FunnelNet: An End-to-End Deep Learning Framework to Monitor Digital Heart Murmur in Real-Time

TL;DR

FunnelNet is a lightweight end-to-end deep learning framework that accurately detects heart murmurs in real-time, suitable for resource-limited environments, with publicly available code.

Contribution

This work introduces a novel, efficient deep learning model for real-time heart murmur detection, optimized for embedded devices and outperforming larger models.

Findings

Achieved 85% accuracy, sensitivity, and 92% specificity on the CirCor dataset.

Converted the model into TinyML format, maintaining high accuracy on Raspberry Pi and Android devices.

Demonstrated the model's effectiveness in resource-constrained settings for accessible diagnostics.

Abstract

Heart murmurs are abnormal sounds caused by turbulent blood flow in the heart. Several diagnostic methods are available to detect heart murmurs and their severity, including cardiac auscultation, echocardiography, and phonocardiography (PCG). However, these methods have limitations, including the need for extensive training among healthcare providers, the cost and accessibility of echocardiography, and noise interference during PCG data processing. This study proposes an end-to-end real-time heart murmur detection approach using traditional and depthwise separable convolutional networks. We applied a Butterworth filter and Continuous Wavelet Transform (CWT) to eliminate noise and extract meaningful features from the PCG data. The proposed network consists of three parts: a Squeeze net that generates a compressed data representation, a Bottleneck layer that minimizes computational complexity using depthwise-separable convolutions, and an Expansion net that up-samples the data to capture fine details. We evaluated our model on the publicly available CirCor pediatric heart sound dataset. Using only $\sim$5.4k parameters, we achieved an accuracy of 85%, a sensitivity of 85%, and a specificity of 92%, successfully outperforming several larger models. Furthermore, we converted our network into a TinyML format and tested it on two resource-constrained devices, achieving an average real-time inference accuracy of 91% on a Raspberry Pi 4B and 80% on an Android smartphone. The proposed lightweight model offers a robust deep learning framework for accurate, real-time heart murmur detection, showing strong promise for accessible medical diagnostics in limited-resource environments. The code is publicly available at https://github.com/jobayer/FunnelNet.