Experimental radiology
The vision of our newly founded "Experimental Radiology" section is the effective utilisation of radiological imaging. The potential of image data has not yet been fully utilised, particularly with regard to precision medicine. We are therefore working on pioneering and innovative methods in the field of machine learning, deep learning and computer vision to address the special challenges in radiology and thus enable better utilisation of data. Our special focus is on pioneering techniques for reliable, robust and efficient learning, especially with little, noisy or unusually annotated data.
We stand for pioneering methodological developments in the field of image-based precision medicine, often referred to as radiomics. We are interested in the entire necessary spectrum, from image registration and segmentation to classification in the sense of a "data science" approach. For us, methodological excellence always requires a view of the entire application. For this reason, our algorithmic research is flanked by improvements in imaging and clinical translation. To this end, we also use our direct integration into the Clinic for Diagnostic and Interventional Radiology, as well as close cooperation with clinical and methodological partners such as the Clinic for Nuclear Medicine and the Experimental Cardiological Imaging research group.
Research areas
Lead: Junior Professor Michael Götz
Our methodological research ranges from basic research in the field of machine learning to application-orientated image analysis. An important point here is always the question of how machine learning can also work with imperfect data. We investigate issues from the entire field of radiomics - image-based precision medicine. This includes, for example, the segmentation of medical data as well as image-based prediction.
Lead: Dr Catharina Lisson
By using new, computer-aided analysis methods, we want to enable more patient-specific image diagnostics. To this end, we use techniques such as radiomics and deep learning to discover and validate new diagnostics in clinical studies. In particular, we are looking at oncological issues to enable patient-specific therapy.
Lead: Dr Arthur Wunderlich
We are researching more patient-specific clinical imaging. We are primarily concerned with questions in the field of functional CT and MR tomography. We have particular expertise in the field of fMRI, where we conduct research in close cooperation with the Neuroradiology Section and the Department of Psychiatry (Prof Spitzer), and in relaxometry of the liver and spleen for iron quantification.
In addition, it offers a wide range of services, such as consulting for interdisciplinary research projects, particularly in the field of computer tomography and magnetic resonance imaging (MRI), ensuring the necessary knowledge in the field of ionising radiation, in particular radiation-saving X-ray examinations (e.g. low-dose CT).
Selected publications
Katerina Deike-Hofmann, Dorottya Dancs, Daniel Paech, Heinz-Peter Schlemmer, Klaus Maier-Hein, Philipp Bäumer, Alexander Radbruch, and Michael Götz."Pre-examinations Improve Automated Metastases Detection on Cranial MRI". In: Investigative Radiology (2021). DOI: 10.1097/RLI.0000000000000745
Michael Götz and Klaus H. Maier-Hein."Optimal Statistical Incorporation of Independent Feature Stability Information into Radiomics Studies". In: Scientific Reports (2020). DOI: 10.1038/s41598-020-57739-8
David Bonekamp, Simon Kohl, Manuel Wiesenfarth, Patrick Schelb, Jan Philipp Radtke, Michael Götz, Philipp Kickingereder, Kaneschka Yaqubi, Bertram Hitthaler, Nils Gählert, Tristan Anselm Kuder, Fenja Deister, Martin Freitag, Markus Hohenfellner, Boris A. Hadaschik, Heinz-Peter Schlemmer, and Klaus H. Maier-Hein."Radiomic Machine Learning for Characterisation of Prostate Lesions with MRI: Comparison to ADC Values". In: Radiology (07/2018). DOI: 10.1148/radiol.2018173064
Philipp Kickingereder, Michael Götz, John Muschelli, Antje Wick, Ulf Neuberger, Russell T. Shinohara, Martin Sill, Martha Nowosielski, Heinz-Peter Schlemmer, Alexander Radbruch, Wolfgang Wick, Martin Bendszus, Klaus H. Maier-Hein, and David Bonekamp."Large-scale Radiomic Profiling of Recurrent Glioblastoma Identifies an Imaging Predictor for Stratifying Anti-Angiogenic Treatment Response". In: Clinical Cancer Research (2016). DOI: 10.1158/1078-0432.CCR-16-0702.
Götz, Michael, Christian, Weber, Franciszek, Binczyk, Joanna, Polanska, Rafal, Tarnawski, Barbara, Bobek-Billewicz, Ullrich, Köthe, Jens, Kleesiek, Bram, Stieltjes, and Klaus H., Maier-Hein."DALSA: Domain Adaptation for Supervised Learning From Sparsely Annotated MR Images". In IEEE Transactions on Medical Imaging (2016): DOI: 10.1109/TMI.2015.2463078
See also google scholar or publons for a complete list of publications.
Vacancies
We are always looking for new Bachelor, Master or PhD students. For more information, please contact the section head or the heads of the subgroups directly.