Altair: Supervised Methodology To Obtain Retinal Vessels Caliber

ADCAIJ-ADVANCES IN DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE JOURNAL(2014)

引用 7|浏览1
暂无评分
摘要
A back of the eye examination allows performing a noninvasive evaluation of the retinal microcirculation, as well as of the vascular damage induced by multiple cardiovascular risk factors. The objective of this work is to study the existing needs to lead to the development and validation (reliability and validity) of a methodology able to extract all the information from the images of the back of the eye to solve the studied needs. Its development will subsequently allow analyzing its utility in various clinical environments. Currently there are different works that evaluate the thickness of the retinal veins and arteries, but they require either full intervention by an observer or no intervention at all, so when facing incorrect analysis (none of them achieves a 100 % accuracy in automatic analysis) erroneous results can be a serious problem when drawing conclusions. The proposed solution refers to the second group (automatic), but providing a supervisor the possibility to interfere with the analysis when any kind of error is produced, which ideally will not happen many times. Thanks to this the possible subjectivity that can be introduced by the supervisor does not affect the final result of the analysis.
更多
查看译文
关键词
Image analysis, Fundus images, Vessels caliber
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要