搜索

x

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

基于变分模态分解与多尺度排列熵的生物组织变性识别

刘备 胡伟鹏 邹孝 丁亚军 钱盛友

引用本文:
Citation:

基于变分模态分解与多尺度排列熵的生物组织变性识别

刘备, 胡伟鹏, 邹孝, 丁亚军, 钱盛友

Recognition of denatured biological tissue based on variational mode decomposition and multi-scale permutation entropy

Liu Bei, Hu Wei-Peng, Zou Xiao, Ding Ya-Jun, Qian Sheng-You
PDF
HTML
导出引用
  • 根据高强度聚焦超声(HIFU)治疗中超声散射回波信号的特点, 本文利用变分模态分解(VMD)与多尺度排列熵(MPE)对生物组织变性识别进行了研究. 首先对生物组织中的超声散射回波信号进行变分模态分解, 根据各阶模态的功率谱信息熵值分离出噪声分量和有用分量; 对分离出的有用信号进行重构并提取其多尺度排列熵; 然后通过Gustafson-Kessel (GK)模糊聚类确定聚类中心, 采用欧氏贴近度与择近原则对生物组织进行变性识别. 将所提方法应用于HIFU治疗中超声散射回波信号实验数据, 用遗传算法对多尺度排列熵的参数优化后, 对293例未变性组织和变性组织的超声散射回波信号数据进行了多尺度排列熵分析, 发现变性组织的超声散射回波信号的多尺度排列熵值要高于未变性组织; 多尺度排列熵可以较好地识别生物组织是否变性. 相对于EMD-MPE-GK模糊聚类以及VMD-小波熵(WE)-GK模糊聚类变性识别方法, 本文所提方法中变性与未变性组织特征交叠区域数据点更少, 聚类效果和分类性能更好; 本实验环境下生物组织变性识别结果表明, 该方法的识别率更高, 高达93.81%.
    It is an important practical problem to accurately recognize whether biological tissue is denatured during high intensity focused ultrasound (HIFU) treatment. Ultrasonic scattering echo signals are related to some physical properties of biological tissues. According to the characteristics of ultrasonic scattering echo signals, the recognition of denatured biological tissues is studied based on the variational mode decomposition (VMD) and multi-scale permutation entropy (MPE) in this paper. The ultrasonic echo signals are decomposed into various modal components by the VMD. The noise components and the useful components are separated according to the power spectrum information entropy of various modal components. The separated useful signals are reconstructed and the MPE are extracted. Furthermore, Gustafson-Kessel (GK) fuzzy clustering analysis is employed to obtain the standard clustering center, and the recognition of denatured biological tissues is carried out by Euclid approach degree and principle of proximity. The proposed method is applied to ultrasonic scattering echo signal during HIFU treatment. In order to determine the parameters of MPE algorithm for ultrasonic scattering echo signals, the embedding dimension of the MPE is discussed, and the scale factor of the MPE algorithm is optimized by genetic algorithm. When the delay time and the embedding dimension are 2 and 7 respectively, the MPE values decrease with scale factor increasing. Assuming that the scale factor is 12 from optimization results, the 293 ultrasonic scattering echo signals from normal tissues and denatured tissues are analyzed by the MPE. It is found that the MPE values of the denatured tissues are higher than those of the normal tissues. The MPE can be used to distinguish normal tissues and denatured tissues. Comparing with the recognition methods of the EMD-MPE-GK fuzzy clustering method and the VMD-WE-GK fuzzy clustering, the proposed method has good clustering performance and separability. Its partition coefficient (PC) is close to 1 and the Xie-Beni (XB) index is smaller. There are fewer feature points in the overlap region between MPE features of denatured tissues and normal tissues. The recognition results of denatured biological tissues in this experimental environment show that the recognition rate based on this method is higher, reaching up to 93.81%.
      通信作者: 钱盛友, syqian@foxmail.com
    • 基金项目: 国家自然科学基金(批准号: 11474090, 11774088, 61502164)和湖南省自然科学基金(批准号: 2016JJ3090)资助的课题.
      Corresponding author: Qian Sheng-You, syqian@foxmail.com
    • Funds: Project supported by the National Natural Science Foundation of China (Grant Nos. 11474090, 11774088, 61502164) and the Natural Science Foundation of Hunan Province, China (Grant No. 2016JJ3090).
    [1]

