高级搜索

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

一种基于深度学习的自适应医学超声图像去斑方法

付晓薇 杨雪飞 陈芳 李曦

付晓薇, 杨雪飞, 陈芳, 李曦. 一种基于深度学习的自适应医学超声图像去斑方法[J]. 电子与信息学报, 2020, 42(7): 1782-1789. doi: 10.11999/JEIT190580
引用本文: 付晓薇, 杨雪飞, 陈芳, 李曦. 一种基于深度学习的自适应医学超声图像去斑方法[J]. 电子与信息学报, 2020, 42(7): 1782-1789. doi: 10.11999/JEIT190580
Xiaowei FU, Xuefei YANG, Fang CHEN, Xi LI. An Adaptive Medical Ultrasound Images Despeckling Method Based on Deep Learning[J]. Journal of Electronics and Information Technology, 2020, 42(7): 1782-1789. doi: 10.11999/JEIT190580
Citation: Xiaowei FU, Xuefei YANG, Fang CHEN, Xi LI. An Adaptive Medical Ultrasound Images Despeckling Method Based on Deep Learning[J]. Journal of Electronics and Information Technology, 2020, 42(7): 1782-1789. doi: 10.11999/JEIT190580

一种基于深度学习的自适应医学超声图像去斑方法

doi: 10.11999/JEIT190580
基金项目: 国家自然科学基金(61873323),材料成形与模具技术国家重点实验室开放课题研究基金(P2018-016),湖北省自然科学基金(2017CFB506),智能信息处理与实时工业系统湖北省重点实验室开放课题项目(2016znss02A, znxx2018ZD01),大学生科技创新基金项目(18ZRA076)
详细信息
    作者简介:

    付晓薇:女,1977年生,教授,研究方向为图像处理、计算机视觉、信号处理与分析

    杨雪飞:女,1994年生,硕士生,研究方向为图像处理、深度学习

    陈芳:女,1972年生,研究方向为肌骨超声图像的调节

    李曦:男,1977年生,教授,研究方向为计算机应用,复杂非线性系统的建模和控制

    通讯作者:

    付晓薇 fxw_wh0409@wust.edu.cn

  • 中图分类号: TN911.73

An Adaptive Medical Ultrasound Images Despeckling Method Based on Deep Learning

Funds: The National Natural Science Foundation of China (61873323), The Open Fund Project of State Key Laboratory of Material Processing and Die & Mould Technology (P2018-016), The Natural Science Foundation of Hubei Provincial (2017CFB506), The Open Fund Project of Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System (2016znss02A, znxx2018ZD01), The University Student Science and Technology Innovation Fund Project (18ZRA076)
  • 摘要: 针对传统医学超声图像去斑方法的不足,该文提出一种自适应多曝光融合框架和前馈卷积神经网络模型图像去斑方法。首先,制作超声图像训练数据集;然后,提出一种自适应增强因子的多曝光融合框架,增强图像进行有效特征提取;最后,通过网络训练去斑模型并获得去斑后的图像。实验结果表明,该文较已有的方法,能更有效地滤除医学超声图像中的斑点噪声并更多的保留图像细节。
  • 图  1  残差网络的基本结构

    图  2  本文流程图

    图  3  网络结构图

    图  4  模拟斑点肝脏超声图像1实验比较

    图  5  模拟斑点肝脏超声图像2实验比较

    图  6  真实医学超声图像去斑后结果比较

    表  1  模拟斑点肝脏超声图像1不同方法PSNR结果(dB)

    方法斑点噪声的标准差σ
    0.50.60.70.80.9
    BI-DTCWT35.422533.846132.536831.426530.3688
    NPSM34.582732.957331.536630.325029.2056
    NL-means34.928934.193433.355432.565831.6134
    BM3D36.170135.755235.248534.895134.2035
    Local_entropy_qsp36.781236.108335.436335.072634.5014
    DnCNN35.770135.839435.818035.676935.3885
    本文方法36.720336.713936.602536.356835.9492
    下载: 导出CSV

    表  4  模拟斑点肝脏超声图像2不同方法$\beta $结果

    方法斑点噪声的标准差σ
    0.50.60.70.80.9
    BI-DTCWT0.70780.63590.56120.50990.4661
    NPSM0.68300.61970.54790.49900.4517
    NL-means0.71910.67610.60370.54490.4899
    BM3D0.80300.79500.78260.76830.7355
    Local_entropy_qsp0.82630.80900.77870.75670.7384
    DnCNN0.92860.92380.91560.90290.8812
    本文方法0.93940.93250.92170.96530.8836
    下载: 导出CSV

