Tian Zhiqiang, Zheng Yaoyue, Li Xiaojian, Du Shaoyi, Xu Xiayu
School of Software Engineering, Xi'an Jiaotong University, Xi'an 710049, China.
Institute of Artificial Intelligence and Robotics, Xi'an Jiaotong University, Xi'an 710049, China.
Biomed Opt Express. 2020 May 13;11(6):3043-3057. doi: 10.1364/BOE.390056. eCollection 2020 Jun 1.
Calculating the cup-to-disc ratio is one of the methods for glaucoma screening with other clinical features. In this paper, we propose a graph convolutional network (GCN) based method to implement the optic disc (OD) and optic cup (OC) segmentation task. We first present a multi-scale convolutional neural network (CNN) as the feature map extractor to generate feature map. The GCN takes the feature map concatenated with the graph nodes as the input for segmentation task. The experimental results on the REFUGE dataset show that the Jaccard index (Jacc) of the proposed method on OD and OC are 95.64% and 91.60%, respectively, while the Dice similarity coefficients (DSC) are 97.76% and 95.58%, respectively. The proposed method outperforms the state-of-the-art methods on the REFUGE leaderboard. We also evaluate the proposed method on the Drishthi-GS1 dataset. The results show that the proposed method outperforms the state-of-the-art methods.
计算杯盘比是青光眼筛查的方法之一，还需结合其他临床特征。在本文中，我们提出了一种基于图卷积网络（GCN）的方法来实现视盘（OD）和视杯（OC）分割任务。我们首先提出一个多尺度卷积神经网络（CNN）作为特征图提取器来生成特征图。GCN将与图节点连接的特征图作为分割任务的输入。在REFUGE数据集上的实验结果表明，所提方法在OD和OC上的杰卡德指数（Jacc）分别为95.64%和91.60%，而骰子相似系数（DSC）分别为97.76%和95.58%。所提方法在REFUGE排行榜上优于现有方法。我们还在Drishthi - GS1数据集上评估了所提方法。结果表明，所提方法优于现有方法。
