Boundary information‐guided adversarial diffusion model for efficient unsupervised synthetic CT generation
Extensive experiments on pelvic datasets demonstrate the effectiveness and robustness of our proposed RadADM in terms of enabling synthesizing sCT at the anatomical level. Our approach is found to offer a valuable and promising direction for clinical MR-only adaptive radiotherapy for pelvic cancer.
Authors
- Junming Jian (ORCID: https://orcid.org/0000-0003-1683-0546)
- Mingming Luo (ORCID: https://orcid.org/0000-0001-9983-2920)
- Changfei Gong (ORCID: https://orcid.org/0000-0002-1935-9684)
- Yun Zhang (ORCID: https://orcid.org/0000-0002-6361-7193)
- Xiaoping Wang (ORCID: https://orcid.org/0000-0001-6265-530X)
- Yuling Huang (ORCID: https://orcid.org/0000-0003-0018-1799)
- Xingxing Yuan (ORCID: https://orcid.org/0000-0002-9894-4127)
- Shenggou Ding
Institutions
- Jiangxi Provincial Cancer Hospital (CN)
Publication Details
- Journal
- Medical Physics
- Published
- 2025-02-28
- DOI
- https://doi.org/10.1002/mp.17723
- Primary Topic
- Generative Adversarial Networks and Image Synthesis
- Type
- article
- Field-Weighted Citation Impact
- 0.00