mlsanityData to 7 Oct 2026

Improving Medical Image Classification with Label Noise Using Dual-uncertainty Estimation

arXiv 2103.00528 ↗First posted 28 Feb 2021cs.CVcited by 13

Not on the map. Why?

Abstract (arXiv)

Deep neural networks are known to be data-driven and label noise can have a marked impact on model performance. Recent studies have shown great robustness to classic image recognition even under a high noisy rate. In medical applications, learning from datasets with label noise is more challenging since medical imaging datasets tend to have asymmetric (class-dependent) noise and suffer from high observer variability. In this paper, we systematically discuss and define the two common types of label noise in medical images - disagreement label noise from inconsistency expert opinions and single-target label noise from wrong diagnosis record. We then propose an uncertainty estimation-based framework to handle these two label noise amid the medical image classification task. We design a dual-uncertainty estimation approach to measure the disagreement label noise and single-target label noise via Direct Uncertainty Prediction and Monte-Carlo-Dropout. A boosting-based curriculum training procedure is later introduced for robust learning. We demonstrate the effectiveness of our method by conducting extensive experiments on three different diseases: skin lesions, prostate cancer, and retinal diseases. We also release a large re-engineered database that consists of annotations from more than ten ophthalmologists with an unbiased golden standard dataset for evaluation and benchmarking.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 30 of its 56 references that are in the map. First posted on arXiv 28 Feb 2021.

Builds on

30 of 56 references.

References · 30

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  5. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  6. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  7. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  8. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  9. 2017ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseasescited by 969
  10. 2016Universal adversarial perturbationscited by 774
  11. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  12. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
18 more
  1. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  2. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
  3. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
  4. 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 461
  5. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 441
  6. 2019Deep learning with noisy labels: exploring techniques and remedies in medical image analysiscited by 173
  7. 2020Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learningcited by 142
  8. 2018CurriculumNet: Weakly Supervised Learning from Large-Scale Web Imagescited by 126
  9. 2019Learning From Noisy Labels By Regularized Estimation Of Annotator Confusioncited by 126
  10. 2019Curriculum Loss: Robust Learning and Generalization against Label Corruptioncited by 87
  11. 2018Direct Uncertainty Prediction for Medical Second Opinionscited by 61
  12. 2019Asymmetric Co-Teaching for Unsupervised Cross Domain Person Re-Identificationcited by 36
  13. 2019Robust Learning at Noisy Labeled Medical Images: Applied to Skin Lesion Classificationcited by 33
  14. 2019IMAE for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude's Variance Matterscited by 33
  15. 2019Quantifying and Leveraging Classification Uncertainty for Chest Radiograph Assessmentcited by 23
  16. 2019Interpreting chest X-rays via CNNs that exploit hierarchical disease dependencies and uncertainty labelscited by 8
  17. 2019A Survey on Deep Learning of Small Sample in Biomedical Image Analysiscited by 7
  18. 2017Transfer Learning with Label Noisecited by 4

Built on by

Cited by year

Citing papers per year: 2021: 5; 2022: 7; 2023: 0; 2024: 0; 2025: 1.

13 papers.

Sort:

  1. 2021Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognitioncited by 27
  2. 2021Interpretability-Driven Sample Selection Using Self Supervised Learning For Disease Classification And Segmentationcited by 22
  3. 2021CT Image Synthesis Using Weakly Supervised Segmentation and Geometric Inter-Label Relations For COVID Image Analysiscited by 8
  4. 2022Unsupervised Domain Adaptive Fundus Image Segmentation with Category-level Regularizationcited by 6
  5. 2021Learning of Inter-Label Geometric Relationships Using Self-Supervised Learning: Application To Gleason Grade Segmentationcited by 5
  6. 2022Unsupervised Domain Adaptation Using Feature Disentanglement And GCNs For Medical Image Classificationcited by 5
  7. 2021Multimodal Generalized Zero Shot Learning for Gleason Grading using Self-Supervised Learningcited by 4
  8. 2022On the Ramifications of Human Label Uncertaintycited by 3
  9. 2022Interpretable Saliency Maps And Self-Supervised Learning For Generalized Zero Shot Medical Image Classificationcited by 2
  10. 2022Improved Super Resolution of MR Images Using CNNs and Vision Transformerscited by 1
  11. 2025Synthetic Generation and Latent Projection Denoising of Rim Lesions in Multiple Sclerosiscited by 1
  12. 2022Cyclic Generative Adversarial Networks With Congruent Image-Report Generation For Explainable Medical Image Analysiscited by 0
1 more
  1. 2022Establishment of Neural Networks Robust to Label Noisecited by 0