Saved datasets
Last updated
Download format
Usage rights
License from data provider
Please review the applicable license to make sure your contemplated use is permitted.
Cost to access
Described as free to access or have a license that allows redistribution.
100+ datasets found
  1. NIH Chest X-rays

    Updated Feb 21, 2018
  2. Chest X-Ray Images (Pneumonia)

    Updated Mar 24, 2018
  3. G

    Utah FORGE: X-Ray Diffraction Data

    • +3more
    archive +1
    Updated Feb 7, 2018
  4. f

    COVID-19 Chest X-Ray Image Repository

    Updated Feb 2, 2022
  5. COVID-19 chest xray

    Updated May 15, 2020
  6. a

    Montgomery County X-ray Set

    Updated Feb 12, 2019
  7. d

    Data Collection by Shaip: Text, Audio, Image, Video for AI & ML Training

    Updated Mar 17, 2021
  8. Pulmonary Chest X-Ray Abnormalities

    Updated Mar 9, 2018
  9. Random Sample of NIH Chest X-ray Dataset

    Updated Nov 23, 2017
  10. Data from: Tomographic X-ray data of carved cheese

    Updated May 12, 2017
  11. p

    Data from: Smartphone-Captured Chest X-Ray Photographs

    Updated Sep 27, 2020
  12. Chest Xray Masks and Labels

    Updated Jan 21, 2019
  13. G

    Utah FORGE Well 16A(78)-32 X-ray Diffraction Data

    • +2more
    Updated Jul 29, 2021
  14. m

    Digital Knee X-ray Images

    Updated Jun 23, 2020
  15. Medical X-ray global market size in 2018 and 2025

    Updated Feb 5, 2020
  16. a

    Shenzhen Hospital X-ray Set

    Updated Feb 12, 2019
  17. P

    ChestX-ray14 Dataset

  18. CoronaHack -Chest X-Ray-Dataset

    Updated Mar 20, 2020
  19. c

    Data from: Solving structure with sparse, randomly-oriented x-ray data

    Updated Jun 20, 2012
  20. m

    COVID19, Pneumonia and Normal Chest X-ray PA Dataset

    Updated Apr 9, 2021
Click to copy link
Link copied
National Institutes of Health Chest X-Ray Dataset (2018). NIH Chest X-rays [Dataset].
Organization logo

NIH Chest X-rays

Over 112,000 Chest X-ray images from more than 30,000 unique patients

120 scholarly articles cite this dataset (View in Google Scholar)
zip(45096150231 bytes)Available download formats
Dataset updated
Feb 21, 2018
Dataset authored and provided by
National Institutes of Health Chest X-Ray Dataset

CC0 1.0 Universal Public Domain Dedication
License information was derived automatically


NIH Chest X-ray Dataset

National Institutes of Health Chest X-Ray Dataset

Chest X-ray exams are one of the most frequent and cost-effective medical imaging examinations available. However, clinical diagnosis of a chest X-ray can be challenging and sometimes more difficult than diagnosis via chest CT imaging. The lack of large publicly available datasets with annotations means it is still very difficult, if not impossible, to achieve clinically relevant computer-aided detection and diagnosis (CAD) in real world medical sites with chest X-rays. One major hurdle in creating large X-ray image datasets is the lack resources for labeling so many images. Prior to the release of this dataset, Openi was the largest publicly available source of chest X-ray images with 4,143 images available.

This NIH Chest X-ray Dataset is comprised of 112,120 X-ray images with disease labels from 30,805 unique patients. To create these labels, the authors used Natural Language Processing to text-mine disease classifications from the associated radiological reports. The labels are expected to be >90% accurate and suitable for weakly-supervised learning. The original radiology reports are not publicly available but you can find more details on the labeling process in this Open Access paper: "ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases." (Wang et al.)

Link to paper

Data limitations:

  1. The image labels are NLP extracted so there could be some erroneous labels but the NLP labeling accuracy is estimated to be >90%.
  2. Very limited numbers of disease region bounding boxes (See BBox_list_2017.csv)
  3. Chest x-ray radiology reports are not anticipated to be publicly shared. Parties who use this public dataset are encouraged to share their “updated” image labels and/or new bounding boxes in their own studied later, maybe through manual annotation

File contents

  • Image format: 112,120 total images with size 1024 x 1024

  • Contains 4999 images

  • Contains 10,000 images

  • Contains 10,000 images

  • Contains 10,000 images

  • Contains 10,000 images

  • Contains 10,000 images

  • Contains 10,000 images

  • Contains 10,000 images

  • Contains 10,000 images

  • Contains 10,000 images

  • Contains 10,000 images

  • Contains 7,121 images

  • README_ChestXray.pdf: Original README file

  • BBox_list_2017.csv: Bounding box coordinates. Note: Start at x,y, extend horizontally w pixels, and vertically h pixels

    • Image Index: File name
    • Finding Label: Disease type (Class label)
    • Bbox x
    • Bbox y
    • Bbox w
    • Bbox h
  • Data_entry_2017.csv: Class labels and patient data for the entire dataset

    • Image Index: File name
    • Finding Labels: Disease type (Class label)
    • Follow-up #
    • Patient ID
    • Patient Age
    • Patient Gender
    • View Position: X-ray orientation
    • OriginalImageWidth
    • OriginalImageHeight
    • OriginalImagePixelSpacing_x
    • OriginalImagePixelSpacing_y

Class descriptions

There are 15 classes (14 diseases, and one for "No findings"). Images can be classified as "No findings" or one or more disease classes:

  • Atelectasis
  • Consolidation
  • Infiltration
  • Pneumothorax
  • Edema
  • Emphysema
  • Fibrosis
  • Effusion
  • Pneumonia
  • Pleural_thickening
  • Cardiomegaly
  • Nodule Mass
  • Hernia

Full Dataset Content

There are 12 zip files in total and range from ~2 gb to 4 gb in size. Additionally, we randomly sampled 5% of these images and created a smaller dataset for use in Kernels. The random sample contains 5606 X-ray images and class labels.

Modifications to original data

  • Original TAR archives were converted to ZIP archives to be compatible with the Kaggle platform

  • CSV headers slightly modified to be more explicit in comma separation and also to allow fields to be self-explanatory



This work was supported by the Intramural Research Program of the NClinical Center ( and National Library of Medicine (

Clear search
Close search
Google apps
Main menu