Separation of Heart Sounds & Lung Sounds using Independent Component Analysis

Abstract

Auscultation is the most common way of physical examination of a patient by a physician. Recently, in order to develop automated home care system and to assist physician getting better auscultation results; electronic stethoscope and computer analysis have become an inevitable trend. On this account a fuzzy expert system based body sounds analysis kit designed by HemaKumar [1]. In this existing kit, the interface part design is the most important aspect. The problem with the existing design is that it needs separate channels for heart and lung sounds to be analyzed by the fuzzy model. Such separation of heart and lung sounds becomes very much important for an acute care physician in an ICCU (Intensive Coronary Care Unit). In this study, to separate the two signals, a novel Heart sound (HS) separation method based on Independent Component Analysis (ICA) is developed. This method applies an ICA algorithm to the spectrograms of two simultaneous lung sound recordings obtained at two different locations on the chest and yields the independent spectrograms of the separated signals. Then, by implementing the Inverse Short Time Fourier Transform, the separated signals are reconstructed in the time domain. The method was applied to data of 25 healthy subjects. Analysis of the results indicates the efficiency of the proposed method in terms of HS separation from lung sounds.