# The (de)biasing effect of GAN-based augmentation methods on skin lesion images

arXiv: https://arxiv.org/abs/2206.15182 · HTML: https://mlsanity.com/paper/2206.15182/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 26 references that are in the map.
- First posted on arXiv 30 Jun 2022.

## Builds on (most cited first, 13 of 13)

- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [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)
- [BCN20000: Dermoscopic Lesions in the Wild](https://mlsanity.com/paper/1908.02288/) (2019)
- [Reducing Gender Bias in Abusive Language Detection](https://mlsanity.com/paper/1808.07231/) (2018)
- [A Patient-Centric Dataset of Images and Metadata for Identifying Melanomas Using Clinical Context](https://mlsanity.com/paper/2008.07360/) (2020)
- [(De)Constructing Bias on Skin Lesion Datasets](https://mlsanity.com/paper/1904.08818/) (2019)
- [GAN-Based Data Augmentation and Anonymization for Skin-Lesion Analysis: A Critical Review](https://mlsanity.com/paper/2104.10603/) (2021)
- [Detecting Melanoma Fairly: Skin Tone Detection and Debiasing for Skin Lesion Classification](https://mlsanity.com/paper/2202.02832/) (2022)
- [Skin Deep Unlearning: Artefact and Instrument Debiasing in the Context of Melanoma Classification](https://mlsanity.com/paper/2109.09818/) (2021)
- [Bias Amplification in Artificial Intelligence Systems](https://mlsanity.com/paper/1809.07842/) (2018)

## Built on by (most cited first, 9 of 9)

- [Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision](https://mlsanity.com/paper/2303.00885/) (2023)
- [Generative AI for Synthetic Data Across Multiple Medical Modalities: A Systematic Review of Recent Developments and Challenges](https://mlsanity.com/paper/2407.00116/) (2024)
- [Artifact-Based Domain Generalization of Skin Lesion Models](https://mlsanity.com/paper/2208.09756/) (2022)
- [Fairness-Aware Data Augmentation for Cardiac MRI using Text-Conditioned Diffusion Models](https://mlsanity.com/paper/2403.19508/) (2024)
- [Birds look like cars: Adversarial analysis of intrinsically interpretable deep learning](https://mlsanity.com/paper/2503.08636/) (2025)
- [A survey on bias in machine learning research](https://mlsanity.com/paper/2308.11254/) (2023)
- [Targeted Data Augmentation for bias mitigation](https://mlsanity.com/paper/2308.11386/) (2023)
- [Prompting Medical Vision-Language Models to Mitigate Diagnosis Bias by Generating Realistic Dermoscopic Images](https://mlsanity.com/paper/2504.01838/) (2025)
- [Class-N-Diff: Classification-Induced Diffusion Model Can Make Fair Skin Cancer Diagnosis](https://mlsanity.com/paper/2510.16887/) (2025)

## Abstract (arXiv)

New medical datasets are now more open to the public, allowing for better and more extensive research. Although prepared with the utmost care, new datasets might still be a source of spurious correlations that affect the learning process. Moreover, data collections are usually not large enough and are often unbalanced. One approach to alleviate the data imbalance is using data augmentation with Generative Adversarial Networks (GANs) to extend the dataset with high-quality images. GANs are usually trained on the same biased datasets as the target data, resulting in more biased instances. This work explored unconditional and conditional GANs to compare their bias inheritance and how the synthetic data influenced the models. We provided extensive manual data annotation of possibly biasing artifacts on the well-known ISIC dataset with skin lesions. In addition, we examined classification models trained on both real and synthetic data with counterfactual bias explanations. Our experiments showed that GANs inherited biases and sometimes even amplified them, leading to even stronger spurious correlations. Manual data annotation and synthetic images are publicly available for reproducible scientific research.