Fundus photography has been widely used for inspecting eye disorders by ophthalmologists or computer algorithms. Biomarkers related to retinal vessels plays an essential role to detect early diabetes. To quantify vascular biomarkers or the corresponding changes, an accurate artery and vein classification is necessary. In this work, we propose a new framework to boost local vessel classification with a global vascular network model using graph convolution. We compare our proposed method with two traditional state-of-the-art methods on a testing dataset of 750 images from the Maastricht Study. After incorporating global information, our model achieves the best accuracy of 86.45% compared to 85.5% from convolutional neural networks (CNN) and 82.9% from handcrafted pixel feature classification (HPFC). Our model also obtains the best area under receiver operating characteristic curve (AUC) of 0.95, compared to 0.93 from CNN and 0.90 from HPFC. The new classification framework has the advantage of easy deployment on top of local classification features. It corrects the local classification error by minimizing global classification error and it brings free additional classification performance.

中文翻译：

---

从局部到全局：视网膜动脉/静脉分类的图框架


眼底摄影已被眼科医生或计算机算法广泛用于检查眼部疾病。与视网膜血管相关的生物标志物在检测早期糖尿病中发挥着重要作用。为了量化血管生物标志物或相应的变化，准确的动脉和静脉分类是必要的。在这项工作中，我们提出了一个新的框架，通过使用图卷积的全局血管网络模型来促进局部血管分类。我们在马斯特里赫特研究的 750 张图像的测试数据集上将我们提出的方法与两种传统的最先进方法进行比较。合并全局信息后，我们的模型实现了 86.45% 的最佳准确率，而卷积神经网络 (CNN) 的准确率是 85.5%，手工像素特征分类 (HPFC) 的准确率是 82.9%。我们的模型还获得了 0.95 的最佳受试者工作特征曲线下面积 (AUC)，而 CNN 为 0.93，HPFC 为 0.90。新的分类框架在本地分类功能之上具有易于部署的优点。它通过最小化全局分类误差来纠正局部分类误差，并带来免费的额外分类性能。