基于结构联合字典的肺部LDCT图像降噪

doi:10.3969/j.issn.0372-2112.2018.06.025

电子学报 ›› 2018, Vol. 46 ›› Issue (6): 1445-1453.DOI: 10.3969/j.issn.0372-2112.2018.06.025

基于结构联合字典的肺部LDCT图像降噪

代晓婷, 龚敬, 聂生东

上海理工大学医疗器械与食品学院, 上海 200093

收稿日期:2016-11-30 修回日期:2017-06-12 出版日期:2018-06-25
- 通讯作者:
- 聂生东
- 作者简介:
- 代晓婷,女,1993年10月出生于河南驻马店.2015年于新乡医学院生物医学工程专业获得学士学位,现为上海理工大学硕士研究生.主要研究方向为:医学图像处理.E-mail:dxting0204ls@163.com;龚敬,男,1990年6月出生于河南南阳.2013年至今在上海理工大学硕博连读,攻读博士学位.主要研究方向为:医学图像处理与分析.E-mail:gongjing1990@163.com
- 基金资助:
- 国家自然科学基金 (No.60972122）; 上海市自然科学基金 (No.14ZR1427900）

Low-Dose Lung CT Image Denoising Using Joint Structural Dictionary

DAI Xiao-ting, GONG Jing, NIE Sheng-dong

School of Medical Instrument and Food Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China

Received:2016-11-30 Revised:2017-06-12 Online:2018-06-25 Published:2018-06-25
- Corresponding author:
- NIE Sheng-dong
- Supported by:
- National Natural Science Foundation of China (No.60972122); National Natural Science Foundation of Shanghai Municipality, China (No.14ZR1427900)

摘要/Abstract

摘要： 肺部LDCT（Low-Dose Computed Tomography）图像中噪声及条状伪影等异常显著，顶部和底部图像尤为严重.为提高整个肺部LDCT图像的质量，本文提出一种基于结构联合字典的图像降噪方法.首先，利用肺部CT图像的灰度特点，将HRCT（High Resolution Computed Tomography）图像块分类并训练，获得4类字典，通过计算原子的信息熵和HOG（Histogram of Oriented Gradient）特征，得到相应的结构字典，进而构造出结构联合字典；然后，在对肺部LDCT图像进行非局部均值滤波的基础上，将结构联合字典作为全局字典，对图像进行稀疏表示及重构，获得降噪后的图像.为验证算法有效性，选用模拟和临床两类数据进行实验，并与KSVD、AS-LNLM、BF-MCA等3种算法对比.对比发现，本文算法在去除噪声和条状伪影以及保留细节方面效果较好，特别是对序列顶层和底层图像处理优势更加明显.该方法能够显著提升整个肺部LDCT图像的质量.

关键词: 肺部低剂量CT图像, 联合字典, 稀疏表示, 图像降噪

Abstract: Noise and streak artifacts are serious in low-dose CT (LDCT) images of lung,especially for the top and bottom layers.To improve the quality of LDCT sequential images,we proposed a method to remove noise and streak artifacts by using a joint structural dictionary.Firstly,according to the gray-scale features of lung CT image,we divided high resolution CT (HRCT) images into four groups,and obtained four dictionaries for each group by dictionary training.Secondly,computed the information entropy and the histogram of oriented gradient (HOG) of each dictionary atom.And then obtained the structure dictionary of corresponding group by feature clustering.Finally,the joint structural dictionary can be obtained by combining these four structure dictionaries.On the basis of non-local mean filtering for LDCT images,the joint structural dictionary is used as a global dictionary to get the denoised image by sparse representation and reconstruction.In order to validate the effectiveness of the proposed method,simulated and clinical LDCT data are used.Compared with reported methods (KSVD,AS-LNLM and BF-MCA),our method performed better in denoising,streak artifact-removing and details-preserving for the whole LDCT scans,especially for the top and bottom layers.The proposed algorithm can significantly improve the quality of lung LDCT images.

Key words: low-dose lung CT image, joint dictionary, sparse representation, image denoising

中图分类号:

TP391

代晓婷, 龚敬, 聂生东. 基于结构联合字典的肺部LDCT图像降噪[J]. 电子学报, 2018, 46(6): 1445-1453.

DAI Xiao-ting, GONG Jing, NIE Sheng-dong . Low-Dose Lung CT Image Denoising Using Joint Structural Dictionary[J]. Acta Electronica Sinica, 2018, 46(6): 1445-1453.

