A new tool to connect blood vessels in fundus retinal images

Abstract

This paper presents a novel tool that allows a user to reconstruct the retinal vascular network from fundus images. The retinal vasculature consists of trees of arteries and veins. Common segmentation algorithms are not able to completely segment out the blood vessels in fundus images. This failure results in a set of disconnected or broken up vascular segments. Reconstructing the whole network has crucial importance because it can offer insight into global features not considered so far, including retinal fluid dynamics. This tool uses implicit neural cost functions to join vessel segments. Results have shown that the quality of the segmentation affects the outcome of connectivity algorithms and by enhancing the segmentation the connectivity can be improved.

IterNet: Retinal Image Segmentation Utilizing Structural Redundancy in Vessel Networks

“…This is a common phenomenon in medical image segmentation and can lead to a defective vessel map consisting of a set of disconnected or broken up segments. This issue makes it very difficult to analyze the blood vessel condition by doctors or standard imaging methodologies using the segmented images [7]. Therefore, connectivity is also an important problem for retina segmentation.…”

A simplified fluid–structure model for arterial flow. Application to retinal hemodynamics

“…The original image was taken in the Drive dataset [21]. The vasculature has been segmented by applying the imaging methods presented in [22,23]. The 2D data have then been expanded into a 3D-network by assuming a circular section and projecting the results onto a sphere representing the eye.…”