An Algorithm for Automatic Segmentation of Heart Sound Signal Acquired Using Seismocardiography

Automatic diagnosis of the heart valve diseases generally requires the segmentation of heart sound signal. Henceforth, in this paper a novel algorithm for automatic segmentation of the heart sound signal is proposed. The heart sound signal is acquired using seismocardiography (SCG), which uses a sensor called accelerometer. The accelerometer is of small size and low weight and thus convenient to wear. The proposed algorithm performs in three steps. First, the signal is filtered using the developed denoising algorithm based on discrete wavelet transform. The computational complexity of this algorithm is reduced by processing only two levels, which are expected to have heart sound signal, and other levels are discarded. To improve the performance of denoising, an adaptive threshold is obtained for both the levels separately, and applied. Then, the denoised signal is obtained by reconstructing the thresholded coefficients. In the second step, peaks are detected in the denoised signal using an adaptive threshold, obtained using Otsu's method. Then, false detected peaks and noise contaminated parts of the signal are identified and discarded from further analyses. In the third step, the heart sound components are identified as S1, and S2 based on the energy of the particular component and segmentation is performed. The results of denoising, show that the developed algorithm outperforms the existing method. Further, the segmentation results show that the developed algorithm is able to identify the heart sound components, accurately, even in the presence of noise.