Artificial intelligence-enabled ultrasound diagnosis and stratification of follicular thyroid neoplasms: a multi-center study - PubMed
12 hours ago
- #Ultrasound Diagnosis
- #Thyroid Neoplasms
- #Artificial Intelligence
- AI model developed to differentiate follicular thyroid carcinoma (FTC) from follicular thyroid adenoma (FTA) using ultrasound images.
- Multicenter study involving 31 hospitals with 1531 patients for model development and 900 for validation.
- High diagnostic performance with AUCs of 0.816-0.847 for FTC vs FTA discrimination across external test sets.
- Model outperformed radiologists and improved diagnostic accuracy as an assistive tool.
- Provides a reliable, non-invasive tool for preoperative diagnosis and risk stratification of follicular thyroid neoplasms.