# URL: Combating Label Noise for Lung Nodule Malignancy Grading

arXiv: https://arxiv.org/abs/2308.08772 · HTML: https://mlsanity.com/paper/2308.08772/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 29 references that are in the map.
- First posted on arXiv 17 Aug 2023.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [Early-Learning Regularization Prevents Memorization of Noisy Labels](https://mlsanity.com/paper/2007.00151/) (2020)
- [NLNL: Negative Learning for Noisy Labels](https://mlsanity.com/paper/1908.07387/) (2019)
- [Selective-Supervised Contrastive Learning with Noisy Labels](https://mlsanity.com/paper/2203.04181/) (2022)
- [Learning with Neighbor Consistency for Noisy Labels](https://mlsanity.com/paper/2202.02200/) (2022)
- [ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks](https://mlsanity.com/paper/2005.03788/) (2020)
- [Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression](https://mlsanity.com/paper/2204.00309/) (2022)
- [Robustness of Accuracy Metric and its Inspirations in Learning with Noisy Labels](https://mlsanity.com/paper/2012.04193/) (2020)
- [Learning from Ambiguous Labels for Lung Nodule Malignancy Prediction](https://mlsanity.com/paper/2104.11436/) (2021)
- [Modeling Annotator Preference and Stochastic Annotation Error for Medical Image Segmentation](https://mlsanity.com/paper/2111.13410/) (2021)
- [CNLL: A Semi-supervised Approach For Continual Noisy Label Learning](https://mlsanity.com/paper/2204.09881/) (2022)
- [Transformer-based Annotation Bias-aware Medical Image Segmentation](https://mlsanity.com/paper/2306.01340/) (2023)
- [Meta Ordinal Regression Forest for Medical Image Classification with Ordinal Labels](https://mlsanity.com/paper/2203.07725/) (2022)

## Built on by (most cited first, 2 of 2)

- [Unleashing the Potential of Open-set Noisy Samples Against Label Noise for Medical Image Classification](https://mlsanity.com/paper/2406.12293/) (2024)
- [Self-Relaxed Joint Training: Sample Selection for Severity Estimation with Ordinal Noisy Labels](https://mlsanity.com/paper/2410.21885/) (2024)

## Abstract (arXiv)

Due to the complexity of annotation and inter-annotator variability, most lung nodule malignancy grading datasets contain label noise, which inevitably degrades the performance and generalizability of models. Although researchers adopt the label-noise-robust methods to handle label noise for lung nodule malignancy grading, they do not consider the inherent ordinal relation among classes of this task. To model the ordinal relation among classes to facilitate tackling label noise in this task, we propose a Unimodal-Regularized Label-noise-tolerant (URL) framework. Our URL contains two stages, the Supervised Contrastive Learning (SCL) stage and the Memory pseudo-labels generation and Unimodal regularization (MU) stage. In the SCL stage, we select reliable samples and adopt supervised contrastive learning to learn better representations. In the MU stage, we split samples with multiple annotations into multiple samples with a single annotation and shuffle them into different batches. To handle label noise, pseudo-labels are generated using the similarity between each sample and the central feature of each class, and temporal ensembling is used to obtain memory pseudo-labels that supervise the model training. To model the ordinal relation, we introduce unimodal regularization to keep the ordinal relation among classes in the predictions. Moreover, each lung nodule is characterized by three orthographic views. Experiments conducted on the LIDC-IDRI dataset indicate the superiority of our URL over other competing methods. Code is available at https://github.com/axz520/UR.