An unsupervised coarse-to-fine algorithm for blood vessel segmentation in fundus images
作者：
Highlights：
• An unsupervised method to detect blood vessels in fundus images is proposed.
• The algorithm effectively tackles image distortions such as central vessel reflex.
• The two expert vessel identification images present significant differences.
• The average observer plays an important role in defining a neutral standard.
• Balanced accuracy is an alternative for performance evaluation of segmentation.
摘要
•An unsupervised method to detect blood vessels in fundus images is proposed.•The algorithm effectively tackles image distortions such as central vessel reflex.•The two expert vessel identification images present significant differences.•The average observer plays an important role in defining a neutral standard.•Balanced accuracy is an alternative for performance evaluation of segmentation.
论文关键词：Retinal vasculature,Local coarse segmentation,Balanced accuracy,Vessel refinement
论文评审过程：Received 25 July 2016, Revised 6 February 2017, Accepted 7 February 2017, Available online 9 February 2017, Version of Record 20 February 2017.
论文官网地址：https://doi.org/10.1016/j.eswa.2017.02.015
