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 | |