Automatic polyp region segmentation for colonoscopy images using watershed algorithm and ellipse segmentation

Sae Hwang, JungHwan Oh, Wallapak Tavanapong, Johnny Wong, Piet C. De Groen

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

2 Citations (Scopus)

Abstract

In the US, colorectal cancer is the second leading cause of all cancer deaths behind lung cancer. Colorectal polyps are the precursor lesions of colorectal cancer. Therefore, early detection of polyps and at the same time removal of these precancerous lesions is one of the most important goals of colonoscopy. To objectively document detection and removal of colorectal polyps for quality purposes, and to facilitate real-time detection of polyps in the future, we have initiated a computer-based research program that analyzes video files created during colonoscopy. For computer-based detection of polyps, texture based techniques have been proposed. A major limitation of the existing texture-based analytical methods is that they depend on a fixed-size analytical window. Such a fixed-sized window may work for still images, but is not efficient for analysis of colonoscopy video files, where a single polyp can have different relative sizes and color features, depending on the viewing position and distance of the camera. In addition, the existing methods do not consider shape features. To overcome these problems, we here propose a novel polyp region segmentation method primarily based on the elliptical shape that nearly all small polyps and many larger polyps possess. Experimental results indicate that our proposed polyp detection method achieves a sensitivity and specificity of 93% and 98%, respectively.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume6514
EditionPART 1
DOIs
StatePublished - 2007
EventMedical Imaging 2007: Computer-Aided Diagnosis - San Diego, CA
Duration: Feb 20 2007Feb 22 2007

Other

OtherMedical Imaging 2007: Computer-Aided Diagnosis
CitySan Diego, CA
Period2/20/072/22/07

Fingerprint

Watersheds
Textures
Cameras
Color

Keywords

  • Colonoscopy video
  • Ellipse segmentation
  • Polyp segmentation
  • Watershed image segmentation

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Hwang, S., Oh, J., Tavanapong, W., Wong, J., & De Groen, P. C. (2007). Automatic polyp region segmentation for colonoscopy images using watershed algorithm and ellipse segmentation. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (PART 1 ed., Vol. 6514). [65141D] https://doi.org/10.1117/12.709835

Automatic polyp region segmentation for colonoscopy images using watershed algorithm and ellipse segmentation. / Hwang, Sae; Oh, JungHwan; Tavanapong, Wallapak; Wong, Johnny; De Groen, Piet C.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6514 PART 1. ed. 2007. 65141D.

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

Hwang, S, Oh, J, Tavanapong, W, Wong, J & De Groen, PC 2007, Automatic polyp region segmentation for colonoscopy images using watershed algorithm and ellipse segmentation. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. PART 1 edn, vol. 6514, 65141D, Medical Imaging 2007: Computer-Aided Diagnosis, San Diego, CA, 2/20/07. https://doi.org/10.1117/12.709835
Hwang S, Oh J, Tavanapong W, Wong J, De Groen PC. Automatic polyp region segmentation for colonoscopy images using watershed algorithm and ellipse segmentation. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. PART 1 ed. Vol. 6514. 2007. 65141D https://doi.org/10.1117/12.709835
Hwang, Sae ; Oh, JungHwan ; Tavanapong, Wallapak ; Wong, Johnny ; De Groen, Piet C. / Automatic polyp region segmentation for colonoscopy images using watershed algorithm and ellipse segmentation. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 6514 PART 1. ed. 2007.
@inproceedings{d0744701057a49da81c5aed6d59c14ec,
title = "Automatic polyp region segmentation for colonoscopy images using watershed algorithm and ellipse segmentation",
abstract = "In the US, colorectal cancer is the second leading cause of all cancer deaths behind lung cancer. Colorectal polyps are the precursor lesions of colorectal cancer. Therefore, early detection of polyps and at the same time removal of these precancerous lesions is one of the most important goals of colonoscopy. To objectively document detection and removal of colorectal polyps for quality purposes, and to facilitate real-time detection of polyps in the future, we have initiated a computer-based research program that analyzes video files created during colonoscopy. For computer-based detection of polyps, texture based techniques have been proposed. A major limitation of the existing texture-based analytical methods is that they depend on a fixed-size analytical window. Such a fixed-sized window may work for still images, but is not efficient for analysis of colonoscopy video files, where a single polyp can have different relative sizes and color features, depending on the viewing position and distance of the camera. In addition, the existing methods do not consider shape features. To overcome these problems, we here propose a novel polyp region segmentation method primarily based on the elliptical shape that nearly all small polyps and many larger polyps possess. Experimental results indicate that our proposed polyp detection method achieves a sensitivity and specificity of 93{\%} and 98{\%}, respectively.",
keywords = "Colonoscopy video, Ellipse segmentation, Polyp segmentation, Watershed image segmentation",
author = "Sae Hwang and JungHwan Oh and Wallapak Tavanapong and Johnny Wong and {De Groen}, {Piet C.}",
year = "2007",
doi = "10.1117/12.709835",
language = "English (US)",
isbn = "0819466328",
volume = "6514",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
edition = "PART 1",

