Model card
TorchXRayVision.
Cohen Labopen-sourceDenseNet-121 / ResNetApache 2.02 current SOTA
Pre-trained on 8 datasets (MIMIC, CheXpert, NIH, etc.). Unified 18-pathology output.
§ 01 · Benchmarks
Every benchmark TorchXRayVision has a recorded score for.
| # | Benchmark | Area · Task | Metric | Value | Rank | Date | Source |
|---|---|---|---|---|---|---|---|
| 01 | NIH ChestX-ray14 | Medical · Disease Classification | auroc | 85.8% | #1 | — | source ↗ |
| 02 | PadChest | Medical · Disease Classification | auroc | 84.6% | #1 | — | source ↗ |
| 03 | COVID-19 Image Data Collection | Medical · Disease Classification | auroc | 93.2% | #2 | — | source ↗ |
| 04 | MIMIC-CXR | Medical · Disease Classification | auroc | 86.3% | #2 | — | source ↗ |
| 05 | VinDr-CXR | Medical · Disease Classification | auroc | 87.9% | #2 | — | source ↗ |
| 06 | CheXpert | Medical · Disease Classification | auroc | 87.4% | #6 | — | source ↗ |
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 02 · Strengths by area
Where TorchXRayVision actually performs.
§ 05 · Sources & freshness
Where these numbers come from.
github-readme
5
results
research-paper
1
result
0 of 6 rows marked verified.