Automated Topographic Segmentation and Transit Time Estimation in Endoscopic Capsule Exams

Author

Cunha, J. P Silva ; Coimbra, M. ; Campos, P. ; Soares, J.M.

Author_Institution

Univ. of Aveiro, Aveiro

Volume

27

Issue

1

fYear

2008

Firstpage

19

Lastpage

27

Abstract

Endoscopic capsule is a recent medical technology with important clinical benefits but suffering from a practical handicap: long exam annotation times. This paper proposes and compares two approaches (Bayesian and support vector machines) that can be used to segment the gastrointestinal tract into its four major topographic areas, allowing the automatic estimation of the clinically relevant gastric and intestinal sections and corresponding transit times. According to medical specialists, this can reduce exam annotation times by up to 12% (15 min). This automatic tool has been integrated into our CapView annotation software that is currently being used by three medical institutions.

Keywords

Bayes methods; endoscopes; image segmentation; medical image processing; support vector machines; Bayesian approach; CapView annotation software; automated topographic segmentation; endoscopic capsule exams; gastrointestinal tract; support vector machines; transit time estimation; Batteries; Biomedical imaging; Endoscopes; Frequency; Gastrointestinal tract; Intestines; Lenses; Optical imaging; Optical transmitters; Support vector machines; Capsule endoscopy; MPEG-7; support vector machines (SVMs); video annotation; Algorithms; Artificial Intelligence; Capsule Endoscopy; Gastrointestinal Motility; Gastrointestinal Tract; Humans; Image Enhancement; Image Interpretation, Computer-Assisted; Imaging, Three-Dimensional; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity; Time Factors; User-Computer Interface;

fLanguage

English

Journal_Title

Medical Imaging, IEEE Transactions on

Publisher

ieee

ISSN

0278-0062

Type

jour

DOI

10.1109/TMI.2007.901430

Filename

4408707