What license is VQA-RAD: Visual Question Answering for Radiology under?

VQA-RAD: Visual Question Answering for Radiology is available under mit.

VQA-RAD: Visual Question Answering for Radiology

Active

VQA-RAD is the first manually constructed VQA dataset in radiology, where clinicians asked naturally occurring questions about radiology images and provided reference answers. It contains 315 radiology images (head CTs/MRIs, chest X-rays, abdominal CTs) with

Open

Publisher: U.S. National Library of Medicine (NIH/NLM)
Domain: Multimodal
License: mit
Published: Apr 2026
Notable for: Benchmark for evaluating Multimodal.
Canonical: github.com/UKGovernmentBEIS/inspect_evals/tree/main/src/inspect_evals/vqa_rad

Cite

Notes

Only stored in your browser.

Attribution

README: github.com/UKGovernmentBEIS/inspect_evals/blob/main/src/inspect_evals/vqa_rad/eval.yamlMIT

Attribution policy →

FAQ

What is VQA-RAD: Visual Question Answering for Radiology?: VQA-RAD is the first manually constructed VQA dataset in radiology, where clinicians asked naturally occurring questions about radiology images and provided reference answers. It contains 315 radiology images (head CTs/MRIs, chest X-rays, abdominal CTs) with
What license is VQA-RAD: Visual Question Answering for Radiology under?: VQA-RAD: Visual Question Answering for Radiology is available under mit.