Publications & talks
When can you trust a computer’s outline of a tumour, and how does a busy clinician check it quickly? Everything below is one of three attempts at an answer.
T2 Fast and Reliable Dosimetric Contour QA, PhD thesis, University of Bern, 2025.
C conference · J journal · W workshop · T thesis, numbered oldest to newest.
For citation counts and export-ready references, my Google Scholar profile is kept up to date.
Robust Segmentation Models
Which design choices survive a scan from a different hospital, and which quietly break. Watch them break.
- J5 The impact of U-Net architecture choices and skip connections on the robustness of segmentation across texture variations
paper - J4 DreamOn: a data augmentation strategy to narrow the robustness gap between expert radiologists and deep learning classifiers
paper - C7 Do we really need that skip-connection? Understanding its interplay with task complexity
paper · talk - W2 How do 3D image segmentation networks behave across the context versus foreground ratio trade-off?
paper · project page
Personalized Contour Review and Correction
Two experts outline the same tumour differently and both can be right. Telling genuine errors apart from reasonable disagreement.
- W4 DoMa-Seg: dose map guidance for medical image segmentation in head and neck radiotherapy
paper - J7 Predicting the impact of target volume contouring variations on the organ at risk dose: results of a qualitative survey
paper - J6 A dual-layer quality assurance approach leveraging dose prediction for efficient review of automated contours of organs at risk in the brain in radiotherapy
paper - W3 AutoDoseRank: automated dosimetry-informed segmentation ranking for radiotherapy
paper · project page - C8 Comparing the performance of radiation oncologists versus a deep learning dose predictor to estimate dosimetric impact of segmentation variations
paper · talk - C6 Dose guidance for radiotherapy-oriented deep learning segmentation
paper - C5 ASTRA: atomic surface transformations for radiotherapy quality assurance
paper · talk · project page
Fast and Sensitive Dose Prediction
Predicting the radiation dose an outline would produce in seconds rather than hours, without losing the sensitivity that makes it worth having.
- J2 Deep-learning-based dose predictor for glioblastoma: assessing the sensitivity and robustness for dose awareness in contouring
paper · project page - C4 How sensitive are deep learning based radiotherapy dose prediction models to variability in organs at risk segmentation?
paper · talk · project page - C3 Evaluating a deep learning based 3D dose prediction model for quality assurance of organ at risk contours
paper
Other Work
Outside the three axes above. The older entries are from a previous life in diffusion MRI.
- J3 Orchestrating explainable artificial intelligence for multimodal and longitudinal data in medical imaging
paper - J1 PyRaDiSe: a Python package for DICOM-RT-based auto-segmentation pipeline construction and DICOM-RT data conversion
paper · package - C2 Optimal acquisition protocol for white matter fiber orientation mapping using generalized CSA-ODF reconstruction
paper - W1 Generalized constant solid angle ODF and optimal acquisition protocol for fiber orientation mapping
paper - T1 A generalized CSA-ODF model for fiber orientation mapping
record - C1 A novel device to monitor mobilization of fingers during treatment for stiffness of tendons
paper
Talks
Invited talks and presentations, newest first. Tutorials are under Teaching.
- 2026 SSRMP webinar, December 2026 (scheduled).
- 2026 Science Slam Bern 4.0, Alumni UniBE, Stellwerk Bern: research for a general audience.
- 2026 ENLIGHT Teaching & Learning Conference, Bern: a course design in which students build with AI coding tools and are graded on explaining their work (the course).
- 2026 Invited talk, Data Science Colloquium, Utrecht University.
- 2025 Invited talk, SASRO 2025, Davos: Fast and Reliable Dosimetric Contour QA (thesis).
- 2024 Falling Walls Science Summit, Berlin: Breaking Walls with AI — Revolutionizing Radiotherapy Quality Control (Falling Walls Lab).
- 2024 Oral presentation, MIDL 2024, Paris (C8).
- 2024 Full talk, GCB Symposium 2024, Bern.
- 2023 Oral presentation, IEEE EMBC 2023, Sydney (C5).
- 2023 “Young Researchers Tales”, MVUB 8x8 event, Bern.
- 2021 Short talk with Julia Hoerner (MathWorks), Brain Tumor Segmentation with MATLAB, MIUA 2021.
- 2020 Invited short talk, i-True webinar on AI in urology, MIT Manipal, online (recording).