A Robust and Efficient Workflow for Heart Valve Disease Detection from PCG Signals: Integrating WCNN, MFCC Optimization, and Signal Quality Evaluation

TL;DR

This paper presents an efficient system for detecting heart valve diseases from heart sounds using a lightweight neural network and optimized features, suitable for real-world use.

Contribution

A novel lightweight WCNN with a key weighting calculation layer and optimized MFCCs for robust and efficient heart valve disease detection from PCG signals.

Findings

The proposed model achieved 99.6% accuracy on the GitHub PCG database and 90.74% on the PhysioNet/CinC Challenge 2016 database.

The model uses 74.9% fewer parameters and 99.3% fewer FLOPs compared to prior work by Karhade et al.

Real-time detection was achieved on a Raspberry Pi with a detection time of 1.87 ms for a 1.4 s signal.

Abstract

This study proposes a comprehensive and computationally efficient system for the recognition of heart valve diseases (HVDs) in phonocardiogram (PCG) signals, emphasizing an end-to-end workflow suitable for real-world deployment. The core of the system is a lightweight weighted convolutional neural network (WCNN) featuring a key weighting calculation (KWC) layer, which enhances noise robustness by adaptively weighting feature map channels based on global average pooling. The proposed system incorporates optimized feature extraction using Mel-frequency cepstral coefficients (MFCCs) guided by GradCAM, and a band energy ratio (BER) metric to assess signal quality, showing that lower BER values are associated with higher misclassification rates due to noise. Experimental results demonstrated classification accuracies of 99.6% and 90.74% on the GitHub PCG and PhysioNet/CinC Challenge 2016 databases, respectively, where the models were trained and tested independently. The proposed model achieved superior accuracy using significantly fewer parameters (312,357) and lower computational cost (4.5 M FLOPs) compared with previously published research. Compared with the model proposed by Karhade et al., the proposed model use 74.9% fewer parameters and 99.3% fewer FLOPs. Furthermore, the proposed model was implemented on a Raspberry Pi, achieving real-time HVDs detection with a detection time of only 1.87 ms for a 1.4 s signal.

Figures