Research map / Label-efficient and robust learning / Recognition and long-tail
CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Map uncertain Atelectasis labels to positive rather than negative (ablation) | DenseNet121 uncertainty-label training · Atelectasis validation | AUROC: 0.811 -> 0.858 | Helped |
| Treat uncertain Cardiomegaly labels as a separate class rather than ignore them (ablation) | DenseNet121 uncertainty-label training · Cardiomegaly validation | AUROC: 0.828 -> 0.854 | Helped |
| Map uncertain Atelectasis labels to positive rather than ignore them (ablation) | DenseNet121 uncertainty-label training · Atelectasis validation | AUROC: 0.818 -> 0.858 | Mixed |
| Map uncertain Edema labels to positive rather than ignore them (ablation) | DenseNet121 uncertainty-label training · Edema validation | AUROC: 0.934 -> 0.941 | No clear effect |
| Map uncertain Consolidation labels to positive rather than negative (ablation) | DenseNet121 uncertainty-label training · Consolidation validation | AUROC: 0.932 -> 0.899 | Hurt |
| Use different uncertainty-label strategies for different pathologies (ablation) | Final CheXpert model · Five competition tasks validation | AUROC | Mixed |
| Apply isotonic regression calibration (ablation) | Final CheXpert model · Competition tasks test | average scaled Brier score: 0.110 -> 0.107 | Helped |
| Apply Platt scaling calibration (ablation) | Final CheXpert model · Competition tasks test | average scaled Brier score: 0.110 -> 0.101 | Helped |
Closest papers by meaning
- CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays (NeurIPS 2025 · similarity 0.86)
- CXPMRG-Bench: Pre-training and Benchmarking for X-ray Medical Report Generation on CheXpert Plus Dataset (CVPR 2025 · similarity 0.85)
- BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays (NeurIPS 2024 · similarity 0.85)
- CheXWorld: Exploring Image World Modeling for Radiograph Representation Learning (CVPR 2025 · similarity 0.85)
- Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models (CVPR 2024 · similarity 0.85)
- PAC Prediction Sets Under Label Shift (ICLR 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.