Abstract not found

Content--based image retrieval systems (CBIRSs) have frequently been proposed for the use in medical image databases and PACS. Still, only few systems were developed and used in a real clinical environment. It rather seems that medical professionals define their needs and computer scientists develop systems based on data sets they receive with little or no interaction between the two groups. A first study on the diagnostic use of medical image retrieval also shows an improvement in diagnostics when using CBIRSs which underlines the potential importance of this technique.

Background: Content-based medical image retrieval is now getting more and more attention in the world, a feasible and efficient retrieving algorithm for clinical endoscopic images is urgently required. Methods: Based on the study of single feature image retrieving techniques, including color clustering, color texture and shape, a new retrieving method with multi-features fusion and relevance feedback is proposed to retrieve the desired endoscopic images. Results: A prototype system is set up to evaluate the proposed method’s performance and some evaluating parameters such as the retrieval precision & recall, statistical average position of top 5 most similar image on various features, etc. are therefore given. Conclusions: The algorithm with multi-features fusion and relevance feedback gets more accurate and quicker retrieving capability than the one with single feature image retrieving