# Active Label Refinement for Robust Training of Imbalanced Medical Image Classification Tasks in the Presence of High Label Noise

arXiv: https://arxiv.org/abs/2407.05973 · HTML: https://mlsanity.com/paper/2407.05973/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 8 Jul 2024.

## Builds on (most cited first, 14 of 14)

- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Deep learning with noisy labels: exploring techniques and remedies in medical image analysis](https://mlsanity.com/paper/1912.02911/) (2019)
- [A Survey on Active Learning and Human-in-the-Loop Deep Learning for Medical Image Analysis](https://mlsanity.com/paper/1910.02923/) (2019)
- [Estimating Example Difficulty Using Variance of Gradients](https://mlsanity.com/paper/2008.11600/) (2020)
- [Active label cleaning for improved dataset quality under resource constraints](https://mlsanity.com/paper/2109.00574/) (2021)
- [Loss-Curvature Matching for Dataset Selection and Condensation](https://mlsanity.com/paper/2303.04449/) (2023)
- [Robust Medical Image Classification from Noisy Labeled Data with Global and Local Representation Guided Co-training](https://mlsanity.com/paper/2205.04723/) (2022)
- [A Survey of Crowdsourcing in Medical Image Analysis](https://mlsanity.com/paper/1902.09159/) (2019)
- [Co-Correcting: Noise-tolerant Medical Image Classification via mutual Label Correction](https://mlsanity.com/paper/2109.05159/) (2021)
- [Improving Medical Image Classification in Noisy Labels Using Only Self-supervised Pretraining](https://mlsanity.com/paper/2308.04551/) (2023)
- [ActiveLab: Active Learning with Re-Labeling by Multiple Annotators](https://mlsanity.com/paper/2301.11856/) (2023)

## Built on by (most cited first, 3 of 3)

- [A2LC: Active and Automated Label Correction for Semantic Segmentation](https://mlsanity.com/paper/2506.11599/) (2025)
- [Active Label Cleaning for Reliable Detection of Electron Dense Deposits in Transmission Electron Microscopy Images](https://mlsanity.com/paper/2602.05250/) (2026)
- [Detecting and refurbishing ground truth errors during training of deep learning-based echocardiography segmentation models](https://mlsanity.com/paper/2604.12832/) (2026)

## Abstract (arXiv)

The robustness of supervised deep learning-based medical image classification is significantly undermined by label noise. Although several methods have been proposed to enhance classification performance in the presence of noisy labels, they face some challenges: 1) a struggle with class-imbalanced datasets, leading to the frequent overlooking of minority classes as noisy samples; 2) a singular focus on maximizing performance using noisy datasets, without incorporating experts-in-the-loop for actively cleaning the noisy labels. To mitigate these challenges, we propose a two-phase approach that combines Learning with Noisy Labels (LNL) and active learning. This approach not only improves the robustness of medical image classification in the presence of noisy labels, but also iteratively improves the quality of the dataset by relabeling the important incorrect labels, under a limited annotation budget. Furthermore, we introduce a novel Variance of Gradients approach in LNL phase, which complements the loss-based sample selection by also sampling under-represented samples. Using two imbalanced noisy medical classification datasets, we demonstrate that that our proposed technique is superior to its predecessors at handling class imbalance by not misidentifying clean samples from minority classes as mostly noisy samples.