{"title":"Retinal blood vessel tortuosity measurement for analysis of hypertensive retinopathy","authors":"S. Nirmala, Sanyukta Chetia","doi":"10.1109/IESPC.2017.8071862","DOIUrl":null,"url":null,"abstract":"The retinal blood vessels act as landmark for detecting some retinal diseases. The changes in the vessel characteristics such as tortuosity may be used to estimate the effect of hypertension. In this paper, a simple distance metric (DM) method is used to evaluate the tortuosity of blood vessels. Initially, the method is applied on synthetically generated blood vessels of normal, moderate and severely tortuous nature. Then retinal vessels are segmented using image processing methods. Small vessel segments are selected manually and used for tortuosity evaluation. These images are collected from local eye hospital, DRIVE database and VICAVR database. The results obtained show that the method is capable enough to estimate the tortuosity and have close correlation with subjective evaluation of tortuosity.","PeriodicalId":383252,"journal":{"name":"2017 International Conference on Innovations in Electronics, Signal Processing and Communication (IESC)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 International Conference on Innovations in Electronics, Signal Processing and Communication (IESC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IESPC.2017.8071862","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 8
Abstract
The retinal blood vessels act as landmark for detecting some retinal diseases. The changes in the vessel characteristics such as tortuosity may be used to estimate the effect of hypertension. In this paper, a simple distance metric (DM) method is used to evaluate the tortuosity of blood vessels. Initially, the method is applied on synthetically generated blood vessels of normal, moderate and severely tortuous nature. Then retinal vessels are segmented using image processing methods. Small vessel segments are selected manually and used for tortuosity evaluation. These images are collected from local eye hospital, DRIVE database and VICAVR database. The results obtained show that the method is capable enough to estimate the tortuosity and have close correlation with subjective evaluation of tortuosity.