Heart Sound Classification using Residual Neural Network and Convolution Block Attention Module

Listening to the heart sound with digital or manual stethoscopes has become one of the practical ways to identify heart diseases in recent years. It's still difficult because of its manual approach and the fact that only experienced healthcare practitioners can use it to diagnose anomalies. The...

Full description

Saved in:
Bibliographic Details
Main Authors: Frimpong, Enoch Adjei, Zhiguang, Qin, Kwadwo, Tenagyei Edwin, Rutherford, Patamia Agbeshi, Baagyere, Edward Y., Turkson, Regina Esi
Format: Conference Proceeding
Language:English
Subjects:
Cardiovascular diseases
Convolution
Deep learning
Feature extraction
Heart
Heart sound
Machine learning
Manuals
Media
Medical services
Spectrogram Augmentation
Stethoscope
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Listening to the heart sound with digital or manual stethoscopes has become one of the practical ways to identify heart diseases in recent years. It's still difficult because of its manual approach and the fact that only experienced healthcare practitioners can use it to diagnose anomalies. The automatic extraction of heart sound features to aid in classification has been explored, however there is still potential for improvement. This paper proposes a residual neural network integrated with a convolutional block attention module (CBAM) for heart sound analysis, using generated Mel-spectrograms as input for our network. We tested our model using the Pascal Heart Sound Challenge dataset, and it performed favorably to other cutting-edge models.
ISSN:2576-8964
DOI:10.1109/ICCWAMTIP56608.2022.10016549