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

TL;DR

This work tackles real-time, accessible heart murmur detection from PCG data. It introduces FunnelNet, an end-to-end architecture that combines Morlet-based $CWT$ time-frequency features, a three-part encoder-decoder with depthwise separable convolutions, and lightweight preprocessing including outlier removal, noise filtering, and SMOTE oversampling. On four public datasets, the method achieves state-of-the-art sensitivity, specificity, and accuracy, and demonstrates practical on-device performance on Raspberry Pi and Android via TinyML. The approach promises scalable, low-cost screening and remote monitoring for cardiovascular health, with public code and a clear path for further improvements through dataset expansion and advanced signal processing.

Abstract

Objective: Heart murmurs are abnormal sounds caused by turbulent blood flow within the heart. Several diagnostic methods are available to detect heart murmurs and their severity, such as cardiac auscultation, echocardiography, phonocardiogram (PCG), etc. However, these methods have limitations, including extensive training and experience among healthcare providers, cost and accessibility of echocardiography, as well as noise interference and PCG data processing. This study aims to develop a novel end-to-end real-time heart murmur detection approach using traditional and depthwise separable convolutional networks. Methods: Continuous wavelet transform (CWT) was applied to extract meaningful features from the PCG data. The proposed network has three parts: the Squeeze net, the Bottleneck, and the Expansion net. The Squeeze net generates a compressed data representation, whereas the Bottleneck layer reduces computational complexity using a depthwise-separable convolutional network. The Expansion net is responsible for up-sampling the compressed data to a higher dimension, capturing tiny details of the representative data. Results: For evaluation, we used four publicly available datasets and achieved state-of-the-art performance in all datasets. Furthermore, we tested our proposed network on two resource-constrained devices: a Raspberry PI and an Android device, stripping it down into a tiny machine learning model (TinyML), achieving a maximum of 99.70%. Conclusion: The proposed model offers a deep learning framework for real-time accurate heart murmur detection within limited resources. Significance: It will significantly result in more accessible and practical medical services and reduced diagnosis time to assist medical professionals. The code is publicly available at TBA.

Figures (2)

• Figure 1: An illustration of the proposed FunnelCNN network architecture, divided into three parts: the squeeze net, the bottleneck, and the expansion net. The Squeeze net and the Expansion net work like an encoder and decoder to compress and upscale the most relevant input features. A depthwise CNN has been employed at the Bottleneck for reduced computational complexity. A fully connected layer is placed at the end to predict the correct class.
• Figure 2: An illustration of training accuracy, validation loss, training loss, and validation loss with respect to epochs. The accuracy and loss functions for the training and validation phases are shown over the four datasets (CinC, CirCor, Pascal, and Synthetic). Here, all datasets achieved satisfactory accuracy levels, while the Synthetic had the maximum and Pascal had the minimum validation accuracy. Moreover, Synthetic had the maximum, and Pascal had the minimum validation loss over time.