# Demographically-Conditioned Synthetic Medical Images for Bias Mitigation and Bias Detection in Disease Classifiers

arXiv: https://arxiv.org/abs/2607.14984 · HTML: https://mlsanity.com/paper/2607.14984/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 16 Jul 2026.

## Builds on (most cited first, 16 of 16)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs](https://mlsanity.com/paper/1706.02633/) (2017)
- [CheXclusion: Fairness gaps in deep chest X-ray classifiers](https://mlsanity.com/paper/2003.00827/) (2020)
- [RoentGen: Vision-Language Foundation Model for Chest X-ray Generation](https://mlsanity.com/paper/2211.12737/) (2022)
- [Generating High Fidelity Data from Low-density Regions using Diffusion Models](https://mlsanity.com/paper/2203.17260/) (2022)
- [Class-Balancing Diffusion Models](https://mlsanity.com/paper/2305.00562/) (2023)
- [Generation of Anonymous Chest Radiographs Using Latent Diffusion Models for Training Thoracic Abnormality Classification Systems](https://mlsanity.com/paper/2211.01323/) (2022)
- [Don't Play Favorites: Minority Guidance for Diffusion Models](https://mlsanity.com/paper/2301.12334/) (2023)
- [Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data](https://mlsanity.com/paper/2310.16524/) (2023)
- [COVID-19 CT Image Synthesis with a Conditional Generative Adversarial Network](https://mlsanity.com/paper/2007.14638/) (2020)
- [COVID-Net CT-2: Enhanced Deep Neural Networks for Detection of COVID-19 from Chest CT Images Through Bigger, More Diverse Learning](https://mlsanity.com/paper/2101.07433/) (2021)
- [Evaluate underdiagnosis and overdiagnosis bias of deep learning model on primary open-angle glaucoma diagnosis in under-served patient populations](https://mlsanity.com/paper/2301.11315/) (2023)
- [The Limits of Fair Medical Imaging AI In The Wild](https://mlsanity.com/paper/2312.10083/) (2023)

## Abstract (arXiv)

Per-subgroup fairness audits of medical image classifiers face a sample-size problem: minority subgroups in held-out test sets have so few samples that the resulting confidence intervals on per-subgroup performance are wider than the bias the audit is meant to detect. We argue that a demographically-conditioned synthetic generator can do both: mitigate bias on the training side and detect bias on the evaluation side. Working on COVID-19 chest CT classification with an end-to-end fine-tuned Stable Diffusion 2.1 generator, we make two findings. For bias mitigation (training), a demographically-balanced synthetic cohort is most useful as a pretraining prior, not as joint augmentation: with the same fixed data, sequential pretraining followed by fine-tuning substantially outperforms joint augmentation, and the resulting classifier surpasses the full-real baseline at ~100× real-data efficiency. For bias detection (evaluation), across five synthetic minority cohorts and five classifier seeds, the synthetic estimator reproduces the subgroup ranking of a well-powered real oracle (Spearman ρ = 1.00 on MCC and Recall) and gives the more reliable per-cell estimate where the small real test set runs out of samples. The synthetic cohort is therefore most useful in exactly the cells that fairness audits care about, as both a fix for and a measure of subgroup bias.