RadImageNet-VQA: A Large-Scale CT and MRI Dataset for Radiologic Visual Question Answering
Abstract
In this work, we introduce RadImageNet-VQA, a large-scale dataset designed to advance radiologic visual question answering (VQA) on CT and MRI exams. While existing medical VQA datasets are limited in scale, dominated by X-ray imaging or biomedical illustrations, and prone to text-based shortcuts, RadImageNet-VQA is built from expert-curated annotations and provides 750K images paired with 7.5M QA samples. It covers three key tasks—abnormality detection, anatomy recognition, and pathology identification—spanning 8 anatomical regions and 97 pathology categories, and supports open-ended, closed-ended, and multiple-choice questions. Extensive experiments show that state-of-the-art vision-language models still struggle with fine-grained pathology identification, especially in open-ended settings and even after fine-tuning. Text-only analysis further reveals that model accuracies collapse to near-random without image inputs, confirming that RadImageNet-VQA is free from linguistic shortcuts.
Cite
Text
Butsanets et al. "RadImageNet-VQA: A Large-Scale CT and MRI Dataset for Radiologic Visual Question Answering." Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, 2026.Markdown
[Butsanets et al. "RadImageNet-VQA: A Large-Scale CT and MRI Dataset for Radiologic Visual Question Answering." Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, 2026.](https://mlanthology.org/midl/2026/butsanets2026midl-radimagenetvqa/)BibTeX
@inproceedings{butsanets2026midl-radimagenetvqa,
title = {{RadImageNet-VQA: A Large-Scale CT and MRI Dataset for Radiologic Visual Question Answering}},
author = {Butsanets, Léo and Corbière, Charles and Khlaut, Julien and Manceron, Pierre and Dancette, Corentin},
booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning},
year = {2026},
pages = {3036-3068},
volume = {315},
url = {https://mlanthology.org/midl/2026/butsanets2026midl-radimagenetvqa/}
}