Wavelet-based fundamental heart sound recognition method using morphological and interval features

• Published in: Healthcare technology letters Vol. 5; no. 3; pp. 81 - 87
• Main Authors: Nivitha Varghees, V, Ramachandran, K.I, Soman, K.P
• Format: Journal Article
• Language: English
• Published: Warwick The Institution of Engineering and Technology 01-06-2018; John Wiley & Sons, Inc; Wiley
• Subjects: Algorithms; amplitude-dependent thresholding rule; decision-rule algorithm; eGeneralMedical databases; Energy; feature extraction; Heart; high-frequency noises; HS delineation; HS patterns; interval features; Kurtosis; low-frequency noises; medical signal processing; morphological features; Morphology; murmurs; Neural networks; Noise; PASCAL HSs Challenge; PCG signal; phonocardiogram; phonocardiography; PhysioNet/CinC HS Challenge; Pulmonary arteries; Shannnon energy envelope; Sound; Support vector machines; synchrosqueezing wavelet transform; Wavelet transforms; wavelet-based fundamental heart sound recognition method; WFHSR method; wavelet transforms; WFHSR method; HS delineation; interval features; PhysioNet/CinC HS Challenge; synchrosqueezing wavelet transform; HS patterns; wavelet-based fundamental heart sound recognition method; high-frequency noises; amplitude-dependent thresholding rule; phonocardiogram; low-frequency noises; medical signal processing; PASCAL HSs Challenge; feature extraction; Shannnon energy envelope; PCG signal; phonocardiography; morphological features; murmurs; decision-rule algorithm; eGeneralMedical databases
• ISSN: 2053-3713; 2053-3713
• DOI: 10.1049/htl.2016.0109

Accurate and reliable recognition of fundamental heart sounds (FHSs) plays a significant role in automated analysis of heart sound (HS) patterns. This Letter presents an automated wavelet-based FHS recognition (WFHSR) method using morphological and interval features. The proposed method first performs the decomposition of phonocardiogram (PCG) signal using a synchrosqueezing wavelet transform to extract the HSs and suppresses the murmurs, low-frequency and high-frequency noises. The HS delineation (HSD) is presented using Shannnon energy envelope and amplitude-dependent thresholding rule. The FHS recognition (FHSR) is presented using interval, HS duration and envelope area features with a decision-rule algorithm. The performance of the method is evaluated on PASCAL HSs Challenge, PhysioNet/CinC HS Challenge, eGeneralMedical databases and real-time recorded PCG signals. Results show that the HSD approach achieves an average sensitivity (Se) of 98.87%, positive predictivity (Pp) of 97.50% with detection error rate of 3.67% for PCG signals with signal-to-noise ratio of 10 dB, and outperforms the existing HSD methods. The proposed FHSR method achieves a Se of 99.00%, Sp of 99.08% and overall accuracy of 99.04% on both normal and abnormal PCG signals. Evaluation results show that the proposed WFHSR method is able to accurately recognise the S1/S2 HSs in noisy real-world PCG recordings with murmurs and other abnormal sounds.