Large language models for efficient whole-organ MRI score-based reports and categorization in knee osteoarthritis
GPT-4o successfully generated WORMS-based knee MRI reports. GPT-4o with COT prompting achieved impressive accuracy in categorizing knee OA severity. Greater preference and higher efficiency were reported for LLM-generated reports.
Authors
- Hongyue Tao (ORCID: https://orcid.org/0000-0003-0681-1229)
- Hong Liang (ORCID: https://orcid.org/0000-0002-3430-9167)
- Yuxue Xie (ORCID: https://orcid.org/0000-0002-5008-6725)
- Xinmin Lu
- Lei Wang (ORCID: https://orcid.org/0000-0003-2887-6322)
- Shuang Chen (ORCID: https://orcid.org/0000-0001-6716-1763)
- Yiwen Hu (ORCID: https://orcid.org/0000-0003-2779-3066)
- Zhonghua Hu (ORCID: https://orcid.org/0000-0002-4210-3329)
- Xiangwen Li (ORCID: https://orcid.org/0000-0002-8274-6679)
Institutions
- Fudan University (CN)
- Shanghai Institute of Process Automation Instrumentation (China) (CN)
- Huashan Hospital (CN)
- Siemens (China) (CN)
Publication Details
- Journal
- Insights into Imaging
- Published
- 2025-05-14
- DOI
- https://doi.org/10.1186/s13244-025-01976-w
- Citations
- 3
- Primary Topic
- Radiology practices and education
- Type
- article
- Field-Weighted Citation Impact
- 4.08
Funders
- National Natural Science Foundation of China