FairDiffusion: Enhancing equity in latent diffusion models via fair Bayesian perturbation
Open Access
- 4 April 2025
- journal article
- Published by American Association for the Advancement of Science (AAAS) in Science Advances
- Vol. 11 (14) , eads4593
Abstract
Recent advancements in generative AI, particularly diffusion models, have proven valuable for text-to-image synthesis. In health care, these models offer immense potential in generating synthetic datasets and aiding medical training. Despite these strong performances, it remains uncertain whether the image generation quality is consistent across different demographic subgroups. To address this, we conduct a comprehensive analysis of fairness in medical text-to-image diffusion models. Evaluations of the Stable Diffusion model reveal substantial disparities across gender, race, and ethnicity. To reduce these biases, we propose FairDiffusion, an equity-aware latent diffusion model that improves both image quality and the semantic alignment of clinical features. In addition, we design and curate FairGenMed, a dataset tailored for fairness studies in medical generative models. FairDiffusion is further assessed on HAM10000 (dermatoscopic images) and CheXpert (chest x-rays), demonstrating its effectiveness in diverse medical imaging modalities. Together, FairDiffusion and FairGenMed advance research in fair generative learning, promoting equitable benefits of generative AI in health care.Keywords
This publication has 48 references indexed in Scilit:
- FairDomain: Achieving Fairness in Cross-Domain Medical Image Segmentation and Classification2024
- Discriminative kernel convolution network for multi-label ophthalmic disease detection on imbalanced fundus image datasetComputers in Biology and Medicine, 2023
- Brain Imaging Generation with Latent Diffusion Models2022
- Measurement-Conditioned Denoising Diffusion Probabilistic Model for Under-Sampled Medical Image Reconstruction2022
- Score-based diffusion models for accelerated MRIMedical Image Analysis, 2022
- Data augmentation using Generative Adversarial Networks (GANs) for GAN-based detection of Pneumonia and COVID-19 in chest X-ray imagesInformatics in Medicine Unlocked, 2021
- PadChest: A large chest x-ray image dataset with multi-label annotated reportsMedical Image Analysis, 2020
- Data Augmentation with GAN: Improving Chest X-Ray Pathologies Prediction on Class-Imbalanced Cases2019
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- On Bayesian Methods for Seeking the Extremum1975