# Quantifying and Leveraging Classification Uncertainty for Chest Radiograph Assessment

arXiv: https://arxiv.org/abs/1906.07775 · HTML: https://mlsanity.com/paper/1906.07775/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2019.

## Built on by (most cited first, 23 of 23)

- [A Survey of Uncertainty in Deep Neural Networks](https://mlsanity.com/paper/2107.03342/) (2021)
- [Deep Learning for Chest X-ray Analysis: A Survey](https://mlsanity.com/paper/2103.08700/) (2021)
- [Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimation](https://mlsanity.com/paper/2110.03051/) (2021)
- [Trustworthy clinical AI solutions: a unified review of uncertainty quantification in deep learning models for medical image analysis](https://mlsanity.com/paper/2210.03736/) (2022)
- [A Review of Uncertainty Estimation and its Application in Medical Imaging](https://mlsanity.com/paper/2302.08119/) (2023)
- [Diminishing Uncertainty within the Training Pool: Active Learning for Medical Image Segmentation](https://mlsanity.com/paper/2101.02323/) (2021)
- [A review of uncertainty quantification in medical image analysis: probabilistic and non-probabilistic methods](https://mlsanity.com/paper/2310.06873/) (2023)
- [QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results](https://mlsanity.com/paper/2112.10074/) (2021)
- [Evaluating the Fairness of Deep Learning Uncertainty Estimates in Medical Image Analysis](https://mlsanity.com/paper/2303.03242/) (2023)
- [Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation](https://mlsanity.com/paper/2103.00528/) (2021)
- [Deep learning with noisy labels in medical prediction problems: a scoping review](https://mlsanity.com/paper/2403.13111/) (2024)
- [Robust Classification from Noisy Labels: Integrating Additional Knowledge for Chest Radiography Abnormality Assessment](https://mlsanity.com/paper/2104.05261/) (2021)
- [Flow-Mixup: Classifying Multi-labeled Medical Images with Corrupted Labels](https://mlsanity.com/paper/2102.08148/) (2021)
- [Benchmarking Real-World Medical Image Classification with Noisy Labels: Challenges, Practice, and Outlook](https://mlsanity.com/paper/2512.09315/) (2025)
- [Limitations of Public Chest Radiography Datasets for Artificial Intelligence: Label Quality, Domain Shift, Bias and Evaluation Challenges](https://mlsanity.com/paper/2509.15107/) (2025)
- [Joint Dermatological Lesion Classification and Confidence Modeling with Uncertainty Estimation](https://mlsanity.com/paper/2107.08770/) (2021)
- [Handling Label Uncertainty on the Example of Automatic Detection of Shepherd's Crook RCA in Coronary CT Angiography](https://mlsanity.com/paper/2306.01752/) (2023)
- [Domain Transfer Through Image-to-Image Translation for Uncertainty-Aware Prostate Cancer Classification](https://mlsanity.com/paper/2307.00479/) (2023)
- [M2EF-NNs: Multimodal Multi-instance Evidence Fusion Neural Networks for Cancer Survival Prediction](https://mlsanity.com/paper/2408.04170/) (2024)
- [MEGAN: Mixture of Experts for Robust Uncertainty Estimation in Endoscopy Videos](https://mlsanity.com/paper/2509.12772/) (2025)
- [Joint Embedding Variational Bayes](https://mlsanity.com/paper/2602.05639/) (2026)
- [Clinically Aware Synthetic Image Generation for Concept Coverage in Chest X-ray Models](https://mlsanity.com/paper/2603.15525/) (2026)
- [Trustworthy Medical Segmentation: Uncertainty-Aware U-Net Evaluation Under Clinical Image Degradation](https://mlsanity.com/paper/2607.22727/) (2026)

## Abstract (arXiv)

The interpretation of chest radiographs is an essential task for the detection of thoracic diseases and abnormalities. However, it is a challenging problem with high inter-rater variability and inherent ambiguity due to inconclusive evidence in the data, limited data quality or subjective definitions of disease appearance. Current deep learning solutions for chest radiograph abnormality classification are typically limited to providing probabilistic predictions, relying on the capacity of learning models to adapt to the high degree of label noise and become robust to the enumerated causal factors. In practice, however, this leads to overconfident systems with poor generalization on unseen data. To account for this, we propose an automatic system that learns not only the probabilistic estimate on the presence of an abnormality, but also an explicit uncertainty measure which captures the confidence of the system in the predicted output. We argue that explicitly learning the classification uncertainty as an orthogonal measure to the predicted output, is essential to account for the inherent variability characteristic of this data. Experiments were conducted on two datasets of chest radiographs of over 85,000 patients. Sample rejection based on the predicted uncertainty can significantly improve the ROC-AUC, e.g., by 8% to 0.91 with an expected rejection rate of under 25%. Eliminating training samples using uncertainty-driven bootstrapping, enables a significant increase in robustness and accuracy. In addition, we present a multi-reader study showing that the predictive uncertainty is indicative of reader errors.