Diabetes can induce diseases including diabetic retinopathy, cataracts, glaucoma, etc. The blindness caused by these diseases is irreversible. Early analysis of retinal fundus images, including optic disc and optic cup detection and retinal blood vessel segmentation, can effectively identify these diseases. The existing methods lack sufficient discrimination power for the fundus image and are easily affected by pathological regions. This paper proposes a novel multi-path recurrent U-Net architecture to achieve the segmentation of retinal fundus images. The effectiveness of the proposed network structure was proved by two segmentation tasks: optic disc and optic cup segmentation and retinal vessel segmentation. Our method achieved state-of-the-art results in the segmentation of the Drishti-GS1 dataset. Regarding optic disc segmentation, the accuracy and Dice values reached 0.9967 and 0.9817, respectively; as regards optic cup segmentation, the accuracy and Dice values reached 0.9950 and 0.8921, respectively. Our proposed method was also verified on the retinal blood vessel segmentation dataset DRIVE and achieved a good accuracy rate.

中文翻译：

---

视网膜眼底图像的多路径循环U-Net分割

糖尿病可诱发糖尿病性视网膜病，白内障，青光眼等疾病。这些疾病引起的失明是不可逆的。视网膜底图像的早期分析，包括视盘和视杯检测以及视网膜血管分割，可以有效地识别这些疾病。现有的方法对于眼底图像缺乏足够的辨别力，并且容易受到病理区域的影响。本文提出了一种新颖的多路径递归U-Net架构，以实现视网膜眼底图像的分割。通过两种分割任务证明了所提出的网络结构的有效性：视盘和视杯分割以及视网膜血管分割。我们的方法在Drishti-GS1数据集的分割中取得了最先进的结果。关于光盘分割，准确度和Dice值分别达到0.9967和0.9817；在光学杯分割方面，准确性和Dice值分别达到0.9950和0.8921。我们的方法在视网膜血管分割数据集DRIVE上也得到了验证，并达到了较高的准确率。