Generation of Structurally Realistic Retinal Fundus Images with Diffusion Models
This addresses the problem of limited and privacy-sensitive medical imaging data for researchers and clinicians, though it is incremental as it applies existing diffusion models to a specific domain.
The paper tackles generating anatomically accurate retinal fundus images using diffusion models, resulting in high-quality images that improve data augmentation for vessel segmentation and artery/vein classification, with Turing tests showing experts struggle to distinguish them from real images.
We introduce a new technique for generating retinal fundus images that have anatomically accurate vascular structures, using diffusion models. We generate artery/vein masks to create the vascular structure, which we then condition to produce retinal fundus images. The proposed method can generate high-quality images with more realistic vascular structures and can create a diverse range of images based on the strengths of the diffusion model. We present quantitative evaluations that demonstrate the performance improvement using our method for data augmentation on vessel segmentation and artery/vein classification. We also present Turing test results by clinical experts, showing that our generated images are difficult to distinguish with real images. We believe that our method can be applied to construct stand-alone datasets that are irrelevant of patient privacy.