Comparison between multimodal foundation models and radiologists for the diagnosis of challenging neuroradiology cases with text and images.
Journal:
Diagnostic and interventional imaging
Published Date:
May 9, 2025
Abstract
PURPOSE: The purpose of this study was to compare the ability of two multimodal models (GPT-4o and Gemini 1.5 Pro) with that of radiologists to generate differential diagnoses from textual context alone, key images alone, or a combination of both using complex neuroradiology cases.
Authors
Keywords
No keywords available for this article.