摘要
目的探讨基于小波变换的心电图ST段形态的识别算法。方法首先利用二次样条小波对心电信号进行分解,并根据信号奇异点与其小波变换模极大值的对应关系,提出了在不同尺度下进行心电信号中关键特征点的提取策略;然后对ST段进行直线拟合,识别出ST段的形态;最后采用MIT/BIH标准心电数据库的数据进行检验。结果利用作者所提算法编制的自动诊断软件能较准确地提取心电信号的特征点,成功识别了ST段的形态。结论该自动分析算法可以提高ST段分析的准确性和可靠性,为临床诊断冠心病提供更准确的依据。
Aim : To study the extraction of R-wave and ST segment fiducial points based on wavelet transform(WT) , and to design a algorithm, which is used to recognize the shape of ST segment. Methods:Electrocardiogram(ECG) signals are decomposed by wavelet transform algorithm using dyadic spline wavelets. Based on the relation between the characteristic points of ECG signals and the modulus maximum pairs of the signals WT, a scheme was developed to identify fiducial points of the ECG signals at different wavelet decomposition scales. Then, ST segments were fitted by line and the shapes of ST segments were recognized. The proposed method was demonstrated by the datum from the standard MIT/BIH ECG database. Results: Automatic ECG analysis system based on the proposed method can abstract the extraction of ECG characters correctly and distinguish the shape of ST segment successfully. Conclusion: The proposed automatic algotithm couldbe uesd to analyze ST segment of ECG correctly and reliably, and the result can give more useful information for clinical diagnosis of coronary heart disease.
出处
《郑州大学学报(医学版)》
CAS
北大核心
2006年第2期275-277,共3页
Journal of Zhengzhou University(Medical Sciences)
基金
河南省重点科技攻关基金资助项目496061101
关键词
心电图
ST段
小波变换
直线拟合
electrocardiogram
ST segment
wavelet transform
straight line fitting