An unsupervised and uncued segmentation methodology using a time-scale representation correctly segmented over 90% of 1068 fundamental heart sounds in phonocardiograms.
A novel unsupervised methodology using time-scale representation successfully segments fundamental heart sounds in phonocardiograms without requiring supplementary ECG cues or training examples.
A methodology is proposed to segment and label the fundamental activities, namely the first and second heart sounds, S1 and S2, of the phonocardiogram (PCG). Information supplementary to the PCG, such as a cue from a synchronously acquired electrocardiogram (ECG), subject-specific prior information, or training examples regarding the activities, is not required by the proposed methodology. A bank of Morlet wavelet correlators is used to obtain a time-scale representation of the PCG. An energy profile of the time-scale representation and a singular value decomposition (SVD) technique are used to identify segments of the PCG that contain the fundamental activities. The robustness of the methodology is demonstrated by the correct segmentation of over 90% of 1068 fundamental activities in a challenging set of PCGs which were recorded from patients with normally functioning and abnormally functioning bioprosthetic valves. The PCGs included highly varying fundamental activities that overlapped in time and frequency with other aberrant non-fundamental activities such as murmurs and noise-like artifacts.
Rajan et al. (Tue,) conducted a other in Normally and abnormally functioning bioprosthetic valves. Unsupervised and uncued segmentation methodology using a time-scale representation was evaluated on Correct segmentation of fundamental activities (S1 and S2). An unsupervised and uncued segmentation methodology using a time-scale representation correctly segmented over 90% of 1068 fundamental heart sounds in phonocardiograms.