Generative Deep Learning and Signal Processing for Data Augmentation of Cardiac Auscultation Signals: Improving Model Robustness Using Synthetic Audio

TL;DR

This paper demonstrates that using generative deep learning models to create synthetic cardiac auscultation signals enhances the robustness and accuracy of classification models, especially in imbalanced and out-of-distribution scenarios.

Contribution

It introduces a novel data augmentation approach combining traditional audio techniques with diffusion models like WaveGrad and DiffWave to improve model robustness.

Findings

Enhanced in-distribution and out-of-distribution performance with augmented data

Improved accuracy, balanced accuracy, and Matthew's correlation coefficient

Synthetic data helps address class imbalance issues

Abstract

Accurately interpreting cardiac auscultation signals plays a crucial role in diagnosing and managing cardiovascular diseases. However, the paucity of labelled data inhibits classification models' training. Researchers have turned to generative deep learning techniques combined with signal processing to augment the existing data and improve cardiac auscultation classification models to overcome this challenge. However, the primary focus of prior studies has been on model performance as opposed to model robustness. Robustness, in this case, is defined as both the in-distribution and out-of-distribution performance by measures such as Matthew's correlation coefficient. This work shows that more robust abnormal heart sound classifiers can be trained using an augmented dataset. The augmentations consist of traditional audio approaches and the creation of synthetic audio conditionally generated using the WaveGrad and DiffWave diffusion models. It is found that both the in-distribution and out-of-distribution performance can be improved over various datasets when training a convolutional neural network-based classification model with this augmented dataset. With the performance increase encompassing not only accuracy but also balanced accuracy and Matthew's correlation coefficient, an augmented dataset significantly contributes to resolving issues of imbalanced datasets. This, in turn, helps provide a more general and robust classifier.