There has been growing interest in content-based indexing of biomedical images, especially for developing an automated or computer-aided interactive medical information retrieval system. A digital archive of 17,000 cervical and lumbar spine x-ray images from the second National Health and Nutrition Examination Survey (NHANES II) is maintained by the Lister Hill National Center of Biomedical Communications at National Library of Medicine (NLM) at the National Institutes of Health (NIH). Research work has been done to index and retrieve these images so that pathological features such as anterior osteophyte and disc space narrowing, could be extracted and used by medical experts and other users. We have developed query-by-sketch and query-by-example based methods for shape-based image retrieval, which offers visual search of these images.

 Project Sponsors:

 National Library of Medicine (2003)

 Collaborators:

 Dr. Sameer Antani, National Library of Medicine
 Mr. L. Rodney Long, National Library of Medicine
 Dr. George Thoma, National Library of Medicine

 Graduate Students:

 Xiaoqian Xu

Publications:

1. D.J. Lee, S.K. Antani, X. Xu, and L.R. Long, ”Design and Evaluation of a Curve Matching-Based Spine X-ray Image Retrieval System”, SPIE Medical Imaging, Picture Archive and Communication Systems (PACS) and Imaging Informatics, vol. 5748-47, p. 365-373, San Diego, CA, USA, February 12-17, 2005.

2. X. Xu, D.J. Lee, S.K. Antani, and L.R. Long, “Curve Matching for Spine X-ray Image Retrieval Using Dynamic Programming”, The 8th World Multi-Conference on Systemics, Cybernetics, and Informatics, Image, Acoustic, Speech and Signal Processing, vol. XVII, p. 172-176, Orlando, Florida, USA, July 18-21, 2004.

3. X. Xu, D.J. Lee, S.K. Antani, and L.R. Long, ”Partial Shape Matching of Spine X-ray Shapes Using Dynamic Programming”, Proceedings of The 17th IEEE Symposium on Computer-Based Medical Systems, p. 97-102 , Bethesda, Maryland, USA, June 24-25, 2004.