diagnostic image details.

参考文献/References:

[1] Yazdi M,Beaulieu L.Artifacts in spiral X-ray CT scanners:problems and solutions [J].Proc World Acad Sci Eng Technol,2007,26(3):376-380.
[2] Wang J,Lu H,Wen J,et al.Multiscale penalized weighted least-squares sinogram restoration for low-dose X-Ray computed tomography [J].IEEE Transactions on Biomedical Engineering,2008,55(3):1022-1031.
[3] Rust G F,Aurich V,Reiser M.Noise/dose reduction and image improvements in screening virtual colonoscopy with tube currents of 20mAs with nonlinear Gaussian filter chains [J].Proc SPIE Int Soc Opt Eng,2002,4683:186-197.
[4] Olshausen B A,Field D J.Emergence of simple-cell receptive field properties by learning a sparse code for natural images [J].Nature,1996,381(6583):607-609.
[5] Starck J L,Candes E J,Donoho D L.The curvelet transform for image denoising [J].IEEE Transactions on Image Processing,2002,11(6):670-684.
[6] Wakin M B,Romberg J K,Choi H,et al.Wavelet-domain approximation and compression of piecewise smooth images [J].IEEE Transactions on Image Processing,2006,15(5):1071-1087.
[7] Needell D,Tropp J A.CoSaMP:iterative signal recovery from incomplete and inaccurate samples [J].Applied and Computational Harmon Analysis.2009,26(3):301-321.
[8] Engan K,Aase S O,Hankon H J.Method of optimal directions for frame design [C] // Proceedings of 1999 IEEE International Conference on Acoustics,Speech and Signal Processing.Phoenix,AZ,USA,1999:2443-2446.
[9] Aharon M,Elad M,Bruckstein A.The K-SVD:an algorithm for designing overcomplete dictionaries for sparse representation [J].IEEE Transactions on Signal Processing,2006,54(11):4311-4322.
[10] Blumensath T,Davies M.Sparse and shift-invariant representations of music [J].IEEE Transactions on Speech Audio Processing,2006,14(1):50-55.
[11] Rubinstein R,Zibulevsky M,Elad M.Double sparsity:learning sparse dictionaries for sparse signal approximation [J].IEEE Transactions on Signal Processing,2010,58(3):1553-1564.
[12] Elad M,Aharon M.Image denoising via sparse and redundant representations over learned dictionaries [J].IEEE Transactions on Image Processing,2006,15(12):3736-3745.

备注/Memo

备注/Memo:
作者简介: 朱永成(1988—),男,硕士生; 陈阳(联系人),男,博士,chenyang.list@seu.edu.cn.
引文格式: 朱永成,陈阳,罗立民,等.基于字典学习的低剂量X-ray CT图像去噪[J].东南大学学报:自然科学版,2012,42(5):864-868. [doi:10.3969/j.issn.1001-0505.2012.05.013]
更新日期/Last Update: 2012-09-20