CheXpert

Overview edit

Variants: CheXpert

Associated Benchmarks

This dataset is used in 2 benchmarks:

• Multi-Label Classification - Metrics: AVERAGE AUC ON 14 LABEL, NUM RADS BELOW CURVE
• Concept-based Classification - Metrics: Task Accuracy (%), Concept Accuracy (%)

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• Masks and Manuscripts: Advancing Medical Pre-training with End-to-End Masking and Narrative Structuring (2024) -
• Image Projective Transformation Rectification with Synthetic Data for Smartphone-captured Chest X-ray Photos Classification (2022) -
• Anatomy-XNet: An Anatomy Aware Convolutional Neural Network for Thoracic Disease Classification in Chest X-rays (2021) -
• Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification (2020) -
• CheXclusion: Fairness gaps in deep chest X-ray classifiers (2020) -
• Interpreting chest X-rays via CNNs that exploit hierarchical disease dependencies and uncertainty labels (2019) -
• CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison (2019) -