Desribes the development of a segmentation algorithm which separates the heart sound signal into four parts: the first heart sound, the systole, the second heart sound and the diastole. The segmentation of phonocardiogram (PCG) signals is the first step of analysis and the most important procedure in the automatic diagnosis of heart sounds. This algorithm is based on the normalized average Shannon energy of a PCG signal. The performance of the algorithm has been evaluated using 515 periods of PCG signals recording from 37 objects including normal and abnormal. The algorithm has achieved a 93 percent correct ratio.

Heart sound segmentation algorithm based on heart sound envelogram

Antagonism of cortical excitation of striatal neurons by glutamic acid diethyl ester: evidence for glutamic acid as an excitatory transmitter in the rat striatum.

A novel method for segmentation of heart sounds (HSs) into single cardiac cycle (S"1-Systole-S"2-Diastole) using homomorphic filtering and K-means clustering is presented. Feature vectors were formed after segmentation by using Daubechies-2 wavelet detail coefficients at the second decomposition level. These feature vectors were then used as input to the neural networks. Grow and Learn (GAL) and Multilayer perceptron-Backpropagation (MLP-BP) neural networks were used for classification of three different HSs (Normal, Systolic murmur and Diastolic murmur). It was observed that the classification performance of GAL was similar to MLP-BP. However, the training and testing times of GAL were lower as compared to MLP-BP. The proposed framework could be a potential solution for automatic analysis of HSs that may be implemented in real time for classification of HSs.

Neural network classification of homomorphic segmented heart sounds

Digital low-pass differentiation is often required in processing various biological or biomechanical data. However, both the nature of biological signals and the use of micro-or minicomputers in such applications imply the need for simple, low-order, and fast differentiation methods, rather than sophisticated high-order algorithms. Responding to this need, we investigate here the low-pass first- and second-order digital differentiation from both theoretical and practical points of view, in order to achieve good and simple algorithms. In contrast with most of the research works previously done in this field, whose main aim was to achieve better accuracy even in the cost of using quite high-order algorithms, we restrict ourselves in this study only to low orders, being interested not only in the accuracy achieved, but also in the simplicity of the algorithm. After discussing the theoretical considerations concerning our optimum low-pass differentiation filters, we present our simple low-order filters and show them to be not only very convenient for use, but also almost optimum.

Digital Low-Pass Differentiation for Biological Signal Processing

This paper describes a comparative study of the envelope extraction algorithms for the cardiac sound signal segmentation. In order to extract the envelope curves based on the time elapses of the first and the second heart sounds of cardiac sound signals, three representative algorithms such as the normalized average Shannon energy, the envelope information of Hilbert transform, and the cardiac sound characteristic waveform (CSCW) are introduced. Performance comparison of the envelope extraction algorithms, and the advantages and disadvantages of the methods are examined by some parameters.

Comparison of envelope extraction algorithms for cardiac sound signal segmentation

A detection algorithm for the first and the second heart sounds, which is one of the most important problems in an automatic diagnostic system for phonocardiograms, has been developed. It is based on the frequency-domain characteristics of heart sounds analysed by a linear-prediction method. The performance of the algorithm has been evaluated in 187 samples that contain 881 cardiac cycles including normal and abnormal subjects. The algorithm uses low frequency spectral tracking for the time series of the phonocardiogram. It can track spectral level smoothly so that it is fairly effective for the detection of heart sounds. This tracking procedure can be used in other applications such as electroencephalogram processing.

Algorithm for detecting the first and the second heart sounds by spectral tracking

The paper reports some results with phonocardiogram pattern classification. Linear prediction analysis was applied to extract the spectral pattern from phonocardiogram signals, a relatively new technique. In this examination, 29 design samples are classified correctly, except for three samples; and 19 test samples correctly, except for five samples. The characteristics for each class are well extracted and the results of the classifications are good. The efficiency of the spectral features for phonocardiogram classification has been confirmed experimentally.

Pattern classification of the phonocardiogram using linear prediction analysis.

An absolute calibration by means of the reciprocity theorem has been applied to the calibration of contact-type phonocardiographic microphones. The methods are discussed in detail and examples of the results are presented. Human chest wall vibrations have been measured with these calibrated microphones and the results are also presented.

Kazuo Ikegaya

Papers

Algorithm for detecting the first and the second heart sounds by spectral tracking

Pattern classification of the phonocardiogram using linear prediction analysis.

Absolute calibration of phonocardiographic microphones and measurements of chest wall vibration.

The Two-Dimensional Inverse Omega Network.

Statistical characteristics of finite amplitude acoustic noise propagating in a tube