{"url":"/dataset/chestx-ray14","name":"ChestX-ray14","full_name":"ChestX-ray14","description_markdown":"**ChestX-ray14** is a medical imaging dataset which comprises 112,120 frontal-view X-ray images of 30,805 (collected from the year of 1992 to 2015) unique patients with the text-mined fourteen common disease labels, mined from the text radiological reports via NLP techniques. It expands on ChestX-ray8 by adding six additional thorax diseases: Edema, Emphysema, Fibrosis, Pleural Thickening and Hernia.\r\n\r\nSource: [https://nihcc.app.box.com/v/ChestXray-NIHCC/file/220660789610](https://nihcc.app.box.com/v/ChestXray-NIHCC/file/220660789610)\r\nImage Source: [https://nihcc.app.box.com/v/ChestXray-NIHCC](https://nihcc.app.box.com/v/ChestXray-NIHCC)","description_withheld":null,"homepage":"https://nihcc.app.box.com/v/ChestXray-NIHCC","introduced_date":"2017-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/chestx-ray8-hospital-scale-chest-x-ray","title":"ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases","first_author":"Xiaosong Wang","url":null},"license":{"name":"Unknown","url":null},"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":"Multi-Task Learning","url":"/task/multi-task-learning","datasets_with_task":"/datasets/task/multi-task-learning"},{"name":"Medical Image Generation","url":"/task/medical-image-generation","datasets_with_task":"/datasets/task/medical-image-generation"},{"name":"Pneumonia Detection","url":"/task/pneumonia-detection","datasets_with_task":"/datasets/task/pneumonia-detection"},{"name":"Thoracic Disease Classification","url":"/task/thoracic-disease-classification","datasets_with_task":"/datasets/task/thoracic-disease-classification"}],"languages":[],"variants":["ChestX-ray14","ChestXray14 1024x1024"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/alkzar90/NIH-Chest-X-ray-dataset","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/activeloopai/Hub","url":"https://docs.activeloop.ai/datasets/nih-chest-x-ray-dataset#nih-chestx-ray-data-fields","frameworks":["tf","pytorch"]}],"num_papers_in_archive":237,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/pneumonia-detection-on-chestx-ray14","task":"Pneumonia Detection","dataset_variant":"ChestX-ray14","rows":5,"metrics":["AUROC","Params","FLOPS"],"first_row_in_archive_order":{"model":"NSGANetV1-A3","paper":"/paper/multi-criterion-evolutionary-design-of-deep","metrics":{"AUROC":"0.847","Params":"5.0M"},"code_links":[{"title":"mikelzc1990/nsganetv2","url":"https://github.com/mikelzc1990/nsganetv2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multi-label-classification-on-chestx-ray14","task":"Multi-Label Classification","dataset_variant":"ChestX-ray14","rows":4,"metrics":["Average AUC on 14 label","Macro F1"],"first_row_in_archive_order":{"model":"SynthEnsemble","paper":"/paper/synthensemble-a-fusion-of-cnn-vision","metrics":{"Average AUC on 14 label":"85.433"},"code_links":[{"title":"syednabilashraf/SynthEnsemble","url":"https://github.com/syednabilashraf/SynthEnsemble"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/medical-image-generation-on-chestxray14","task":"Medical Image Generation","dataset_variant":"ChestXray14 1024x1024","rows":2,"metrics":["FID"],"first_row_in_archive_order":{"model":"StyleGAN2-ADA","paper":"/paper/evaluating-the-performance-of-stylegan2-ada","metrics":{"FID":"3.52"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/thoracic-disease-classification-on-chestx","task":"Thoracic Disease Classification","dataset_variant":"ChestX-ray14","rows":2,"metrics":["AUROC"],"first_row_in_archive_order":{"model":"DenseNet121","paper":null,"metrics":{"AUROC":"84.2"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/medical-image-generation-on-chestx-ray14","task":"Medical Image Generation","dataset_variant":"ChestX-ray14","rows":1,"metrics":["FID"],"first_row_in_archive_order":{"model":"StyleGAN2 with DiffAugment","paper":"/paper/importance-of-feature-extraction-in-the","metrics":{"FID":"3.07"},"code_links":[{"title":"mckellwoodland/fid-med-eval","url":"https://github.com/mckellwoodland/fid-med-eval"},{"title":"mckellwoodland/radfid","url":"https://github.com/mckellwoodland/radfid"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/multi-task-learning-on-chestx-ray14","task":"Multi-Task Learning","dataset_variant":"ChestX-ray14","rows":1,"metrics":["delta_m"],"first_row_in_archive_order":{"model":"BayesAgg-MTL","paper":"/paper/bayesian-uncertainty-for-gradient-aggregation","metrics":{"delta_m":"−14.96"},"code_links":[{"title":"ssi-research/bayesagg_mtl","url":"https://github.com/ssi-research/bayesagg_mtl"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/reproducing-and-improving-chexnet-deep","title":"Reproducing and Improving CheXNet: Deep Learning for Chest X-ray Disease Classification","date":"2025-05-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/bayesian-uncertainty-for-gradient-aggregation","title":"Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning","date":"2024-02-06","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":7,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/importance-of-feature-extraction-in-the","title":"Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend","date":"2023-11-22","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/synthensemble-a-fusion-of-cnn-vision","title":"SynthEnsemble: A Fusion of CNN, Vision Transformer, and Hybrid Models for Multi-Label Chest X-Ray Classification","date":"2023-11-13","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/evaluating-the-performance-of-stylegan2-ada","title":"Evaluating the Performance of StyleGAN2-ADA on Medical Images","date":"2022-10-07","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/breaking-with-fixed-set-pathology-recognition","title":"Breaking with Fixed Set Pathology Recognition through Report-Guided Contrastive Training","date":"2022-05-14","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/synthesising-clinically-realistic-chest-x","title":"Evaluating the Clinical Realism of Synthetic Chest X-Rays Generated Using Progressively Growing GANs","date":"2020-10-07","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/muxconv-information-multiplexing-in","title":"MUXConv: Information Multiplexing in Convolutional Neural Networks","date":"2020-03-31","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"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/multi-criterion-evolutionary-design-of-deep","title":"Multi-Objective Evolutionary Design of Deep Convolutional Neural Networks for Image Classification","date":"2019-12-03","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/jointly-learning-convolutional","title":"Jointly Learning Convolutional Representations to Compress Radiological Images and Classify Thoracic Diseases in the Compressed Domain","date":"2018-12-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/chexnet-radiologist-level-pneumonia-detection","title":"CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning","date":"2017-11-14","rows_on_this_dataset":1,"code_links":47,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":37,"samples_ran":7,"samples_unverified":30,"pointer_only_for_licence":12,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":50,"samples_ran":17,"samples_unverified":33,"pointer_only_for_licence":17,"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."}