中国组织工程研究

中国组织工程研究 ›› 2011, Vol. 15 ›› Issue (30): 5615-5619.doi: 10.3969/j.issn.1673-8225.2011.30.026

• 数字化骨科 digital orthopedics • 上一篇    下一篇

基于小波变换的心音包络提取算法及应用

周  酥，朱  蒂，吴效明，黄岳山   

  1. 华南理工大学生物医学工程系，广东省广州市   510006
  • 收稿日期:2011-03-22 修回日期:2011-05-12 出版日期:2011-07-23 发布日期:2011-07-23
  • 通讯作者: 吴效明，博士，教授，博士生导师，华南理工大学生物医学工程系，广东省广州市 510006 bmxmwus@scut.edu.cn
  • 作者简介:周酥★，女，1986年生，湖北省天门市人，汉族，华南理工大学在读硕士，主要从事生物医学信号处理的研究。 zhousuok@163.com
  • 基金资助:

    广东省科技计划项目(2007B031302003):课题名称：基于无线穿戴式检测技术的社区数字医疗健康服务系统;广东省科技计划项目(2009B030801004)：课题名称：面向社区家庭的医疗服务与检测仪器。

Envelope extraction algorithm and phonocardiogram signal application based on wavelet transform

Zhou Su, Judith Diengi Zeyi, Wu Xiao-ming, Huang Yue-shan   

  1. Department of Biomedical Engineering, South China University of Technology, Guangzhou  510006, Guangdong Province, China
  • Received:2011-03-22 Revised:2011-05-12 Online:2011-07-23 Published:2011-07-23
  • Contact: Wu Xiao-ming, Doctor, Professor, Doctoral supervisor, Department of Biomedical Engineering, South China University of Technology, Guangzhou 510006, Guangdong Province, China bmxmwus@scut.edu.cn
  • About author:Zhou Su★, Studying for master’s degree, Department of Biomedical Engineering, South China University of Technology, Guangzhou 510006, Guangdong Province, China zhousuok@163.com
  • Supported by:

    the Guangdong Science and Technology Plan, No. 2007B031302003, 2009B030801004**

PDF

1360

被引次数

45

摘要：

背景：心音信号包含了大量心脏瓣膜活动的生理信息，心音分析对诊断心脏疾病具有重要的临床意义。
目的：旨在通过心音的包络提取，分析心音信号的各种特征，进而判断心音中是否包含杂音，以改善传统听诊技术高度依赖医生经验、听诊范围受限的缺点。
方法：提出了一种采用小波变换来提取心音包络的方法，通过与采用希尔伯特-黄变换、数学形态学、平均香农能量等心音包络求解方法进行对比，证明这种方法具有算法简便、曲线光滑、特征点突出等优点。
结果与结论：将该方法用于临床真实心音的包络提取，利用支持向量机来训练所提取心音包络的面积和小波能量两个特征参数，判别心音信号是否明显包含杂音。选用35例心音数据对算法进行验证，结果表明该算法的准确率达到95%，具有很强的实用性。

关键词: 心音, 小波变换, 包络提取, 支持向量机, 特征参数

Abstract:

BACKGROUND: The activity of heart valves can be reflected by cardiac sounds, even some heart disease can also find expression in the abnormal heart sounds. So heart sounds analysis has important clinical significance.
OBJECTIVE: Through extraction envelope and analysis of the various features of heart sounds, to detect whether there is noise or not in phonocardiogram signals so as to improve the weakness of traditional auscultation technology such as high dependence on the doctors’ experience and the limited auscultation range.
METHODS: Extraction envelope curve is one of the commonly used methods to analyze heart sounds. A new method based on wavelet transform to extract the heart sound signals envelope was presented, in contrast to the common methods as Hilbert-Huang transform (HHT), mathematical morphology and average Shannon energy. Through practice, the method was proved to contain many advantages: simple algorithm, smooth feature, outstanding feature point.
RESULTS AND CONCLUSION: In order to test the accuracy of discriminating normal and abnormal heart sounds, 35 heart sounds were collected and analyzed. The experiment demonstrated that the accuracy performances were achieved by 95%, which is very useful in many aspects.

中图分类号: