Counterfactual MRI Data Augmentation using Conditional Denoising Diffusion Generative Models

TL;DR

This paper introduces a novel data augmentation method using conditional denoising diffusion models to generate counterfactual MRI images, improving deep learning model robustness across diverse imaging conditions.

Contribution

The work presents a new approach for generating counterfactual MRI images with cDDGMs to enhance model generalization without altering patient anatomy.

Findings

Improved segmentation accuracy in out-of-distribution scenarios

Enhanced robustness of models across different imaging parameters

Code implementation is publicly available

Abstract

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