Automatic Gunn and Salus sign quantification in retinal images

Jeffrey Wigdahl, Pedro Guimarães, Georgios Leontidis, Areti Triantafyllou, Alfredo Ruggeri

Research output: Chapter in Book/Report/Conference proceedingPublished conference contribution

2 Citations (Scopus)

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.

Original languageEnglish
Title of host publication37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
PublisherIEEE Explore
Pages5251-5254
Number of pages4
ISBN (Electronic)978-1-4244-9271-8
DOIs
Publication statusPublished - Aug 2015

Keywords

  • Image Processing
  • Retina

Fingerprint

Dive into the research topics of 'Automatic Gunn and Salus sign quantification in retinal images'. Together they form a unique fingerprint.

Cite this