Evaluating Consistency and Accuracy of GPT-4 Omni to Analyze Thyroid Ultrasound Features and ACR TR Categories to Aid Report Generation
GPT-4o's consistency and accuracy of analyzing thyroid sonography images can be gradually improved by segmentation methods and a few-shot setting, and finally achieves a junior-radiologist level in this preliminary study. This can potentially benefit report generation, while multicenter validation is needed.
Authors
- Zebang Yang
- Tongyi Huang (ORCID: https://orcid.org/0000-0003-0737-0568)
- Xiaoer Zhang (ORCID: https://orcid.org/0000-0003-4699-9414)
- Wei Wu (ORCID: https://orcid.org/0000-0001-6984-3581)
- Jiaqian YAO
- Lei Huang
- Ming Xu
- Xiaoyan Xie
- Lin Jiang
Institutions
- Sun Yat-sen University (CN)
- The First Affiliated Hospital, Sun Yat-sen University (CN)
Publication Details
- Journal
- Current Medical Imaging Formerly Current Medical Imaging Reviews
- Published
- 2026-03-12
- DOI
- https://doi.org/10.2174/0115734056437835260214191655
- Primary Topic
- Radiology practices and education
- Type
- article
- Field-Weighted Citation Impact
- 0.00