Three Sigma and Multilevel Active Contour Approach to Detect Optic Disc and Optic Cup

N. C. Patil, P. V. Rao
{"title":"Three Sigma and Multilevel Active Contour Approach to Detect Optic Disc and Optic Cup","authors":"N. C. Patil, P. V. Rao","doi":"10.1109/ICATIECE45860.2019.9063813","DOIUrl":null,"url":null,"abstract":"One of the key factors to be looked at during design of an automated eye screening system is to find the optic disc and optic cup. Objective: In eye screening of diabetic patients, the feature such as hard exudates and cotton wool spots can be noticed which share similar properties with optic disc In certain diseases like glaucoma ophthalmologist look at the ratio of optic cup with optic disc to detect the presence or absence of glaucoma Currently, the process is manual performed by ophthalmologist, which a time consuming and tedious job. This fact motivated to design a fully automated procedure to detect optic cup and optic disc. Method: In the current paper a multilevel active contour technique is used that generates the snake to detect boundaries of optic cup and optic disc using intensity of the border pixels which are tested using 3σ control limits. The algorithm works in two parts. In part-1, optic disc boundary is detected and in part-2, the optic cup is marked by concentrating inside the area marked as optic disc in part-1. Findings: This approach reduces processing area and hence improves computational time A local database to carry out this work was created by collecting images from Karnataka Institute of Diabetology, Bangalore The results obtained by the proposed procedure are encouraging and have yielded 100% results with the fundus images containing full optic disc Improvement: The method is fully automatic and no user intervention is required","PeriodicalId":106496,"journal":{"name":"2019 1st International Conference on Advanced Technologies in Intelligent Control, Environment, Computing & Communication Engineering (ICATIECE)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2019-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 1st International Conference on Advanced Technologies in Intelligent Control, Environment, Computing & Communication Engineering (ICATIECE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICATIECE45860.2019.9063813","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

One of the key factors to be looked at during design of an automated eye screening system is to find the optic disc and optic cup. Objective: In eye screening of diabetic patients, the feature such as hard exudates and cotton wool spots can be noticed which share similar properties with optic disc In certain diseases like glaucoma ophthalmologist look at the ratio of optic cup with optic disc to detect the presence or absence of glaucoma Currently, the process is manual performed by ophthalmologist, which a time consuming and tedious job. This fact motivated to design a fully automated procedure to detect optic cup and optic disc. Method: In the current paper a multilevel active contour technique is used that generates the snake to detect boundaries of optic cup and optic disc using intensity of the border pixels which are tested using 3σ control limits. The algorithm works in two parts. In part-1, optic disc boundary is detected and in part-2, the optic cup is marked by concentrating inside the area marked as optic disc in part-1. Findings: This approach reduces processing area and hence improves computational time A local database to carry out this work was created by collecting images from Karnataka Institute of Diabetology, Bangalore The results obtained by the proposed procedure are encouraging and have yielded 100% results with the fundus images containing full optic disc Improvement: The method is fully automatic and no user intervention is required
三西格玛和多层主动轮廓法检测视盘和视杯
在设计自动眼睛筛查系统时,要考虑的关键因素之一是找到视盘和视杯。目的:在糖尿病患者的眼部筛查中,可观察到硬渗出物、棉絮斑等与视盘具有相似性质的特征。在青光眼等疾病中,眼科医生通过观察视杯与视盘的比例来判断是否存在青光眼。目前,这一过程主要由眼科医生手工完成,耗时且繁琐。这一事实促使我们设计了一种完全自动化的程序来检测视杯和视盘。方法:本文采用多层次主动轮廓技术,利用边界像素的强度,利用3σ控制极限检测视盘和视杯的边界,生成蛇形图像。该算法分为两部分。在第1部分中,检测视盘边界,在第2部分中,通过在第1部分中标记为视盘的区域内集中来标记视杯。研究结果:该方法减少了处理面积,从而提高了计算时间,通过收集卡纳塔克邦糖尿病研究所(Bangalore)的图像创建了一个本地数据库来开展这项工作。通过所建议的程序获得的结果令人鼓舞,并且眼底图像包含全视盘的结果达到了100%
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信