Classi cation-Driven Medical Image Retrieval

We propose a novel image retrieval framework centered around classi cation-driven search for a weighted similarity metric for image retrieval. This approach is rmly rooted in Bayes decision theory. Given a well-de ned image set, we argue that image classi cation and image retrieval share fundamentally the same goal. Thus, the distance metric de ning a classi er that performs well on the image set should also generate good results when used as the similarity metric for image retrieval. In this paper we report our methodology and initial results on neuroradiological image retrieval, where the approximate bilateral symmetry of normal human brains is exploited.