New multimodal large language models (LLMs) like OpenAI o3 and Gemini 2.5 Pro demonstrated significant advancements in answering Japanese radiology board exam questions, particularly with image input.
Key Details
- 1Eight LLMs were tested on the Japan Diagnostic Radiology Board Examination (JDRBE).
- 2OpenAI o3 achieved 67% accuracy (text-only) and 72% with image input.
- 3Gemini 2.5 Pro also showed notable accuracy improvements with image data.
- 4Both OpenAI o3 and Gemini 2.5 Pro received higher legitimacy scores from radiologist raters than some competitors.
- 5The test set included 233 questions and 477 images (184 CT, 159 MRI, 15 x-ray, 90 nuclear medicine).
- 6Image input statistically improved diagnostic accuracy for several models.
Why It Matters
This study marks the first demonstration of statistically significant improvement in LLM diagnostic accuracy with image input on a radiology board exam, signaling meaningful progress for AI-assisted radiological training and assessment.
Source
AuntMinnie
Related News
•Radiology Business
Study Highlights Limitations of AI in Prostate MRI Screening
New research points to several shortcomings in implementing AI for MRI-based prostate cancer screening.
•AuntMinnie
Deep Learning Model Predicts Brain Tumor MRI Enhancement Without Gadolinium
German researchers developed a deep learning approach to predict MRI contrast enhancement in brain tumors without the need for gadolinium-based agents.
•HealthExec
Stanford Study: LLM-Generated Hospital Notes Safe, Aid Physician Wellbeing
Stanford research shows agentic LLMs can safely draft hospital discharge summaries, reducing physician burnout with minimal risk of patient harm.