Enhancing online adaptive radiotherapy with uncertainty based segmentation error and out-of-distribution detection
Uncertainty estimation from a DL-based segmentation model was seen to correlate with Dice scores for segmentation of MR-guided radiotherapy prostate cancer images. This implies that uncertainty estimation could be used to label the quality of the segmentations in the online adaptive radiotherapy workflow. Preliminary results showed that uncertainty estimation could be used to distinguish between ID and OOD data.
Authors
- Samuel Fransson (ORCID: https://orcid.org/0000-0002-7883-5724)
- David Tilly (ORCID: https://orcid.org/0000-0002-2842-7116)
- Robin Viktor Strand
- Marissa van Lente
- Josien Pluim
Institutions
- Uppsala University (SE)
- Information Technology University (PK)
- Uppsala University Hospital (SE)
- Radboud University Nijmegen (NL)
- University Medical Center (US)
- Radboud University Medical Center (NL)
- Eindhoven University of Technology (NL)
Publication Details
- Journal
- Frontiers in Oncology
- Published
- 2026-01-14
- DOI
- https://doi.org/10.3389/fonc.2025.1637198
- Primary Topic
- Advanced Radiotherapy Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00