Variational Image Segmentation for Endoscopic Human Colonic Aberrant Crypt Foci

Author

Figueiredo, Isabel N. ; Figueiredo, Pedro N. ; Stadler, Georg ; Ghattas, Omar ; Araújo, Adérito

Author_Institution

Dept. of Math., Univ. of Coimbra, Coimbra, Portugal

Volume

29

Issue

4

fYear

2010

fDate

4/1/2010 12:00:00 AM

Firstpage

998

Lastpage

1011

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

biological organs; biomedical optical imaging; cancer; endoscopes; finite difference methods; finite element analysis; image segmentation; medical image processing; physiological models; tumours; aberrant crypt foci; active contours enhance; colorectal cancer; endoscopy; finite difference analysis; finite element analysis; human colon; variational image segmentation; Active contours; Cancer detection; Colon; Endoscopes; Finite element methods; Humans; Image edge detection; Image segmentation; In vivo; Level set; Active contours; endoscopic images; image segmentation; level sets; Aberrant Crypt Foci; Algorithms; Colorectal Neoplasms; Endoscopy, Gastrointestinal; Humans; Image Enhancement; Image Interpretation, Computer-Assisted; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity;

fLanguage

English

Journal_Title

Medical Imaging, IEEE Transactions on

Publisher

ieee

ISSN

0278-0062

Type

jour

DOI

10.1109/TMI.2009.2036258

Filename

5338023