    表  2  模拟斑点肝脏超声图像2不同方法PSNR结果(dB)

    方法斑点噪声的标准差σ
    0.50.60.70.80.9
    BI-DTCWT31.047729.540928.085627.434226.2056
    NPSM31.537430.098528.674527.669926.6843
    NL-means32.736031.753930.486029.510528.4174
    BM3D33.878633.309632.543632.019931.2079
    Local_entropy_qsp34.315733.242632.170631.532930.8599
    DnCNN34.976035.038234.849734.385133.6562
    本文方法35.928035.917035.628935.030134.1677
    下载: 导出CSV

    表  3  模拟斑点肝脏超声图像1不同方法$\beta $结果

    方法斑点噪声的标准差σ
    0.50.60.70.80.9
    BI-DTCWT0.64160.56110.48230.42910.3846
    NPSM0.59720.51540.43520.38170.3393
    NL-means0.45220.41020.35640.32620.2949
    BM3D0.59690.58200.56850.54770.5016
    Local_entropy_qsp0.65400.62870.59910.58420.5621
    DnCNN0.78030.77260.75950.73930.7106
    本文方法0.81280.80110.78310.75640.7208
    下载: 导出CSV

    表  5  真实斑点超声图像不同方法ENL结果

    方法ENL等效视数值
    BI-DTCWT61.2209
    NPSM64.6016
    NL-means109.5584
    BM3D93.4877
    Local_entropy_qsp79.1016
    DnCNN132.9184
    本文方法134.3287
    下载: 导出CSV

    表  6  50张真实斑点超声图像不同方法ENL平均值比较

    方法ENL等效视数值平均值
    BI-DTCWT75.5182
    NPSM75.5941
    NL-means110.6393
    BM3D110.9127
    Local_entropy_qsp93.7911
    DnCNN140.3622
    本文方法147.0689
    下载: 导出CSV
  • [1] KANAYAMA Y and YANO M. Ultrasound diagnosis apparatus and ultrasound imaging method[P]. USA Patent, 10231710, 2019.
    [2] ZHOU Yingyue, ZANG Hongbin, XU Su, et al. An iterative speckle filtering algorithm for ultrasound images based on bayesian nonlocal means filter model[J]. Biomedical Signal Processing and Control, 2019, 48: 104–117. doi:  10.1016/j.bspc.2018.09.011
    [3] JOEL T and SIVAKUMAR R. An extensive review on Despeckling of medical ultrasound images using various transformation techniques[J]. Applied Acoustics, 2018, 138: 18–27. doi:  10.1016/j.apacoust.2018.03.023
    [4] 沈民奋, 陈婷婷, 张琼, 等. 医用超声图像散斑去噪方法综述[J]. 中国医疗器械信息, 2013, 19(3): 17–22. doi:  10.3969/j.issn.1006-6586.2013.03.003

    SHEN Minfen, CHEN Tingting, ZHANG Qiong, et al. The review of speckle denoising in medical ultrasound imaging[J]. China Medical Device Information, 2013, 19(3): 17–22. doi:  10.3969/j.issn.1006-6586.2013.03.003
    [5] KUAN D, SAWCHUK A, STRAND T, et al. Adaptive restoration of images with speckle[J]. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1987, 35(3): 373–383. doi:  10.1109/TASSP.1987.1165131
    [6] 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. doi:  10.1109/TIP.2007.901238
    [7] 肖佳, 张俊华, 梅礼晔. 改进的三维块匹配去噪算法[J]. 计算机科学, 2019, 46(6): 288–294. doi:  10.11896/j.issn.1002-137X.2019.06.043

