Content-based Image Retrieval for Biomedical Image Archives:
Achievements, Problems, and Prospects

A MICCAI 2007 Workshop, October 29th, 2007

Home | Scope | Organizers | Important Dates | Submissions | Registration | Preliminary Program

In most biomedical disciplines, digital image data is rapidly expanding in quantity and heterogeneity, and there is an increasing trend towards the formation of archives adequate to support diagnostics and preventive medicine. Exploration, exploitation, and consolidation of the immense image collections, from to macro, require tools to access structurally different data for research, diagnostics and teaching. Currently, image data is linked to textual descriptions, and data access is provided only via these textual additives. There are virtually no tools available to access medical images directly by their content or to cope with their structural differences. Visual-based (i.e. content-based) indexing and retrieval based on information contained in the pixel data of medical images is expected to have a great impact on biomedical image databases. However, existing systems are not applicable to the medical imagery special needs, and novel methodologies are urgently needed

The goal of this workshop is to introduce the topic of content-based image retrieval (CBIR), in particular CBIR in medical image archives (medical image retrieval), and to brainstorm on the key issues that are critical to short- and long-term advances in the field. Also, we will assess the prospects of advancing biomedical CBIR with new, publicly-available Web-based systems, new collaborative efforts among existing research groups, or new CBIR deployments in biomedical environments where high impact is likely. Intended audience includes both the engineers and computer scientists who develop image processing algorithms, as well as medical experts who we believe can utilize the CBIR technology to augment diagnostics, research and training.

---------------------------------------------------------------------------------------------------------------------------------------------------------

The authors of the three best presentations will be invited to contribute a paper to a special issue of the International Journal of Healthcare Information Systems and Informatics (IJHISI), a publication of the

Information Resources Management Association (IRMA).

http://www.irma-international.org/journals/details.asp?id=4835

*** We are currently in the process of discussing with a publishing house a possible book in the field. Research groups contributing to the workshop may be invited to contribute a chapter on their respective research contributions.