Automatic segmentation of Phonocardiogram using the occurrence of the cardiac events

M. Vishwanath Shervegar, Ganesh V. Bhat

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Objective This paper presents automatic method of segmentation of heart sound using the occurrence of the cardiac rhythmic events. Methods Noisy heart sound is filtered using the 6th order Chebyshev type I low pass filter to remove the redundant noise. Bark Spectrogram is calculated from the cardiac signal by converting spectrogram to the bark scale. The bark spectrogram is smoothened and the loudness index is calculated by averaging the amplitude across all frequency bands. The loudness index is smoothened and differentiated to obtain the event detection function. The smoothened event detection function gives the occurrence of the cardiac events namely the first and the second heart sounds. Conclusion This method is highly effective in identifying peaks S1 and S2 with the segmentation accuracy of 96.98% giving an F1 measure of 97.09%. Significance This method does not require the setting up of any type of threshold. So it is a highly effective type of segmentation under noisy conditions.

Original languageEnglish
Pages (from-to)6-10
Number of pages5
JournalInformatics in Medicine Unlocked
Volume9
DOIs
Publication statusPublished - 01-01-2017
Externally publishedYes

Fingerprint

Heart Sounds
Noise

All Science Journal Classification (ASJC) codes

  • Health Informatics

Cite this

@article{6c1a7bf4012848d0a374c23ba23d676d,
title = "Automatic segmentation of Phonocardiogram using the occurrence of the cardiac events",
abstract = "Objective This paper presents automatic method of segmentation of heart sound using the occurrence of the cardiac rhythmic events. Methods Noisy heart sound is filtered using the 6th order Chebyshev type I low pass filter to remove the redundant noise. Bark Spectrogram is calculated from the cardiac signal by converting spectrogram to the bark scale. The bark spectrogram is smoothened and the loudness index is calculated by averaging the amplitude across all frequency bands. The loudness index is smoothened and differentiated to obtain the event detection function. The smoothened event detection function gives the occurrence of the cardiac events namely the first and the second heart sounds. Conclusion This method is highly effective in identifying peaks S1 and S2 with the segmentation accuracy of 96.98{\%} giving an F1 measure of 97.09{\%}. Significance This method does not require the setting up of any type of threshold. So it is a highly effective type of segmentation under noisy conditions.",
author = "Shervegar, {M. Vishwanath} and Bhat, {Ganesh V.}",
year = "2017",
month = "1",
day = "1",
doi = "10.1016/j.imu.2017.05.002",
language = "English",
volume = "9",
pages = "6--10",
journal = "Informatics in Medicine Unlocked",
issn = "2352-9148",
publisher = "Elsevier Limited",

}

Automatic segmentation of Phonocardiogram using the occurrence of the cardiac events. / Shervegar, M. Vishwanath; Bhat, Ganesh V.

In: Informatics in Medicine Unlocked, Vol. 9, 01.01.2017, p. 6-10.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automatic segmentation of Phonocardiogram using the occurrence of the cardiac events

AU - Shervegar, M. Vishwanath

AU - Bhat, Ganesh V.

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Objective This paper presents automatic method of segmentation of heart sound using the occurrence of the cardiac rhythmic events. Methods Noisy heart sound is filtered using the 6th order Chebyshev type I low pass filter to remove the redundant noise. Bark Spectrogram is calculated from the cardiac signal by converting spectrogram to the bark scale. The bark spectrogram is smoothened and the loudness index is calculated by averaging the amplitude across all frequency bands. The loudness index is smoothened and differentiated to obtain the event detection function. The smoothened event detection function gives the occurrence of the cardiac events namely the first and the second heart sounds. Conclusion This method is highly effective in identifying peaks S1 and S2 with the segmentation accuracy of 96.98% giving an F1 measure of 97.09%. Significance This method does not require the setting up of any type of threshold. So it is a highly effective type of segmentation under noisy conditions.

AB - Objective This paper presents automatic method of segmentation of heart sound using the occurrence of the cardiac rhythmic events. Methods Noisy heart sound is filtered using the 6th order Chebyshev type I low pass filter to remove the redundant noise. Bark Spectrogram is calculated from the cardiac signal by converting spectrogram to the bark scale. The bark spectrogram is smoothened and the loudness index is calculated by averaging the amplitude across all frequency bands. The loudness index is smoothened and differentiated to obtain the event detection function. The smoothened event detection function gives the occurrence of the cardiac events namely the first and the second heart sounds. Conclusion This method is highly effective in identifying peaks S1 and S2 with the segmentation accuracy of 96.98% giving an F1 measure of 97.09%. Significance This method does not require the setting up of any type of threshold. So it is a highly effective type of segmentation under noisy conditions.

UR - http://www.scopus.com/inward/record.url?scp=85029712875&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029712875&partnerID=8YFLogxK

U2 - 10.1016/j.imu.2017.05.002

DO - 10.1016/j.imu.2017.05.002

M3 - Article

VL - 9

SP - 6

EP - 10

JO - Informatics in Medicine Unlocked

JF - Informatics in Medicine Unlocked

SN - 2352-9148

ER -