Wang Xingzhi, Yang Hongbo, Zong Rong, Pan Jiahua, Wang Weilian
School of Information Science and Engineering, Yunnan University, Kunming 650504, P.R.China.
Fuwai Cardiovascular Hospital of Yunnan Province, Kunming 650102, P.R.China.
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2021 Oct 25;38(5):969-978. doi: 10.7507/1001-5515.202012024.
Automatic classification of heart sounds plays an important role in the early diagnosis of congenital heart disease. A kind of heart sound classification algorithms based on sub-band envelope feature and convolution neural network was proposed in this paper, which did not need to segment the heart sounds according to cardiac cycle accurately. Firstly, the heart sound signal was divided into some frames. Then, the frame level heart sound signal was filtered with Gammatone filter bank to obtain the sub-band signals. Next, the sub-band envelope was extracted by Hilbert transform. After that, the sub-band envelope was stacked into a feature map. Finally, type Ⅰ and type Ⅱ convolution neural network were selected as classifier. The result shown that the sub-band envelope feature was better in type Ⅰ than type Ⅱ. The algorithm is tested with 1 000 heart sound samples. The test results show that the overall performance of the algorithm proposed in this paper is significantly improved compared with other similar algorithms, which provides a new method for automatic classification of congenital heart disease, and speeds up the process of automatic classification of heart sounds applied to the actual screening.
心音的自动分类在先天性心脏病的早期诊断中起着重要作用。本文提出了一种基于子带包络特征和卷积神经网络的心音分类算法，该算法无需精确地根据心动周期对心音进行分割。首先，将心音信号划分为若干帧。然后，使用伽马通滤波器组对帧级心音信号进行滤波以获得子带信号。接下来，通过希尔伯特变换提取子带包络。之后，将子带包络堆叠成一个特征图。最后，选择Ⅰ型和Ⅱ型卷积神经网络作为分类器。结果表明，子带包络特征在Ⅰ型中比在Ⅱ型中更好。该算法用1000个心音样本进行了测试。测试结果表明，本文提出的算法与其他类似算法相比，整体性能有显著提高，为先天性心脏病的自动分类提供了一种新方法，并加快了心音自动分类应用于实际筛查的进程。
