{"url":"/dataset/medicat","name":"MedICaT","full_name":null,"description_markdown":"**MedICaT** is a dataset of medical images, captions, subfigure-subcaption annotations, and inline textual references.\nFigures and captions are extracted from open access articles in PubMed Central and corresponding reference text is derived from S2ORC.\nThe dataset consists of:\n217,060 figures from 131,410 open access papers\n7507 subcaption and subfigure annotations for 2069 compound figures\nInline references for ~25K figures in the ROCO dataset\n\nSource: [https://github.com/allenai/medicat](https://github.com/allenai/medicat)","description_withheld":null,"homepage":"https://github.com/allenai/medicat","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/medicat-a-dataset-of-medical-images-captions","title":"MedICaT: A Dataset of Medical Images, Captions, and Textual References","first_author":"Sanjay Subramanian","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[{"name":"Text Matching","url":"/task/text-matching","datasets_with_task":"/datasets/task/text-matching"}],"languages":[],"variants":["MedICaT"],"data_loaders":[{"repo":"https://github.com/allenai/medicat","url":"https://github.com/allenai/medicat","frameworks":[]}],"num_papers_in_archive":28,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}