🚀 We're looking for ML Engineers and Medical Reviewers! Join the OpenPHR Mission →
Back to Marketplace
Dataset

NIH Chest X-ray Dataset

Radiology / Imaging Radiology / Pulmonology CC0 1.0 Universal De-identified / Open Access
N/A GitHub Stars
N/A Open Issues
N/A Docker Support
N/A Last Updated

Technical Summary

The NIH Chest X-ray dataset comprises 112,120 frontal-view X-ray images of 30,805 unique patients with text-mined disease labels from the associated radiological reports.

Key Features

  • Scale: Over 100,000 images, making it one of the largest publicly available chest X-ray datasets.
  • Annotations: Natural language processing was used to extract 14 distinct disease labels (e.g., Atelectasis, Consolidation, Infiltration, Pneumothorax) from the original reports.
  • Baseline: Widely used as a benchmark for weak-supervised multi-label image classification and disease localization in medical imaging.

Model Card Details

Architecture

N/A

Intended Use Cases

Training algorithms to detect 14 common thoracic pathologies from frontal chest X-rays.