    Cranston D 2015 Ultrason. Sonochem. 27 654Google Scholar

    [2]

    Ellens N, Hynynen K 2015 Med. Phys. 42 4896Google Scholar

    [3]

    Bailey M, Khokhlova V, Sapozhnikov O, Kargl S, Crum L 2003 Acoust.Phys. 49 369Google Scholar

    [4]

    Worthington A E, Tranchtenberg J, Sherar M D 2002 Ultrasound Med. Biol. 10 1311

    [5]

    Damianou C A, Sanghvi N T, Fry F J, Maass-Moreno R 1997 J. Acoust. Soc. Am. 102 628Google Scholar

    [6]

    盛磊, 周著黄, 吴水才, 丁琪瑛, 曾毅 2014 北京工业大学学报 40 139Google Scholar

    Sheng L, Zhou Z H, Wu S C, Ding Q Y, Zeng Y 2014 Journal of Beijing Polytechnic University 40 139Google Scholar

    [7]

    Bamber J C, Hill C R 1979 Ultrasound Med. Biol. 5 149Google Scholar

    [8]

    明文, 谭乔来, 钱盛友, 邹孝, 廖志远 2015 测试技术学报 5 404Google Scholar

    Ming W, Tan Q L, Qian S Y, Zou X, Liao Z Y 2015 Journal of Test and Measurement Technology 5 404Google Scholar

    [9]

    Arthur R M, Straube W L, Starman J D, Moros E G 2003 Med. Phys. 30 1021Google Scholar

    [10]

    Seip R, Ebbini E S 1995 IEEE Trans. Biomed. Eng. 42 828Google Scholar

    [11]

    Parker K J 1983 Ultrasound Med. Biol. 9 363Google Scholar

    [12]

    Bloch S, Bailey M R, Crum L A, Kaczkowski P J, Keilman G W, Mourad P D 1998 J. Acoust. Soc. Am. 103 2868

    [13]

    Wu Z H, Huang N E, Chen X Y 2009 Adv. Adapt. Data Anal. 1 1Google Scholar

    [14]

    周彦婷, 汪源源 2010 声学学报 5 495

    Zhou Y T, Wang Y Y 2010 Acta Acustica 5 495

    [15]

    Dragomiretskiy K, Zosso D 2014 IEEE Trans. Signal Process. 62 531

    [16]

    Li J, Ning X 2006 Phys. Rev. E 73 88

    [17]

    杨孝敬, 杨阳, 李淮周, 钟宁 2016 物理学报 65 218701Google Scholar

    Yang X J, Yang Y, Li H Z, Zhong N 2016 Acta Phys. Sin. 65 218701Google Scholar

    [18]

    严碧歌, 赵婷婷 2011 物理学报 60 078701

    Yan B G, Zhao T T 2011 Acta Phys. Sin. 60 078701

    [19]

    Bandt C, Pompe B 2002 Phys. Rev. Lett. 88 174102Google Scholar

    [20]

    Gao Y, Villecco F, Li M, Song W 2017 Entropy 19 176Google Scholar

    [21]

    姚文坡, 刘铁兵, 戴加飞, 王俊 2014 物理学报 63 078704

    Yao W P, Liu T B, Dai J F, Wang J 2014 Acta Phys. Sin. 63 078704

    [22]

    Rahimian S,Tavakkoli J 2013 J. Ther. Ultrasound 1 1

    [23]

    Davari A, Marhaban M H, Noor S, Karimadini M, Karimoddini A 2010 Fuzzy Sets Syst. 163 45

  • 图 1  仿真信号及其对应非噪声成分的时域图 (a)加入噪声的仿真信号时域图; (b)对应非噪声成分的时域图

    Fig. 1.  Time-domain diagram of the simulated signal and its non-noise components: (a) Time-domain diagram of the simulated signal with added noise; (b) time-domain diagram corresponding to non-noise components.

