# Learning to Segment Skin Lesions from Noisy Annotations

arXiv: https://arxiv.org/abs/1906.03815 · HTML: https://mlsanity.com/paper/1906.03815/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Jun 2019.

## Built on by (most cited first, 25 of 25)

- [Superpixel-guided Iterative Learning from Noisy Labels for Medical Image Segmentation](https://mlsanity.com/paper/2107.10100/) (2021)
- [Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models](https://mlsanity.com/paper/2103.00429/) (2021)
- [A Survey on Deep Learning for Skin Lesion Segmentation](https://mlsanity.com/paper/2206.00356/) (2022)
- [Label Cleaning Multiple Instance Learning: Refining Coarse Annotations on Single Whole-Slide Images](https://mlsanity.com/paper/2109.10778/) (2021)
- [Sharp U-Net: Depthwise Convolutional Network for Biomedical Image Segmentation](https://mlsanity.com/paper/2107.12461/) (2021)
- [Modeling Annotator Preference and Stochastic Annotation Error for Medical Image Segmentation](https://mlsanity.com/paper/2111.13410/) (2021)
- [Distilling effective supervision for robust medical image segmentation with noisy labels](https://mlsanity.com/paper/2106.11099/) (2021)
- [Label noise in segmentation networks : mitigation must deal with bias](https://mlsanity.com/paper/2107.02189/) (2021)
- [L2B: Learning to Bootstrap Robust Models for Combating Label Noise](https://mlsanity.com/paper/2202.04291/) (2022)
- [Transformer-based Annotation Bias-aware Medical Image Segmentation](https://mlsanity.com/paper/2306.01340/) (2023)
- [On Image Segmentation With Noisy Labels: Characterization and Volume Properties of the Optimal Solutions to Accuracy and Dice](https://mlsanity.com/paper/2206.06484/) (2022)
- [Data efficient deep learning for medical image analysis: A survey](https://mlsanity.com/paper/2310.06557/) (2023)
- [Uncertainty-based method for improving poorly labeled segmentation datasets](https://mlsanity.com/paper/2102.08021/) (2021)
- [Co-Seg: An Image Segmentation Framework Against Label Corruption](https://mlsanity.com/paper/2102.00523/) (2021)
- [MetaSeg: Content-Aware Meta-Net for Omni-Supervised Semantic Segmentation](https://mlsanity.com/paper/2401.11738/) (2024)
- [Pushing the Envelope of Thin Crack Detection](https://mlsanity.com/paper/2101.03326/) (2021)
- [Meta Mask Correction for Nuclei Segmentation in Histopathological Image](https://mlsanity.com/paper/2111.12498/) (2021)
- [Learning Confident Classifiers in the Presence of Label Noise](https://mlsanity.com/paper/2301.00524/) (2023)
- [Marginal Thresholding in Noisy Image Segmentation](https://mlsanity.com/paper/2304.04116/) (2023)
- [Accurate Segmentation of Optic Disc And Cup from Multiple Pseudo-labels by Noise-aware Learning](https://mlsanity.com/paper/2311.18496/) (2023)
- [Beyond Strong labels: Weakly-supervised Learning Based on Gaussian Pseudo Labels for The Segmentation of Ellipse-like Vascular Structures in Non-contrast CTs](https://mlsanity.com/paper/2402.03492/) (2024)
- [HyperSORT: Self-Organising Robust Training with hyper-networks](https://mlsanity.com/paper/2506.21430/) (2025)
- [Learning from Sparse Point Labels for Dense Carcinosis Localization in Advanced Ovarian Cancer Assessment](https://mlsanity.com/paper/2507.06643/) (2025)
- [Learning from Disagreement: A Group Decision Simulation Framework for Robust Medical Image Segmentation](https://mlsanity.com/paper/2510.10462/) (2025)
- [Federated Medical Image Segmentation under Real-World Label Noise: A Benchmark Suite for Noisy Label Learning Method Selection](https://mlsanity.com/paper/2606.16868/) (2026)

## Abstract (arXiv)

Deep convolutional neural networks have driven substantial advancements in the automatic understanding of images. Requiring a large collection of images and their associated annotations is one of the main bottlenecks limiting the adoption of deep networks. In the task of medical image segmentation, requiring pixel-level semantic annotations performed by human experts exacerbate this difficulty. This paper proposes a new framework to train a fully convolutional segmentation network from a large set of cheap unreliable annotations and a small set of expert-level clean annotations. We propose a spatially adaptive reweighting approach to treat clean and noisy pixel-level annotations commensurately in the loss function. We deploy a meta-learning approach to assign higher importance to pixels whose loss gradient direction is closer to those of clean data. Our experiments on training the network using segmentation ground truth corrupted with different levels of annotation noise show how spatial reweighting improves the robustness of deep networks to noisy annotations.