{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/chexpert-a-large-chest-radiograph-dataset","title":"CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison","arxiv_id":"1901.07031","date":"2019-01-21","proceeding":null,"authors":["Jeremy Irvin","Pranav Rajpurkar","Michael Ko","Yifan Yu","Silviana Ciurea-Ilcus","Chris Chute","Henrik Marklund","Behzad Haghgoo","Robyn Ball","Katie Shpanskaya","Jayne Seekins","David A. Mong","Safwan S. Halabi","Jesse K. Sandberg","Ricky Jones","David B. Larson","Curtis P. Langlotz","Bhavik N. Patel","Matthew P. Lungren","Andrew Y. Ng"],"abstract":"Large, labeled datasets have driven deep learning methods to achieve\nexpert-level performance on a variety of medical imaging tasks. We present\nCheXpert, a large dataset that contains 224,316 chest radiographs of 65,240\npatients. We design a labeler to automatically detect the presence of 14\nobservations in radiology reports, capturing uncertainties inherent in\nradiograph interpretation. We investigate different approaches to using the\nuncertainty labels for training convolutional neural networks that output the\nprobability of these observations given the available frontal and lateral\nradiographs. On a validation set of 200 chest radiographic studies which were\nmanually annotated by 3 board-certified radiologists, we find that different\nuncertainty approaches are useful for different pathologies. We then evaluate\nour best model on a test set composed of 500 chest radiographic studies\nannotated by a consensus of 5 board-certified radiologists, and compare the\nperformance of our model to that of 3 additional radiologists in the detection\nof 5 selected pathologies. On Cardiomegaly, Edema, and Pleural Effusion, the\nmodel ROC and PR curves lie above all 3 radiologist operating points. We\nrelease the dataset to the public as a standard benchmark to evaluate\nperformance of chest radiograph interpretation models.\n  The dataset is freely available at\nhttps://stanfordmlgroup.github.io/competitions/chexpert .","url_abs":"http://arxiv.org/abs/1901.07031v1","url_pdf":"http://arxiv.org/pdf/1901.07031v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"chexpert-a-large-chest-radiograph-dataset","repo_url":"https://github.com/Stomper10/CheXpert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"chexpert-a-large-chest-radiograph-dataset","repo_url":"https://github.com/gaetandi/cheXpert","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"chexpert-a-large-chest-radiograph-dataset","repo_url":"https://github.com/icanswim/cxr","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"chexpert-a-large-chest-radiograph-dataset","repo_url":"https://github.com/nalbarr/coursera-ai4med-course3","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"chexpert-a-large-chest-radiograph-dataset","repo_url":"https://github.com/shreyavarshini/Cancer-Detection","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"chexpert-a-large-chest-radiograph-dataset","repo_url":"https://github.com/shreyavarshini/VAE-Lung-Cancer","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"chexpert-a-large-chest-radiograph-dataset","repo_url":"https://github.com/simongrest/chexpert-entries","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"chexpert-a-large-chest-radiograph-dataset","repo_url":"https://github.com/stanfordmlgroup/MedSelect","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"chexpert-a-large-chest-radiograph-dataset","repo_url":"https://github.com/stanfordmlgroup/MoCo-CXR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"chexpert-a-large-chest-radiograph-dataset","repo_url":"https://github.com/stanfordmlgroup/chexpert-labeler","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"chexpert-a-large-chest-radiograph-dataset","repo_url":"https://github.com/yichigo/Chest-X-Ray","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"chexpert-a-large-chest-radiograph-dataset","repo_url":"https://github.com/Disiok/chexpert-fusion","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"lung-disease-classification","task_name":"Lung Disease Classification"}],"methods":[],"datasets_introduced":[{"slug":"chexpert","name":"CheXpert","full_name":"CheXpert"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/multi-label-classification-on-chexpert","task":"Multi-Label Classification","dataset":"CheXpert","model":"Stanford Baseline (ensemble)","rank_in_archive_order":96,"of":226,"metrics":{"AVERAGE AUC ON 14 LABEL":"0.907","NUM RADS BELOW CURVE":"1.800"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.07031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.07031"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yichigo/Chest-X-Ray","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Disiok/chexpert-fusion","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stanfordmlgroup/MedSelect","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stanfordmlgroup/MoCo-CXR","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shreyavarshini/VAE-Lung-Cancer","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gaetandi/cheXpert","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Stomper10/CheXpert","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/nalbarr/coursera-ai4med-course3","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/icanswim/cxr","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/simongrest/chexpert-entries","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shreyavarshini/Cancer-Detection","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stanfordmlgroup/chexpert-labeler","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":1},"by_repo_kind":{},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"9b8289076669fe4f","entry":"accuracy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"9b8289076669fe4f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}