In adapting and advancing state-of-the-art medical image processing methods and their use in current clinical problems, model-based approaches and the integration of machine learning and artificial intelligence (AI) methods are playing a growing role alongside classical image processing. Numerous problems can only be solved with the help of additional prior knowledge - similar to doctors whose medical knowledge helps them interpret imaging data. We take the knowledge generated from training data and integrate it into models with which imaging data can then be analyzed automatically.
In addition to the predominant modalities of CT, MRI and ultrasound, 2D imaging data from, e.g., cameras also plays an important role. We develop computer vision methods for problems in the fields of dermatology or dentistry and offer processes for matching 2D images to radiological imaging data.