Synthetic CT generation from CBCT using deep learning for adaptive radiotherapy in prostate cancer
Deep learning models trained with simple architectures such as U-Net and ResU-Net provide effective and feasible solutions for the generation of clinically relevant sCT from CBCT images, supporting accurate dose calculation and facilitating adaptive radiotherapy workflows in prostate cancer management.
Authors
- Mustafa Çağlar (ORCID: https://orcid.org/0000-0002-0106-7683)
- M Cebe (ORCID: https://orcid.org/0009-0007-6923-4998)
- Evrim Metcalfe (ORCID: https://orcid.org/0000-0002-6769-1788)
- İsmail Oğuz Kara (ORCID: https://orcid.org/0000-0003-4963-2028)
- Navid Kheradmand (ORCID: https://orcid.org/0009-0005-6556-598X)
- Kerime Selin Ertaş
Institutions
- Istanbul Medipol University (TR)
Publication Details
- Journal
- Frontiers in Radiology
- Published
- 2025-11-13
- DOI
- https://doi.org/10.3389/fradi.2025.1680803
- Citations
- 1
- Primary Topic
- Advanced Radiotherapy Techniques
- Type
- article
- Field-Weighted Citation Impact
- 1.88