skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Image analysis of ocular fundus for retinopathy characterization

Abstract

Automated analysis of ocular fundus images is a common procedure in countries as England, including both nonemergency examination and retinal screening of patients with diabetes mellitus. This involves digital image capture and transmission of the images to a digital reading center for evaluation and treatment referral. In collaboration with the Optometry Department, University of California, Berkeley, we have tested computer vision algorithms to segment vessels and lesions in ground-truth data (DRIVE database) and hundreds of images of non-macular centric and nonuniform illumination views of the eye fundus from EyePACS program. Methods under investigation involve mathematical morphology (Figure 1) for image enhancement and pattern matching. Recently, we have focused in more efficient techniques to model the ocular fundus vasculature (Figure 2), using deformable contours. Preliminary results show accurate segmentation of vessels and high level of true-positive microaneurysms.

Authors:
;
Publication Date:
Research Org.:
Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States)
Sponsoring Org.:
Computational Research Division
OSTI Identifier:
1004692
Report Number(s):
LBNL-4227E-Poster
TRN: US201105%%97
DOE Contract Number:  
DE-AC02-05CH11231
Resource Type:
Technical Report
Resource Relation:
Conference: Bay Area Vision Meeting, Feb 5th, Berkeley, CA 2010.
Country of Publication:
United States
Language:
English
Subject:
60; ALGORITHMS; COMPUTERS; DIABETES MELLITUS; EVALUATION; EYES; GROUND TRUTH MEASUREMENTS; ILLUMINANCE; MORPHOLOGY; PATIENTS; VISION

Citation Formats

Ushizima, Daniela, and Cuadros, Jorge. Image analysis of ocular fundus for retinopathy characterization. United States: N. p., 2010. Web. doi:10.2172/1004692.
Ushizima, Daniela, & Cuadros, Jorge. Image analysis of ocular fundus for retinopathy characterization. United States. https://doi.org/10.2172/1004692
Ushizima, Daniela, and Cuadros, Jorge. 2010. "Image analysis of ocular fundus for retinopathy characterization". United States. https://doi.org/10.2172/1004692. https://www.osti.gov/servlets/purl/1004692.
@article{osti_1004692,
title = {Image analysis of ocular fundus for retinopathy characterization},
author = {Ushizima, Daniela and Cuadros, Jorge},
abstractNote = {Automated analysis of ocular fundus images is a common procedure in countries as England, including both nonemergency examination and retinal screening of patients with diabetes mellitus. This involves digital image capture and transmission of the images to a digital reading center for evaluation and treatment referral. In collaboration with the Optometry Department, University of California, Berkeley, we have tested computer vision algorithms to segment vessels and lesions in ground-truth data (DRIVE database) and hundreds of images of non-macular centric and nonuniform illumination views of the eye fundus from EyePACS program. Methods under investigation involve mathematical morphology (Figure 1) for image enhancement and pattern matching. Recently, we have focused in more efficient techniques to model the ocular fundus vasculature (Figure 2), using deformable contours. Preliminary results show accurate segmentation of vessels and high level of true-positive microaneurysms.},
doi = {10.2172/1004692},
url = {https://www.osti.gov/biblio/1004692}, journal = {},
number = ,
volume = ,
place = {United States},
year = {Fri Feb 05 00:00:00 EST 2010},
month = {Fri Feb 05 00:00:00 EST 2010}
}