{"url":"/dataset/chexpert","name":"CheXpert","full_name":"CheXpert","description_markdown":"The **CheXpert** dataset contains 224,316 chest radiographs of 65,240 patients with both frontal and lateral views available. The task is to do automated chest x-ray interpretation, featuring uncertainty labels and radiologist-labeled reference standard evaluation sets.\r\n\r\nSource: [Deep Mining External Imperfect Data for Chest X-ray Disease Screening](https://arxiv.org/abs/2006.03796)\r\nImage Source: [https://stanfordmlgroup.github.io/competitions/chexpert/](https://stanfordmlgroup.github.io/competitions/chexpert/)","description_withheld":null,"homepage":"https://stanfordmlgroup.github.io/competitions/chexpert/","introduced_date":"2019-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/chexpert-a-large-chest-radiograph-dataset","title":"CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison","first_author":"Jeremy Irvin","url":null},"license":{"name":"Custom","url":"https://stanfordmlgroup.github.io/competitions/chexpert/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[{"name":"Multi-Label Classification","url":"/task/multi-label-classification","datasets_with_task":"/datasets/task/multi-label-classification"},{"name":"Concept-based Classification","url":"/task/concept-based-classification","datasets_with_task":"/datasets/task/concept-based-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Korean","url":"/datasets/language/korean"}],"variants":["CheXpert"],"data_loaders":[{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/chexpert","frameworks":["tf","jax"]}],"num_papers_in_archive":628,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multi-label-classification-on-chexpert","task":"Multi-Label Classification","dataset_variant":"CheXpert","rows":226,"metrics":["AVERAGE AUC ON 14 LABEL","NUM RADS BELOW CURVE"],"first_row_in_archive_order":{"model":"CFT (ensemble) Macao Polytechnic University","paper":"/paper/category-wise-fine-tuning-for-image-multi","metrics":{"AVERAGE AUC ON 14 LABEL":"0.933"},"code_links":[{"title":"maxium0526/category-wise-fine-tuning","url":"https://github.com/maxium0526/category-wise-fine-tuning"},{"title":"maxium0526/cft-chexpert","url":"https://github.com/maxium0526/cft-chexpert"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/concept-based-classification-on-chexpert","task":"Concept-based Classification","dataset_variant":"CheXpert","rows":1,"metrics":["Task Accuracy (%)","Concept Accuracy (%)"],"first_row_in_archive_order":{"model":"CGEM (ResNet-34)","paper":"/paper/concept-graph-embedding-models-for-enhanced","metrics":{"Concept Accuracy (%)":"63.52","Task Accuracy (%)":"89.25"},"code_links":[{"title":"jumpsnack/cgem","url":"https://github.com/jumpsnack/cgem"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/medical-image-deblurring-on-chexpert","task":"Medical Image Deblurring","dataset_variant":"ChexPert","rows":1,"metrics":["Average PSNR"],"first_row_in_archive_order":{"model":"MedDeblur","paper":"/paper/meddeblur-medical-image-deblurring-with","metrics":{"Average PSNR":"28.09"},"code_links":[{"title":"sharif-apu/MedDeblur","url":"https://github.com/sharif-apu/MedDeblur"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/concept-graph-embedding-models-for-enhanced","title":"Concept Graph Embedding Models for Enhanced Accuracy and Interpretability","date":"2024-08-13","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/masks-and-manuscripts-advancing-medical-pre","title":"Masks and Manuscripts: Advancing Medical Pre-training with End-to-End Masking and Narrative Structuring","date":"2024-07-23","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/category-wise-fine-tuning-for-image-multi","title":"Category-Wise Fine-Tuning for Image Multi-label Classification with Partial Labels","date":"2023-11-27","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/meddeblur-medical-image-deblurring-with","title":"MedDeblur: Medical Image Deblurring with Residual Dense Spatial-Asymmetric Attention","date":"2022-12-27","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"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":3,"code_links":1,"syntology":null},{"paper":"/paper/anatomy-x-net-a-semi-supervised-anatomy-aware","title":"Anatomy-XNet: An Anatomy Aware Convolutional Neural Network for Thoracic Disease Classification in Chest X-rays","date":"2021-06-10","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/robust-deep-auc-maximization-a-new-surrogate","title":"Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification","date":"2020-12-06","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/chexclusion-fairness-gaps-in-deep-chest-x-ray","title":"CheXclusion: Fairness gaps in deep chest X-ray classifiers","date":"2020-02-14","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/interpreting-chest-x-rays-via-cnns-that","title":"Interpreting chest X-rays via CNNs that exploit hierarchical disease dependencies and uncertainty labels","date":"2019-11-15","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/chexpert-a-large-chest-radiograph-dataset","title":"CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison","date":"2019-01-21","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-09-25T09:33:49+00:00","samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+00:00","papers_with_samples":1,"samples_harvested":1,"samples_ran":0,"samples_unverified":1,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":1,"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."}