# What Can We Learn from Inter-Annotator Variability in Skin Lesion Segmentation?

arXiv: https://arxiv.org/abs/2508.09381 · HTML: https://mlsanity.com/paper/2508.09381/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 48 references that are in the map.
- First posted on arXiv 12 Aug 2025.

## Builds on (most cited first, 21 of 21)

- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks](https://mlsanity.com/paper/1710.11063/) (2017)
- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1710.05006/) (2017)
- [BCN20000: Dermoscopic Lesions in the Wild](https://mlsanity.com/paper/1908.02288/) (2019)
- [The Benefit of Multitask Representation Learning](https://mlsanity.com/paper/1505.06279/) (2015)
- [Deep Semantic Segmentation of Natural and Medical Images: A Review](https://mlsanity.com/paper/1910.07655/) (2019)
- [A Mutual Bootstrapping Model for Automated Skin Lesion Segmentation and Classification](https://mlsanity.com/paper/1903.03313/) (2019)
- [Coherent Concept-based Explanations in Medical Image and Its Application to Skin Lesion Diagnosis](https://mlsanity.com/paper/2304.04579/) (2023)
- [A Survey on Deep Learning for Skin Lesion Segmentation](https://mlsanity.com/paper/2206.00356/) (2022)
- [A survey, review, and future trends of skin lesion segmentation and classification](https://mlsanity.com/paper/2208.12232/) (2022)
- [ExAID: A Multimodal Explanation Framework for Computer-Aided Diagnosis of Skin Lesions](https://mlsanity.com/paper/2201.01249/) (2022)
- [D-LEMA: Deep Learning Ensembles from Multiple Annotations -- Application to Skin Lesion Segmentation](https://mlsanity.com/paper/2012.07206/) (2020)
- [A Novel Multi-task Deep Learning Model for Skin Lesion Segmentation and Classification](https://mlsanity.com/paper/1703.01025/) (2017)
- [Crowd disagreement about medical images is informative](https://mlsanity.com/paper/1806.08174/) (2018)
- [That Label's Got Style: Handling Label Style Bias for Uncertain Image Segmentation](https://mlsanity.com/paper/2303.15850/) (2023)
- [Handling Inter-Annotator Agreement for Automated Skin Lesion Segmentation](https://mlsanity.com/paper/1906.02415/) (2019)
- [Less is More: Sample Selection and Label Conditioning Improve Skin Lesion Segmentation](https://mlsanity.com/paper/2004.13856/) (2020)
- [ENHANCE (ENriching Health data by ANnotations of Crowd and Experts): A case study for skin lesion classification](https://mlsanity.com/paper/2107.12734/) (2021)
- [Segmentation Style Discovery: Application to Skin Lesion Images](https://mlsanity.com/paper/2408.02787/) (2024)
- [MSE-Nets: Multi-annotated Semi-supervised Ensemble Networks for Improving Segmentation of Medical Image with Ambiguous Boundaries](https://mlsanity.com/paper/2311.10380/) (2023)

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

- [SplitFed-CL: A Split Federated Co-Learning Framework for Medical Image Segmentation with Inaccurate Labels](https://mlsanity.com/paper/2605.11060/) (2026)
- [A Multi-Annotator Study of Segmentation Noise and Uncertainty in Turbid Underwater Images](https://mlsanity.com/paper/2608.15363/) (2026)

## Abstract (arXiv)

Medical image segmentation exhibits intra- and inter-annotator variability due to ambiguous object boundaries, annotator preferences, expertise, and tools, among other factors. Lesions with ambiguous boundaries, e.g., spiculated or infiltrative nodules, or irregular borders per the ABCD rule, are particularly prone to disagreement and are often associated with malignancy. In this work, we curate IMA++, the largest multi-annotator skin lesion segmentation dataset, on which we conduct an in-depth study of variability due to annotator, malignancy, tool, and skill factors. We find a statistically significant (p<0.001) association between inter-annotator agreement (IAA), measured using Dice, and the malignancy of skin lesions. We further show that IAA can be accurately predicted directly from dermoscopic images, achieving a mean absolute error of 0.108. Finally, we leverage this association by utilizing IAA as a "soft" clinical feature within a multi-task learning objective, yielding a 4.2% improvement in balanced accuracy averaged across multiple model architectures and across IMA++ and four public dermoscopic datasets. The code is available at https://github.com/sfu-mial/skin-IAV.