眼底图像动静脉宽度差变化率测量方法

发布时间：2018-06-04 17:41

本文选题：眼底图像 + 血管宽度　；参考：《仪器仪表学报》2016年04期

【摘要】：眼底图像中动静脉血管的宽度变化能够体现患者糖尿病的病程情况,人工确定血管宽度及其差值耗时费力且需要丰富经验。本文针对辽宁何氏眼科医院眼病筛查系统中受检者的眼底图像提出了动静脉宽度差变化率的概念,指出了其与糖尿病诊断之间的关系,并选取RGB、LAB、YCb Cr、Gaussian 4个颜色空间中不同的通道分量,定义了新的基于血管中心线像素和血管像素的特征向量,采用线性判别分析(LDA)分类器完成了对动静脉的全自动分类,继而实现了对动静脉血管宽度测量及相应差值变化率的计算。实验结果表明,与其他算法相比,本文方法在血管分割、动静脉分类、血管宽度及差值计算等方面都较准确,其诊断结果与临床诊断基本一致,具有一定的临床应用价值。
[Abstract]:The variation of the width of arteriovenous vessels in fundus images can reflect the course of diabetes in patients. The artificial determination of vascular width and its difference is time-consuming and requires a lot of experience. In this paper, the concept of the variation rate of arteriovenous width difference in the ophthalmopathy screening system of Liaoning Ho's ophthalmological hospital was put forward, and the relationship between it and the diagnosis of diabetes mellitus was pointed out. The different channel components in four color spaces of RGB / LABX YCb CrGaussian are selected, and a new feature vector based on the central pixel and the vascular pixel is defined. The automatic classification of the artery and vein is accomplished by using the linear discriminant analysis (LDA) classifier. Then the measurement of the vascular width of the arteriovenous vein and the calculation of the variation rate of the corresponding difference are realized. The experimental results show that compared with other algorithms, this method is more accurate in blood vessel segmentation, arteriovenous classification, vascular width and difference calculation, and its diagnostic results are basically consistent with clinical diagnosis, which has certain clinical application value.
【作者单位】：沈阳工业大学信息科学与工程学院;
【基金】：辽宁省教育厅优秀人才项目(LJQ2014011);辽宁省教育厅一般项目(L2014041) 沈阳市科技攻关项目(F12-010-2-00) 沈阳工业大学第三批青年学术骨干教师(3029906)项目资助
【分类号】：TP391.41

【参考文献】