Patient and fraction specific model adaptation for cone beam computed tomography (CBCT) multi‐organ segmentation
Integrating large-scale pretraining with LoRA-based patient- and fraction-specific adaptation significantly enhances CBCT multi-organ segmentation accuracy and clinical transferability. The PFS-STU-Net framework demonstrates robust performance across institutions and provides a scalable, efficient solution for real-time CBCT-guided adaptive radiotherapy.
Authors
- Keyur D Shah (ORCID: https://orcid.org/0000-0002-0886-655X)
- Joseph W. Shelton (ORCID: https://orcid.org/0000-0003-0426-8197)
- Richard L. J. Qiu (ORCID: https://orcid.org/0000-0002-7877-1900)
- Tonghe Wang (ORCID: https://orcid.org/0000-0001-9021-1204)
- Aparna H. Kesarwala (ORCID: https://orcid.org/0000-0001-8297-9643)
- Vanessa Lynne Wildman
- Ryan James Sanford
- Xiaoqian Chen
- Xiaofeng Yang
- Chih‐Wei Chang
- Yuheng Li
Institutions
- Memorial Sloan Kettering Cancer Center (US)
- Emory University (US)
Publication Details
- Journal
- Medical Physics
- Published
- 2025-12-26
- DOI
- https://doi.org/10.1002/mp.70251
- Primary Topic
- Advanced Radiotherapy Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Memorial Sloan-Kettering Cancer Center
- National Institutes of Health