Ophthalmologists have used fundus images to screen and diagnose eye diseases. However, different equipments and ophthalmologists pose large variations to the quality of fundus images. Low-quality (LQ) degraded fundus images easily lead to uncertainty in clinical screening and generally increase the risk of misdiagnosis. Thus, real fundus image restoration is worth studying. Unfortunately, real clinical benchmark has not been explored for this task so far. In this paper, we investigate the real clinical fundus image restoration problem. Firstly, We establish a clinical dataset, Real Fundus (RF), including 120 low- and high-quality (HQ) image pairs. Then we propose a novel Transformer-based Generative Adversarial Network (RFormer) to restore the real degradation of clinical fundus images. The key component in our network is the Window-based Self-Attention Block (WSAB) which captures non-local self-similarity and long-range dependencies. To produce more visually pleasant results, a Transformer-based discriminator is introduced. Extensive experiments on our clinical benchmark show that the proposed RFormer significantly outperforms the state-of-the-art (SOTA) methods. In addition, experiments of downstream tasks such as vessel segmentation and optic disc/cup detection demonstrate that our proposed RFormer benefits clinical fundus image analysis and applications. The dataset, code, and models are publicly available at https://github.com/dengzhuo-AI/Real-Fundus
翻译:phphalmlogists使用基金图象来筛选和诊断眼科疾病,然而,不同的设备和眼科医生使用基金状图象来筛选和诊断眼科疾病,但是,不同的设备和眼科医生对基金状图象的质量有很大的差别。低质量(LQ)退化的基金状图象很容易导致临床筛选的不确定性,并普遍增加诊断错误的风险。因此,真正的基金状图象恢复值得研究。遗憾的是,迄今为止,还没有为这项任务探索真正的临床基准。在本文中,我们调查真正的临床基金图象恢复问题。首先,我们建立了一个临床数据集,Real Fundus(RF),包括120个低质量和高质量(HQ)的图像配对。然后,我们提出了一个新的基于变异基因的基金形图象网络(RQQQ),以恢复临床基金图象的真正退化。我们网络中的关键组成部分是基于窗口的自我保护区块(WSAAB),它捕捉到非本地的自我差异和远程依赖性图象。为了产生更视觉的好的结果,我们引入了以变基金为基础的分析器质分析。 在我们的临床基准基准上进行广泛的实验, 在研究中, 提议的模型的模型的模型中, 测试中, 展示了我们现有的的模型分析中, 展示了我们现有的的模型的模型的模型分析中, 展示了我们现有的的模型/图象分析。