Image features of spectral correlation function for arrhythmia classification

Recently, computerized arrhythmia classification tools have been intensively used to aid physicians to recognize different irregular heartbeats. In this paper, we introduce arrhythmia CAD system exploiting cyclostationary signal analysis through estimation of the spectral correlation function for 5 different beat types. Two experiments were performed. Raw spectral correlation data were used as features in the first experiment while the other experiment which dealt with the spectral correlation coefficients as image included extraction of wavelet and shape features followed by fisher score for dimensionality reduction. As for the classification task, Support Vector Machine (SVM) with linear kernel was used for both experiments. The experimental results showed that both proposed approaches are superior compared to several state of the art methods. This approach achieved sensitivity, specificity, accuracy, positive predictive value (PPV) and negative predictive value (NPV) of 99.20%, 99.70%, 98.60%, 99.90% and 97.60% respectively.

[1]  U. Rajendra Acharya,et al.  Application of higher order spectra for accurate delineation of atrial arrhythmia , 2013, 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[2]  W. Marsden.  I and J , 2012 .

[3]  Tho Le-Ngoc,et al.  Efficient Cooperative Cyclostationary Spectrum Sensing in Cognitive Radios at Low SNR Regimes , 2011, IEEE Transactions on Wireless Communications.

[4]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[5]  David I. McLean,et al.  Detection and Analysis of Irregular Streaks in Dermoscopic Images of Skin Lesions , 2013, IEEE Transactions on Medical Imaging.

[6]  Chandan Chakraborty,et al.  Application of principal component analysis to ECG signals for automated diagnosis of cardiac health , 2012, Expert Syst. Appl..

[7]  G.B. Moody,et al.  The impact of the MIT-BIH Arrhythmia Database , 2001, IEEE Engineering in Medicine and Biology Magazine.

[8]  Enzo Pasquale Scilingo,et al.  Robust multiple cardiac arrhythmia detection through bispectrum analysis , 2011, Expert Syst. Appl..

[9]  Linda Teplitz,et al.  The Only EKG Book You'll Ever Need , 1989 .

[10]  C. Chiou,et al.  Cardiac arrhythmia diagnosis method using linear discriminant analysis on ECG signals , 2009 .

[11]  William A. Gardner,et al.  Cyclostationarity in communications and signal processing , 1994 .

[12]  Amjed S. Al-Fahoum,et al.  A quantitative analysis approach for cardiac arrhythmia classification using higher order spectral techniques , 2005, IEEE Transactions on Biomedical Engineering.

[13]  Chih-Jen Lin,et al.  Errata to "A comparison of methods for multiclass support vector machines" , 2002, IEEE Trans. Neural Networks.

[14]  David G. Stork,et al.  Pattern Classification (2nd ed.) , 1999 .

[15]  Chandan Chakraborty,et al.  Application of Higher Order cumulant Features for Cardiac Health Diagnosis using ECG signals , 2013, Int. J. Neural Syst..

[16]  J. Chambers,et al.  Blind separation of convolutive mixtures of cyclostationary signals , 2004 .

[17]  Yun-Chi Yeh,et al.  Heartbeat Case Determination Using Fuzzy Logic Method on ECG Signals , 2009 .

[18]  Che Wun Chiou,et al.  Analyzing ECG for cardiac arrhythmia using cluster analysis , 2012, Expert Syst. Appl..

[19]  Shing-Tai Pan,et al.  Heartbeat Recognition from ECG Signals Using Hidden Markov Model with Adaptive Features , 2013, 2013 14th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing.

[20]  William A. Gardner,et al.  Statistical spectral analysis : a nonprobabilistic theory , 1986 .

[21]  Chandan Chakraborty,et al.  Cardiac decision making using higher order spectra , 2013, Biomed. Signal Process. Control..

[22]  Wang Xiao-hui.  Cyclostationary Signal Analysis and Simulation for Multi-modulation Signals , 2012 .