# Label Cleaning Multiple Instance Learning: Refining Coarse Annotations on Single Whole-Slide Images

arXiv: https://arxiv.org/abs/2109.10778 · HTML: https://mlsanity.com/paper/2109.10778/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 61 references that are in the map.
- First posted on arXiv 22 Sep 2021.

## Builds on (most cited first, 27 of 27)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images](https://mlsanity.com/paper/2004.09666/) (2020)
- [Learning to Reweight Examples for Robust Deep Learning](https://mlsanity.com/paper/1803.09050/) (2018)
- [Robust Loss Functions under Label Noise for Deep Neural Networks](https://mlsanity.com/paper/1712.09482/) (2017)
- [Calibrating Deep Neural Networks using Focal Loss](https://mlsanity.com/paper/2002.09437/) (2020)
- [CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise](https://mlsanity.com/paper/1711.07131/) (2017)
- [Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysis](https://mlsanity.com/paper/1804.06353/) (2018)
- [U-Net and its variants for medical image segmentation: theory and applications](https://mlsanity.com/paper/2011.01118/) (2020)
- [Deep neural network models for computational histopathology: A survey](https://mlsanity.com/paper/1912.12378/) (2019)
- [Revisiting Multiple Instance Neural Networks](https://mlsanity.com/paper/1610.02501/) (2016)
- [Deep Label Distribution Learning with Label Ambiguity](https://mlsanity.com/paper/1611.01731/) (2016)
- [CAMEL: A Weakly Supervised Learning Framework for Histopathology Image Segmentation](https://mlsanity.com/paper/1908.10555/) (2019)
- [Interpreting Chest X-rays via CNNs that Exploit Hierarchical Disease Dependencies and Uncertainty Labels](https://mlsanity.com/paper/2005.12734/) (2020)
- [Deep k-NN for Noisy Labels](https://mlsanity.com/paper/2004.12289/) (2020)
- [Learning with Confident Examples: Rank Pruning for Robust Classification with Noisy Labels](https://mlsanity.com/paper/1705.01936/) (2017)
- [Constrained Deep Weak Supervision for Histopathology Image Segmentation](https://mlsanity.com/paper/1701.00794/) (2017)
- [Classification and Disease Localization in Histopathology Using Only Global Labels: A Weakly-Supervised Approach](https://mlsanity.com/paper/1802.02212/) (2018)
- [Spatially Varying Label Smoothing: Capturing Uncertainty from Expert Annotations](https://mlsanity.com/paper/2104.05788/) (2021)
- [A Semi-Supervised Two-Stage Approach to Learning from Noisy Labels](https://mlsanity.com/paper/1802.02679/) (2018)
- [Learning to Segment Skin Lesions from Noisy Annotations](https://mlsanity.com/paper/1906.03815/) (2019)
- [Self-similarity Student for Partial Label Histopathology Image Segmentation](https://mlsanity.com/paper/2007.09610/) (2020)
- [Uncertainty Based Detection and Relabeling of Noisy Image Labels](https://mlsanity.com/paper/1906.11876/) (2019)
- [CT organ segmentation using GPU data augmentation, unsupervised labels and IOU loss](https://mlsanity.com/paper/1811.11226/) (2018)

## Built on by (most cited first, 13 of 13)

- [Multiple Instance Learning for Digital Pathology: A Review on the State-of-the-Art, Limitations & Future Potential](https://mlsanity.com/paper/2206.04425/) (2022)
- [Pseudo-Bag Mixup Augmentation for Multiple Instance Learning-Based Whole Slide Image Classification](https://mlsanity.com/paper/2306.16180/) (2023)
- [Deep Learning in Breast Cancer Imaging: A Decade of Progress and Future Directions](https://mlsanity.com/paper/2304.06662/) (2023)
- [Weakly Supervised Learning Significantly Reduces the Number of Labels Required for Intracranial Hemorrhage Detection on Head CT](https://mlsanity.com/paper/2211.15924/) (2022)
- [Robust Tumor Detection from Coarse Annotations via Multi-Magnification Ensembles](https://mlsanity.com/paper/2303.16533/) (2023)
- [CAMEL2: Enhancing weakly supervised learning for histopathology images by incorporating the significance ratio](https://mlsanity.com/paper/2310.05394/) (2023)
- [A Prototype-Guided Coarse Annotations Refining Approach for Whole Slide Images](https://mlsanity.com/paper/2503.19407/) (2025)
- [RefineSeg: Dual Coarse-to-Fine Learning for Medical Image Segmentation](https://mlsanity.com/paper/2508.02844/) (2025)
- [Emerging Semantic Segmentation from Positive and Negative Coarse Label Learning](https://mlsanity.com/paper/2508.18186/) (2025)
- [Revisiting Data Challenges of Computational Pathology: A Pack-based Multiple Instance Learning Training Framework](https://mlsanity.com/paper/2509.20923/) (2025)
- [Rewis3d: Reconstruction Improves Weakly-Supervised Semantic Segmentation](https://mlsanity.com/paper/2603.06374/) (2026)
- [Self-Supervised Contrastive Learning for Cardiac MR Sequence Classification](https://mlsanity.com/paper/2605.24789/) (2026)
- [Statistical Testing for Multiple Instance Learning via Selective Inference with Applications to Computational Pathology](https://mlsanity.com/paper/2609.31712/) (2026)

## Abstract (arXiv)

Annotating cancerous regions in whole-slide images (WSIs) of pathology samples plays a critical role in clinical diagnosis, biomedical research, and machine learning algorithms development. However, generating exhaustive and accurate annotations is labor-intensive, challenging, and costly. Drawing only coarse and approximate annotations is a much easier task, less costly, and it alleviates pathologists' workload. In this paper, we study the problem of refining these approximate annotations in digital pathology to obtain more accurate ones. Some previous works have explored obtaining machine learning models from these inaccurate annotations, but few of them tackle the refinement problem where the mislabeled regions should be explicitly identified and corrected, and all of them require a -- often very large -- number of training samples. We present a method, named Label Cleaning Multiple Instance Learning (LC-MIL), to refine coarse annotations on a single WSI without the need of external training data. Patches cropped from a WSI with inaccurate labels are processed jointly within a multiple instance learning framework, mitigating their impact on the predictive model and refining the segmentation. Our experiments on a heterogeneous WSI set with breast cancer lymph node metastasis, liver cancer, and colorectal cancer samples show that LC-MIL significantly refines the coarse annotations, outperforming state-of-the-art alternatives, even while learning from a single slide. Moreover, we demonstrate how real annotations drawn by pathologists can be efficiently refined and improved by the proposed approach. All these results demonstrate that LC-MIL is a promising, light-weight tool to provide fine-grained annotations from coarsely annotated pathology sets.