In this study, an effective methodology for segmenting the temporal trace of phonocardiographic signals (PCG) is presented. Initially, inter-beat segmentation is carried out using the DII lead of the ECG recording for locating the occurrence of the first heart sound (S1). Next, the intra-beat segmentation is achieved by using recurrence time statistics (RTS), which is
IntroductionThe segmentation process of PCG signals is a very important task in order to perform murmur detection, and diagnosis of other cardiac pathologies using computer analysis. Thus, it is essential that different components of heart cycle can be timed and separated [1]. Segmentation is performed in two main steps: inter-beat segmentation and intra-beat segmentation. The first one refers to the identification and separation of the beats with the aim of performing an individual diagnostic in each one of them. The second step includes the separation of the beat into its four principal components: first cardiac sound (S1), systole, second cardiac sound (S2) and diastole [2].Cardiac murmurs are present in systole, diastole or both. In this way, it is crucial to precisely detect the boundaries in order to correctly locate the components of heart sounds (HS), and then, to perform an accurate diagnosis and classification of the murmur if it is present. The main problem in HS segmentation occurs when a murmur is present and produces high distortion in the temporal trace.A large variety of algorithms to perform PCG segmentation have been proposed in the literature. In [1] the PCG signal segmentation is based on synchronized electrocardiographic (ECG) signal acquired with PCG. On the other hand, the envelope of PCG can be used to perform the segmentation, in [3] the envelope is estimated using homomorphic filtering, while in [4] it is estimated by means of Shannon normalized average energy. Moreover, Shannon energy can be used with more complex methodologies: wavelet transform in order to enhance the spectral components of S1 and S2; or with Mel-scaled filter-banks and Hidden Markov Models. Another approach to segment PCG is based on time-frequency analysis, implemented with wavelet transform or distributions belonging to the Cohen's quadratic class. That PCG signal exhibits nonlinear dynamics, this fact motivates the use of complexity measures [5], and RTS [6]. In our work, we combine the best of these methodologies with the aim of developing a reliable algorithm capable of segmenting the PCG signal with high accuracy.In this paper, we propose a method for the boundary identification of S1 and S2, using the ECG signal as reference in order to separate each beat according to the methodology proposed in [7]; later, the end of S1, beginning of S2 and end of S2 are detected using RTS and threshold rules. The results obtained in the previous stage are validated using biomedical features; if the fiducial points are out of certain boundaries given by physiological considerations, an alternative segmentation method is used. It is based on wavelet dec...