参考文献

[1] Pierce D A,Preston D L.Radiation-related cancer risks at low doses among atomic bomb survivors[J].Radiation Research,2000,154(2):178-186.
[2] Yu L,Liu X,Leng S,et al.Radiation dose reduction in computed tomography:techniques and future perspective[J].Imaging in Medicine,2009,1(1):65-84.
[3] Russi E W.Lung cancer screening has the potential to safe lives,but shall we do it?[J].Swiss Medical Weekly,2011,141:w13185.
[4] Mayo J R,Hartman T E,Lee K S,et al.CT of the chest:minimal tube current required for good image quality with the least radiation dose[J].American Journal of Roentgenology,1995,164(3):603-607.
[5] Li T,Li X,Wang J,et al.Nonlinear sinogram smoothing for low-dose X-ray CT[J].IEEE Transactions on Nuclear Science,2004,51(5):2505-2513.
[6] Hu S,Liao Z,Chen W.Sinogram restoration for low-dosed X-ray computed tomography using fractional-order perona-malik diffusion[J].Mathematical Problems in Engineering,2012,2012(1):243-253.
[7] Liao Z,Hu S,Li M,et al.Noise estimation for single-slice sinogram of low-dose X-ray computed tomography using homogenous patch[J].Mathematical Problems in Engineering,2012,2012(2):208-212.
[8] Tang J,Nett B E,Chen G-H.Performance comparison between total variation (TV)-based compressed sensing and statistical iterative reconstruction algorithms[J].Physics in Medicine and Biology,2009,54(19):5781-5804.
[9] Lee H,Xing L,Davidi R,et al.Improved compressed sensing-based cone-beam CT reconstruction using adaptive prior image constraints[J].Physics in Medicine and Biology,2012,57(8):2287-307.
[10] 张权.低剂量X线CT重建若干问题研究[D].南京:东南大学,2015. ZHANG Quan.A study on some problems in image reconstruction for low-dose CT system[D].Nanjing:Southeast University,2015.(in Chinese)
[11] Buades A,Coll B,Morel J M.A non-local algorithm for image denoising[A].Computer Vision and Pattern Recognition,2005.CVPR 2005.IEEE Computer Society Conference on[C].San Diego,CA,USA:IEEE,2005.60-65.
[12] Dabov K,Foi A,Katkovnik V,et al.Image denoising by sparse 3-D transform-domain collaborative filtering[J].IEEE Transactions on Image Processing,2007,16(8):2080-2095.
[13] 毕一鸣,马建华,路利军,等.基于标准剂量CT图像非局部权值先验的低剂量图像恢复[J].电子学报,2010,38(5):1146-1151. BI Yi-ming,MA Jian-hua,LU Li-jun,et al.Low-dose CT image restoration using a non-local weights prior from previous normal-dose scan image[J].Acta Electrica Sinica,2010,38(5):1146-1151.(in Chinese)
[14] Ha S,Mueller K.Low dose CT image restoration using a database of image patches[J].Physics in Medicine and Biology,2015,60(2):869.
[15] Xu W,Ha S,Mueller K.Database-assisted low-dose CT image restoration[J].Medical Physics,2013,40(3):31109.
[16] 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. ZHU Yong-cheng,CHEN Yang,LUO Li-min,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.(in Chinese)
[17] Chen Y,Yang Z,Hu Y,et al.Thoracic low-dose CT image processing using an artifact suppressed large-scale nonlocal means[J].Physics in Medicine and Biology,2012,57(9):2667-2688.
[18] Chen Y,Shi L,Feng Q,et al.Artifact suppressed dictionary learning for low-dose CT image processing[J].IEEE Transactions on Medical Imaging,2014,33(12):2271-2292.
[19] Cui X Y,Gui Z G,Zhang Q,et al.Learning-based artifact removal via image decomposition for low-dose CT image processing[J].IEEE Transactions on Nuclear Science,2016,63(3):1860-1873.
[20] Ravishankar S,Bresler Y.MR image reconstruction from highly undersampled k-space data by dictionary learning[J].IEEE Transactions on Medical Imaging,2011,30(5):1028-1041.
[21] Aharon M,Elad M,Bruckstein A.K-SVD:An algorithm for designing overcomplete dictionaries for sparse representation[J].IEEE Transactions on Signal Processing,2006,54(11):4311-4322.
[22] 蔡泽民,赖剑煌.一种基于超完备字典学习的图像去噪方法[J].电子学报,2009,37(2):347-350. CAI Ze-min,LAI Jian-huang.An over-complete learned dictionary-based image de-noising method[J].Acta Electronica Sinica,2009,37(2):347-350.(in Chinese)
[23] Dong W,Zhang L,Shi G,et al.Image deblurring and super-resolution by adaptive sparse domain selection and adaptive regularization[J].IEEE Transactions on Image Processing,2010,20(7):1838-1857.
[24] Kang L W,Lin C W,Fu Y H.Automatic single-image-based rain streaks removal via image decomposition[J].IEEE Transactions on Image Processing,2012,21(4):1742-1755.
[25] Massoumzadeh P,Don S,Hildebolt C F,et al.Validation of CT dose-reduction simulation[J].Medical Physics,2009,36(1):174-189.
[26] Horiuchi T,Yamamoto S,Murase K.Development of DICOM image-based CT low dose simulator using fan-beam transform[J].Technology and Health Care,2013,21(5):441-454.
[27] Ai D,Yang J,Fan J,et al.Adaptive tensor-based principal component analysis for low-dose CT image denoising[J].Plos One,2015,10(5):e0126914.

