NIH Chest X-ray Dataset
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.