Home/Browse/Medical/Disease Classification/NIH ChestX-ray14

NIH ChestX-ray14

Unknown

112,120 frontal-view chest X-ray images from 30,805 unique patients with 14 disease labels extracted using NLP from radiology reports. Foundational benchmark for chest X-ray AI.

PaperLeaderboard

Benchmark Stats

Models4
Papers4
Metrics1

SOTA History

Coming Soon
Visual timeline of state-of-the-art progression over time will appear here.

auroc

auroc

Higher is better

RankModelCodeScorePaper / Source
1torchxrayvision

Multi-dataset pre-training improves over single-dataset.

85.8GitHub
2chexnet

Original CheXNet on ChestX-ray14. Exceeded radiologist performance on pneumonia (0.768 vs 0.633).

84.1research-paper
3densenet-121-cxr

Original NIH baseline model.

-82.6research-paper
4resnet-50-cxr

ResNet-50 baseline.

-80.4research-paper
Back to Disease Classification