From Text to Image: Exploring GPT-4Vision's Potential in Advanced Radiological Analysis across Subspecialties

This addresses the problem of improving diagnostic accuracy in radiology by leveraging vision models, but it appears incremental as it compares existing models without introducing new methods.

The study evaluated GPT-4 and GPT-4Vision for radiological tasks, finding that GPT-4Vision may recognize radiological features from images, potentially enhancing diagnostic capabilities over text-based descriptions.