Generation of Structurally Realistic Retinal Fundus Images with Diffusion Models

05/11/2023
by   Sojung Go, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 5

page 6

page 9

research
09/09/2022

Retinal Image Restoration and Vessel Segmentation using Modified Cycle-CBAM and CBAM-UNet

Clinical screening with low-quality fundus images is challenging and sig...
research
05/19/2021

Exploring The Limits Of Data Augmentation For Retinal Vessel Segmentation

Retinal Vessel Segmentation is important for diagnosis of various diseas...
research
08/16/2023

Denoising Diffusion Probabilistic Model for Retinal Image Generation and Segmentation

Experts use retinal images and vessel trees to detect and diagnose vario...
research
07/12/2022

Robust and efficient computation of retinal fractal dimension through deep approximation

A retinal trait, or phenotype, summarises a specific aspect of a retinal...
research
06/13/2023

Adding 3D Geometry Control to Diffusion Models

Diffusion models have emerged as a powerful method of generative modelin...
research
06/21/2023

Ambigram Generation by A Diffusion Model

Ambigrams are graphical letter designs that can be read not only from th...
research
07/31/2023

C-DARL: Contrastive diffusion adversarial representation learning for label-free blood vessel segmentation

Blood vessel segmentation in medical imaging is one of the essential ste...

Please sign up or login with your details

Forgot password? Click here to reset