Lightweight End-to-End Neural Network Model for Automatic Heart Sound Classification

Tao Li,Ming Liu,Sitao Zhang,Kainan Ma,Yibo Yin

doi:10.3390/info12020054

Abstract

Heart sounds play an important role in the initial screening of heart diseases. However, the accurate diagnosis with heart sound signals requires doctors to have many years of clinical experience and relevant professional knowledge. In this study, we proposed an end-to-end lightweight neural network model that does not require heart sound segmentation and has very few parameters. We segmented the original heart sound signal and performed a short-time Fourier transform (STFT) to obtain the frequency domain features. These features were sent to the improved two-dimensional convolutional neural network (CNN) model for features learning and classification. Considering the imbalance of positive and negative samples, we introduced FocalLoss as the loss function, verified our network model with multiple random verifications, and, hence, obtained a better classification result. Our main purpose is to design a lightweight network structure that is easy for hardware implementation. Compared with the results of the latest literature, our model only uses 4.29 K parameters, which is 1/10 of the size of the state-of-the-art work.

Highlights

According to statistics from the World Health Organization, cardiovascular disease has become one of the leading causes of death in the world [1]
The window of each small segment of the signal (3 s) was used for each short-time Fourier transform (STFT) computation, and the two-dimensional features obtained were sent to the convolutional neural network (CNN) network model for training and classification
We determined the final model parameters according to the validation set of the highest accuracy by conducting multiple random tests on the length of the window of the STFT, the parameters of the FocalLoss function, and the output threshold

Summary

Introduction

According to statistics from the World Health Organization, cardiovascular disease has become one of the leading causes of death in the world [1]. Auscultation of heart sounds is an important part of the physical examination. The heart undergoes electrical stimulation, and the formation of atrial and ventricular contractions leads to mechanical activity. This mechanical activity, as well as the sudden starting or stopping of blood flow in the heart, will cause the entire heart structure to vibrate. These vibrations can be heard on the chest wall, and specific heart sounds can give an indication of heart health [2]. It is necessary to investigate a method for automatically classifying heart sounds that can be applied to develop a portable low-power automatic monitoring device

Methods

Results

Discussion

Conclusion