Model-based segmentation of CT images

Marte, O-C; Marais, P

UnisaIR Home
→
College of Science, Engineering and Technology
→
School of Computing
→
SAICSIT Digital Archive
→
SAICSIT Proceedings: 1979-2001
→
2001 National Research and Development Conference
→
View Item

dc.contributor.author	Marte, O-C
dc.contributor.author	Marais, P
dc.contributor.editor	Renaud, K.
dc.contributor.editor	Kotze, P
dc.contributor.editor	Barnard, A
dc.date.accessioned	2018-08-23T10:35:14Z
dc.date.available	2018-08-23T10:35:14Z
dc.date.issued	2001
dc.identifier.citation	Marte, O-C. & Marais, P. (2001) Model-based segmentation of CT images. Hardware, Software and Peopleware: Proceedings of the Annual Conference of the South African Institute of Computer Scientists and Information Technologists, University of South Africa, Pretoria, 25-28 September 200	en
dc.identifier.isbn	1-86888-195-4
dc.identifier.uri	http://hdl.handle.net/10500/24767
dc.description.abstract	This paper presents preliminary work on the segmentation of Computed Tomography data using a model-based approach. Conventional image processing of CT data is aimed at the production of simple iso-surfaces far surgical planning or diagnosis - such methods are not suitable far the automated detection of fractures, which is the ultimate application of our work. To address these deficiencies a surface-based technique with appropriate constraints is introduced. The output of the segmentation phase is a triangulated surface representing the bane or bones of interest. We illustrate the method applied to low resolution CT test data and discuss its robustness and performance.	en
dc.language.iso	en	en
dc.subject	Image processing	en
dc.subject	Computer vision	en
dc.subject	Registration	en
dc.subject	Segmentation	en
dc.subject	Medical imaging	en
dc.subject	Radiology	en
dc.subject	CT	en
dc.title	Model-based segmentation of CT images	en