    图 2  VMD与EMD的结果 (a)VMD方法; (b)EMD方法

    Fig. 2.  Results of VMD and EMD: (a) VMD method; (b) EMD method.

    图 3  实际超声回波信号与VMD结果 (a)实际超声回波信号; (b)超声回波信号VMD结果

    Fig. 3.  Actual ultrasonic echo signals and their VMD results: (a) Actual ultrasonic echo signals; (b) VMD results of ultrasonic echo signals.

    图 4  不同嵌入维数时变性与未变性情况的MPE分布 (a) m = 3; (b) m = 5; (c) m = 7

    Fig. 4.  MPE distribution of denatured and undenatured cases with different embedding dimension: (a) m = 3; (b) m = 5; (c) m = 7.

    图 5  不同聚类方法对未变性与变性生物组织超声散射回波信号的聚类效果 (a) EMD-MPE-GK; (b) VMD-WE-GK; (c) VMD-MPE-GK

    Fig. 5.  Clustering effect on ultrasonic scattering echo signals of undenatured and denatured biological tissues through different clustering methods: (a) EMD-MPE-GK; (b) VMD-WE-GK; (c) VMD-MPE-GK.

    表 1  三组样本在嵌入维数m = 7时各尺度下排列熵平均值

    Table 1.  The average entropy of the three samples at each scale when the embedding dimension m = 7.

    尺度因子s样本1样本2样本3
    未变性变性未变性变性未变性变性
    10.70680.73960.70850.74080.70280.7366
    20.65040.71630.64910.70130.64490.6958
    30.62000.68550.61940.67180.61450.6715
    40.58360.64980.58390.63610.57810.6378
    50.55690.62410.55750.61760.55300.6151
    60.53280.59940.53290.59620.52730.5934
    70.51420.57800.51300.57710.50870.5776
    80.49540.56090.49580.56180.49080.5602
    90.47920.54580.47960.54530.47370.5418
    100.46570.53130.46460.53250.46220.5320
    110.45360.51520.45060.52460.44710.5173
    120.43840.51390.43790.51880.43500.5059
    130.43640.46260.43670.46860.42890.5042
    下载: 导出CSV

    表 2  变性与未变性组织识别结果

    Table 2.  Recognition results of denatured and undenatured tissues.

    聚类方法PCXB识别率/%
    VMD-MPE-GK0.81194.49893.81
    EMD-MPE-GK0.808811.58987.44
    VMD-WE-GK0.79014.87885.29
    下载: 导出CSV
  • [1]

    Cranston D 2015 Ultrason. Sonochem. 27 654Google Scholar

    [2]

    Ellens N, Hynynen K 2015 Med. Phys. 42 4896Google Scholar

    [3]

    Bailey M, Khokhlova V, Sapozhnikov O, Kargl S, Crum L 2003 Acoust.Phys. 49 369Google Scholar

    [4]

    Worthington A E, Tranchtenberg J, Sherar M D 2002 Ultrasound Med. Biol. 10 1311

    [5]

    Damianou C A, Sanghvi N T, Fry F J, Maass-Moreno R 1997 J. Acoust. Soc. Am. 102 628Google Scholar

    [6]

    盛磊, 周著黄, 吴水才, 丁琪瑛, 曾毅 2014 北京工业大学学报 40 139Google Scholar

    Sheng L, Zhou Z H, Wu S C, Ding Q Y, Zeng Y 2014 Journal of Beijing Polytechnic University 40 139Google Scholar

