Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group

Use of a Neural Network to Classify Electroretinograms in Central Retinal Vein Occlusion

Not Accessible

Your library or personal account may give you access

Abstract

The electroretinogram (ERG) has been shown to be an excellent predictor of outcome in central retinal vein occlusion (CRVO), distinguishing with high sensitivity and specificity those eyes that will develop neovascularization of the iris (NVI) from those that will not (no-NVI).1-6 Although few of these studies agree on the parameter that best separates NVI eyes from no-NVI eyes, most of the parameters investigated in these studies (Rmax and log K from Naka-Rushton analysis, 30 Hz flicker implicit time and amplitude, b-wave to a-wave amplitude ratio, b-wave implicit time) perform well in separating the two groups. Examination of the relationships between these parameters show that most of them are correlated.* This leads to the question "Are all of these parameters measuring the same underlying phenomenon (with varying degrees of noise added), or are some of them measuring different things?"

© 1992 Optical Society of America

PDF Article
More Like This
A Theoretical Interpretation of ERG Abnormalities In Central Retinal Vein Occlusion

Mary A. Johnson and Donald C. Hood
WA4 Noninvasive Assessment of the Visual System (NAVS) 1988

Rod Phototransduction is Altered in Proliferative Central Retinal Vein Occlusion

Mary A. Johnson and Donald C. Hood
MA2 Vision Science and its Applications (VSIA) 1995

Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.