# Debiasing Skin Lesion Datasets and Models? Not So Fast

arXiv: https://arxiv.org/abs/2004.11457 · HTML: https://mlsanity.com/paper/2004.11457/

## Key facts

- Cited by 43 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Apr 2020.

## Built on by (most cited first, 30 of 43)

- [Evaluating Deep Neural Networks Trained on Clinical Images in Dermatology with the Fitzpatrick 17k Dataset](https://mlsanity.com/paper/2104.09957/) (2021)
- [Salient ImageNet: How to discover spurious features in Deep Learning?](https://mlsanity.com/paper/2110.04301/) (2021)
- [Leveraging Sparse Linear Layers for Debuggable Deep Networks](https://mlsanity.com/paper/2105.04857/) (2021)
- [Fair Conformal Predictors for Applications in Medical Imaging](https://mlsanity.com/paper/2109.04392/) (2021)
- [Discover and Cure: Concept-aware Mitigation of Spurious Correlation](https://mlsanity.com/paper/2305.00650/) (2023)
- [Editing a classifier by rewriting its prediction rules](https://mlsanity.com/paper/2112.01008/) (2021)
- [A Multimodal Automated Interpretability Agent](https://mlsanity.com/paper/2404.14394/) (2024)
- [Spurious Features Everywhere -- Large-Scale Detection of Harmful Spurious Features in ImageNet](https://mlsanity.com/paper/2212.04871/) (2022)
- [Addressing Fairness Issues in Deep Learning-Based Medical Image Analysis: A Systematic Review](https://mlsanity.com/paper/2209.13177/) (2022)
- [GAN-Based Data Augmentation and Anonymization for Skin-Lesion Analysis: A Critical Review](https://mlsanity.com/paper/2104.10603/) (2021)
- [Ethics Sheet for Automatic Emotion Recognition and Sentiment Analysis](https://mlsanity.com/paper/2109.08256/) (2021)
- [Ethics Sheets for AI Tasks](https://mlsanity.com/paper/2107.01183/) (2021)
- [Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification](https://mlsanity.com/paper/2109.09818/) (2021)
- [Core Risk Minimization using Salient ImageNet](https://mlsanity.com/paper/2203.15566/) (2022)
- [Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency](https://mlsanity.com/paper/2403.10717/) (2024)
- [Epistemic Uncertainty-Weighted Loss for Visual Bias Mitigation](https://mlsanity.com/paper/2204.09389/) (2022)
- [Artifact-Based Domain Generalization of Skin Lesion Models](https://mlsanity.com/paper/2208.09756/) (2022)
- [Interpreting and Controlling Vision Foundation Models via Text Explanations](https://mlsanity.com/paper/2310.10591/) (2023)
- [An Evaluation of Self-Supervised Pre-Training for Skin-Lesion Analysis](https://mlsanity.com/paper/2106.09229/) (2021)
- [Controllable Prompt Tuning For Balancing Group Distributional Robustness](https://mlsanity.com/paper/2403.02695/) (2024)
- [EPVT: Environment-aware Prompt Vision Transformer for Domain Generalization in Skin Lesion Recognition](https://mlsanity.com/paper/2304.01508/) (2023)
- [Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks](https://mlsanity.com/paper/2304.05727/) (2023)
- [Even Small Correlation and Diversity Shifts Pose Dataset-Bias Issues](https://mlsanity.com/paper/2305.05807/) (2023)
- [In the Picture: Medical Imaging Datasets, Artifacts, and their Living Review](https://mlsanity.com/paper/2501.10727/) (2025)
- [Copycats: the many lives of a publicly available medical imaging dataset](https://mlsanity.com/paper/2402.06353/) (2024)
- [BMFT: Achieving Fairness via Bias-based Weight Masking Fine-tuning](https://mlsanity.com/paper/2408.06890/) (2024)
- [PatchAlign:Fair and Accurate Skin Disease Image Classification by Alignment with Clinical Labels](https://mlsanity.com/paper/2409.04975/) (2024)
- [Data AUDIT: Identifying Attribute Utility- and Detectability-Induced Bias in Task Models](https://mlsanity.com/paper/2304.03218/) (2023)
- [Subgroup Performance Analysis in Hidden Stratifications](https://mlsanity.com/paper/2503.10382/) (2025)
- [Content Preserving Image Translation with Texture Co-occurrence and Spatial Self-Similarity for Texture Debiasing and Domain Adaptation](https://mlsanity.com/paper/2110.07920/) (2021)

## Abstract (arXiv)

Data-driven models are now deployed in a plethora of real-world applications - including automated diagnosis - but models learned from data risk learning biases from that same data. When models learn spurious correlations not found in real-world situations, their deployment for critical tasks, such as medical decisions, can be catastrophic. In this work we address this issue for skin-lesion classification models, with two objectives: finding out what are the spurious correlations exploited by biased networks, and debiasing the models by removing such spurious correlations from them. We perform a systematic integrated analysis of 7 visual artifacts (which are possible sources of biases exploitable by networks), employ a state-of-the-art technique to prevent the models from learning spurious correlations, and propose datasets to test models for the presence of bias. We find out that, despite interesting results that point to promising future research, current debiasing methods are not ready to solve the bias issue for skin-lesion models.