Variational image segmentation for endoscopic human colonic aberrant crypt foci

Isabel N. Figueiredo, Pedro N. Figueiredo, Georg Stadler, Omar Ghattas, Adérito Araujo

Research output: Contribution to journalArticle

Abstract

The aim of this paper is to introduce a variational image segmentation method for assessing the aberrant crypt foci (ACF) in the human colon captured in vivo by endoscopy. ACF are thought to be precursors for colorectal cancer, and therefore their early detection may play an important clinical role. We enhance the active contours without edges model of Chan and Vese to account for the ACF's particular structure. We employ level sets to represent the segmentation boundaries and discretize in space by finite elements and in (artificial) time by finite differences. The approach is able to identify the ACF, their boundaries, and some of the internal crypts' orifices.

Original languageEnglish (US)
Article number5338023
Pages (from-to)998-1011
Number of pages14
JournalIEEE Transactions on Medical Imaging
Volume29
Issue number4
DOIs
StatePublished - Apr 2010

Fingerprint

Aberrant Crypt Foci
Endoscopy
Orifices
Image segmentation
Colorectal Neoplasms
Colon

Keywords

  • Active contours
  • Endoscopic images
  • Image segmentation
  • Level sets

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Radiological and Ultrasound Technology
  • Software

Cite this

Variational image segmentation for endoscopic human colonic aberrant crypt foci. / Figueiredo, Isabel N.; Figueiredo, Pedro N.; Stadler, Georg; Ghattas, Omar; Araujo, Adérito.

In: IEEE Transactions on Medical Imaging, Vol. 29, No. 4, 5338023, 04.2010, p. 998-1011.

Research output: Contribution to journalArticle

Figueiredo, Isabel N. ; Figueiredo, Pedro N. ; Stadler, Georg ; Ghattas, Omar ; Araujo, Adérito. / Variational image segmentation for endoscopic human colonic aberrant crypt foci. In: IEEE Transactions on Medical Imaging. 2010 ; Vol. 29, No. 4. pp. 998-1011.
@article{00601562c5d64b798c94eed7191a6819,
title = "Variational image segmentation for endoscopic human colonic aberrant crypt foci",
abstract = "The aim of this paper is to introduce a variational image segmentation method for assessing the aberrant crypt foci (ACF) in the human colon captured in vivo by endoscopy. ACF are thought to be precursors for colorectal cancer, and therefore their early detection may play an important clinical role. We enhance the active contours without edges model of Chan and Vese to account for the ACF's particular structure. We employ level sets to represent the segmentation boundaries and discretize in space by finite elements and in (artificial) time by finite differences. The approach is able to identify the ACF, their boundaries, and some of the internal crypts' orifices.",
keywords = "Active contours, Endoscopic images, Image segmentation, Level sets",
author = "Figueiredo, {Isabel N.} and Figueiredo, {Pedro N.} and Georg Stadler and Omar Ghattas and Ad{\'e}rito Araujo",
year = "2010",
month = "4",
doi = "10.1109/TMI.2009.2036258",
language = "English (US)",
volume = "29",
pages = "998--1011",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - Variational image segmentation for endoscopic human colonic aberrant crypt foci

AU - Figueiredo, Isabel N.

AU - Figueiredo, Pedro N.

AU - Stadler, Georg

AU - Ghattas, Omar

AU - Araujo, Adérito

PY - 2010/4

Y1 - 2010/4

N2 - The aim of this paper is to introduce a variational image segmentation method for assessing the aberrant crypt foci (ACF) in the human colon captured in vivo by endoscopy. ACF are thought to be precursors for colorectal cancer, and therefore their early detection may play an important clinical role. We enhance the active contours without edges model of Chan and Vese to account for the ACF's particular structure. We employ level sets to represent the segmentation boundaries and discretize in space by finite elements and in (artificial) time by finite differences. The approach is able to identify the ACF, their boundaries, and some of the internal crypts' orifices.

AB - The aim of this paper is to introduce a variational image segmentation method for assessing the aberrant crypt foci (ACF) in the human colon captured in vivo by endoscopy. ACF are thought to be precursors for colorectal cancer, and therefore their early detection may play an important clinical role. We enhance the active contours without edges model of Chan and Vese to account for the ACF's particular structure. We employ level sets to represent the segmentation boundaries and discretize in space by finite elements and in (artificial) time by finite differences. The approach is able to identify the ACF, their boundaries, and some of the internal crypts' orifices.

KW - Active contours

KW - Endoscopic images

KW - Image segmentation

KW - Level sets

UR - http://www.scopus.com/inward/record.url?scp=77950438513&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77950438513&partnerID=8YFLogxK

U2 - 10.1109/TMI.2009.2036258

DO - 10.1109/TMI.2009.2036258

M3 - Article

VL - 29

SP - 998

EP - 1011

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 4

M1 - 5338023

ER -