Denoising Diffusion Probabilistic Model for Retinal Image Generation and Segmentation

TL;DR

This paper introduces a novel Denoising Diffusion Probabilistic Model (DDPM) for retinal image synthesis and segmentation, outperforming GANs, and presents a new dataset called ReTree for training and evaluating retinal vessel segmentation models.

Contribution

The paper proposes a new DDPM-based approach for retinal image and vessel tree generation, along with a comprehensive dataset and segmentation network, advancing retinal image analysis methods.

Findings

DDPM outperforms GANs in retinal image synthesis.

The ReTree dataset enables effective training of segmentation models.

Synthetic data trained models perform well on real retinal images.

Abstract

Experts use retinal images and vessel trees to detect and diagnose various eye, blood circulation, and brain-related diseases. However, manual segmentation of retinal images is a time-consuming process that requires high expertise and is difficult due to privacy issues. Many methods have been proposed to segment images, but the need for large retinal image datasets limits the performance of these methods. Several methods synthesize deep learning models based on Generative Adversarial Networks (GAN) to generate limited sample varieties. This paper proposes a novel Denoising Diffusion Probabilistic Model (DDPM) that outperformed GANs in image synthesis. We developed a Retinal Trees (ReTree) dataset consisting of retinal images, corresponding vessel trees, and a segmentation network based on DDPM trained with images from the ReTree dataset. In the first stage, we develop a two-stage DDPM that generates vessel trees from random numbers belonging to a standard normal distribution. Later, the model is guided to generate fundus images from given vessel trees and random distribution. The proposed dataset has been evaluated quantitatively and qualitatively. Quantitative evaluation metrics include Frechet Inception Distance (FID) score, Jaccard similarity coefficient, Cohen's kappa, Matthew's Correlation Coefficient (MCC), precision, recall, F1-score, and accuracy. We trained the vessel segmentation model with synthetic data to validate our dataset's efficiency and tested it on authentic data. Our developed dataset and source code is available at https://github.com/AAleka/retree.