Fast algorithm for detecting the most unusual part of digital images with application to medical databases

@inproceedings{Koroutchev2008FastAF,
  title={Fast algorithm for detecting the most unusual part of digital images with application to medical databases},
  author={Kostadin Koroutchev and Elka Korutcheva},
  year={2008}
}
In this paper we introduce a fast algorithm that can detect the most unusual part of a digital image. The most unusual part of a given shape is defined as a part of the image that has the maximal distance to all non interesting shapes with the same form. The method is tested on two and three-dimensional images and have shown very good results without any predefined model. The results can be used to scan large image databases, as for example medical databases.