基于结构联合字典的肺部LDCT图像降噪

Low-Dose Lung CT Image Denoising Using Joint Structural Dictionary

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	冯西安, 寇思玮, 谭伟杰, 毕杨. 水声信号处理中的稀疏表示理论及应用[J]. 电子学报, 2021, 49(9): 1840-1851.
[2]	禤韵怡, 杨春玲. 基于帧间组稀疏的两阶段递归增强视频压缩感知重构网络[J]. 电子学报, 2021, 49(3): 435-442.
[3]	夏楠, 高紫俊, 李博, 王珏. 一种基于循环稀疏表示的同频带干扰抑制及发射源定位方法[J]. 电子学报, 2021, 49(1): 8-13.
[4]	郑学炜, 杨春玲, 禤韵怡. CVS中基于视频运动特征的多假设-双稀疏重构算法[J]. 电子学报, 2020, 48(2): 249-257.
[5]	脱婷, 马慧芳, 李志欣, 赵卫中. 熵权约束稀疏表示的短文本分类算法[J]. 电子学报, 2020, 48(11): 2131-2137.
[6]	周浦城, 张杰, 薛模根, 尹璋堃. 基于卷积分析稀疏表示和相位一致性的低照度图像增强[J]. 电子学报, 2020, 48(1): 180-188.
[7]	徐少平, 李崇禧, 林官喜, 唐祎玲, 胡凌燕. 基于主成分分析与深度神经网络的快速噪声水平估计算法[J]. 电子学报, 2019, 47(2): 274-281.
[8]	田文飚, 芮国胜, 董道广, 康健. 基于盲自适应KLT的蒸发波导压缩感知方法[J]. 电子学报, 2018, 46(9): 2068-2074.
[9]	王鹏, 邱天爽, 金芳晓, 夏楠, 李景春. 脉冲噪声下基于稀疏表示的韧性DOA估计方法[J]. 电子学报, 2018, 46(7): 1537-1544.
[10]	和志杰, 杨春玲, 汤瑞东. 视频压缩感知中基于结构相似的帧间组稀疏表示重构算法研究[J]. 电子学报, 2018, 46(3): 544-553.
[11]	李鑫, 孙晋, 肖甫. 基于弹性网稀疏表示的芯片参数成品率估算方法[J]. 电子学报, 2017, 45(12): 2917-2924.
[12]	陈小龙, 关键, 于晓涵, 何友. 雷达动目标短时稀疏分数阶傅里叶变换域检测方法[J]. 电子学报, 2017, 45(12): 3030-3036.
[13]	秦晓燕, 袁广林, 李从利, 张旭. 一种快速鲁棒的视频序列运动目标检测方法[J]. 电子学报, 2017, 45(10): 2355-2361.
[14]	唐意东, 黄树彩, 薛爱军. 面向目标检测基于稀疏表示的波段选择方法[J]. 电子学报, 2017, 45(10): 2368-2374.
[15]	詹曙, 方琪, 杨福猛, 常乐乐, 闫婷. 基于耦合特征空间下改进字典学习的图像超分辨率重建[J]. 电子学报, 2016, 44(5): 1189-1195.