Cardiac auscultation is the basic way for primary diagnosis and screening of congenital heart disease(CHD). A new classification algorithm of CHD based on convolution neural network was proposed for analysis and classification of CHD heart sounds in this work. The algorithm was based on the clinically collected diagnosed CHD heart sound signal. Firstly the heart sound signal preprocessing algorithm was used to extract and organize the Mel Cepstral Coefficient (MFSC) of the heart sound signal in the one-dimensional time domain and turn it into a two-dimensional feature sample. Secondly, 1 000 feature samples were used to train and optimize the convolutional neural network, and the training results with the accuracy of 0.896 and the loss value of 0.25 were obtained by using the Adam optimizer. Finally, 200 samples were tested with convolution neural network, and the results showed that the accuracy was up to 0.895, the sensitivity was 0.910, and the specificity was 0.880. Compared with other algorithms, the proposed algorithm has improved accuracy and specificity. It proves that the proposed method effectively improves the robustness and accuracy of heart sound classification and is expected to be applied to machine-assisted auscultation.
心脏听诊是先天性心脏病（简称：先心病，CHD）初诊和筛查的主要手段。本文对先心病心音信号进行分析和分类识别研究，提出了一种基于卷积神经网络的先心病分类算法。本文算法基于临床采集的已确诊先心病心音信号，首先采用心音信号预处理算法提取并组织一维时间域上心音信号的梅尔系数转变成二维特征样本。其次，以 1 000 个特征样本用于训练和优化卷积神经网络，使用自适应矩估计（Adam）优化器，获得了准确率 0.896、损失值 0.25 的训练结果。最后，用卷积神经网络对 200 个心音信号样本进行测试，实验结果表明准确率达 0.895，灵敏度为 0.910，特异度为 0.880。同其它算法相比，本文算法在准确率和特异度上有明显提高，证实了本文方法有效地提高了心音信号分类的鲁棒性和准确性，有望应用于机器辅助听诊。.
Keywords: Mel coefficient; classification; congenital heart disease; convolutional neural network; machine aided auscultation.