Enhancing auto‐contouring with large language model in high‐dose rate brachytherapy for cervical cancers
This study demonstrates the feasibility and effectiveness of integrating LLM-generated task-specific prompts with DL-based segmentation for HDR-BT in CC. The proposed framework enhances segmentation consistency to support accurate treatment planning, addressing critical challenges in HDR-BT workflows.
Authors
- Abolfazl Sarikhani
- Beth Ghavidel (ORCID: https://orcid.org/0009-0003-8590-5246)
- Meysam Tavakoli (ORCID: https://orcid.org/0000-0002-7475-2139)
- Benyamin Khajetash (ORCID: https://orcid.org/0000-0002-3604-2451)
- Jing Wang
- Jiahan Zhang (ORCID: https://orcid.org/0000-0002-4288-6503)
- Mohammad Houshyari (ORCID: https://orcid.org/0000-0002-0077-0078)
- Kaida Yang (ORCID: https://orcid.org/0000-0003-2018-2625)
- Lei Yang (ORCID: https://orcid.org/0000-0001-5070-4549)
- Tian Liu (ORCID: https://orcid.org/0009-0004-2544-5732)
Institutions
- Emory University (US)
- Iran University of Medical Sciences (IR)
- Shahid Beheshti University of Medical Sciences (IR)
- Icahn School of Medicine at Mount Sinai (US)
Publication Details
- Journal
- Medical Physics
- Published
- 2025-09-23
- DOI
- https://doi.org/10.1002/mp.70034
- Citations
- 1
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 1.36