Scholar
Stefan Denner
Google Scholar ID: WeZ0bvgAAAAJ
German Cancer Research Center
Citations & Impact
Citations
617
H-index
7
i10-index
5
Publications
20
Co-authors
13
list available
Publications
Resume (English only)
Academic Achievements
- Published a paper on multiple sclerosis lesion segmentation, proposing a multi-task learning approach that uses an auxiliary self-supervised task of deformable registration between two time-points to guide the neural network towards learning from spatio-temporal changes. The method was tested on a dataset of 70 patients, showing improved segmentation results compared to state-of-the-art methods.
Research Experience
- Involved in the RACOON project, which aims to connect all university clinics in Germany for privacy-preserving federated learning. He also works on automating the annotation and curation of medical image data to make it readily available for machine learning models.
Education
- PhD Candidate at German Cancer Research Center (DKFZ) since 2022; M.Sc. in Informatics from Technical University of Munich (TUM) in 2021; B.Sc. in Computer Science from University of Applied Sciences Würzburg-Schweinfurt in 2018.
Background
- PhD candidate in the Medical Image Computing group, focusing on bringing machine learning algorithms into clinical applications. His research interests include Deep Learning with Medical Data, Bio-signals, Computer Vision, and Software Engineering. He is part of the RACOON project, which aims to establish a nationwide network for privacy-preserving federated learning using real patient data. Additionally, he researches automatic (federated) annotation and curation of medical image data.
