Skip to content
Open Imaging Index
X-ray Chest

CheXpert

CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison

Chest radiographs with labels for common findings taken from radiology reports, including an uncertain state, one of the standard benchmarks for multi-label chest X-ray classification. 224,316 images of 65,240 Stanford patients with 14 labels and a radiologist-labelled validation set. Non-commercial use only.

Go to dataset Edit Report

Overview

CheXpert is a chest radiograph collection from Stanford Hospital released by the Stanford Machine Learning Group and distributed by the Stanford AIMI Center. Its main contribution is a rule-based labeler that reads radiology reports and marks each of 14 observations as positive, negative or uncertain. It is one of the standard benchmarks for multi-label chest X-ray classification.

Composition

The dataset holds 224,316 radiographs of 65,240 patients, taken between October 2002 and July 2017 in inpatient and outpatient settings. Each patient appears in only one split:

Split Patients Studies Images
Training 64,540 187,641 223,414
Validation 200 200 234
Test 500 500 668

Each image is a frontal (AP or PA) or lateral view. Age in years, biological sex and the view are given per image. Images are distributed as 8-bit JPEG files, in a full-resolution and a downsampled version. The datasheet reports that the X-ray device is not recorded.

Annotations

The 14 observations are No Finding, Enlarged Cardiomediastinum, Cardiomegaly, Lung Opacity, Lung Lesion, Edema, Consolidation, Pneumonia, Atelectasis, Pneumothorax, Pleural Effusion, Pleural Other, Fracture and Support Devices. Training labels come from the automatic labeler run on the reports. Validation labels are the majority vote of three board-certified radiologists looking at the images, and test labels the majority vote of five. This index maps the findings that have a vocabulary term; condition counts in the statistics include positive labels only.

Known limitations

  • Training labels are extracted from text and contain errors; uncertain labels are frequent for some findings (e.g. consolidation).
  • Single institution; about half of the images come from 15% of the patients.
  • Very few children are included.
  • The research use agreement forbids commercial use, redistribution and derivative works. A paid commercial license is offered separately.

Cohort

Aggregate numbers from the sources below. Bars are relative to the 65,240 subjects.

Split

  • Training 64,540 99%
  • Test 500 <1%
  • Validation 200 <1%

Table I, p. 2 (Composition) in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020

Age by split

Reported cross table. A dot marks a cell the source does not give.

TrainingValidation
0-13·
13-187662
19-4441,69638
45-6482,75088
65-7962,43364
80+35,76642

Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020

Condition by split

Reported cross table. A dot marks a cell the source does not give.

TrainingValidation
Pulmonary opacity105,581126
Pleural effusion86,18767
Pulmonary edema52,24645
Atelectasis33,37680
Cardiomegaly27,00068
No finding22,38138
Pneumothorax19,4488
Pulmonary consolidation14,78333
Bone fracture9,040·
Pneumonia6,0398

Table IV, Table V in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020

Sex by split

Reported cross table. A dot marks a cell the source does not give.

TrainingValidation
Female28,72994
Male35,811106

Table VII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020

Other reported numbers 31
Studies · Training, Female, 0-1 3Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Studies · Training, Female, 13-18 254Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Studies · Training, Male, 13-18 399Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Studies · Training, Female, 19-44 14,395Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Studies · Training, Male, 19-44 20,055Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Studies · Training, Female, 45-64 27,026Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Studies · Training, Male, 45-64 42,033Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Studies · Training, Female, 65-79 21,653Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Studies · Training, Male, 65-79 31,281Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Studies · Training, Female, 80+ 14,846Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Studies · Training, Male, 80+ 15,696Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Images · Training, Female, 0-1 3Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Images · Training, Female, 13-18 290Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Images · Training, Male, 13-18 476Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Images · Training, Female, 19-44 16,972Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Images · Training, Male, 19-44 24,724Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Images · Training, Female, 45-64 31,653Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Images · Training, Male, 45-64 51,097Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Images · Training, Female, 65-79 24,817Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Images · Training, Male, 65-79 37,616Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Images · Training, Female, 80+ 17,043Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Images · Training, Male, 80+ 18,723Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Images · Validation, Female, 13-18 2Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Images · Validation, Female, 19-44 22Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Images · Validation, Male, 19-44 16Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Images · Validation, Female, 45-64 39Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Images · Validation, Male, 45-64 49Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Images · Validation, Female, 65-79 25Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Images · Validation, Male, 65-79 39Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Images · Validation, Female, 80+ 18Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020
Images · Validation, Male, 80+ 24Table VIII in Garbin et al. 2021, Structured dataset documentation - a datasheet for CheXpert, arXiv 2105.03020

License and access

Our reading of the license, not legal advice. Before you use the data, read the original license and confirm that your use is allowed. We take no responsibility for how you use a dataset. Full disclaimer

Access
Free registration

Create an account and accept terms online

Register and accept the Stanford research use agreement. AIMI datasets are now downloaded through Redivis.

Access page

Stanford University School of Medicine Dataset Research Use Agreement (AIMI)

Free for personal, non-commercial research only. You may not share the data or the download link, may not create derivative works, and must not try to re-identify patients. Stanford sells a separate commercial license.

Original license text Version read: Text shown in the Stanford AIMI shared-datasets portal, read 2026-10-07 (no version number given) Checked 2026-10-07

What you can do

  • No
  • Not stated
  • Not stated
  • No
  • Not stated

What you can share

  • No
  • No
  • Share trained models Not stated

What you must do

  • Yes
  • Share alike No
  • Yes
  • Ethics approval No
  • Manuscript review No
  • Release code No
  • Return results No
  • No

Limits

  • Yes
  • Location limits No

Commercial license: Yes Companies can apply for a one-year license per dataset, reviewed by a Stanford committee. The page lists an annual fee of USD 70,000 per dataset for agreements contracted in FY25. Details

Citation

Irvin J, Rajpurkar P, Ko M, et al. CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison. AAAI 2019. https://arxiv.org/abs/1901.07031. Dataset DOI: https://doi.org/10.71718/y7pj-4v93

Sources

Every number on this page comes from one of these documents. Each chart names the table or page it is taken from. The raw numbers are in stats.csv.