Performance Evaluation of Medical Image Retrieval Systems Based on a Systematic Review of the Current Literature

Background and Aim: Image, as a kind of information vehicle which can convey a large volume of information, is important especially in medicine field. Existence of different attributes of image features and various search algorithms in medical image retrieval systems and lack of an authority to evaluate the quality of retrieval systems, make a systematic review in medical image retrieval systems field necessary. The objective of this study was to conduct a systematic review of papers on medical image retrieval systems appeared between 2000 and 2011. Method: The major scientific databases (Medline, Scopus, Webof Knowledge (ISI), and Google Scholar) were searched, using standard keywords in English between 2000 and 2011. All papers reviewed using standard critical assessment and grading and papers with more than half of the quality scores were considered as qualified to enter to the next stage. Then, the data in selected studies were extracted and classified. Results: Eighty sixreviewed papers were classified into 3 categories. The first category introduced new medical image retrieval systems (40%) and the second category presented a new framework for the major medical image retrieval systems (45%) and the last category was about medical image retrieval systems evaluation (15%). However, the growth rate was increasing during the period and the most papers published in 2009. The CBIR systems were used more (66%) and then hybrid systems (20%) respectively.   Conclusion: Applying medical image retrieval systems with Decision Support Systems (DSS) and other information and computer technologies can help clinicians to present a better service and can help them in diagnosis as well. Meanwhile, these systems can be very useful in education and research, the medical image retrieval systems can be more successful if they are designed for a specific field and based on new and modern image features.