English

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

Image and Video Processing 2026-01-23 v2 Computer Vision and Pattern Recognition

Abstract

The study evaluates and compares GPT-4 and GPT-4Vision for radiological tasks, suggesting GPT-4Vision may recognize radiological features from images, thereby enhancing its diagnostic potential over text-based descriptions.

Keywords

Cite

@article{arxiv.2311.14777,
  title  = {From Text to Image: Exploring GPT-4Vision's Potential in Advanced Radiological Analysis across Subspecialties},
  author = {Felix Busch and Tianyu Han and Marcus Makowski and Daniel Truhn and Keno Bressem and Lisa Adams},
  journal= {arXiv preprint arXiv:2311.14777},
  year   = {2026}
}