![]() ![]() Pre-processing or automatic analysis on these data performed by a computer system is necessary for medical crews to speed up diagnosis processes. During a consultation session, massive diagnoses and media data are recorded. With developments of artificial intelligences, automatic heart sound analysis is no longer a dream (Chauhan et al., 2008, Comak et al., 2007, Debbal and Bereksi-Reguig, 2008, Jiang and Choi, 2006 Sysd, Leed, & Curtis, 2007). An experienced cardiologist can accurately auscultate and diagnose cardiac diseases, but not for inexperienced apprentices. However, the diagnosis based on heart sounds through electronic stethoscope is a very special skill which is very difficult to teach in a structured way (Alpert, 2001, Karnath and Thornton, 2002). In addition, the PCG can be used to detect heart valve disorders with higher accurate rate. Compared with other invasive and non-invasive methods, the diagnosis based on phonocardiograph (PCG) gains the advantage of friendly operation, which records sounds and murmurs by just placing the stethoscope on the skin (Geddes, 2005). Furthermore, some cardiac diseases need to be monitored continuously for a long period of time. Early detection of heart valve disorders and accurate diagnosis of heart conditions has become an important medical research field since valvular heart diseases lead to cardiopulmonary failure or even death. Heart disorders include aortic insufficiency, aortic stenosis, mitral insufficiency, mitral stenosis, and others. Heart diseases have become the second leading cause of death, and most of heart diseases result from heart valve disorders (Jiang & Choi, 2006). A very promising recognition rate has been achieved. The experiments are done by a public heart sound database released by Texas Heart Institute. Many features are extracted, but only a few specific ones are selected for the classification of each hyperplane based on a systematic approach. The feature extraction pipeline includes stages of the short-time Fourier transform, the discrete cosine transform, and the adaptive feature selection. The process of heart beat cycle segmentation includes autocorrelation for predicting the cycle time of a heart beat. This paper presents a complete heart sound analysis system covering from the segmentation of beat cycles to the final determination of heart conditions. Because of this reason, automatic heart sound analysis in computer systems would be very helpful for medical staffs. Skilled cardiologists probe heart sounds by electronic stethoscope through human ears, but interpretations of heart sounds is a very special skill which is quite difficult to teach in a structured way.
0 Comments
Leave a Reply. |
Details
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |