DocumentCode :
186097
Title :
Assessment of vascular changes in retinal images
Author :
Dashtbozorg, Behdad ; Mendonca, Ana Maria ; Campilho, Aurelio
Author_Institution :
INEB-Inst. de Eng. Biomed., Univ. do Porto, Porto, Portugal
fYear :
2014
fDate :
11-12 June 2014
Firstpage :
1
Lastpage :
4
Abstract :
The Arteriolar-to-Venular Ratio (AVR) is a well known index for the early diagnosis of diseases such as diabetes, hypertension or cardio-vascular pathologies. This paper presents an automatic approach for the estimation of the AVR in retinal images. The proposed method includes vessel segmentation, vessel caliber estimation, optic disc detection, region of interest determination, artery/vein classification and finally AVR calculation. This method was evaluated using the images of the INSPIRE-AVR dataset. The mean error of the measured AVR values with respect to the reference ones was 0.05, which is identical to the one achieved by a medical expert using a semi-automated system, thus demonstrating the reliability of the herein proposed solution for AVR estimation.
Keywords :
biomedical optical imaging; blood vessels; diseases; eye; image classification; image segmentation; medical image processing; arteriolar-to-venular ratio; artery classification; cardiovascular pathologies; diabetes; hypertension; optic disc detection; region-of-interest determination; retinal images; semiautomated system; vascular change assessment; vein classification; vessel caliber estimation; vessel segmentation; Adaptive optics; Arteries; Estimation; Image segmentation; Optical imaging; Retina; Veins; Arteriolar-to-Venular Ratio; Artery/Vein classification; Optic disc detection; Retinal images; Vessel segmentation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Medical Measurements and Applications (MeMeA), 2014 IEEE International Symposium on
Conference_Location :
Lisboa
Print_ISBN :
978-1-4799-2920-7
Type :
conf
DOI :
10.1109/MeMeA.2014.6860023
Filename :
6860023
Link To Document :
بازگشت