Multi-centroid diastolic duration distribution based HSMM for heart sound segmentation. (February 2019)

• Record Type: Journal Article
• Authors: Kamson, Alex Paul; Sharma, L.N.; Dandapat, S.
• Is Part Of: Biomedical signal processing and control. Volume 48(2019)
• Page Start: 265
• Page End: 272
• Publication Date: 2019-02
• Subjects: Phononcardiogram (PCG) -- Heart sound segmentation (HSS) -- hidden semi-Markov model (HSMM) -- heart cycle duration (HCD) -- Total variation filter (TVF) -- Homomorphic Envelope of Total Variation Filter (HEoTVF); Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2018.10.018
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: The multi-centroid duration model allows a localized estimate of the duration of heart sound components and self-adjust with the variability of HCD. The cascaded Gaussian distribution of duration model provides a sharper gradient of likelihood improving the discriminability of similar observations. The dual filtering of Butterworth band-pass filter and TVF filter emphasize the S1 and S2 in PCG. Abstract: This paper presents a multi-centroid diastolic duration model for the hidden semi-Markov model (HSMM) based heart sound segmentation. The centroids are calculated by hierarchical agglomerative clustering of the neighboring diastolic duration values using Ward's method until center of clusters are found at least a systolic duration apart. The multiple peak distribution yields a sharper gradient of likelihood around the expected centroids and improves the discriminability of similar observations. The peak density at each centroid acts as a reference point for the HSMM to determine the origin of the hidden-state and adjust the corresponding state duration based on the maximum likelihood criterion. This model overcomes the limitation of the single peak mean value model that may overfit the duration distribution when the heart rate variation is relatively large. An extended logistic regression-HSMM algorithm using the proposed duration model is presented for the heart sound segmentation. In addition, the total variation filter is used to attenuate the effect of noises and emphasize the fundamental heart sounds, S1 and S2. The proposed method is evaluated on the training-set-a of 2016 Physionet/Computing in Cardiology Challenge and yields an averageF1 score of98.36 ± 0.43 .