# Fairness-Aware Data Augmentation for Cardiac MRI using Text-Conditioned Diffusion Models

arXiv: https://arxiv.org/abs/2403.19508 · HTML: https://mlsanity.com/paper/2403.19508/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 11 of its 26 references that are in the map.
- First posted on arXiv 28 Mar 2024.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 11 of 11)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Mitigating Unwanted Biases with Adversarial Learning](https://mlsanity.com/paper/1801.07593/) (2018)
- [Towards Fairness in Visual Recognition: Effective Strategies for Bias Mitigation](https://mlsanity.com/paper/1911.11834/) (2019)
- [Detect and Correct Bias in Multi-Site Neuroimaging Datasets](https://mlsanity.com/paper/2002.05049/) (2020)
- [Pseudo Bias-Balanced Learning for Debiased Chest X-ray Classification](https://mlsanity.com/paper/2203.09860/) (2022)
- [Towards Learning Contrast Kinetics with Multi-Condition Latent Diffusion Models](https://mlsanity.com/paper/2403.13890/) (2024)
- [You Don't Have to Be Perfect to Be Amazing: Unveil the Utility of Synthetic Images](https://mlsanity.com/paper/2305.18337/) (2023)
- [The (de)biasing effect of GAN-based augmentation methods on skin lesion images](https://mlsanity.com/paper/2206.15182/) (2022)

## Built on by (most cited first, 7 of 7)

- [SimuScope: Realistic Endoscopic Synthetic Dataset Generation through Surgical Simulation and Diffusion Models](https://mlsanity.com/paper/2412.02332/) (2024)
- [On Differentially Private 3D Medical Image Synthesis with Controllable Latent Diffusion Models](https://mlsanity.com/paper/2407.16405/) (2024)
- [Can Diffusion Models Bridge the Domain Gap in Cardiac MR Imaging?](https://mlsanity.com/paper/2508.06327/) (2025)
- [The MAMA-MIA Challenge: Advancing Generalizability and Fairness in Breast MRI Tumor Segmentation and Treatment Response Prediction](https://mlsanity.com/paper/2603.01250/) (2026)
- [Synthetic Cardiac MRI Image Generation using Deep Generative Models](https://mlsanity.com/paper/2603.24764/) (2026)
- [CardioDiT: Latent Diffusion Transformers for 4D Cardiac MRI Synthesis](https://mlsanity.com/paper/2603.25194/) (2026)
- [Metadata-Aware Adaptation of a Generative Foundation Model for Conditional CMR Synthesis](https://mlsanity.com/paper/2608.24342/) (2026)

## Abstract (arXiv)

While deep learning holds great promise for disease diagnosis and prognosis in cardiac magnetic resonance imaging, its progress is often constrained by highly imbalanced and biased training datasets. To address this issue, we propose a method to alleviate imbalances inherent in datasets through the generation of synthetic data based on sensitive attributes such as sex, age, body mass index (BMI), and health condition. We adopt ControlNet based on a denoising diffusion probabilistic model to condition on text assembled from patient metadata and cardiac geometry derived from segmentation masks. We assess our method using a large-cohort study from the UK Biobank by evaluating the realism of the generated images using established quantitative metrics. Furthermore, we conduct a downstream classification task aimed at debiasing a classifier by rectifying imbalances within underrepresented groups through synthetically generated samples. Our experiments demonstrate the effectiveness of the proposed approach in mitigating dataset imbalances, such as the scarcity of diagnosed female patients or individuals with normal BMI level suffering from heart failure. This work represents a major step towards the adoption of synthetic data for the development of fair and generalizable models for medical classification tasks. Notably, we conduct all our experiments using a single, consumer-level GPU to highlight the feasibility of our approach within resource-constrained environments. Our code is available at https://github.com/faildeny/debiasing-cardiac-mri.