A Visual Domain Transfer Learning Approach for Heartbeat Sound Classification

TL;DR

This paper introduces a novel method for classifying heartbeat sounds by converting them into spectrogram images and applying transfer learning with CNNs like ResNet and MobileNetV2, achieving high accuracy and robustness across datasets.

Contribution

It pioneers the use of visual domain transfer learning on spectrograms for automated heartbeat sound classification, demonstrating effective feature extraction and high performance.

Findings

Achieved approximately 90% categorical accuracy.

Attained AUROC of around 0.97.

Effective across different datasets and noise conditions.

Abstract

Heart disease is the most common reason for human mortality that causes almost one-third of deaths throughout the world. Detecting the disease early increases the chances of survival of the patient and there are several ways a sign of heart disease can be detected early. This research proposes to convert cleansed and normalized heart sound into visual mel scale spectrograms and then using visual domain transfer learning approaches to automatically extract features and categorize between heart sounds. Some of the previous studies found that the spectrogram of various types of heart sounds is visually distinguishable to human eyes, which motivated this study to experiment on visual domain classification approaches for automated heart sound classification. It will use convolution neural network-based architectures i.e. ResNet, MobileNetV2, etc as the automated feature extractors from spectrograms. These well-accepted models in the image domain showed to learn generalized feature representations of cardiac sounds collected from different environments with varying amplitude and noise levels. Model evaluation criteria used were categorical accuracy, precision, recall, and AUROC as the chosen dataset is unbalanced. The proposed approach has been implemented on datasets A and B of the PASCAL heart sound collection and resulted in ~ 90% categorical accuracy and AUROC of ~0.97 for both sets.