Segmentation of Pathological Signals Phonocardiogram by Using the Shannon Energy Envelogram

Heart sounds and murmurs provide crucial diagnosis information for several heart diseases such as natural or prosthetic valve dysfunction and heart failure, which need to isolate the cardiac pathologies whether murmurs or superimposed sounds to the heart sounds in order to better appreciate their durations to can be processed more easily. This paper presents an algorithm for the detection of heart sounds (the first and second sounds, S1 and S2) and heart murmurs. This algorithm is based essentially on the low pass filtering in order to eliminate the heart murmurs. The normalized average Shannon Energy envelogram is used for detected and to delimit the beginning and end of each heart sound with a threshold set from the maximum value of the envelope, the location of the heart sounds S1 and S2 will enable us thereafter to extract the heart murmurs using a threshold selection of them. The aim of this paper is time measurement of the sounds and the cardiac period and the interpretation of the impact of murmurs on the PCG signal.