{"url":"/dataset/chexphoto","name":"CheXphoto","full_name":null,"description_markdown":"CheXphoto is a competition for x-ray interpretation based on a new dataset of naturally and synthetically perturbed chest x-rays hosted by Stanford and VinBrain.\r\n\r\nChest radiography is the most common imaging examination globally, and is critical for screening, diagnosis, and management of many life threatening diseases. Most chest x-ray algorithms have been developed and validated on digital x-rays, while the vast majority of developing regions use films. An appealing solution to scaled deployment is to leverage the ubiquity of smartphones for automated interpretation of film through cellphone photography. Automated interpretation of photos of chest x-rays at the same high-level of performance as with digital chest x-rays is challenging because photographs of x-rays introduce visual artifacts not commonly found in digital x-rays. To encourage high model performance for this application, we developed CheXphoto, a dataset of photos of chest x-rays and synthetic transformations designed to mimic the effects of photography.\r\n\r\nWith the launch of the CheXphoto competition, we are pleased to announce the release of an additional set of x-ray film images provided by VinBrain, a subsidiary of Vingroup. Please see Validation and Test Sets for details.","description_withheld":null,"homepage":"https://stanfordmlgroup.github.io/competitions/chexphoto/","introduced_date":"2020-07-13","introduced_date_note":null,"introduced_by":{"paper":"/paper/chexphoto-10000-smartphone-photos-and","title":"CheXphoto: 10,000+ Photos and Transformations of Chest X-rays for Benchmarking Deep Learning Robustness","first_author":"Nick A. Phillips","url":null},"license":null,"modalities":[],"tasks":[{"name":"Medical Image Classification","url":"/task/medical-image-classification","datasets_with_task":"/datasets/task/medical-image-classification"}],"languages":[],"variants":["CheXphoto"],"data_loaders":[],"num_papers_in_archive":3,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/medical-image-classification-on-chexphoto","task":"Medical Image Classification","dataset_variant":"CheXphoto","rows":1,"metrics":["Mean AUC"],"first_row_in_archive_order":{"model":"PTRN","paper":"/paper/projective-transformation-rectification-for","metrics":{"Mean AUC":"0.850"},"code_links":[{"title":"maxium0526/ptrn","url":"https://github.com/maxium0526/ptrn"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/projective-transformation-rectification-for","title":"Image Projective Transformation Rectification with Synthetic Data for Smartphone-captured Chest X-ray Photos Classification","date":"2022-10-12","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}