    XIAO Jia, ZHANG Junhua, and MEI Liye. Improved block-matching 3D denoising algorithm[J]. Computer Science, 2019, 46(6): 288–294. doi:  10.11896/j.issn.1002-137X.2019.06.043
    [8] PERONA P and MALIK J. Scale-space and edge detection using anisotropic diffusion[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1990, 12(7): 629–639. doi:  10.1109/34.56205
    [9] YU Yongjian and ACTON S T. Speckle reducing anisotropic diffusion[J]. IEEE Transactions on Image Processing, 2002, 11(11): 1260–1270. doi:  10.1109/TIP.2002.804276
    [10] TIAN Jing and CHEN Li. Image despeckling using a non-parametric statistical model of wavelet coefficients[J]. Biomedical Signal Processing and Control, 2011, 6(4): 432–437. doi:  10.1016/j.bspc.2010.11.006
    [11] SENDUR L and SELESNICK I W. Bivariate shrinkage functions for wavelet-based denoising exploiting interscale dependency[J]. IEEE Transactions on Signal Processing, 2002, 50(11): 2744–2756. doi:  10.1109/TSP.2002.804091
    [12] BURGER H C, SCHULER C J, and HARMELING S. Image denoising: Can plain neural networks compete with BM3D?[C]. 2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, USA, 2012: 2392–2399.
    [13] SCHMIDT U and ROTH S. Shrinkage fields for effective image restoration[C]. The IEEE Conference on Computer Vision and Pattern Recognition, Columbus, USA, 2014: 2774–2781.
    [14] CHEN Yunjin and POCK T. Trainable nonlinear reaction diffusion: A flexible framework for fast and effective image restoration[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1256–1272. doi:  10.1109/TPAMI.2016.2596743
    [15] MAO Xiaojiao, SHEN Chunhua, and YANG Yubin. Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections[C]. Advances in Neural Information Processing Systems, Red Hook, USA, 2016: 2802–2810.
    [16] ZHANG Kai, ZUO Wangmeng, CHEN Yunjin, et al. Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising[J]. IEEE Transactions on Image Processing, 2017, 26(7): 3142–3155. doi:  10.1109/TIP.2017.2662206
    [17] NADEEM M, HUSSAIN A, and MUNIR A. Fuzzy logic based computational model for speckle noise removal in ultrasound images[J]. Multimedia Tools and Applications, 2019, 78(9): 18531–18548.
    [18] 吕晓琪, 吴凉, 谷宇, 等. 基于深度卷积神经网络的低剂量CT肺部去噪[J]. 电子与信息学报, 2018, 40(6): 1353–1359. doi:  10.11999/JEIT170769

    LÜ Xiaoqi, WU Liang, GU Yu, et al. Low dose CT lung denoising model based on deep convolution neural network[J]. Journal of Electronics &Information Technology, 2018, 40(6): 1353–1359. doi:  10.11999/JEIT170769
    [19] YING Zhenqiang, LI Ge, REN Yurui, et al. A new image contrast enhancement algorithm using exposure fusion framework[C]. The 17th International Conference on Computer Analysis of Images and Patterns, Ystad, Sweden, 2017: 36–46.
    [20] ZHENG D, WANG J, and XIAO Z. Image enhancement based on local standard deviation[J]. Journal of Information and Computational Science, 2005, 2(2): 429–437.
    [21] JIFARA W, JIANG Feng, RHO S, et al. Medical image denoising using convolutional neural network: A residual learning approach[J]. The Journal of Supercomputing, 2019, 75(2): 704–718. doi:  10.1007/s11227-017-2080-0
    [22] SIMONYAN K and ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. arXiv, 2014, 1409.1556.
    [23] VEDALDI A and LENC K. MatconvNet: Convolutional neural networks for MATLAB[C]. The 23rd ACM International Conference on Multimedia, Brisbane, Australia, 2015: 689–692.
    [24] FU Xiaowei, WANG Yi, CHEN Li, et al. An image despeckling approach using quantum-inspired statistics in dual-tree complex wavelet domain[J]. Biomedical Signal Processing and Control, 2015, 18: 30–35. doi:  10.1016/j.bspc.2014.11.005
    [25] BUADES A, COLL B, and MOREL J M. A non-local algorithm for image denoising[C]. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, USA, 2005: 60–65.
    [26] 付晓薇, 代芸, 陈黎, 等. 基于局部熵的量子衍生医学超声图像去斑[J]. 电子与信息学报, 2015, 37(3): 560–566. doi:  10.11999/JEIT140587

