Deep learning-powered radiotherapy dose prediction: clinical insights from 622 patients across multiple sites tumor at a single institution
This study demonstrates that automated dose prediction can provide a robust starting point for rapid plan generation. Leveraging model-specific strengths through the "Best Selection" approach enhances prediction accuracy and shows potential to improve clinical efficiency across multiple tumor types.
Authors
- Jian Zhu (ORCID: https://orcid.org/0000-0003-2257-4593)
- Shuangshuang Li
- Yuan Zhang (ORCID: https://orcid.org/0000-0003-2726-2855)
- Juan Liu (ORCID: https://orcid.org/0000-0003-2212-8454)
- Hou Zhen
- Zidong Liu (ORCID: https://orcid.org/0000-0002-8730-997X)
- Qin L (ORCID: https://orcid.org/0000-0002-1754-7083)
- Jiabing Gu (ORCID: https://orcid.org/0000-0002-7061-6260)
- Shanbao Gao
Institutions
- Qingdao University (CN)
- Nanjing University of Information Science and Technology (CN)
- Nanjing University of Science and Technology (CN)
- Southeast University (BD)
- Nanjing Drum Tower Hospital (CN)
- Affiliated Hospital of Qingdao University (CN)
- Southeast University (CN)
- Nanjing Medical University (CN)
Publication Details
- Journal
- Radiation Oncology
- Published
- 2025-05-19
- DOI
- https://doi.org/10.1186/s13014-025-02634-7
- Citations
- 7
- Primary Topic
- Advanced Radiotherapy Techniques
- Type
- article
- Field-Weighted Citation Impact
- 13.18
Funders
- National Natural Science Foundation of China
- National Science and Technology Major Project