Automatic Segmentation of Common Carotid Artery in Longitudinal Mode Ultrasound Images Using Active Oblongs

J. R. Harish Kumar, Kartik Teotia, P. Kevin Raj, Jasbon Andrade, K. V. Rajagopal, Chandra Sekhar Seelamantula

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We propose a fully automated algorithm for the segmentation of common carotid artery in longitudinal mode ultrasound images using active oblongs. The problem of segmentation and subsequent delineation of lumen-intima layer is solved as an optimization of a locally defined contrast function with respect to five degrees-of-freedom that characterize the active oblong. The detection of the common carotid artery and subsequent initialization of the active oblong inside the common carotid artery region has been done using a combination of binary thresholding, Hough transform, and pixel-offset operations. The algorithm has been validated on the Brno university signal processing lab B-mode ultrasound image database, which contains 84 longitudinal mode ultrasound images of the common carotid artery. The segmentation results are validated against the ground truth provided by two practising radiologists using Jaccard and Dice similarity measures. We have achieved a detection and segmentation accuracy of 95.2% and 97.5%, respectively.

Original languageEnglish
Title of host publication2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1353-1357
Number of pages5
ISBN (Electronic)9781479981311
DOIs
Publication statusPublished - 01-05-2019
Event44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom
Duration: 12-05-201917-05-2019

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2019-May
ISSN (Print)1520-6149

Conference

Conference44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
CountryUnited Kingdom
CityBrighton
Period12-05-1917-05-19

Fingerprint

Ultrasonics
Hough transforms
Signal processing
Pixels

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Harish Kumar, J. R., Teotia, K., Raj, P. K., Andrade, J., Rajagopal, K. V., & Sekhar Seelamantula, C. (2019). Automatic Segmentation of Common Carotid Artery in Longitudinal Mode Ultrasound Images Using Active Oblongs. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings (pp. 1353-1357). [8682301] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2019.8682301
Harish Kumar, J. R. ; Teotia, Kartik ; Raj, P. Kevin ; Andrade, Jasbon ; Rajagopal, K. V. ; Sekhar Seelamantula, Chandra. / Automatic Segmentation of Common Carotid Artery in Longitudinal Mode Ultrasound Images Using Active Oblongs. 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 1353-1357 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).
@inproceedings{6b581f813732408f8e3f9964d16fd28e,
title = "Automatic Segmentation of Common Carotid Artery in Longitudinal Mode Ultrasound Images Using Active Oblongs",
abstract = "We propose a fully automated algorithm for the segmentation of common carotid artery in longitudinal mode ultrasound images using active oblongs. The problem of segmentation and subsequent delineation of lumen-intima layer is solved as an optimization of a locally defined contrast function with respect to five degrees-of-freedom that characterize the active oblong. The detection of the common carotid artery and subsequent initialization of the active oblong inside the common carotid artery region has been done using a combination of binary thresholding, Hough transform, and pixel-offset operations. The algorithm has been validated on the Brno university signal processing lab B-mode ultrasound image database, which contains 84 longitudinal mode ultrasound images of the common carotid artery. The segmentation results are validated against the ground truth provided by two practising radiologists using Jaccard and Dice similarity measures. We have achieved a detection and segmentation accuracy of 95.2{\%} and 97.5{\%}, respectively.",
author = "{Harish Kumar}, {J. R.} and Kartik Teotia and Raj, {P. Kevin} and Jasbon Andrade and Rajagopal, {K. V.} and {Sekhar Seelamantula}, Chandra",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/ICASSP.2019.8682301",
language = "English",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1353--1357",
booktitle = "2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings",
address = "United States",

}

Harish Kumar, JR, Teotia, K, Raj, PK, Andrade, J, Rajagopal, KV & Sekhar Seelamantula, C 2019, Automatic Segmentation of Common Carotid Artery in Longitudinal Mode Ultrasound Images Using Active Oblongs. in 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings., 8682301, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2019-May, Institute of Electrical and Electronics Engineers Inc., pp. 1353-1357, 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019, Brighton, United Kingdom, 12-05-19. https://doi.org/10.1109/ICASSP.2019.8682301

Automatic Segmentation of Common Carotid Artery in Longitudinal Mode Ultrasound Images Using Active Oblongs. / Harish Kumar, J. R.; Teotia, Kartik; Raj, P. Kevin; Andrade, Jasbon; Rajagopal, K. V.; Sekhar Seelamantula, Chandra.

2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 1353-1357 8682301 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Automatic Segmentation of Common Carotid Artery in Longitudinal Mode Ultrasound Images Using Active Oblongs

AU - Harish Kumar, J. R.

AU - Teotia, Kartik

AU - Raj, P. Kevin

AU - Andrade, Jasbon

AU - Rajagopal, K. V.

AU - Sekhar Seelamantula, Chandra

PY - 2019/5/1

Y1 - 2019/5/1

N2 - We propose a fully automated algorithm for the segmentation of common carotid artery in longitudinal mode ultrasound images using active oblongs. The problem of segmentation and subsequent delineation of lumen-intima layer is solved as an optimization of a locally defined contrast function with respect to five degrees-of-freedom that characterize the active oblong. The detection of the common carotid artery and subsequent initialization of the active oblong inside the common carotid artery region has been done using a combination of binary thresholding, Hough transform, and pixel-offset operations. The algorithm has been validated on the Brno university signal processing lab B-mode ultrasound image database, which contains 84 longitudinal mode ultrasound images of the common carotid artery. The segmentation results are validated against the ground truth provided by two practising radiologists using Jaccard and Dice similarity measures. We have achieved a detection and segmentation accuracy of 95.2% and 97.5%, respectively.

AB - We propose a fully automated algorithm for the segmentation of common carotid artery in longitudinal mode ultrasound images using active oblongs. The problem of segmentation and subsequent delineation of lumen-intima layer is solved as an optimization of a locally defined contrast function with respect to five degrees-of-freedom that characterize the active oblong. The detection of the common carotid artery and subsequent initialization of the active oblong inside the common carotid artery region has been done using a combination of binary thresholding, Hough transform, and pixel-offset operations. The algorithm has been validated on the Brno university signal processing lab B-mode ultrasound image database, which contains 84 longitudinal mode ultrasound images of the common carotid artery. The segmentation results are validated against the ground truth provided by two practising radiologists using Jaccard and Dice similarity measures. We have achieved a detection and segmentation accuracy of 95.2% and 97.5%, respectively.

UR - http://www.scopus.com/inward/record.url?scp=85069004080&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069004080&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2019.8682301

DO - 10.1109/ICASSP.2019.8682301

M3 - Conference contribution

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 1353

EP - 1357

BT - 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Harish Kumar JR, Teotia K, Raj PK, Andrade J, Rajagopal KV, Sekhar Seelamantula C. Automatic Segmentation of Common Carotid Artery in Longitudinal Mode Ultrasound Images Using Active Oblongs. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 1353-1357. 8682301. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2019.8682301