Children can develop many of the same thyroid conditions as adults, though they're less likely to. Learn about three of the most common conditions in this article.

Background: Thyroid nodules are common, with ultrasound (US) imaging as the primary modality for their assessment. Risk stratification systems like the ACR Thyroid Imaging Reporting and Data System (TI-RADS) have been developed but suffer from inter-observer variability and low specificity. artificial intelligence (#AI) (AI), particularly large language models (LLMs) with multimodal capabilities, present opportunities for efficient end-to-end diagnostic processes. However, their clinical utility remains uncertain. Objective: This study evaluates the accuracy and consistency of multimodal LLMs for thyroid nodule risk stratification using the ACR TI-RADS system, examining the effects of model fine-tuning, image annotation, prompt engineering, and comparing open-source versus commercial models. Methods: Three multimodal vision-language models were evaluated: Microsoft's open-source LLaVA model, its medically fine-tuned variant LLaVA-Med, and OpenAI’s commercial o3 model. A total of 192 thyroid nodules from publicly available US image datasets were assessed. Each model was evaluated using two prompts (basic and modified) and two image scenarios (unlabelled vs. radiologist-annotated), yielding 6,912 responses. Model outputs were compared to expert ratings for accuracy and consistency. Statistical comparisons included Chi-square tests, Mann-Whitney U tests, and Fleiss’ kappa for inter-rater reliability. Results: Overall, 88.4% of responses were valid, with the o3 model producing the highest validity rate (98.6%), followed by LLaVA (91.5%) and LLaVA-Med (75.0%; p

Larger benign thyroid nodules were associated with a greater volume reduction among patients undergoing radiofrequency ablation.

YouTube video by BTFThyroid

YouTube video by BTFThyroid

This comprehensive book is the definitive guide to thyroid radiofrequency ablation (RFA). Thyroid nodules are prevalent many patients seek intervention.