Incorporating patient-specific prior clinical knowledge to improve clinical target volume auto-segmentation generalisability for online adaptive radiotherapy of rectal cancer: A multicenter validation
Adding patient-specific weight maps makes the CTV segmentation model more robust to institutional preferences. Performance was comparable to a model trained locally from scratch. This makes this approach suitable for generalization to multiple centers.
Authors
- Uulke A. van der Heide (ORCID: https://orcid.org/0000-0002-4146-6419)
- Corrie A.M. Marijnen (ORCID: https://orcid.org/0000-0003-0189-5953)
- Femke P. Peters (ORCID: https://orcid.org/0000-0001-9085-447X)
- Martijn Intven (ORCID: https://orcid.org/0000-0002-5068-5517)
- Tomas Janssen (ORCID: https://orcid.org/0000-0003-2807-8670)
- A. Betgen (ORCID: https://orcid.org/0000-0003-2860-006X)
- Erik van der Bijl (ORCID: https://orcid.org/0000-0001-7663-4390)
- Rita Simões (ORCID: https://orcid.org/0000-0002-4976-3557)
- Wouter Van Den Wollenberg
- N Silverio
- Lisa Wiersema
Institutions
- Radboud University Nijmegen (NL)
- Heidelberg University (DE)
- University Hospital Heidelberg (DE)
- Radboud University Medical Center (NL)
- University Medical Center Utrecht (NL)
- Oncode Institute (NL)
Publication Details
- Journal
- Radiotherapy and Oncology
- Published
- 2024-12-13
- DOI
- https://doi.org/10.1016/j.radonc.2024.110667
- Citations
- 4
- Primary Topic
- Advanced Radiotherapy Techniques
- Type
- article
- Field-Weighted Citation Impact
- 2.43