Roger D. Soberanis-Mukul did his PhD (2016–2022) at the Chair for Computer Aided Medical Procedures (CAMP), TU Munich, working with Shadi Albarqouni and Nassir Navab on uncertainty-driven graph convolutional networks for refining organ segmentation (MIDL 2020, MELBA) and on artefact-aware polyp detection in endoscopy (EAD challenge). After a postdoc at the ARCADE Lab, Johns Hopkins University (2022–2025), he became a researcher at ICube and IHU Strasbourg, University of Strasbourg.
Education
- 2022PhD in Computer ScienceTechnical University of Munich
Publications 8 filter all →
An Uncertainty-Driven GCN Refinement Strategy for Organ Segmentation
Journal of Machine Learning for Biomedical Imaging (MELBA) — Special Issue: MIDL 2020, 2020
Uncertainty-based graph convolutional networks for organ segmentation refinement
To appear in the International Conference in Medical Imaging with Deep Learning, 2020, 2020
A learning without forgetting approach to incorporate artifact knowledge in polyp localization tasks
arXiv preprint arXiv:2002.02883, 2020
Polyp-artifact relationship analysis using graph inductive learned representations
arXiv preprint arXiv:2009.07109, 2020
Preprint
Medical Imaging
Focal loss for artefact detection in medical endoscopy
Proceedings of the 2019 Challenge on Endoscopy Artefacts Detection (EAD2019), Venice, Italy, 8th April, 2019