mlsanityData to 14 Oct 2026

Exploring the Impact of Skin Color on Skin Lesion Segmentation

arXiv 2603.29694 ↗First posted 31 Mar 2026cs.CV cs.AIcited by 0

Not on the map. Why?

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.

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

22 of 60 references.

References · 22

  1. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  4. 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,161
  5. 2017Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)cited by 549
  6. 2022FairPrune: Achieving Fairness Through Pruning for Dermatological Disease Diagnosiscited by 59
  7. 2020Debiasing Skin Lesion Datasets and Models? Not So Fastcited by 43
  8. 2019Estimating Skin Tone and Effects on Classification Performance in Dermatology Datasetscited by 29
  9. 2022A Survey on Deep Learning for Skin Lesion Segmentationcited by 22
  10. 2022FairDisCo: Fairer AI in Dermatology via Disentanglement Contrastive Learningcited by 22
  11. 2023From CNN to Transformer: A Review of Medical Image Segmentation Modelscited by 22
  12. 2022CIRCLe: Color Invariant Representation Learning for Unbiased Classification of Skin Lesionscited by 17
10 more
  1. 2020The Effects of Skin Lesion Segmentation on the Performance of Dermatoscopic Image Classificationcited by 14
  2. 2024Comparative Analysis of ImageNet Pre-Trained Deep Learning Models and DINOv2 in Medical Imaging Classificationcited by 14
  3. 2024Achieve Fairness without Demographics for Dermatological Disease Diagnosiscited by 10
  4. 2021On the Fairness of Swarm Learning in Skin Lesion Classificationcited by 9
  5. 2024Achieving Fairness Through Channel Pruning for Dermatological Disease Diagnosiscited by 9
  6. 2024PatchAlign:Fair and Accurate Skin Disease Image Classification by Alignment with Clinical Labelscited by 5
  7. 2022Achieving Fairness in Dermatological Disease Diagnosis through Automatic Weight Adjusting Federated Learning and Personalizationcited by 4
  8. 2024Skin Cancer Machine Learning Model Tone Biascited by 3
  9. 2024Towards Fairness in AI for Melanoma Detection: Systemic Review and Recommendationscited by 3
  10. 2025Enhancing Fairness in Skin Lesion Classification for Medical Diagnosis Using Prune Learningcited by 2

Built on by

Not cited yet.