Abnormal Heart Sound Diagnosis Based on Phonocardiogram Signal Processing

Phonocardiogram PCG signal analysis provides useful clinical information about the physiological and pathological condition of the heart. Since PCG signal is always contaminated with noise, the first step for PCG signal processing is the noise reduction. In this paper, we used a frequency domain adaptive line enhancer (FDALE) to reduce noise from heart sound signal as a preprocessing step. Then, a segmentation algorithm was used to divide the PCG signal into heart cycles. In the next step, we extracted features from each heart cycles based on time, frequency and Cepstral domain, and then selected the optimum feature subset. Using the selected features, PCG classification is performed to classify each segment as normal or abnormal. The experimental result shows that the accuracy of the proposed method for classifying a heart sound signal as normal or abnormal is 96.2%.

[1]  Harun Uguz,et al.  A Biomedical System Based on Artificial Neural Network and Principal Component Analysis for Diagnosis of the Heart Valve Diseases , 2012, Journal of Medical Systems.

[2]  Wen-Chung Kao,et al.  Automatic phonocardiograph signal analysis for detecting heart valve disorders , 2011, Expert Syst. Appl..

[3]  Isao Nakanishi,et al.  Speech Enhancement Based on Frequency Domain ALE with Adaptive De-Correlation Parameters , 2013 .

[4]  Abbas K. Abbas,et al.  Phonocardiography Signal Processing , 2009, Phonocardiography Signal Processing.

[5]  Goutam Saha,et al.  Detection of cardiac abnormality from PCG signal using LMS based least square SVM classifier , 2010, Expert Syst. Appl..

[6]  El-Sayed A. El-Dahshan,et al.  Denoising of Heart Sound Signals Using Discrete Wavelet Transform , 2017, Circuits Syst. Signal Process..

[7]  Zhongwei Jiang,et al.  Cardiac sound murmurs classification with autoregressive spectral analysis and multi-support vector machine technique , 2010, Comput. Biol. Medicine.

[8]  Juan Ignacio Godino-Llorente,et al.  Selection of Dynamic Features Based on Time–Frequency Representations for Heart Murmur Detection from Phonocardiographic Signals , 2009, Annals of Biomedical Engineering.

[9]  Wenjie Zhang,et al.  Heart sound classification based on scaled spectrogram and partial least squares regression , 2017, Biomed. Signal Process. Control..

[10]  Lotfi Senhadji,et al.  Bayesian denoising framework of phonocardiogram based on a new dynamical model , 2013 .

[11]  Euripidis Loukis,et al.  Support Vectors Machine-based identification of heart valve diseases using heart sounds , 2009, Comput. Methods Programs Biomed..

[12]  Juan Ignacio Godino-Llorente,et al.  Digital Auscultation Analysis for Heart Murmur Detection , 2009, Annals of Biomedical Engineering.

[13]  A. Kraskov,et al.  Estimating mutual information. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[14]  Zhongwei Jiang,et al.  Automatic moment segmentation and peak detection analysis of heart sound pattern via short-time modified Hilbert transform , 2014, Comput. Methods Programs Biomed..

[15]  Shyamala C. Doraisamy,et al.  Multi-level basis selection of wavelet packet decomposition tree for heart sound classification , 2013, Comput. Biol. Medicine.

[16]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[17]  Ali Ghaffari,et al.  Cycle selection and neuro-voting system for classifying heart sound recordings , 2016, 2016 Computing in Cardiology Conference (CinC).

[18]  Grzegorz Redlarski,et al.  Wavelet-based denoising method for real phonocardiography signal recorded by mobile devices in noisy environment , 2014, Comput. Biol. Medicine.

[19]  Swati Verma,et al.  ANALYSIS OF HEART SOUND AS BIOMETRIC USING MFCC & LINEAR SVM CLASSIFIER , 2014 .

[20]  Rainer Martin,et al.  A Frequency-Domain Adaptive Line Enhancer With Step-Size Control Based on Mutual Information for Harmonic Noise Reduction , 2016, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[21]  Wenjie Zhang,et al.  Heart sound classification based on scaled spectrogram and tensor decomposition , 2017, Expert Syst. Appl..

[22]  I. Hartimo,et al.  Heart sound segmentation algorithm based on heart sound envelogram , 1997, Computers in Cardiology 1997.

[23]  Ying-Wen Bai,et al.  The embedded digital stethoscope uses the adaptive noise cancellation filter and the type I Chebyshev IIR bandpass filter to reduce the noise of the heart sound , 2005, Proceedings of 7th International Workshop on Enterprise networking and Computing in Healthcare Industry, 2005. HEALTHCOM 2005..

[24]  Márton Áron Goda,et al.  Morphological determination of pathological PCG signals by time and frequency domain analysis , 2016, 2016 Computing in Cardiology Conference (CinC).

[25]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Saeid Sanei,et al.  Separation of heart sound signal from lung sound signal by adaptive line enhancement , 2007, 2007 15th European Signal Processing Conference.