Clustering approach to bone and soft tissue segmentation of digital radiographic images of extremities

Show simple item record

dc.contributor.author Pakin, S. Kubilay en_US
dc.contributor.author Gaborski, Roger en_US
dc.contributor.author Barski, Lori en_US
dc.contributor.author Foos, David en_US
dc.contributor.author Parker, Kevin en_US
dc.date.accessioned 2006-12-18T17:42:08Z en_US
dc.date.available 2006-12-18T17:42:08Z en_US
dc.date.issued 2003-01 en_US
dc.identifier.citation Journal of Electronic Imaging 12N1 (2003) 40-49 en_US
dc.identifier.issn 1017-9909 en_US
dc.identifier.uri http://hdl.handle.net/1850/3121 en_US
dc.description RIT community members may access full-text via RIT Libraries licensed databases: http://library.rit.edu/databases/
dc.description.abstract We present an algorithm for segmentation of computed radiography (CR) images of extremities into bone and soft tissue regions. The algorithm is region-based in which the regions are constructed using a region-growing procedure based on two different statistical tests. Following the region-growing process, a tissue classification method is employed. The purpose of the classification is to label each region as either bone or soft tissue. This binary classification goal is achieved by using a voting procedure that consists of the clustering of regions in each neighborhood system into two classes. The voting procedure provides a crucial compromise between the local and the global analysis of the image, which is necessary due to strong exposure variations seen on the imaging plate. Also, the existence of regions whose size is large enough such that exposure variations can be observed through them makes it necessary to use overlapping blocks during the classification. After the tissue classification step, the resulting bone and soft tissue regions are refined by fitting a second-order surface to each tissue, and reevaluating the label of each region according to the distance between the region and surfaces. The performance of the algorithm is tested on a variety of extremity images using manually segmented images as the gold standard. The experiments show that our algorithm provides a bone boundary with an average area overlap of 90% compared to the gold standard. en_US
dc.description.sponsorship We are grateful for support of this project by Eastman Kodak Health Imaging and the NYS Center for Electronic Imaging Systems. We would also like to thank Thomas Gaborski and Saara Totterman, MD, for their help in the acquisition of manual segmentations that were used in the segmentation evaluation and observer variability studies. en_US
dc.format.extent 566501 bytes en_US
dc.format.mimetype application/pdf en_US
dc.language.iso en_US en_US
dc.publisher International Society for Optical Engineering (SPIE) en_US
dc.relation.ispartofseries vol. 12 en_US
dc.relation.ispartofseries no. 1 en_US
dc.subject Bone en_US
dc.subject Diagnostic radiography en_US
dc.subject Edge detection en_US
dc.subject Image classification en_US
dc.subject Image segmentation en_US
dc.subject Medical image processing en_US
dc.title Clustering approach to bone and soft tissue segmentation of digital radiographic images of extremities en_US
dc.type Article en_US
dc.identifier.url http://dx.doi.org/10.1117/1.1526846

Files in this item

Files Size Format View

An open access version of this file is not available. Check "Publisher URL" field for access

This item appears in the following Collection(s)

Show simple item record

Search RIT DML


Advanced Search

Browse