CUNSB-RFIE: Context-aware Unpaired Neural Schr\"odinger Bridge in Retinal Fundus Image Enhancement

TL;DR

This paper introduces CUNSB-RFIE, a novel retinal image enhancement method using the Schr"odinger Bridge framework combined with Dynamic Snake Convolution to better preserve fine structures, outperforming existing techniques.

Contribution

It is the first to apply the Schr"odinger Bridge approach to retinal image enhancement and incorporates Dynamic Snake Convolution for improved structural detail preservation.

Findings

Outperforms state-of-the-art methods in image quality.

Enhances downstream retinal disease diagnosis tasks.

Effectively preserves blood vessel structures.

Abstract

Retinal fundus photography is significant in diagnosing and monitoring retinal diseases. However, systemic imperfections and operator/patient-related factors can hinder the acquisition of high-quality retinal images. Previous efforts in retinal image enhancement primarily relied on GANs, which are limited by the trade-off between training stability and output diversity. In contrast, the Schr\"odinger Bridge (SB), offers a more stable solution by utilizing Optimal Transport (OT) theory to model a stochastic differential equation (SDE) between two arbitrary distributions. This allows SB to effectively transform low-quality retinal images into their high-quality counterparts. In this work, we leverage the SB framework to propose an image-to-image translation pipeline for retinal image enhancement. Additionally, previous methods often fail to capture fine structural details, such as blood vessels. To address this, we enhance our pipeline by introducing Dynamic Snake Convolution, whose tortuous receptive field can better preserve tubular structures. We name the resulting retinal fundus image enhancement framework the Context-aware Unpaired Neural Schr\"{o}dinger Bridge (CUNSB-RFIE). To the best of our knowledge, this is the first endeavor to use the SB approach for retinal image enhancement. Experimental results on a large-scale dataset demonstrate the advantage of the proposed method compared to several state-of-the-art supervised and unsupervised methods in terms of image quality and performance on downstream tasks.The code is available at https://github.com/Retinal-Research/CUNSB-RFIE .