CUNSB-RFIE：视网膜眼底图像增强中的上下文感知非配对神经薛定谔桥
CUNSB-RFIE: Context-aware Unpaired Neural Schrödinger Bridge in Retinal Fundus Image Enhancement
AI总结：
针对现有视网膜图像增强方法稳定性与多样性难兼顾、易丢失血管等精细结构的问题，提出基于SB框架结合动态蛇形卷积的CUNSB-RFIE增强方法，在图像质量和下游任务上优于现有方法。
摘要：
视网膜眼底摄影在视网膜疾病的诊断和监测中具有重要意义。然而，系统层面的缺陷以及操作者/患者相关因素会阻碍高质量视网膜图像的获取。以往的视网膜图像增强研究主要依赖GANs（生成对抗网络），这类方法受限于训练稳定性与输出多样性之间的权衡。相比之下，薛定谔桥（Schrödinger Bridge, SB）利用最优传输（Optimal Transport, OT）理论对两个任意分布之间的随机微分方程（stochastic differential equation, SDE）进行建模，提供了更稳定的解决方案，使SB能够有效地将低质量视网膜图像转换为高质量对应图像。在本研究中，我们利用SB框架提出了一种用于视网膜图像增强的图像到图像转换流水线。此外，以往方法往往难以捕捉血管等精细结构细节，为解决这一问题，我们引入动态蛇形卷积（Dynamic Snake Convolution）对流水线进行增强，其曲折的感受野能够更好地保留管状结构。我们将由此得到的视网膜眼底图像增强框架命名为上下文感知非配对神经薛定谔桥（Context-aware Unpaired Neural Schrödinger Bridge, CUNSB-RFIE）。据我们所知，这是首次将SB方法应用于视网膜图像增强的研究。在大规模数据集上的实验结果表明，与多种当前最优的有监督和无监督方法相比，该方法在图像质量和下游任务性能方面均具有优势。代码可在https://github.com/Retinal-Research/CUNSB-RFIE 获取。
英文摘要：
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 Schrödinger 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 Schrödinger 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 .
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
