Hello World!
I’m a Ph.D candidate at CV:HCI Lab at the Karlsruhe Institute of Technology (KIT). My project is part of the Helmholtz Information & Data Science School for Health, a doctoral program jointly organized by KIT, the German Cancer Research Center (DKFZ), and Heidelberg University.
Under the supervision of Prof. Rainer Stiefelhagen and Prof. Dr. Dr. Jens Kleesiek I am exploring the exciting intersection of computer vision and radiology.
My research aims to contribute to scalable and clinically meaningful medical image segmentation by exploring methods for generating large anatomical datasets with minimal expert input, integrating anatomical priors into pathology modeling, and developing structure-aware evaluation metrics.
Quick Summary
Within my thesis I focus on advancing medical image segmentation at scale by minimizing radiologist involvement in dataset creation. I develop methods to generate large anatomical datasets through aggregation and semi-automated refinement. Recognizing that large datasets inevitably include annotation noise, I investigate how label quality affects model performance under varying scenarios, including pretraining and task-specific fine-tuning. A core focus is leveraging anatomical priors to improve pathology segmentation, based on the hypothesis that pathology can be modeled as deviations from normal anatomy. I formalized this through the Anatomy-Pathology Exchange (APEx) model. To assess segmentation quality beyond pixel-wise metrics, I develop component-level evaluation methods (e.g. CC metrics) that better reflect clinical relevance. Overall, my work seeks to enable scalable, anatomy-informed, and robust medical image segmentation.
Selected Publications
(* indicates shared authorship)