    [7]

    Bamber J C, Hill C R 1979 Ultrasound Med. Biol. 5 149Google Scholar

    [8]

    明文, 谭乔来, 钱盛友, 邹孝, 廖志远 2015 测试技术学报 5 404Google Scholar

    Ming W, Tan Q L, Qian S Y, Zou X, Liao Z Y 2015 Journal of Test and Measurement Technology 5 404Google Scholar

    [9]

    Arthur R M, Straube W L, Starman J D, Moros E G 2003 Med. Phys. 30 1021Google Scholar

    [10]

    Seip R, Ebbini E S 1995 IEEE Trans. Biomed. Eng. 42 828Google Scholar

    [11]

    Parker K J 1983 Ultrasound Med. Biol. 9 363Google Scholar

    [12]

    Bloch S, Bailey M R, Crum L A, Kaczkowski P J, Keilman G W, Mourad P D 1998 J. Acoust. Soc. Am. 103 2868

    [13]

    Wu Z H, Huang N E, Chen X Y 2009 Adv. Adapt. Data Anal. 1 1Google Scholar

    [14]

    周彦婷, 汪源源 2010 声学学报 5 495

    Zhou Y T, Wang Y Y 2010 Acta Acustica 5 495

    [15]

    Dragomiretskiy K, Zosso D 2014 IEEE Trans. Signal Process. 62 531

    [16]

    Li J, Ning X 2006 Phys. Rev. E 73 88

    [17]

    杨孝敬, 杨阳, 李淮周, 钟宁 2016 物理学报 65 218701Google Scholar

    Yang X J, Yang Y, Li H Z, Zhong N 2016 Acta Phys. Sin. 65 218701Google Scholar

    [18]

    严碧歌, 赵婷婷 2011 物理学报 60 078701

    Yan B G, Zhao T T 2011 Acta Phys. Sin. 60 078701

    [19]

    Bandt C, Pompe B 2002 Phys. Rev. Lett. 88 174102Google Scholar

    [20]

    Gao Y, Villecco F, Li M, Song W 2017 Entropy 19 176Google Scholar

    [21]

    姚文坡, 刘铁兵, 戴加飞, 王俊 2014 物理学报 63 078704

    Yao W P, Liu T B, Dai J F, Wang J 2014 Acta Phys. Sin. 63 078704

    [22]

    Rahimian S,Tavakkoli J 2013 J. Ther. Ultrasound 1 1

    [23]

    Davari A, Marhaban M H, Noor S, Karimadini M, Karimoddini A 2010 Fuzzy Sets Syst. 163 45