}

TY - GEN

T1 - Automatic polyp region segmentation for colonoscopy images using watershed algorithm and ellipse segmentation

AU - Hwang, Sae

AU - Oh, JungHwan

AU - Tavanapong, Wallapak

AU - Wong, Johnny

AU - De Groen, Piet C.

PY - 2007

Y1 - 2007

N2 - In the US, colorectal cancer is the second leading cause of all cancer deaths behind lung cancer. Colorectal polyps are the precursor lesions of colorectal cancer. Therefore, early detection of polyps and at the same time removal of these precancerous lesions is one of the most important goals of colonoscopy. To objectively document detection and removal of colorectal polyps for quality purposes, and to facilitate real-time detection of polyps in the future, we have initiated a computer-based research program that analyzes video files created during colonoscopy. For computer-based detection of polyps, texture based techniques have been proposed. A major limitation of the existing texture-based analytical methods is that they depend on a fixed-size analytical window. Such a fixed-sized window may work for still images, but is not efficient for analysis of colonoscopy video files, where a single polyp can have different relative sizes and color features, depending on the viewing position and distance of the camera. In addition, the existing methods do not consider shape features. To overcome these problems, we here propose a novel polyp region segmentation method primarily based on the elliptical shape that nearly all small polyps and many larger polyps possess. Experimental results indicate that our proposed polyp detection method achieves a sensitivity and specificity of 93% and 98%, respectively.

AB - In the US, colorectal cancer is the second leading cause of all cancer deaths behind lung cancer. Colorectal polyps are the precursor lesions of colorectal cancer. Therefore, early detection of polyps and at the same time removal of these precancerous lesions is one of the most important goals of colonoscopy. To objectively document detection and removal of colorectal polyps for quality purposes, and to facilitate real-time detection of polyps in the future, we have initiated a computer-based research program that analyzes video files created during colonoscopy. For computer-based detection of polyps, texture based techniques have been proposed. A major limitation of the existing texture-based analytical methods is that they depend on a fixed-size analytical window. Such a fixed-sized window may work for still images, but is not efficient for analysis of colonoscopy video files, where a single polyp can have different relative sizes and color features, depending on the viewing position and distance of the camera. In addition, the existing methods do not consider shape features. To overcome these problems, we here propose a novel polyp region segmentation method primarily based on the elliptical shape that nearly all small polyps and many larger polyps possess. Experimental results indicate that our proposed polyp detection method achieves a sensitivity and specificity of 93% and 98%, respectively.

KW - Colonoscopy video

KW - Ellipse segmentation

KW - Polyp segmentation

KW - Watershed image segmentation

UR - http://www.scopus.com/inward/record.url?scp=35248899541&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35248899541&partnerID=8YFLogxK

U2 - 10.1117/12.709835

DO - 10.1117/12.709835

M3 - Conference contribution

AN - SCOPUS:35248899541

SN - 0819466328

SN - 9780819466327

VL - 6514

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

ER -