Intelligent feature selection for model-based bone segmentation in digital radiographs

Publikationstyp
Conference Paper
Date Issued
2009
Sprache
English
Author(s)
Gooßen, André
Peters, Dirk
Gemoth, Thorsten
Pralow, Thomas
Grigat, Rolf-Rainer
Institut
Bildverarbeitungssysteme E-2
TORE-URI
http://hdl.handle.net/11420/10001
Article Number
5394325
Citation
International Conference on Information Technology and Applications in Biomedicine (ITAB 2009)
Contribution to Conference
9th International Conference on Information Technology and Applications in Biomedicine, ITAB 2009
Publisher DOI
10.1109/ITAB.2009.5394325
Scopus ID
2-s2.0-77949577468
Publisher
IEEE
ISBN of container
978-1-4244-5379-5
1-4244-5379-8
In this paper we propose a method to enhance Active Shape Model based bone segmentation. One major weakness of the classic algorithm is the use of a single dedicated image feature. However to model the variation of image content along the object boundaries it is more suitable to use different features for different regions. We derive an automatic intelligent selection of these features and integrate it into the classic Active Shape Model segmentation. We evaluated the proposed algorithm on the task of delineating bone structures in more than 150 clinical radiographs of the lower extremity and achieve superior accuracy compared to previously published approaches.
Subjects
Active shape models
Bone structure
Digital radiography
Orthopedic measurement
Segmentation
DDC Class
610: Medizin