Recognition of normal–abnormal phonocardiographic signals using deep convolutional neural networks and mel-frequency spectral coefficients

Intensive care unit patients are heavily monitored, and several clinically-relevant parameters are routinely extracted from high resolution signals. OBJECTIVE The goal of the 2016 PhysioNet/CinC Challenge was to encourage the creation of an intelligent system that fused information from different phonocardiographic signals to create a robust set of normal/abnormal signal detections. APPROACH Deep convolutional neural networks and mel-frequency spectral coefficients were used for recognition of normal-abnormal phonocardiographic signals of the human heart. This technique was developed using the PhysioNet.org Heart Sound database and was submitted for scoring on the challenge test set. MAIN RESULTS The current entry for the proposed approach obtained an overall score of 84.15% in the last phase of the challenge, which provided the sixth official score and differs from the best score of 86.02% by just 1.87%.

[1]  Aggelos K. Katsaggelos,et al.  Heart sound anomaly and quality detection using ensemble of neural networks without segmentation , 2016, 2016 Computing in Cardiology Conference (CinC).

[2]  Ping Wang,et al.  A computer-aided MFCC-based HMM system for automatic auscultation , 2008, Comput. Biol. Medicine.

[3]  Sebastian Ruder,et al.  An overview of gradient descent optimization algorithms , 2016, Vestnik komp'iuternykh i informatsionnykh tekhnologii.

[4]  Masun Nabhan Homsi,et al.  Automatic heart sound recording classification using a nested set of ensemble algorithms , 2016, 2016 Computing in Cardiology Conference (CinC).

[5]  Chin-Hui Lee,et al.  On the asymptotic statistical behavior of empirical cepstral coefficients , 1993, IEEE Trans. Signal Process..

[6]  Bryan R. Conroy,et al.  Ensemble of feature-based and deep learning-based classifiers for detection of abnormal heart sounds , 2016, 2016 Computing in Cardiology Conference (CinC).

[7]  Johannes J. Struijk,et al.  No evidence of nonlinear or chaotic behavior of cardiovascular murmurs , 2011, Biomed. Signal Process. Control..

[8]  Beth Logan,et al.  Mel Frequency Cepstral Coefficients for Music Modeling , 2000, ISMIR.

[9]  Gari D Clifford,et al.  Automated signal quality assessment of mobile phone-recorded heart sound signals , 2016, Journal of medical engineering & technology.

[10]  Ignacio Diaz Bobillo,et al.  A tensor approach to heart sound classification , 2016, 2016 Computing in Cardiology Conference (CinC).

[11]  J. W. Tukey,et al.  The Measurement of Power Spectra from the Point of View of Communications Engineering , 1958 .

[12]  G. Castellanos-Dominguez,et al.  Selection of Dynamic Features Based on Time–Frequency Representations for Heart Murmur Detection from Phonocardiographic Signals , 2009, Annals of Biomedical Engineering.

[13]  Pavel Jurák,et al.  Discrimination of normal and abnormal heart sounds using probability assessment , 2016, 2016 Computing in Cardiology Conference (CinC).

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

[15]  Zeeshan Syed,et al.  A Framework for the Analysis of Acoustical Cardiac Signals , 2007, IEEE Transactions on Biomedical Engineering.

[16]  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.

[17]  Shadnaz Asgari,et al.  Pediatric heart sound segmentation using Hidden Markov Model , 2014, 2014 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[18]  Lionel Tarassenko,et al.  Support vector machine hidden semi-Markov model-based heart sound segmentation , 2014, Computing in Cardiology 2014.

[19]  S. Pavlopoulos,et al.  A decision tree – based method for the differential diagnosis of Aortic Stenosis from Mitral Regurgitation using heart sounds , 2004, Biomedical engineering online.

[20]  Ting Li,et al.  Segmentation of heart sounds based on dynamic clustering , 2012, Biomed. Signal Process. Control..

[21]  Qiao Li,et al.  An open access database for the evaluation of heart sound algorithms , 2016, Physiological measurement.

[22]  Ping Wang,et al.  Phonocardiographic Signal Analysis Method Using a Modified Hidden Markov Model , 2007, Annals of Biomedical Engineering.

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

[24]  Raimo Sepponen,et al.  Detection of cardiac pathology: time intervals and spectral analysis , 2007, Acta paediatrica.

[25]  Xinghai Yang,et al.  Heart sound diagnosis based on DTW and MFCC , 2010, 2010 3rd International Congress on Image and Signal Processing.

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

[27]  Gerald Penn,et al.  Convolutional Neural Networks for Speech Recognition , 2014, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

[28]  David S. Petruncio.  Evaluation of Various Features for Music Genre Classification with Hidden Markov Models , 2002 .

[29]  Armando J Rotondi,et al.  eICU program favorably affects clinical and economic outcomes , 2005, Critical care.

[30]  Egon Toft,et al.  Acoustic Features for the Identification of Coronary Artery Disease , 2015, IEEE Transactions on Biomedical Engineering.

[31]  H. Liang,et al.  A feature extraction algorithm based on wavelet packet decomposition for heart sound signals , 1998, Proceedings of the IEEE-SP International Symposium on Time-Frequency and Time-Scale Analysis (Cat. No.98TH8380).

[32]  Anurag Agarwal,et al.  DropConnected neural network trained with diverse features for classifying heart sounds , 2016, 2016 Computing in Cardiology Conference (CinC).

[33]  Kumar Sricharan,et al.  Classifying heart sound recordings using deep convolutional neural networks and mel-frequency cepstral coefficients , 2016, 2016 Computing in Cardiology Conference (CinC).

[34]  Mario Spagnuolo,et al.  Computer analysis of phonocardiograms , 1963 .

[35]  Ridvan Saraçoglu,et al.  Hidden Markov model-based classification of heart valve disease with PCA for dimension reduction , 2012, Eng. Appl. Artif. Intell..

[36]  Qiao Li,et al.  Classification of normal/abnormal heart sound recordings: The PhysioNet/Computing in Cardiology Challenge 2016 , 2016, 2016 Computing in Cardiology Conference (CinC).

[37]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[38]  Francesco Beritelli,et al.  Human identity verification based on Mel frequency analysis of digital heart sounds , 2009, 2009 16th International Conference on Digital Signal Processing.

[39]  L. Sakari,et al.  A heart sound segmentation algorithm using wavelet decomposition and reconstruction , 1997, Proceedings of the 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. 'Magnificent Milestones and Emerging Opportunities in Medical Engineering' (Cat. No.97CH36136).

[40]  Kuldip K. Paliwal,et al.  On the usefulness of STFT phase spectrum in human listening tests , 2005, Speech Commun..

[41]  Christer Ahlström,et al.  Nonlinear phonocardiographic Signal Processing , 2008 .

[42]  Konrad Hinsen,et al.  Numerical Python , 1996 .

[43]  Paul F. Dubois,et al.  Extending Python with Fortran , 1999, Comput. Sci. Eng..

[44]  J J Struijk,et al.  Segmentation of heart sound recordings by a duration-dependent hidden Markov model , 2010, Physiological measurement.

[45]  Travis E. Oliphant,et al.  Guide to NumPy , 2015 .

[46]  Jacques P. de Vos,et al.  Automated Pediatric Cardiac Auscultation , 2007, IEEE Transactions on Biomedical Engineering.

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

[48]  E. R. Kanasewich,et al.  Time sequence analysis in geophysics , 1973 .

[49]  J.T.E. McDonnell,et al.  Time-frequency and time-scale techniques for the classification of native and bioprosthetic heart valve sounds , 1998, IEEE Transactions on Biomedical Engineering.