Self-supervised Denoising via Diffeomorphic Template Estimation: Application to Optical Coherence Tomography

TL;DR

This paper introduces a novel self-supervised denoising method for OCT images that accounts for motion-induced deformations using diffeomorphic template estimation, improving image quality without requiring clean ground truth data.

Contribution

It presents a joint framework combining diffeomorphic template estimation with self-supervised denoising to handle motion artifacts in OCT images, a challenge for existing methods.

Findings

Significant qualitative improvements in OCT image quality.

Quantitative reduction in noise levels and artifacts.

Applicable to other imaging modalities with multiple exposures.

Abstract

Optical Coherence Tomography (OCT) is pervasive in both the research and clinical practice of Ophthalmology. However, OCT images are strongly corrupted by noise, limiting their interpretation. Current OCT denoisers leverage assumptions on noise distributions or generate targets for training deep supervised denoisers via averaging of repeat acquisitions. However, recent self-supervised advances allow the training of deep denoising networks using only repeat acquisitions without clean targets as ground truth, reducing the burden of supervised learning. Despite the clear advantages of self-supervised methods, their use is precluded as OCT shows strong structural deformations even between sequential scans of the same subject due to involuntary eye motion. Further, direct nonlinear alignment of repeats induces correlation of the noise between images. In this paper, we propose a joint diffeomorphic template estimation and denoising framework which enables the use of self-supervised denoising for motion deformed repeat acquisitions, without empirically registering their noise realizations. Strong qualitative and quantitative improvements are achieved in denoising OCT images, with generic utility in any imaging modality amenable to multiple exposures.