Random Sample of NIH Chest X-ray Dataset

  • by user1
  • 28 February, 2022

5,606 images and labels sampled from the NIH Chest X-ray Dataset

LicenseCC0: Public Domain

Tagscomputer science, health, biology, image data, healthcareand 2 more

NIH Chest X-ray Dataset Sample

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

File contents – This is a random sample (5%) of the full dataset:

  • sample.zip: Contains 5,606 images with size 1024 x 1024
  • sample_labels.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”) in the full dataset, but since this is drastically reduced version of the full dataset, some of the classes are sparse with the labeled as “No findings”

  • Hernia – 13 images
  • Pneumonia – 62 images
  • Fibrosis – 84 images
  • Edema – 118 images
  • Emphysema – 127 images
  • Cardiomegaly – 141 images
  • Pleural_Thickening – 176 images
  • Consolidation – 226 images
  • Pneumothorax – 271 images
  • Mass – 284 images
  • Nodule – 313 images
  • Atelectasis – 508 images
  • Effusion – 644 images
  • Infiltration – 967 images
  • No Finding – 3044 images

Full Dataset Content

The full dataset can be found here. There are 12 zip files in total and range from ~2 gb to 4 gb in size.

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 BBoxlist2017.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

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

Citations

Acknowledgements

This work was supported by the Intramural Research Program of the NClinical Center (clinicalcenter.nih.gov) and National Library of Medicine (www.nlm.nih.gov).

Size: 4400742 KB Price: Free Author: National Institutes of Health Chest X-Ray Dataset Data source: kaggle.com

Download
Categories