Wang Yuanlin, Sun Jing, Yang Hongbo, Guo Tao, 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. 2022 Dec 25;39(6):1140-1148. doi: 10.7507/1001-5515.202111059.
Heart sound analysis is significant for early diagnosis of congenital heart disease. A novel method of heart sound classification was proposed in this paper, in which the traditional mel frequency cepstral coefficient (MFCC) method was improved by using the Fisher discriminant half raised-sine function (F-HRSF) and an integrated decision network was used as classifier. It does not rely on segmentation of the cardiac cycle. Firstly, the heart sound signals were framed and windowed. Then, the features of heart sounds were extracted by using improved MFCC, in which the F-HRSF was used to weight sub-band components of MFCC according to the Fisher discriminant ratio of each sub-band component and the raised half sine function. Three classification networks, convolutional neural network (CNN), long and short-term memory network (LSTM), and gated recurrent unit (GRU) were combined as integrated decision network. Finally, the two-category classification results were obtained through the majority voting algorithm. An accuracy of 92.15%, sensitivity of 91.43%, specificity of 92.83%, corrected accuracy of 92.01%, and score of 92.13% were achieved using the novel signal processing techniques. It shows that the algorithm has great potential in early diagnosis of congenital heart disease.
心音分析对于先天性心脏病的早期诊断具有重要意义。本文提出了一种新的心音分类方法，该方法通过使用Fisher判别半升余弦函数（F-HRSF）改进传统的梅尔频率倒谱系数（MFCC）方法，并使用集成决策网络作为分类器。它不依赖于心动周期的分割。首先，对心音信号进行加帧和加窗处理。然后，使用改进的MFCC提取心音特征，其中F-HRSF根据每个子带分量的Fisher判别比和升半余弦函数对MFCC的子带分量进行加权。将卷积神经网络（CNN）、长短期记忆网络（LSTM）和门控循环单元（GRU）这三种分类网络组合成集成决策网络。最后，通过多数投票算法获得两类分类结果。使用新型信号处理技术实现了92.15%的准确率、91.43%的灵敏度、92.83%的特异性、92.01%的校正准确率和92.13%的评分。结果表明，该算法在先天性心脏病的早期诊断中具有很大潜力。
