About me

I am a PhD student in the Division of Medical Image Computing at the German Cancer Research Center (DKFZ) and a member of the Helmholtz Information and Data Science School for Health (HIDSS4Health). I develop deep learning methods for 3D medical imaging. A large part of my work is on longitudinal imaging: radiologists rarely read a scan on its own, but compare it with earlier exams to see how a lesion has changed. I build methods that use this context, from segmenting lesions consistently across follow-up scans to tracking them interactively, with the clinician verifying each step. I am also interested in foundation models for radiology, learning general 3D representations through self-supervised learning on large collections of scans and connecting images with text through vision-language pretraining. Most of my research code is open source.

Before my PhD, I studied physics at Heidelberg University, where I completed my B.Sc. and M.Sc. with a scholarship from the German Academic Scholarship Foundation (Studienstiftung des deutschen Volkes). For my master's thesis, I spent a year as a visiting research student at the Institute for Particle Physics Phenomenology (IPPP) in Durham, where I applied machine learning to the electroweak phase transition in the early universe.