Biomedical Department, ChongQing Institute of Technology, China.
Comput Methods Programs Biomed. 2010 May;98(2):140-50. doi: 10.1016/j.cmpb.2009.09.008. Epub 2009 Oct 24.
This paper presents two new ideas. The first one is to apply the Viola integral waveform method to analyze the heart sounds recorded by an electric stethoscope, and the multi-scale moment analysis is proposed to locate each cycle of heart sounds. A fast algorithm for calculating characteristic waveform (CW) and characteristic moment waveform (CMW) of heart sound can be expressed by the Viola integral method, and their calculation time has nothing to do with their scales. The second idea is easier to segment the heart sound based on its approximate cyclical characteristic than the ordinary methods. Each heart sound cycle can be quickly found by CMW's Local Extreme Points (LEPs). Based on the information of LEPs and CW, a high accurate search algorithm to segment S1 and S2 sounds is submitted. By numerical experiments, the important parameters of time scale delta=0.05s for CW and l=0.45s for CMW are obtained and validated for segmentation of heart sound.
More exact segmentation boundaries of the heart sound signal could be located fast in an automated way, and a further performance analysis is presented. Owing to the use of the rhythm of CMW curves, the proposed method not only gives a higher success segmentation rate, but also it is actually simpler and faster than the wavelet method.
本论文提出了两个新的观点。第一个观点是将 Viola 积分波形方法应用于分析电动听诊器记录的心音，并提出多尺度矩分析来定位心音的每个周期。Viola 积分方法可以表达心音特征波形 (CW) 和特征矩波形 (CMW) 的快速算法，其计算时间与尺度无关。第二个观点是，与普通方法相比，基于心音的近似周期性特征更容易对心音进行分段。CMW 的局部极值点 (LEPs) 可以快速找到每个心音周期。基于 LEPs 和 CW 的信息，提出了一种高精度的 S1 和 S2 声音分段搜索算法。通过数值实验，获得了 CW 的时间尺度参数 delta=0.05s 和 CMW 的 l=0.45s，并对心音分段进行了验证。
通过自动方式可以快速定位心音信号更准确的分段边界，并进行了进一步的性能分析。由于使用了 CMW 曲线的节奏，该方法不仅给出了更高的成功分段率，而且实际上比小波方法更简单、更快。
