Robert Graf

I am a researcher at the IDEAL Lab and the Paetzold Lab, working at the intersection of machine learning and medical imaging. My research focuses on developing and applying deep learning methods for medical image analysis, including diffusion models, image-to-image translation, image registration, segmentation, and automated anatomical measurements, particularly for the spine and the full torso.

Previously, I worked at the Institute of Neuroradiology at TUM University Hospital, where I developed AI-based methods for medical imaging and conducted large-scale automated statistical analyses of population imaging cohorts, including the UK Biobank and the German National Cohort (NAKO). I received my B.Sc. and M.Sc. degrees in Computer Science from the Technical University of Munich. I am interested in developing robust and scalable computational methods to extract meaningful anatomical information from medical images and advance population-based imaging research.

Google Scholar Publications LinkedIn