Heart Sound Segmentation Using Deep Learning Techniques

TL;DR

This paper introduces a deep learning-based method for segmenting and classifying heart sounds into S1 and S2, utilizing FFT filtering, dynamic programming, and Siamese networks to improve accuracy on the PASCAL dataset.

Contribution

It presents a novel combination of FFT filtering, dynamic programming, and Siamese networks for heart sound segmentation and classification, outperforming existing methods.

Findings

Superior performance on PASCAL dataset

Effective segmentation of S1 and S2 sounds

Robust classification using Siamese networks

Abstract

Heart disease remains a leading cause of mortality worldwide. Auscultation, the process of listening to heart sounds, can be enhanced through computer-aided analysis using Phonocardiogram (PCG) signals. This paper presents a novel approach for heart sound segmentation and classification into S1 (LUB) and S2 (DUB) sounds. We employ FFT-based filtering, dynamic programming for event detection, and a Siamese network for robust classification. Our method demonstrates superior performance on the PASCAL heart sound dataset compared to existing approaches.