Automatic Segmentation of Heart Sounds (S1 & S2) Using Wavelet

Majlesi Journal of Electrical Engineering

مقاله 8، دوره 3، شماره 1، فروردین 2009، صفحه 61-68   

نوع مقاله: Review Article

شناسه دیجیتال (DOI): 10.1234/mjee.v3i1.188

نویسندگان

MohammadAli Saghafi^* ؛ Rasoul Amirfattahi؛ Mojtaba Mansouri؛ Mohsen Kazemi

چکیده

In this paper a new method approach is proposed for automatic segmentation of heart sounds (S1, S2) based on wavelet transform. Unlike many other approaches, this method does not use ECG as reference for detection. The applied criterion for segmentation is based on a very important physiologic attribute of heart which is the difference between the pressure of heart valves while opening and closing which causes high frequency components in heart sound. The main idea in this paper is to extract detail and approximation wavelet coefficients of heart sound (PCG) to detect the heart cycle via the Shannon energy of coefficients and then segment S1 and S2. The results show the present algorithm is capable of accurate segmentation of 90% of first heart sounds (S1) and 88.9% of second heart sounds (S2).

کلیدواژه‌ها

Phonocardiogram؛ en؛ Wavelet Transform؛ Detail and Approximation coefficients؛ S1 and S2 sounds

مراجع

[1] S. Omran, M. Tayel; “A Heart Sound

Segmentation and Feature Extraction

Algorithm Using Wavelets”, 1st

International Symposium on Control,

Communications and Signal Processing, pp.

235-238, 2004.

[2] M. Karimi, R. Amirfattahi, S. Sadri;

“Noninvasive Detection and Classification

of Coronary Artery Occlusions Using

Wavelet Analysis of Heart Sounds With

Neural Networks”, The 3rd IEEE

International Seminar on Medical

Applications of signal Processing, pp.117-120,

2005.

[3] M. B. Malarvili, I. Kamarulafizam; “Heart

Sound Segmentation Algorithm Based on

Instantaneous Energy of Electro

Cardiogram” Proc. of the IEEE Conf. on

Computers in Cardiology, 327-330, 2003.

[4] N. Shamsuddin, M. N. Mustafa, S. Husin, M.

N. Taib; “Classification of Heart Sounds

[5] Using a Multilayer Feed-Forward Neural

Network”, International Conference on new

Techniques in Pharmaceutical and Biomedical

Research, pp.88-90, 2005.

[6] L. G. Gamero, R. Watrous; “Detection of the

First and Second Heart Sound Using

Probabilistic Models”, Proceedings of the 25'

Annual International Conference of the IEEE

EMBS, Mexico, pp.2877-2880, 2003.

[7] P. Wang, Y. Kim, L. H. Ling; “First Heart

Sound Detection for Phonocardiogram

Segmentation” Proc. of the IEEE

Engineering in Medicine and biology 27th

Annual Conf, pp. 5519 – 5522, 2005.

[8] S. Goutam, P. Kumar; “An Efficient Heart

Sound Segmentation Algorithm for Cardiac

Diseases”, 1st India Annual Conference, Proc.

of the IEEE INDICON, pp.344-348, 2004.

[9] K. O. Lib, Y. C. Liew, C.H Oh; “Analysis of

Mitral and Aortic Valve Vibrations and

Their Role in the Production of the First

and Second Heart Sounds”, in Journal of

Physics in Medicine and Biology, pp 727-733,

1980.

[10] J. Chebil, J. Al –Nabulsi; “Classification of

Heart Sound Signals Using Discrete

Wavelet Analysis”, International Journal of

soft Computing, PP.37-41, 2007.

[11] D. Komar, P. Carvalho, M. Antunes;

“Detection of S1 and S2 Heart Sounds by

High Frequency Signatures”, Engineering in

Medicine and Biology Society, IEEE, 1410 –

1416, 2006.

[12] J. D. Bronzion; “The Biomedical

Engineering Hand Book”, CRC Press, New

York, 1995.

[13] N. Bruce Eugene; “Biomedical Signal

Processing and Signal Modeling”, John

Wiley & Sons, 2001