Peer Reviewed

1

DOI

10.17077/omia.1007

Conference Location

Boston, MA, USA

Publication Date

September 2014

Abstract

Arteriolar-to-venular diameter ratio (AVR) is an important clinical measurement that allows to characterize retinal vascular abnormalities. A reliable AVR measurement requires accurate and reproducible width measurement. However, in order to measure the vessel width automatically, an approximation of the intensity profile is required by fitting a model. The aim of the proposed study is to assess the uncertainties introduced in the vessel width measurements when choosing a specific distribution as an intensity profile model. Different models are described and an automatic vessel width measurement procedure is presented. The uncertainty introduced by each model is evaluated by computing the standard deviation of the difference between the automatic and the manual measurements. The results show that the intensity profile model should be chosen according to the relative width of the targeted vessels.

Rights

Copyright © 2014, Fantin Girard, Conrad Kavalec, Houssem Ben Tahar, and Farida Cheriet.

Included in

Ophthalmology Commons

Share

COinS
 
Sep 14th, 12:00 AM Sep 14th, 12:00 AM

Uncertainty assessment of vessels width measurement from intensity profile model fitting in fundus images

Boston, MA, USA

Arteriolar-to-venular diameter ratio (AVR) is an important clinical measurement that allows to characterize retinal vascular abnormalities. A reliable AVR measurement requires accurate and reproducible width measurement. However, in order to measure the vessel width automatically, an approximation of the intensity profile is required by fitting a model. The aim of the proposed study is to assess the uncertainties introduced in the vessel width measurements when choosing a specific distribution as an intensity profile model. Different models are described and an automatic vessel width measurement procedure is presented. The uncertainty introduced by each model is evaluated by computing the standard deviation of the difference between the automatic and the manual measurements. The results show that the intensity profile model should be chosen according to the relative width of the targeted vessels.