Fairness-Aware Data Augmentation for Cardiac MRI using Text-Conditioned Diffusion Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915483462139904 |
|---|---|
| author | Skorupko, Grzegorz Osuala, Richard Szafranowska, Zuzanna Kushibar, Kaisar Dang, Vien Ngoc Aung, Nay Petersen, Steffen E Lekadir, Karim Gkontra, Polyxeni |
| author_facet | Skorupko, Grzegorz Osuala, Richard Szafranowska, Zuzanna Kushibar, Kaisar Dang, Vien Ngoc Aung, Nay Petersen, Steffen E Lekadir, Karim Gkontra, Polyxeni |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_19508 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Fairness-Aware Data Augmentation for Cardiac MRI using Text-Conditioned Diffusion Models Skorupko, Grzegorz Osuala, Richard Szafranowska, Zuzanna Kushibar, Kaisar Dang, Vien Ngoc Aung, Nay Petersen, Steffen E Lekadir, Karim Gkontra, Polyxeni Image and Video Processing Computer Vision and Pattern Recognition Machine Learning 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. |
| title | Fairness-Aware Data Augmentation for Cardiac MRI using Text-Conditioned Diffusion Models |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2403.19508 |