Cycle Diffusion Model for Counterfactual Image Generation
This work addresses the problem of reliable direct and counterfactual generation for medical imaging applications, such as data augmentation and disease modeling, but it is incremental as it refines existing diffusion models with cycle constraints.
The authors tackled the challenge of ensuring conditioning faithfulness and high-quality synthetic images in medical image generation by introducing a cycle training framework to fine-tune diffusion models. Their method improved conditioning accuracy and enhanced image quality, as shown by FID and SSIM metrics on a combined 3D brain MRI dataset.
Deep generative models have demonstrated remarkable success in medical image synthesis. However, ensuring conditioning faithfulness and high-quality synthetic images for direct or counterfactual generation remains a challenge. In this work, we introduce a cycle training framework to fine-tune diffusion models for improved conditioning adherence and enhanced synthetic image realism. Our approach, Cycle Diffusion Model (CDM), enforces consistency between generated and original images by incorporating cycle constraints, enabling more reliable direct and counterfactual generation. Experiments on a combined 3D brain MRI dataset (from ABCD, HCP aging & young adults, ADNI, and PPMI) show that our method improves conditioning accuracy and enhances image quality as measured by FID and SSIM. The results suggest that the cycle strategy used in CDM can be an effective method for refining diffusion-based medical image generation, with applications in data augmentation, counterfactual, and disease progression modeling.