Login (DCU Staff Only)
Login (DCU Staff Only)

DORAS | DCU Research Repository

Explore open access research and scholarly works from DCU

Advanced Search

A method for automatic segmentation of collapsed colons at CT colonography

Chowdhury, Tarik A., Whelan, Paul F. orcid logoORCID: 0000-0001-9230-7656 and Ghita, Ovidiu (2005) A method for automatic segmentation of collapsed colons at CT colonography. In: Indian International Conference on Artificial Intelligence, Dec 2005, India.

This paper details the development of a novel method for automatic segmentation of collapsed colon lumen based on prior knowledge of colon geometrical features and anatomical structure. After the removal of the surrounding air voxels and lungs from the volumetric Computed Tomography (CT) data, labeling was performed to to detect the remaining air voxel regions inside the CT data. Volume by length analysis, orientation, length, and points, geometrical position in the volumetric data, the gradient of centreline of each labeled air region were used as geometrical features to automatically segment the colon in CT data. The proposed method was validated by using 115 datasets. Collapsed colon surface detection was always higher than 95% with an average of 1.07% extra colonic surface inclusion . When the devised segmentation technique was applied to well-distended colon surface the colon detection was close to 100%
Item Type:Conference or Workshop Item (Paper)
Event Type:Conference
Uncontrolled Keywords:computer vision; image analysis; Automatic segmentation; Computed topography; CT; Colon geometrical features
DCU Faculties and Centres:DCU Faculties and Schools > Faculty of Engineering and Computing > School of Electronic Engineering
Copyright Information:© 2005 IICAI
Use License:This item is licensed under a Creative Commons Attribution-NonCommercial-Share Alike 3.0 License. View License
ID Code:18721
Deposited On:15 Aug 2013 08:26 by Mark Sweeney . Last Modified 16 Jan 2019 12:36

Full text available as:

[thumbnail of whelan_2005_98.pdf]
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader


Downloads per month over past year

Archive Staff Only: edit this record