A Preliminary Study on Deep Learning-Based Plan Quality Prediction in Gamma Knife Radiosurgery for Brain Metastases
The proposed method outperformed the baseline model in capturing overall trends, improving per-lesion accuracy, and enhancing robustness to dataset variability. It can serve as a pre-planning tool to guide planners in constraint setting and priority tuning, a post-planning quality control tool to identify subpar plans that could be substantially improved, and as a foundation for developing deep reinforcement learning-based automated planning of GK treatments for brain metastases.
Authors
- Aranee Sivananthan
- Malvern Madondo (ORCID: https://orcid.org/0000-0002-9191-0127)
- A Zhang (ORCID: https://orcid.org/0009-0001-4146-0615)
- Mohammadamin Moradi (ORCID: https://orcid.org/0000-0003-2096-6876)
- Yingzi Liu (ORCID: https://orcid.org/0000-0001-9975-0984)
- Mark Korpics (ORCID: https://orcid.org/0000-0001-8449-2986)
- Chih‐Wei Chang (ORCID: https://orcid.org/0000-0002-3818-4381)
- Zhen Tian (ORCID: https://orcid.org/0000-0002-7026-7582)
- Xiaofeng Yang (ORCID: https://orcid.org/0000-0001-9023-5855)
- Yuan Shao
- Runyu Jiang (ORCID: https://orcid.org/0000-0002-2097-764X)
Institutions
- Rush University Medical Center (US)
- Emory University (US)
- University of Chicago (US)
Publication Details
- Journal
- Cancers
- Published
- 2025-09-18
- DOI
- https://doi.org/10.3390/cancers17183056
- Primary Topic
- Advanced Radiotherapy Techniques
- Type
- article
- Field-Weighted Citation Impact
- 0.00