A recursive Bayesian approach to describe retinal vasculature geometry
作者：
Highlights：
• A Deep Belief Net (DBN) is trained to detect vessel interior, centreline and edges.
• Particle filtering is used to quantify vasculature by using the output of the DBN.
• A vessel profile is represented with probability profiles of centreline and edges.
• The appearance of vessels in fundus images is considered in a vessel geometry model.
• The lack of labelled data for segmentation was tackled using a probabilistic approach.
摘要
•A Deep Belief Net (DBN) is trained to detect vessel interior, centreline and edges.•Particle filtering is used to quantify vasculature by using the output of the DBN.•A vessel profile is represented with probability profiles of centreline and edges.•The appearance of vessels in fundus images is considered in a vessel geometry model.•The lack of labelled data for segmentation was tackled using a probabilistic approach.
论文关键词：Particle filtering,Deep neural network,Deep Belief Net,Fundus image,Width estimation,Tracking
论文评审过程：Received 28 November 2017, Revised 5 October 2018, Accepted 13 October 2018, Available online 15 October 2018, Version of Record 23 October 2018.
论文官网地址：https://doi.org/10.1016/j.patcog.2018.10.017
