Patient-specific deep learning tracking for real-time 2D pancreas localisation in kV-guided radiotherapy
The patient-specific CBCT-models outperformed the CT-models and predicted the three contours with 90th-percentile error ≤2.0 mm, indicating the potential for clinical real-time application.
Authors
- Carlito Coronel
- Paul Keall (ORCID: https://orcid.org/0000-0003-4803-6507)
- Adam Mylonas (ORCID: https://orcid.org/0000-0001-6941-383X)
- Maegan Stewart (ORCID: https://orcid.org/0000-0002-7756-5187)
- Brian V. Y. Chow (ORCID: https://orcid.org/0000-0001-9294-3361)
- Jeremy Booth (ORCID: https://orcid.org/0000-0003-4004-1109)
- Ryan Brown (ORCID: https://orcid.org/0000-0002-7650-9685)
- Meegan Shepherd (ORCID: https://orcid.org/0000-0001-8041-8017)
- Alex Turk
- Leigh Ambrose (ORCID: https://orcid.org/0000-0002-2565-4807)
- Andrew Kneebone (ORCID: https://orcid.org/0000-0002-7629-504X)
- Levi Madden (ORCID: https://orcid.org/0000-0002-7754-0756)
- Abdella Ahmed (ORCID: https://orcid.org/0000-0002-8210-4908)
- George Hruby (ORCID: https://orcid.org/0000-0003-4193-9682)
- Gabrielle Metz
- M. Crispin
Institutions
- University of Technology Sydney (AU)
- The University of Sydney (AU)
- Royal North Shore Hospital (AU)
Publication Details
- Journal
- Physics and Imaging in Radiation Oncology
- Published
- 2025-06-06
- DOI
- https://doi.org/10.1016/j.phro.2025.100794
- Citations
- 1
- Primary Topic
- Advanced Radiotherapy Techniques
- Type
- article
- Field-Weighted Citation Impact
- 1.88
Funders
- Varian Medical Systems