  • [1] 李朝锋, 王振, 刘欣宇, 杨苏辉, 徐震, 樊超阳. 基于VMD-ICA的水下激光雷达抗散射信号处理方法研究. 物理学报, 2024, 0(0): 0-0. doi: 10.7498/aps.73.20231993
    [2] 钱骏, 谢伟, 周小伟, 谭坚文, 王智彪, 杜永洪, 李雁浩. 基于换能器驱动信号特征的高强度聚焦超声焦域损伤实时监测. 物理学报, 2022, 71(3): 037201. doi: 10.7498/aps.71.20211443
    [3] 宋人杰, 袁紫燕, 张琪, 于洁, 薛洪惠, 屠娟, 章东. 基于超声RF信号熵分析的声空化时空监测方法. 物理学报, 2022, 71(17): 174301. doi: 10.7498/aps.71.20220558
    [4] 黄泽徽, 李亚安, 陈哲, 刘恋. 基于多尺度熵的Duffing混沌系统阈值确定方法. 物理学报, 2020, 69(16): 160501. doi: 10.7498/aps.69.20191642
    [5] 许子非, 缪维跑, 李春, 金江涛, 李蜀军. 流场非线性特征提取与混沌分析. 物理学报, 2020, 69(24): 249501. doi: 10.7498/aps.69.20200625
    [6] 许子非, 岳敏楠, 李春. 优化递归变分模态分解及其在非线性信号处理中的应用. 物理学报, 2019, 68(23): 238401. doi: 10.7498/aps.68.20191005
    [7] 杜义浩, 齐文靖, 邹策, 张晋铭, 谢博多, 谢平. 基于变分模态分解-相干分析的肌间耦合特性. 物理学报, 2017, 66(6): 068701. doi: 10.7498/aps.66.068701
    [8] 郭各朴, 宿慧丹, 丁鹤平, 马青玉. 基于电阻抗层析成像的高强度聚焦超声温度监测技术. 物理学报, 2017, 66(16): 164301. doi: 10.7498/aps.66.164301
    [9] 谢平, 杨芳梅, 李欣欣, 杨勇, 陈晓玲, 张利泰. 基于变分模态分解-传递熵的脑肌电信号耦合分析. 物理学报, 2016, 65(11): 118701. doi: 10.7498/aps.65.118701
    [10] 熊志成, 朱丽霖, 刘诚, 高淑梅, 朱健强. 基于纳米天线的多通道高强度定向表面等离子体波激发. 物理学报, 2015, 64(24): 247301. doi: 10.7498/aps.64.247301
    [11] 向郑涛, 陈宇峰, 李昱瑾, 熊励. 基于多尺度熵的交通流复杂性分析. 物理学报, 2014, 63(3): 038903. doi: 10.7498/aps.63.038903
    [12] 刘大钊, 王俊, 李锦, 李瑜, 徐文敏, 赵筱. 颠倒睡眠状态调制心率变异性信号的功率谱和基本尺度熵分析. 物理学报, 2014, 63(19): 198703. doi: 10.7498/aps.63.198703
    [13] 耿昊, 范庭波, 张喆, 屠娟, 郭霞生, 李发琪, 章东. 球形集声器在生物组织中形成的组织损伤. 物理学报, 2014, 63(4): 044301. doi: 10.7498/aps.63.044301
    [14] 姚文坡, 刘铁兵, 戴加飞, 王俊. 脑电信号的多尺度排列熵分析. 物理学报, 2014, 63(7): 078704. doi: 10.7498/aps.63.078704
    [15] 李鹏, 刘澄玉, 李丽萍, 纪丽珍, 于守元, 刘常春. 多尺度多变量模糊熵分析. 物理学报, 2013, 62(12): 120512. doi: 10.7498/aps.62.120512
    [16] 孙健明, 于洁, 郭霞生, 章东. 基于分数导数研究高强度聚焦超声的非线性声场. 物理学报, 2013, 62(5): 054301. doi: 10.7498/aps.62.054301
    [17] 杜萌, 金宁德, 高忠科, 朱雷, 王振亚. 油水两相流水包油流型多尺度排列熵分析. 物理学报, 2012, 61(23): 230507. doi: 10.7498/aps.61.230507
    [18] 徐丰, 陆明珠, 万明习, 方飞. 256阵元高强度聚焦超声相控阵系统误差与多焦点模式精确控制. 物理学报, 2010, 59(2): 1349-1356. doi: 10.7498/aps.59.1349
    [19] 黄晓林, 崔胜忠, 宁新宝, 卞春华. 心率变异性基本尺度熵的多尺度化研究. 物理学报, 2009, 58(12): 8160-8165. doi: 10.7498/aps.58.8160
    [20] 陆明珠, 万明习, 施雨, 宋延淳. 多阵元高强度聚焦超声多目标控制方法研究. 物理学报, 2002, 51(4): 928-934. doi: 10.7498/aps.51.928
计量
  • 文章访问数:  7683
  • PDF下载量:  72
  • 被引次数: 0
出版历程
  • 收稿日期:  2018-09-26
  • 修回日期:  2018-10-26
  • 上网日期:  2019-01-01
  • 刊出日期:  2019-01-20

/

返回文章
返回