Disease Burden over Skin Tone: Decomposing the Dermatology-AI Generalization Gap

• URL: http://arxiv.org/abs/2609.02111v1
• Date: Wed, 02 Sep 2026 04:55:23 GMT
• Title: Disease Burden over Skin Tone: Decomposing the Dermatology-AI Generalization Gap
• Abstract summary: We investigate whether poor generalization is primarily caused by skin-tone underrepresentation or disease-distribution shift.<n>Models are evaluated on a tone-stratified disease-matched dataset and a disease-shifted tone-diverse dataset.<n>Our results show that disease-distribution shift contributes more than skin tone in the evaluated settings.
• Score: 0.7068165275780814
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Dermatology artificial intelligence (AI) models are predominantly trained on light-skinned, cancer-focused image collections, yet they are increasingly proposed for deployment in resource-constrained settings where patients differ from training populations along two confounded axes: skin tone and disease distribution. We investigate whether poor generalization is primarily caused by skin-tone underrepresentation or disease-distribution shift. We evaluate a cancer-trained baseline (ResNet-50 fine-tuned on HAM10000 and ISIC 2019), two dermatology foundation models (DermLIP and MONET), and a general-purpose vision model (DINOv3) as frozen feature extractors. Models are evaluated on a tone-stratified disease-matched dataset (Diverse Dermatology Images, DDI) and a disease-shifted tone-diverse dataset (Skin Condition Image Network, SCIN). Our results show that disease-distribution shift contributes more than skin tone in the evaluated settings. The cancer baseline decreases from 0.62 to 0.21 balanced accuracy when transferred to unfamiliar clinical conditions, while the within-disease skin-tone gap is smaller (0.10-0.18) and inconsistent. Label-free representation analysis shows that this failure reflects a representational limitation rather than only missing output labels: cancer-specialized features poorly cluster unfamiliar conditions (kNN purity lift +0.06 over chance), whereas dermatology-pretrained features retain stronger transferable structure (+0.23). Finally, we show that representation quality predicts recoverable performance under lightweight adaptation. Starting from dermatology foundation models, approximately ten labeled examples per clinical category recover most attainable performance. We release the evaluation protocol and code to support reproducible auditing of dermatology AI generalization.

Related papers

• BenchX: Benchmarking AI Models for Cancer Detection and Localization with Demographic and Protocol Biases [59.19934491064188]
  Artificial intelligence (AI) has achieved remarkable success in medical imaging.<n>These models often perform inconsistently across real-world clinical settings.<n>We develop a benchmark of 85,355 CT scans that systematically evaluates 12 tumor-detection AI models.
  arXiv  Detail & Related papers  (2026-06-23T17:58:59Z)
• DermaFlux: Synthetic Skin Lesion Generation with Rectified Flows for Enhanced Image Classification [72.0680382603686]
  DermaFlux is a rectified flow-based text-to-image generative framework that synthesizes clinically grounded skin lesion images.<n>We construct image-text pairs using synthetic textual captions generated by Llama 3.2.<n>Our ImageNet-pretrained ViT fine-tuned with only 2,500 real images and 4,375 DermaFlux-generated samples achieves 78.04% binary classification accuracy and an AUC of 0.859, surpassing the next best dermatology model by 8%.
  arXiv  Detail & Related papers  (2026-03-17T11:25:46Z)
• A Generative AI Approach for Reducing Skin Tone Bias in Skin Cancer Classification [2.676349883103404]
  Skin cancer is one of the most common cancers worldwide and early detection is critical for effective treatment.<n>Current AI diagnostic tools are often trained on datasets dominated by lighter skin tones, leading to reduced accuracy and fairness for people with darker skin.<n>This paper addresses the challenge of skin tone imbalance in automated skin cancer detection using dermoscopic images.
  arXiv  Detail & Related papers  (2026-02-16T00:20:56Z)
• Colorimeter-Supervised Skin Tone Estimation from Dermatoscopic Images for Fairness Auditing [0.0]
  We develop neural networks that predict Fitzpatrick skin type via ordinal regression and the Individual Typology Angle (ITA) via color regression.<n>We release code and pretrained models as an open-source tool for rapid skin-tone annotation and bias auditing.<n>This is, to our knowledge, the first dermatoscopic skin-tone estimation neural network validated against colorimeter measurements.
  arXiv  Detail & Related papers  (2026-02-10T20:20:45Z)
• Adapting Large Language Models to Mitigate Skin Tone Biases in Clinical Dermatology Tasks: A Mixed-Methods Study [2.3034630097498883]
  We evaluated performance biases in SkinGPT-4 across skin tones on common skin diseases.<n>We leveraged the SkinGPT-4 backbone to develop finetuned models for custom skin disease classification tasks.
  arXiv  Detail & Related papers  (2025-09-28T09:40:40Z)
• DermINO: Hybrid Pretraining for a Versatile Dermatology Foundation Model [92.66916452260553]
  DermNIO is a versatile foundation model for dermatology.<n>It incorporates a novel hybrid pretraining framework that augments the self-supervised learning paradigm.<n>It consistently outperforms state-of-the-art models across a wide range of tasks.
  arXiv  Detail & Related papers  (2025-08-17T00:41:39Z)
• FairSkin: Fair Diffusion for Skin Disease Image Generation [54.29840149709033]
  Diffusion Model (DM) has become a leading method in generating synthetic medical images, but it suffers from a critical twofold bias. We propose FairSkin, a novel DM framework that mitigates these biases through a three-level resampling mechanism. Our approach significantly improves the diversity and quality of generated images, contributing to more equitable skin disease detection in clinical settings.
  arXiv  Detail & Related papers  (2024-10-29T21:37:03Z)
• Brain Tumor Classification on MRI in Light of Molecular Markers [56.99710477905796]
  Co-deletion of the 1p/19q gene is associated with clinical outcomes in low-grade gliomas.<n>This study aims to utilize a specially MRI-based convolutional neural network for brain cancer detection.
  arXiv  Detail & Related papers  (2024-09-29T07:04:26Z)
• Evaluating Machine Learning-based Skin Cancer Diagnosis [0.0]
  The research assesses two convolutional neural network architectures: a MobileNet-based model and a custom CNN model. Both models are evaluated for their ability to classify skin lesions into seven categories and to distinguish between dangerous and benign lesions. The study concludes that while the models show promise in explainability, further development is needed to ensure fairness across different skin tones.
  arXiv  Detail & Related papers  (2024-09-04T02:44:48Z)
• DDI-CoCo: A Dataset For Understanding The Effect Of Color Contrast In Machine-Assisted Skin Disease Detection [51.92255321684027]
  We study the interaction between skin tone and color difference effects and suggest that color difference can be an additional reason behind model performance bias between skin tones. Our work provides a complementary angle to dermatology AI for improving skin disease detection.
  arXiv  Detail & Related papers  (2024-01-24T07:45:24Z)
• A Web-based Mpox Skin Lesion Detection System Using State-of-the-art Deep Learning Models Considering Racial Diversity [1.846958522363092]
  'Mpox', formerly known as 'Monkeypox', has become a significant public health concern and has spread to over 110 countries globally. Computer-aided screening tools have been proven valuable in cases where Polymerase Chain Reaction (PCR) based diagnosis is not immediately available. Deep learning methods are powerful in learning complex data representations, but their efficacy largely depends on adequate training data.
  arXiv  Detail & Related papers  (2023-06-25T08:23:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.