Relevance feedback (RF) has been an active research area in Content-based Image Retrieval (CBIR). RF bridges the gap between the low-level image features and the high-level human visual perception by analyzing and employing the feedback information provided by the user. This gap becomes more evident and important in medical image retrieval due to the two distinct facts with regard to medical images: (1) subtle differences between images, even between pathological and non-pathological images; (2) subjective and different diagnosis even among experts.

 Project Sponsors:

 National Library of Medicine (2004-2005)

 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. X. Xu, D.J. Lee, S.K. Antani, L.R. Long, and J.K. Archibald,? Using Relevance Feedback with Short-term Memory for Content-based Spine X-ray Image Retrieval, ?Journal of Neurocomputing, vol. 72/10-12, p. 2259-2269, June 2009.

2. X. Xu, S.K. Antani, D.J. Lee, L.R. Long, and G.R. Thoma, ? Relevance Feedback for Shape-based Pathology in Spine X-ray Image Retrieval ?, SPIE Medical Imaging, Picture Archive and Communication Systems (PACS) and Imaging Informatics, vol. 6145-21, p. 120-129, San Diego, CA, USA, February 11-16, 2006.

3. X. Xu, D.J. Lee, S.K. Antani, and L.R. Long, ? Relevance Feedback for Spine X-ray Retrieval ?, Proceedings of The 18th IEEE Symposium on Computer-Based Medical Systems, Dublin, Ireland, p. 197-202, June 23-24, 2005.