Diagnosis of Heart Disorders by Heart Sound Segmentation

Phonocardiogram, the digital recording of heart sounds is becoming increasingly popular as a primary detection system for diagnosing heart disorders and it is relatively inexpensive. This study was carried out on 100 patients with normal and abnormal heart sounds. The algorithm uses homomorphic filtering to produce intensity envelopes of main heart sounds in time domain and separates that into four parts: the first heart sound, the systolic period, the second heart sound, and the diastolic period. The performance of the algorithm has been evaluated using 14000 cardiac periods from 100 digital honocardiographic recordings, including normal and abnormal heart sounds. In tests, the algorithm was over 95 percent correct in detecting the first and second heart sounds. The presented automatic segmentation algorithm using wavelet decomposition and reconstruction to select suitable frequency band for envelope calculations has been found to be effective to segment phonocardiogram signals into four parts without using an ECG.

Keywords:

Phonocardiography , murmurs , Homomorphic Filtering , Segmentation