Radiology-GPT: A large language model for radiology
We introduce Radiology-GPT, a large language model for radiology. Using an instruction tuning approach on an extensive dataset of radiology domain knowledge, Radiology-GPT demonstrates superior performance compared to general language models such as StableLM, Dolly, and LLaMA. It exhibits significant versatility in radiological diagnosis, research, and communication. This work serves as a catalyst for future developments in clinical NLP. The successful implementation of Radiology-GPT is indicative of the potential of localizing generative large language models, specifically tailored for distinctive medical specialties, while ensuring adherence to privacy standards such as HIPAA. The prospect of developing individualized, large-scale language models that cater to specific needs of various hospitals presents a promising direction. The fusion of conversational competence and domain-specific knowledge in these models is set to foster future development in healthcare AI. A demo of Radiology-GPT is available at https://huggingface.co/spaces/allen-eric/radiology-gpt . • Introduced Radiology-GPT, a specialized large language model for radiology. • Model exhibits enhanced performance in radiological diagnosis and research. • Localized deployment ensures privacy and regulatory compliance in healthcare. • Radiology-GPT demonstrates superior results over general-purpose language models. • Paves the way for AI integration across various medical specialties.
Authors
- Dinggang G. Shen (ORCID: https://orcid.org/0000-0002-7934-5698)
- Dajiang Zhu (ORCID: https://orcid.org/0000-0002-6940-3911)
- Sekeun Kim (ORCID: https://orcid.org/0000-0003-4196-6242)
- Chao Ju
- Quanzheng Li (ORCID: https://orcid.org/0000-0002-9651-5820)
- Zihao Wu (ORCID: https://orcid.org/0000-0001-7483-6570)
- Aoxiao Zhong (ORCID: https://orcid.org/0000-0002-7584-5476)
- Xiang Li (ORCID: https://orcid.org/0000-0002-9851-6376)
- Lin Zhao (ORCID: https://orcid.org/0000-0003-2567-627X)
- Jun Liu (ORCID: https://orcid.org/0000-0003-4007-6109)
- Cheng Chen (ORCID: https://orcid.org/0000-0002-6040-6833)
- Yiwei Li (ORCID: https://orcid.org/0000-0003-2389-3203)
- Tianming Liu (ORCID: https://orcid.org/0000-0002-8132-9048)
- Wei Liu (ORCID: https://orcid.org/0000-0003-0935-3999)
- Chong Ma (ORCID: https://orcid.org/0000-0002-5068-8814)
- Zhengliang Liu (ORCID: https://orcid.org/0000-0001-7061-6714)
- Haixing Dai
- Yi Pan (ORCID: https://orcid.org/0000-0001-8271-0521)
- Hanqi Jiang (ORCID: https://orcid.org/0009-0007-2778-959X)
- Lichao Sun (ORCID: https://orcid.org/0000-0002-5660-2102)
- Peng Shu (ORCID: https://orcid.org/0009-0008-7108-0366)
- Longtao Yang
Institutions
- Central South University (CN)
- University of Georgia (US)
- Northwestern Polytechnical University (CN)
- Lehigh University (US)
- The University of Texas at Arlington (US)
- Harvard University Press (US)
- ShanghaiTech University (CN)
- Massachusetts General Hospital (US)
- Mayo Clinic in Arizona (US)
- Mayo Clinic Hospital (US)
- United Imaging Healthcare (China) (CN)
- Second Xiangya Hospital of Central South University (CN)
- Shanghai Clinical Research Center (CN)
Publication Details
- Journal
- Meta-Radiology
- Published
- 2025-05-16
- DOI
- https://doi.org/10.1016/j.metrad.2025.100153
- Citations
- 18
- Primary Topic
- Radiomics and Machine Learning in Medical Imaging
- Type
- article
- Field-Weighted Citation Impact
- 24.48