

Image retrieval is currently a very active research field due to the large amount of visual data being produced in most modern hospitals. Most often, the goal is to aid the diagnostic process. Unfortunately, only very few medical image retrieval systems are currently used in clinical routine. One of the application domains for image retrieval is the analysis and retrieval of lung CTs. A first user study in the United States shows that these systems allow improving the diagnostic quality.
This article describes the approach to an aid for lung CT diagnostics. The analysis incorporates several steps and the goal is to automate the process as much as possible for easy integration into diagnostics. Thus, several automatic steps are proposed from a selection of the most characteristic slices, to an automatic segmentation of the lung tissue and a classification on the segmented area into diagnostic classes. Feedback to the MD will be given in the form of marked regions in the images that appear to be different from the norm of healthy tissue. We are currently working on a small set of training images with marked and annotated regions but a larger set of images for the evaluation of our algorithm is in work. For this reason, the article does currently not contain much quantitative evaluation.
For several tasks we use existing open source software such as Weka and itk. This allows an easy reproduction of the search results.