Counterfactual MRI Data Augmentation using Conditional Denoising Diffusion Generative 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_ | 1866929570096087040 |
|---|---|
| author | Morão, Pedro Santinha, Joao Forghani, Yasna Loução, Nuno Gouveia, Pedro Figueiredo, Mario A. T. |
| author_facet | Morão, Pedro Santinha, Joao Forghani, Yasna Loução, Nuno Gouveia, Pedro Figueiredo, Mario A. T. |
| contents | Deep learning (DL) models in medical imaging face challenges in generalizability and robustness due to variations in image acquisition parameters (IAP). In this work, we introduce a novel method using conditional denoising diffusion generative models (cDDGMs) to generate counterfactual magnetic resonance (MR) images that simulate different IAP without altering patient anatomy. We demonstrate that using these counterfactual images for data augmentation can improve segmentation accuracy, particularly in out-of-distribution settings, enhancing the overall generalizability and robustness of DL models across diverse imaging conditions. Our approach shows promise in addressing domain and covariate shifts in medical imaging. The code is publicly available at https: //github.com/pedromorao/Counterfactual-MRI-Data-Augmentation |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_23835 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Counterfactual MRI Data Augmentation using Conditional Denoising Diffusion Generative Models Morão, Pedro Santinha, Joao Forghani, Yasna Loução, Nuno Gouveia, Pedro Figueiredo, Mario A. T. Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Deep learning (DL) models in medical imaging face challenges in generalizability and robustness due to variations in image acquisition parameters (IAP). In this work, we introduce a novel method using conditional denoising diffusion generative models (cDDGMs) to generate counterfactual magnetic resonance (MR) images that simulate different IAP without altering patient anatomy. We demonstrate that using these counterfactual images for data augmentation can improve segmentation accuracy, particularly in out-of-distribution settings, enhancing the overall generalizability and robustness of DL models across diverse imaging conditions. Our approach shows promise in addressing domain and covariate shifts in medical imaging. The code is publicly available at https: //github.com/pedromorao/Counterfactual-MRI-Data-Augmentation |
| title | Counterfactual MRI Data Augmentation using Conditional Denoising Diffusion Generative Models |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.23835 |