<![CDATA[Background: Accurate radiographic diagnosis requires images obtained with proper technique. Artifacts are unwanted irregularities or densities not produced by the primary X-ray beam and may obscure anatomical details in radiographic images. This retrospective study aimed to evaluate the performance of ChatGPT, Claude AI, and intern dental students in detecting artifacts in panoramic radiographs (PRs). Methods: Between January and December 2024, panoramic radiographs of 40 patients containing 74 artifacts (motion, mispositioning, airway/soft tissue, and foreign body/metal artifacts) were retrospectively evaluated. The artifact detection performance of ChatGPT-4.0, Claude AI 3.5 Sonnet, and intern dental students was subsequently evaluated and compared with the radiologist-defined gold standard. Results: Dental students demonstrated higher overall accuracy than both AI models in detecting artifacts on PRs. Among the LLMs, Claude AI showed higher accuracy than ChatGPT in detecting motion artifacts (65.0% vs 42.5%), foreign body/metal artifacts (90.0% vs 62.5%), and patient mispositioning (85.0% vs 67.5%), whereas ChatGPT performed better in identifying airway/soft tissue artifacts (87.5% vs 65.0%). Conclusions: ChatGPT and Claude AI demonstrated lower performance than dental students in detecting artifacts in panoramic radiographs. These findings suggest that human evaluation remains essential in radiographic interpretation, and further development of LLMs is needed for reliable clinical application.]]>
Copyrights © 2026
