Bridging the Generalist-Subspecialist Gap with GPT-5-Thinking: Dual-Center Evaluation in Orbital and Head-and-Neck Tumor MRI Reports

The authors aimed to determine whether the Generative Pretrained Transformer (GPT)-5-Thinking model could match subspecialist accuracy in interpreting MRI scans of orbital and head-and-neck tumors, thereby bridging the expertise gap for generalist radiologists. The study found that GPT-5-Thinking achieved diagnostic accuracy comparable to subspecialists and significantly improved the diagnostic performance of generalists when interpreting MRI reports.