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

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.

[1]  K. I. Ramachandran,et al.  Effective Heart Sound Segmentation and Murmur Classification Using Empirical Wavelet Transform and Instantaneous Phase for Electronic Stethoscope , 2017, IEEE Sensors Journal.

[2]  P. Wang,et al.  First Heart Sound Detection for Phonocardiogram Segmentation , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[3]  Mirko van der Baan,et al.  Applications of the synchrosqueezing transform in seismic time-frequency analysis , 2014 .

[4]  Anith Mohan,et al.  Monitoring Cardiac Stress Using Features Extracted From S 1 Heart Sounds , 2016 .

[5]  Christian Brandt,et al.  A robust heart sounds segmentation module based on S-transform , 2013, Biomed. Signal Process. Control..

[6]  J. Habetha,et al.  Detection of S1 and S2 Heart Sounds by High Frequency Signatures , 2006, 2006 International Conference of the IEEE Engineering in Medicine and Biology Society.

[7]  H. Naseri,et al.  Detection and Boundary Identification of Phonocardiogram Sounds Using an Expert Frequency-Energy Based Metric , 2012, Annals of Biomedical Engineering.

[8]  Yu Tsao,et al.  S 1 and S 2 Heart Sound Recognition using Deep Neural Networks , 2022 .

[9]  N. Suzumura,et al.  Algorithm for detecting the first and the second heart sounds by spectral tracking , 2006, Medical and Biological Engineering and Computing.

[10]  Wei Chen,et al.  An improved empirical mode decomposition-wavelet algorithm for phonocardiogram signal denoising and its application in the first and second heart sound extraction , 2013, 2013 6th International Conference on Biomedical Engineering and Informatics.

[11]  N. Intrator,et al.  Detection and identification of heart sounds using homomorphic envelogram and self-organizing probabilistic model , 2005, Computers in Cardiology, 2005.

[12]  Raymond L. Watrous,et al.  Detection of the first heart sound using a time-delay neural network , 2002, Computers in Cardiology.

[13]  Lionel Tarassenko,et al.  Logistic Regression-HSMM-Based Heart Sound Segmentation , 2016, IEEE Transactions on Biomedical Engineering.

[14]  I. Daubechies,et al.  Synchrosqueezed wavelet transforms: An empirical mode decomposition-like tool , 2011 .

[15]  J. N. Torry,et al.  Neural network and conventional classifiers to distinguish between first and second heart sounds , 1996 .

[16]  Mark D. Plumbley,et al.  Denoising and segmentation of the second heart sound using matching pursuit , 2012, 2012 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[17]  Leontios J. Hadjileontiadis,et al.  Efficient Heart Sound Segmentation and Extraction Using Ensemble Empirical Mode Decomposition and Kurtosis Features , 2014, IEEE Journal of Biomedical and Health Informatics.

[18]  Changchun Liu,et al.  Detection of the First and Second Heart Sound Using Heart Sound Energy , 2009, 2009 2nd International Conference on Biomedical Engineering and Informatics.

[19]  Feng Jiang,et al.  Measurement of Duration, Energy of Instantaneous Frequencies, and Splits of Subcomponents of the Second Heart Sound , 2015, IEEE Transactions on Instrumentation and Measurement.

[20]  Francesco Beritelli,et al.  Biometric Identification Based on Frequency Analysis of Cardiac Sounds , 2007, IEEE Transactions on Information Forensics and Security.

[21]  Raymond L. Watrous,et al.  Detection of the first and second heart sound using probabilistic models , 2003, Proceedings of the 25th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (IEEE Cat. No.03CH37439).

[22]  Yuan-Ting Zhang,et al.  Relations Between the Timing of the Second Heart Sound and Aortic Blood Pressure , 2008, IEEE Transactions on Biomedical Engineering.

[23]  K. I. Ramachandran,et al.  A novel heart sound activity detection framework for automated heart sound analysis , 2014, Biomed. Signal Process. Control..

[24]  K. P. Soman,et al.  Robust heart sound activity detection in noisy environments , 2010 .

[25]  A. Mondal,et al.  Boundary estimation of cardiac events S1 and S2 based on Hilbert transform and adaptive thresholding approach , 2013, 2013 Indian Conference on Medical Informatics and Telemedicine (ICMIT).

[26]  Gian Marti,et al.  Heart sound classification using deep structured features , 2016, 2016 Computing in Cardiology Conference (CinC).