# Disparities in Dermatology AI: Assessments Using Diverse Clinical Images

arXiv: https://arxiv.org/abs/2111.08006 · HTML: https://mlsanity.com/paper/2111.08006/

## Key facts

- Cited by 134 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 59 references that are in the map.
- First posted on arXiv 15 Nov 2021.

## Builds on (most cited first, 10 of 10)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization](https://mlsanity.com/paper/1911.08731/) (2019)
- [Deep CORAL: Correlation Alignment for Deep Domain Adaptation](https://mlsanity.com/paper/1607.01719/) (2016)
- [Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)](https://mlsanity.com/paper/1902.03368/) (2019)
- [How Does Mixup Help With Robustness and Generalization?](https://mlsanity.com/paper/2010.04819/) (2020)
- [Evaluating Deep Neural Networks Trained on Clinical Images in Dermatology with the Fitzpatrick 17k Dataset](https://mlsanity.com/paper/2104.09957/) (2021)
- [A deep learning system for differential diagnosis of skin diseases](https://mlsanity.com/paper/1909.05382/) (2019)
- [TrueImage: A Machine Learning Algorithm to Improve the Quality of Telehealth Photos](https://mlsanity.com/paper/2010.02086/) (2020)

## Built on by (most cited first, 30 of 134)

- [A Closer Look at the Intervention Procedure of Concept Bottleneck Models](https://mlsanity.com/paper/2302.14260/) (2023)
- [SkinCon: A skin disease dataset densely annotated by domain experts for fine-grained model debugging and analysis](https://mlsanity.com/paper/2302.00785/) (2023)
- [The Clever Hans Mirage: A Comprehensive Survey on Spurious Correlations in Machine Learning](https://mlsanity.com/paper/2402.12715/) (2024)
- [Towards Transparency in Dermatology Image Datasets with Skin Tone Annotations by Experts, Crowds, and an Algorithm](https://mlsanity.com/paper/2207.02942/) (2022)
- [Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision](https://mlsanity.com/paper/2303.00885/) (2023)
- [Improving dermatology classifiers across populations using images generated by large diffusion models](https://mlsanity.com/paper/2211.13352/) (2022)
- [Beyond Confidence: Reliable Models Should Also Consider Atypicality](https://mlsanity.com/paper/2305.18262/) (2023)
- [A Survey on Deep Learning for Skin Lesion Segmentation](https://mlsanity.com/paper/2206.00356/) (2022)
- [WBCAtt: A White Blood Cell Dataset Annotated with Detailed Morphological Attributes](https://mlsanity.com/paper/2306.13531/) (2023)
- [Augmenting medical image classifiers with synthetic data from latent diffusion models](https://mlsanity.com/paper/2308.12453/) (2023)
- [Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlooks](https://mlsanity.com/paper/2410.02331/) (2024)
- [CIRCLe: Color Invariant Representation Learning for Unbiased Classification of Skin Lesions](https://mlsanity.com/paper/2208.13528/) (2022)
- [Beyond Skin Tone: A Multidimensional Measure of Apparent Skin Color](https://mlsanity.com/paper/2309.05148/) (2023)
- [Integrating Clinical Knowledge into Concept Bottleneck Models](https://mlsanity.com/paper/2407.06600/) (2024)
- [The Data Addition Dilemma](https://mlsanity.com/paper/2408.04154/) (2024)
- [Slicing Through Bias: Explaining Performance Gaps in Medical Image Analysis using Slice Discovery Methods](https://mlsanity.com/paper/2406.12142/) (2024)
- [MM-Skin: Enhancing Dermatology Vision-Language Model with an Image-Text Dataset Derived from Textbooks](https://mlsanity.com/paper/2505.06152/) (2025)
- [Are Sex-based Physiological Differences the Cause of Gender Bias for Chest X-ray Diagnosis?](https://mlsanity.com/paper/2308.05129/) (2023)
- [Skin Deep: Investigating Subjectivity in Skin Tone Annotations for Computer Vision Benchmark Datasets](https://mlsanity.com/paper/2305.09072/) (2023)
- [What's documented in AI? Systematic Analysis of 32K AI Model Cards](https://mlsanity.com/paper/2402.05160/) (2024)
- [Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat](https://mlsanity.com/paper/2307.05350/) (2023)
- [Ecosystem-level Analysis of Deployed Machine Learning Reveals Homogeneous Outcomes](https://mlsanity.com/paper/2307.05862/) (2023)
- [DERM12345: A Large, Multisource Dermatoscopic Skin Lesion Dataset with 38 Subclasses](https://mlsanity.com/paper/2406.07426/) (2024)
- [Benchmark Data Repositories for Better Benchmarking](https://mlsanity.com/paper/2410.24100/) (2024)
- [Achieving Reliable and Fair Skin Lesion Diagnosis via Unsupervised Domain Adaptation](https://mlsanity.com/paper/2307.03157/) (2023)
- [From Majority to Minority: A Diffusion-based Augmentation for Underrepresented Groups in Skin Lesion Analysis](https://mlsanity.com/paper/2406.18375/) (2024)
- [Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedback](https://mlsanity.com/paper/2506.12323/) (2025)
- [Intrinsic Self-Supervision for Data Quality Audits](https://mlsanity.com/paper/2305.17048/) (2023)
- [Are generative models fair? A study of racial bias in dermatological image generation](https://mlsanity.com/paper/2501.11752/) (2025)
- [China and the U.S. produce more impactful AI research when collaborating together](https://mlsanity.com/paper/2304.11123/) (2023)

## Abstract (arXiv)

More than 3 billion people lack access to care for skin disease. AI diagnostic tools may aid in early skin cancer detection; however most models have not been assessed on images of diverse skin tones or uncommon diseases. To address this, we curated the Diverse Dermatology Images (DDI) dataset - the first publicly available, pathologically confirmed images featuring diverse skin tones. We show that state-of-the-art dermatology AI models perform substantially worse on DDI, with ROC-AUC dropping 29-40 percent compared to the models' original results. We find that dark skin tones and uncommon diseases, which are well represented in the DDI dataset, lead to performance drop-offs. Additionally, we show that state-of-the-art robust training methods cannot correct for these biases without diverse training data. Our findings identify important weaknesses and biases in dermatology AI that need to be addressed to ensure reliable application to diverse patients and across all disease.