Multimedia Medical Conceptual Web for Intelligent Information Access

With the advancement of digital technologies for acquiring medical images and storage of digital medical records, there is now an explosion of medical information in any moderate sized hospital. Access to such information provided by standard medical databases is very limited. For text documents such as medical reports, access is primarily based on keyword matching, which is imprecise as any user of Google would have experienced. Access to images is mainly based on patient identities and, to some extent, study characteristics and modality described in DICOM (Digital Image Communications in Medicine) image file headers. The state-of-the-art in image retrieval is still struggling to bridge the so-called semantic gap between low-level image features that the computer understands and high-level concepts that humans use.

Our research goal is to go beyond the state-of-the-art in multimedia information retrieval. The proposed system will provide more efficient and precise methods for accessing medical information. This will allow the medical professionals to efficiently locate information that they seek for diagnosis, medical research, and teaching. In the Information Age, where information is the most valuable resource, the system can help to improve the quality and reduce the cost of health care and medical research and education.

Last update: 10 Sep 2008