This article describes the use of a medical image retrieval system on a database of 16'000 fractures, selected from
surgical routine over several years. Image retrieval has been a very active domain of research for several years.
It was frequently proposed for the medical domain, but only few running systems were ever tested in clinical
routine. For the planning of surgical interventions after fractures, x-ray images play an important role. The
fractures are classified according to exact fracture location, plus whether and to which degree the fracture is
damaging articulations to see how complicated a reparation will be. Several classification systems for fractures
exist and the classification plus the experience of the surgeon lead in the end to the choice of surgical technique
(screw, metal plate, ...). This choice is strongly influenced by the experience and knowledge of the surgeons with
respect to a certain technique. Goal of this article is to describe a prototype that supplies similar cases to an
example to help treatment planning and find the most appropriate technique for a surgical intervention.
Our database contains over 16'000 fracture images before and after a surgical intervention. We use an image
retrieval system (GNU Image Finding Tool, GIFT) to find cases/images similar to an example case currently
under observation. Problems encountered are varying illumination of images as well as strong anatomic differences
between patients. Regions of interest are usually small and the retrieval system needs to focus on this region.
Results show that GIFT is capable of supplying similar cases, particularly when using relevance feedback, on
such a large database. Usual image retrieval is based on a single image as search target but for this application
we have to select images by case as similar cases need to be found and not images. A few false positive cases
often remain in the results but they can be sorted out quickly by the surgeons.
Image retrieval can well be used for the planning of operations by supplying similar cases. A variety of
challenges has been identified and partly solved (varying luminosity, small region of interested, case-based instead
of image-based). This article mainly presents a case study to identify potential benefits and problems. Several
steps for improving the system have been identified as well and will be described at the end of the paper.