# Learning from Ambiguous Labels for Lung Nodule Malignancy Prediction

arXiv: https://arxiv.org/abs/2104.11436 · HTML: https://mlsanity.com/paper/2104.11436/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 58 references that are in the map.
- First posted on arXiv 23 Apr 2021.

## Builds on (most cited first, 13 of 13)

- [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)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Symmetric Cross Entropy for Robust Learning with Noisy Labels](https://mlsanity.com/paper/1908.06112/) (2019)
- [NLNL: Negative Learning for Noisy Labels](https://mlsanity.com/paper/1908.07387/) (2019)
- [Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey](https://mlsanity.com/paper/1912.05170/) (2019)
- [Learning from Complementary Labels](https://mlsanity.com/paper/1705.07541/) (2017)
- [A 3D Probabilistic Deep Learning System for Detection and Diagnosis of Lung Cancer Using Low-Dose CT Scans](https://mlsanity.com/paper/1902.03233/) (2019)
- [Shape and Margin-Aware Lung Nodule Classification in Low-dose CT Images via Soft Activation Mapping](https://mlsanity.com/paper/1810.12494/) (2018)
- [TumorNet: Lung Nodule Characterization Using Multi-View Convolutional Neural Network with Gaussian Process](https://mlsanity.com/paper/1703.00645/) (2017)
- [ProCAN: Progressive Growing Channel Attentive Non-Local Network for Lung Nodule Classification](https://mlsanity.com/paper/2010.15417/) (2020)
- [Learning Efficient, Explainable and Discriminative Representations for Pulmonary Nodules Classification](https://mlsanity.com/paper/2101.07429/) (2021)
- [Meta ordinal weighting net for improving lung nodule classification](https://mlsanity.com/paper/2102.00456/) (2021)

## Built on by (most cited first, 15 of 15)

- [CLIP-Lung: Textual Knowledge-Guided Lung Nodule Malignancy Prediction](https://mlsanity.com/paper/2304.08013/) (2023)
- [Modeling Annotator Preference and Stochastic Annotation Error for Medical Image Segmentation](https://mlsanity.com/paper/2111.13410/) (2021)
- [DVPT: Dynamic Visual Prompt Tuning of Large Pre-trained Models for Medical Image Analysis](https://mlsanity.com/paper/2307.09787/) (2023)
- [Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning](https://mlsanity.com/paper/2305.16912/) (2023)
- [Federated Learning for Medical Image Classification: A Comprehensive Benchmark](https://mlsanity.com/paper/2504.05238/) (2025)
- [Multi-Instance Partial-Label Learning with Margin Adjustment](https://mlsanity.com/paper/2501.12597/) (2025)
- [Trustworthy Multi-phase Liver Tumor Segmentation via Evidence-based Uncertainty](https://mlsanity.com/paper/2305.05344/) (2023)
- [Towards Collective Intelligence: Uncertainty-aware SAM Adaptation for Ambiguous Medical Image Segmentation](https://mlsanity.com/paper/2403.10931/) (2024)
- [Re-thinking and Re-labeling LIDC-IDRI for Robust Pulmonary Cancer Prediction](https://mlsanity.com/paper/2207.14238/) (2022)
- [URL: Combating Label Noise for Lung Nodule Malignancy Grading](https://mlsanity.com/paper/2308.08772/) (2023)
- [Parse and Recall: Towards Accurate Lung Nodule Malignancy Prediction like Radiologists](https://mlsanity.com/paper/2307.10824/) (2023)
- [Unleashing the Potential of Open-set Noisy Samples Against Label Noise for Medical Image Classification](https://mlsanity.com/paper/2406.12293/) (2024)
- [LiMT: A Multi-task Liver Image Benchmark Dataset](https://mlsanity.com/paper/2511.19889/) (2025)
- [Faithful learning with sure data for lung nodule diagnosis](https://mlsanity.com/paper/2202.12515/) (2022)
- [Learning Trustworthy Model from Noisy Labels based on Rough Set for Surface Defect Detection](https://mlsanity.com/paper/2301.10441/) (2023)

## Abstract (arXiv)

Lung nodule malignancy prediction is an essential step in the early diagnosis of lung cancer. Besides the difficulties commonly discussed, the challenges of this task also come from the ambiguous labels provided by annotators, since deep learning models may learn, even amplify, the bias embedded in them. In this paper, we propose a multi-view "divide-and-rule" (MV-DAR) model to learn from both reliable and ambiguous annotations for lung nodule malignancy prediction. According to the consistency and reliability of their annotations, we divide nodules into three sets: a consistent and reliable set (CR-Set), an inconsistent set (IC-Set), and a low reliable set (LR-Set). The nodule in IC-Set is annotated by multiple radiologists inconsistently, and the nodule in LR-Set is annotated by only one radiologist. The proposed MV-DAR contains three DAR submodels to characterize a lung nodule from three orthographic views. Each DAR consists of a prediction network (Prd-Net), a counterfactual network (CF-Net), and a low reliable network (LR-Net), learning on CR-Set, IC-Set, and LR-Set, respectively. The image representation ability learned by CF-Net and LR-Net is then transferred to Prd-Net by negative-attention module (NA-Module) and consistent-attention module (CA-Module), aiming to boost the prediction ability of Prd-Net. The MV-DAR model has been evaluated on the LIDC-IDRI dataset and LUNGx dataset. Our results indicate not only the effectiveness of the proposed MV-DAR model in learning from ambiguous labels but also its superiority over present noisy label-learning models in lung nodule malignancy prediction.