Real-time target localization on 1.5 T magnetic resonance imaging linac orthogonal cine images using transfer learning
We have found the 0.35 T model trained on sagittal cine-MRIs cannot be directly applied to a 1.5 T interleaved orthogonal cine-MRI system. However, PS transfer learning could improve the target tracking performance and reach an accuracy comparable to the inter-observer variability.
Authors
- Stefanie Corradini (ORCID: https://orcid.org/0000-0001-8709-7252)
- Claus Belka (ORCID: https://orcid.org/0000-0002-1287-7825)
- Yue Zhao (ORCID: https://orcid.org/0000-0001-8390-2410)
- Christopher Kurz
- Marco Riboldi (ORCID: https://orcid.org/0000-0002-2431-4966)
- Guillaume Landry (ORCID: https://orcid.org/0000-0003-1707-4068)
- Jie Wang (ORCID: https://orcid.org/0000-0002-1262-6719)
- Fan Yu (ORCID: https://orcid.org/0000-0002-0576-7396)
- Yiling Wang (ORCID: https://orcid.org/0000-0002-6794-5004)
- Elia Lombardo (ORCID: https://orcid.org/0000-0003-4522-8298)
Institutions
- University of Electronic Science and Technology of China (CN)
- German Cancer Research Center (DE)
- LMU Klinikum (DE)
- Sichuan Cancer Hospital (CN)
- Deutsches Konsortium für Translationale Krebsforschung (DE)
- Ludwig-Maximilians-Universität München (DE)
Publication Details
- Journal
- Physics and Imaging in Radiation Oncology
- Published
- 2025-04-01
- DOI
- https://doi.org/10.1016/j.phro.2025.100789
- Primary Topic
- Medical Imaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- China Postdoctoral Science Foundation
- Sichuan Province Science and Technology Support Program