Retinal Vascular Network Topology Reconstruction and Artery/Vein Classification via Dominant Set Clustering
Retinal Vascular Network Topology Reconstruction and Artery/Vein Classification via Dominant Set Clustering
复制标题
通过优势集聚类进行视网膜血管网络拓扑重建和动脉/静脉分类
DOI：
10.1109/tmi.2019.2926492
复制
发表时间：
2020-02-01
影响因子：
10.6
通讯作者：
Liu, Jiang
中科院分区：
文献类型：
--
作者：
Zhao, Yitian;Liu, Yonghuai;Liu, Jiang
复杂网络中血管网络拓扑的估计对于理解血管变化与多种疾病之间的关系非常重要。将视网膜血管树自动分类为动脉和静脉，可以直接帮助眼科医生诊断和治疗眼部疾病。然而，由于它们的投影模糊性以及成像过程中外观、对比度和几何形状的微妙变化，它具有挑战性。在本文中，我们提出了一种能够根据血管网络拓扑特性区分视网膜彩色眼底图像中的动脉/静脉（A/V）的新方法。为此，我们采用视网膜血管拓扑估计和 A/V 分类的概念并将其形式化为成对聚类问题。该图是通过图像分割、骨架化和重要节点识别来构建的。边缘权重定义为强度、方向、曲率、直径和熵特征空间中其两个端点之间的逆欧氏距离。重建的血管网络根据其强度和形态分为动脉和静脉。该方法已应用于INSPIRE、IOSTAR、VICAVR、DRIVE和WIDE这五个公共数据库，分别获得了95.1%、94.2%、93.8%、91.1%和91.0%的高精度。此外，我们还对 INSPIRE、IOSTAR、VICAVR 和 DRIVE 数据集的血管拓扑进行了手动注释，并将这些注释发布给公众访问，以方便社区研究人员。
The estimation of vascular network topology in complex networks is important in understanding the relationship between vascular changes and a wide spectrum of diseases. Automatic classification of the retinal vascular trees into arteries and veins is of direct assistance to the ophthalmologist in terms of diagnosis and treatment of eye disease. However, it is challenging due to their projective ambiguity and subtle changes in appearance, contrast, and geometry in the imaging process. In this paper, we propose a novel method that is capable of making the artery/vein (A/V) distinction in retinal color fundus images based on vascular network topological properties. To this end, we adapt the concept of and formalize the retinal blood vessel topology estimation and the A/V classification as a pairwise clustering problem. The graph is constructed through image segmentation, skeletonization, and identification of significant nodes. The edge weight is defined as the inverse Euclidean distance between its two end points in the feature space of intensity, orientation, curvature, diameter, and entropy. The reconstructed vascular network is classified into arteries and veins based on their intensity and morphology. The proposed approach has been applied to five public databases, namely INSPIRE, IOSTAR, VICAVR, DRIVE, and WIDE, and achieved high accuracies of 95.1%, 94.2%, 93.8%, 91.1%, and 91.0%, respectively. Furthermore, we have made manual annotations of the blood vessel topologies for INSPIRE, IOSTAR, VICAVR, and DRIVE datasets, and these annotations are released for public access so as to facilitate researchers in the community.