    FU Xiaowei, DAI Wei, CHEN Li, et al. Quantum-inspired despeckling of medical ultrasound images based on local entropy[J]. Journal of Electronics &Information Technology, 2015, 37(3): 560–566. doi:  10.11999/JEIT140587
    [27] PIZURICA A, PHILIPS W, LEMAHIEU I, et al. A versatile wavelet domain noise filtration technique for medical imaging[J]. IEEE Transactions on Medical Imaging, 2003, 22(3): 323–331. doi:  10.1109/TMI.2003.809588
    [28] RODTOOK A and MAKHANOV S S. Multi-feature gradient vector flow snakes for adaptive segmentation of the ultrasound images of breast cancer[J]. Journal of Visual Communication and Image Representation, 2013, 24(8): 1414–1430. doi:  10.1016/j.jvcir.2013.09.009
  • [1] 柯丽, 王丹妮, 杜强, 姜楚迪.  基于卷积长短时记忆网络的心律失常分类方法, 电子与信息学报. doi: 10.11999/JEIT190712
    [2] 游凌, 李伟浩, 张文林, 王科人.  基于深度神经网络的Morse码自动译码算法, 电子与信息学报. doi: 10.11999/JEIT190658
    [3] 刘政怡, 刘俊雷, 赵鹏.  基于样本选择的RGBD图像协同显著目标检测, 电子与信息学报. doi: 10.11999/JEIT190393
    [4] 陈怡, 唐迪, 邹维.  基于深度学习的Android恶意软件检测:成果与挑战, 电子与信息学报. doi: 10.11999/JEIT200009
    [5] 柳长源, 王琪, 毕晓君.  基于多通道多尺度卷积神经网络的单幅图像去雨方法, 电子与信息学报. doi: 10.11999/JEIT190755
    [6] 朱建清, 曾焕强, 杜永兆, 雷震, 郑力新, 蔡灿辉.  基于新型三元卷积神经网络的行人再辨识算法, 电子与信息学报. doi: 10.11999/JEIT170803
    [7] 郭立民, 寇韵涵, 陈涛, 张明.  基于栈式稀疏自编码器的低信噪比下低截获概率雷达信号调制类型识别, 电子与信息学报. doi: 10.11999/JEIT170588
    [8] 吴建国, 邵婷, 刘政怡*.  融合显著深度特征的RGB-D图像显著目标检测, 电子与信息学报. doi: 10.11999/JEIT161304
    [9] 伍家松, 达臻, 魏黎明, SENHADJILotfi, 舒华忠.  基于分裂基-2/(2a)FFT算法的卷积神经网络加速性能的研究, 电子与信息学报. doi: 10.11999/JEIT160357
    [10] 侯志强, 王鑫, 余旺盛, 戴铂, 金泽芬芬.  基于自适应深度稀疏网络的在线跟踪算法, 电子与信息学报. doi: 10.11999/JEIT160762
    [11] 彭天强, 栗芳.  基于深度卷积神经网络和二进制哈希学习的图像检索方法, 电子与信息学报. doi: 10.11999/JEIT151346
    [12] 李寰宇, 毕笃彦, 查宇飞, 杨源.  一种易于初始化的类卷积神经网络视觉跟踪算法, 电子与信息学报. doi: 10.11999/JEIT150600
    [13] 李祖贺, 樊养余, 王凤琴.  YUV空间中基于稀疏自动编码器的无监督特征学习, 电子与信息学报. doi: 10.11999/JEIT150557
    [14] 王星, 周一鹏, 周东青, 陈忠辉, 田元荣.  基于深度置信网络和双谱对角切片的低截获概率雷达信号识别, 电子与信息学报. doi: 10.11999/JEIT160031
    [15] 侯志强, 戴铂, 胡丹, 余旺盛, 陈晨, 范舜奕.  基于感知深度神经网络的视觉跟踪, 电子与信息学报. doi: 10.11999/JEIT151449
    [16] 孙锐, 张广海, 高隽.  基于深度分层特征表示的行人识别方法, 电子与信息学报. doi: 10.11999/JEIT150982
    [17] 李寰宇, 毕笃彦, 杨源, 查宇飞, 覃兵, 张立朝.  基于深度特征表达与学习的视觉跟踪算法研究, 电子与信息学报. doi: 10.11999/JEIT150031
    [18] 程帅, 曹永刚, 孙俊喜, 赵立荣, 刘广文, 韩广良.  基于增强群跟踪器和深度学习的目标跟踪, 电子与信息学报. doi: 10.11999/JEIT141362
    [19] 程帅, 孙俊喜, 曹永刚, 刘广文, 韩广良.  多示例深度学习目标跟踪, 电子与信息学报. doi: 10.11999/JEIT150319
    [20] 孙志军, 薛磊, 许阳明.  基于深度学习的边际Fisher分析特征提取算法, 电子与信息学报. doi: 10.3724/SP.J.1146.2012.00949
  • 加载中
  • 图(6) / 表ll (6)
    计量
    • 文章访问数:  1594
    • HTML全文浏览量:  666
    • PDF下载量:  52
    • 被引次数: 0
    出版历程
    • 收稿日期:  2019-07-31
    • 修回日期:  2020-03-18
    • 网络出版日期:  2020-04-11
    • 刊出日期:  2020-07-01

    目录

      /

      返回文章
      返回

      官方微信,欢迎关注