# Robust Classification from Noisy Labels: Integrating Additional Knowledge for Chest Radiography Abnormality Assessment

arXiv: https://arxiv.org/abs/2104.05261 · HTML: https://mlsanity.com/paper/2104.05261/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 68 references that are in the map.
- First posted on arXiv 12 Apr 2021.

## Builds on (most cited first, 30 of 36)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning](https://mlsanity.com/paper/1506.02142/) (2015)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels](https://mlsanity.com/paper/1805.07836/) (2018)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning](https://mlsanity.com/paper/1711.05225/) (2017)
- [Unsupervised Label Noise Modeling and Loss Correction](https://mlsanity.com/paper/1904.11238/) (2019)
- [Scalable and accurate deep learning for electronic health records](https://mlsanity.com/paper/1801.07860/) (2018)
- [Variational Dropout Sparsifies Deep Neural Networks](https://mlsanity.com/paper/1701.05369/) (2017)
- [Deep learning with noisy labels: exploring techniques and remedies in medical image analysis](https://mlsanity.com/paper/1912.02911/) (2019)
- [Deep Learning is Robust to Massive Label Noise](https://mlsanity.com/paper/1705.10694/) (2017)
- [Thoracic Disease Identification and Localization with Limited Supervision](https://mlsanity.com/paper/1711.06373/) (2017)
- [Post-DAE: Anatomically Plausible Segmentation via Post-Processing with Denoising Autoencoders](https://mlsanity.com/paper/2006.13791/) (2020)
- [DeepLung: Deep 3D Dual Path Nets for Automated Pulmonary Nodule Detection and Classification](https://mlsanity.com/paper/1801.09555/) (2018)
- [Diagnose like a Radiologist: Attention Guided Convolutional Neural Network for Thorax Disease Classification](https://mlsanity.com/paper/1801.09927/) (2018)
- [Learning to diagnose from scratch by exploiting dependencies among labels](https://mlsanity.com/paper/1710.10501/) (2017)
- [Learning to recognize Abnormalities in Chest X-Rays with Location-Aware Dense Networks](https://mlsanity.com/paper/1803.04565/) (2018)
- [IMAE for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude's Variance Matters](https://mlsanity.com/paper/1903.12141/) (2019)
- [Attention-Guided Curriculum Learning for Weakly Supervised Classification and Localization of Thoracic Diseases on Chest Radiographs](https://mlsanity.com/paper/1807.07532/) (2018)
- [Quantifying and Leveraging Predictive Uncertainty for Medical Image Assessment](https://mlsanity.com/paper/2007.04258/) (2020)
- [Quantifying and Leveraging Classification Uncertainty for Chest Radiograph Assessment](https://mlsanity.com/paper/1906.07775/) (2019)
- [Weakly Supervised Medical Diagnosis and Localization from Multiple Resolutions](https://mlsanity.com/paper/1803.07703/) (2018)
- [Weakly Supervised Deep Learning for Thoracic Disease Classification and Localization on Chest X-rays](https://mlsanity.com/paper/1807.06067/) (2018)
- [Large Scale Automated Reading of Frontal and Lateral Chest X-Rays using Dual Convolutional Neural Networks](https://mlsanity.com/paper/1804.07839/) (2018)
- [Attention U-Net Based Adversarial Architectures for Chest X-ray Lung Segmentation](https://mlsanity.com/paper/2003.10304/) (2020)

## Built on by (most cited first, 6 of 6)

- [Self-supervised Learning from 100 Million Medical Images](https://mlsanity.com/paper/2201.01283/) (2022)
- [A Survey of Medical Vision-and-Language Applications and Their Techniques](https://mlsanity.com/paper/2411.12195/) (2024)
- [Deep learning with noisy labels in medical prediction problems: a scoping review](https://mlsanity.com/paper/2403.13111/) (2024)
- [A Systematic Review of Generalization Research in Medical Image Classification](https://mlsanity.com/paper/2403.12167/) (2024)
- [Structure is Supervision: Multiview Masked Autoencoders for Radiology](https://mlsanity.com/paper/2511.22294/) (2025)
- [Radiologist-Guided Causal Concept Bottleneck Models for Chest X-Ray Interpretation](https://mlsanity.com/paper/2605.07785/) (2026)

## Abstract (arXiv)

Chest radiography is the most common radiographic examination performed in daily clinical practice for the detection of various heart and lung abnormalities. The large amount of data to be read and reported, with more than 100 studies per day for a single radiologist, poses a challenge in consistently maintaining high interpretation accuracy. The introduction of large-scale public datasets has led to a series of novel systems for automated abnormality classification. However, the labels of these datasets were obtained using natural language processed medical reports, yielding a large degree of label noise that can impact the performance. In this study, we propose novel training strategies that handle label noise from such suboptimal data. Prior label probabilities were measured on a subset of training data re-read by 4 board-certified radiologists and were used during training to increase the robustness of the training model to the label noise. Furthermore, we exploit the high comorbidity of abnormalities observed in chest radiography and incorporate this information to further reduce the impact of label noise. Additionally, anatomical knowledge is incorporated by training the system to predict lung and heart segmentation, as well as spatial knowledge labels. To deal with multiple datasets and images derived from various scanners that apply different post-processing techniques, we introduce a novel image normalization strategy. Experiments were performed on an extensive collection of 297,541 chest radiographs from 86,876 patients, leading to a state-of-the-art performance level for 17 abnormalities from 2 datasets. With an average AUC score of 0.880 across all abnormalities, our proposed training strategies can be used to significantly improve performance scores.