# Exploring the Impact of Skin Color on Skin Lesion Segmentation

arXiv: https://arxiv.org/abs/2603.29694 · HTML: https://mlsanity.com/paper/2603.29694/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 60 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Builds on (most cited first, 22 of 22)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [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)
- [FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosis](https://mlsanity.com/paper/2203.02110/) (2022)
- [Debiasing Skin Lesion Datasets and Models? Not So Fast](https://mlsanity.com/paper/2004.11457/) (2020)
- [Estimating Skin Tone and Effects on Classification Performance in Dermatology Datasets](https://mlsanity.com/paper/1910.13268/) (2019)
- [A Survey on Deep Learning for Skin Lesion Segmentation](https://mlsanity.com/paper/2206.00356/) (2022)
- [FairDisCo: Fairer AI in Dermatology via Disentanglement Contrastive Learning](https://mlsanity.com/paper/2208.10013/) (2022)
- [From CNN to Transformer: A Review of Medical Image Segmentation Models](https://mlsanity.com/paper/2308.05305/) (2023)
- [CIRCLe: Color Invariant Representation Learning for Unbiased Classification of Skin Lesions](https://mlsanity.com/paper/2208.13528/) (2022)
- [The Effects of Skin Lesion Segmentation on the Performance of Dermatoscopic Image Classification](https://mlsanity.com/paper/2008.12602/) (2020)
- [Comparative Analysis of ImageNet Pre-Trained Deep Learning Models and DINOv2 in Medical Imaging Classification](https://mlsanity.com/paper/2402.07595/) (2024)
- [Achieve Fairness without Demographics for Dermatological Disease Diagnosis](https://mlsanity.com/paper/2401.08066/) (2024)
- [On the Fairness of Swarm Learning in Skin Lesion Classification](https://mlsanity.com/paper/2109.12176/) (2021)
- [Achieving Fairness Through Channel Pruning for Dermatological Disease Diagnosis](https://mlsanity.com/paper/2405.08681/) (2024)
- [PatchAlign:Fair and Accurate Skin Disease Image Classification by Alignment with Clinical Labels](https://mlsanity.com/paper/2409.04975/) (2024)
- [Achieving Fairness in Dermatological Disease Diagnosis through Automatic Weight Adjusting Federated Learning and Personalization](https://mlsanity.com/paper/2208.11187/) (2022)
- [Skin Cancer Machine Learning Model Tone Bias](https://mlsanity.com/paper/2410.06385/) (2024)
- [Towards Fairness in AI for Melanoma Detection: Systemic Review and Recommendations](https://mlsanity.com/paper/2411.12846/) (2024)
- [Enhancing Fairness in Skin Lesion Classification for Medical Diagnosis Using Prune Learning](https://mlsanity.com/paper/2509.00745/) (2025)

## Abstract (arXiv)

Skin cancer, particularly melanoma, remains a major cause of morbidity and mortality, making early detection critical. AI-driven dermatology systems often rely on skin lesion segmentation as a preprocessing step to delineate the lesion from surrounding skin and support downstream analysis. While fairness concerns regarding skin tone have been widely studied for lesion classification, the influence of skin tone on the segmentation stage remains under-quantified and is frequently assessed using coarse, discrete skin tone categories. In this work, we evaluate three strong segmentation architectures (UNet, DeepLabV3 with a ResNet50 backbone, and DINOv2) on two public dermoscopic datasets (HAM10000 and ISIC2017) and introduce a continuous pigment or contrast analysis that treats pixel-wise ITA values as distributions. Using Wasserstein distances between within-image distributions for skin-only, lesion-only, and whole-image regions, we quantify lesion skin contrast and relate it to segmentation performance across multiple metrics. Within the range represented in these datasets, global skin tone metrics (Fitzpatrick grouping or mean ITA) show weak association with segmentation quality. In contrast, low lesion-skin contrast is consistently associated with larger segmentation errors in models, indicating that boundary ambiguity and low contrast are key drivers of failure. These findings suggest that fairness improvements in dermoscopic segmentation should prioritize robust handling of low-contrast lesions, and the distribution-based pigment measures provide a more informative audit signal than discrete skin-tone categories.