Unsupervised Denoising of Retinal OCT with Diffusion Probabilistic Model

TL;DR

This paper introduces an unsupervised diffusion probabilistic model for denoising retinal OCT images, effectively reducing speckle noise without requiring clean reference images, thus improving image quality with minimal training data.

Contribution

The study presents a novel unsupervised diffusion model that learns from noise directly, enabling effective OCT image denoising without the need for clean training references.

Findings

Significant noise reduction in OCT images.

Effective with limited training data.

Simple pipeline for practical use.

Abstract

Optical coherence tomography (OCT) is a prevalent non-invasive imaging method which provides high resolution volumetric visualization of retina. However, its inherent defect, the speckle noise, can seriously deteriorate the tissue visibility in OCT. Deep learning based approaches have been widely used for image restoration, but most of these require a noise-free reference image for supervision. In this study, we present a diffusion probabilistic model that is fully unsupervised to learn from noise instead of signal. A diffusion process is defined by adding a sequence of Gaussian noise to self-fused OCT b-scans. Then the reverse process of diffusion, modeled by a Markov chain, provides an adjustable level of denoising. Our experiment results demonstrate that our method can significantly improve the image quality with a simple working pipeline and a small amount of training data.