Wavelet-based Segmentation and Feature Extraction of Heart Sounds for Intelligent PDA-based Phonocardiography

Prenatal identification of CHD murmur using four segment phonocardiographic signal analysis

Congenital heart defects (CHD) are one of the utmost birth defects present in the neonatal after birth and a big challenge for the researchers to identify the structural abnormality during the antepartum period. An algorithm is presented here to identify the presence of CHD through foetal phonocardiographic (fPCG) signals. The recorded fPCG is decomposed using Daubechies4 wavelet with sub-level threshold to remove the noise in the signal. The Shannon energy is used to identify the different peaks of signals and then S1 and S2 according to the intervals between adjacent peaks. The signal is segmented into four important parts: S1, S1S2, S2 and S2S1. The FFT is used to identify the frequency component present in four segments which in turn indicates the presence of pathological murmur that may turn into CHD. The algorithm is tested on 25 samples with accuracy rate 88% in identifying the presence of a murmur.

Detection and identification of S1 and S2 heart sounds using wavelet decomposition method

Phonocardiogram (PCG), the digital recording of heart sounds is becoming increasingly popular as a primary detection system for diagnosing heart disorders and it is relatively inexpensive. Electrocardiogram (ECG) is used during the PCG in order to identify the systolic and diastolic parts manually. In this study a heart sound segmentation algorithm has been developed which separates the heart sound signal into these parts automatically. This study was carried out on 100 patients with normal and abnormal heart sounds. The algorithm uses discrete wavelet decomposition and reconstruction to produce PCG intensity envelopes and separates that into four parts: the first heart sound, the systolic period, the second heart sound and the diastolic period. The performance of the algorithm has been evaluated using 14,000 cardiac periods from 100 digital PCG recordings, including normal and abnormal heart sounds. In tests, the algorithm was over 93% correct in detecting the first and second heart sounds. The presented automatic segmentation algorithm using wavelet decomposition and reconstruction to select suitable frequency band for envelope calculations has been found to be effective to segment PCG signals into four parts without using an ECG.