Noise-Robust Contrastive Learning with an MFCC-Conformer For Coronary Artery Disease Detection

TL;DR

This paper presents a noise-robust deep learning approach using MFCC-Conformer and multichannel noise rejection for improved coronary artery disease detection from phonocardiogram signals.

Contribution

It introduces a novel multichannel energy-based noisy-segment rejection algorithm combined with a conformer-based classifier for robust CAD detection in noisy real-world data.

Findings

Achieved 78.4% accuracy and 78.2% balanced accuracy on 297 subjects.

Improved performance by approximately 4% with noisy-segment rejection.

Demonstrated effectiveness of multichannel noise rejection and MFCC-Conformer in noisy environments.

Abstract

Cardiovascular diseases (CVD) are the leading cause of death worldwide, with coronary artery disease (CAD) comprising the largest subcategory of CVDs. Recently, there has been increased focus on detecting CAD using phonocardiogram (PCG) signals, with high success in clinical environments with low noise and optimal sensor placement. Multichannel techniques have been found to be more robust to noise; however, achieving robust performance on real-world data remains a challenge. This work utilises a novel multichannel energy-based noisy-segment rejection algorithm, using heart and noise-reference microphones, to discard audio segments with large amounts of nonstationary noise before training a deep learning classifier. This conformer-based classifier takes mel-frequency cepstral coefficients (MFCCs) from multiple channels, further helping improve the model's noise robustness. The proposed method achieved 78.4% accuracy and 78.2% balanced accuracy on 297 subjects, representing improvements of 4.1% and 4.3%, respectively, compared to training without noisy-segment rejection.