Automatic Gunn and Salus sign quantification in retinal images

Wigdahl, Jeffrey and Guimarães, Pedro and Leontidis, Georgios and Triantafyllou, Areti and Ruggeri, Alfredo (2015) Automatic Gunn and Salus sign quantification in retinal images. In: Engineering in Medicine and Biology Society, 2015 37th Annual International Conference of the IEEE, 25-29 August, 2015, Milan, Italy.

Full content URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arn...

Documents
EMBC15_Leontidis&Wigdahl.pdf
[img]
[Download]
[img]
Preview
PDF
EMBC15_Leontidis&Wigdahl.pdf - Whole Document

434kB
Item Type:Conference or Workshop contribution (Paper)
Item Status:Live Archive

Abstract

Prolonged hypertension can lead to abnormal changes in the retinal vasculature, including sclerosis and thickening of the arteriole walls. These changes can cause compression (Gunn’s sign) and deflection (Salus’s sign) of the veins at arteriovenous crossings. In retinal images, Gunn’s sign appears as a tapering of the vein at a crossing point, while Salus’s sign presents as an S-shaped curving. This paper presents a method for the automatic quantification of these two signs once a crossover has been detected; combining segmentation, artery vein classification, and morphological feature extraction techniques to calculate vein widths and angles entering and exiting the crossover. The method was tested on a small set of crossings, graded by a set of 3 doctors who were in agreement as having or not having Gunn/Salus sign. Results show separation between the two classes and that we can reliably detect and quantify these sign under the right conditions.

Keywords:Retina, Hypertension, Gunn and Salus
Subjects:G Mathematical and Computer Sciences > G400 Computer Science
G Mathematical and Computer Sciences > G740 Computer Vision
Divisions:College of Science > School of Computer Science
ID Code:19002
Deposited On:14 Oct 2015 08:55

Repository Staff Only: item control page