Shape-based indexing in a medical image database

Reports on a prototype of a clinical radiograph image database to be indexed by image content. The underlying content-based search engine is based on the modal shape description method for characterizing the shape of a 2-D image region (S.E. Sclaroff, 1995). Using a similarity metric defined in a modal vector space, the authors´ system successfully classified radiographic images according to the dental pathologies they depicted. This successful classification demonstrates that the proposed similarity metric effectively captures clinical similarity between images in the database. The prototype is implemented in a Web-based environment, allowing remote users in the field to search a central repository of images. Examples of classification performance and typical queries are provided