NOTICE: Labnodes now supports vumc.org email addresses. If your email changed, please update your profile today.
Edward Chaum
Last active: 6/11/2018

Locating the optic nerve in retinal images: comparing model-based and Bayesian decision methods.

Karnowski TP, Govindasamy VP, Tobin KW, Chaum E
Conf Proc IEEE Eng Med Biol Soc. 2006 1: 4436-9

PMID: 17945838 · DOI:10.1109/IEMBS.2006.259406

In this work we compare two methods for automatic optic nerve (ON) localization in retinal imagery. The first method uses a Bayesian decision theory discriminator based on four spatial features of the retina imagery. The second method uses a principal component-based reconstruction to model the ON. We report on an improvement to the model-based technique by incorporating linear discriminant analysis and Bayesian decision theory methods. We explore a method to combine both techniques to produce a composite technique with high accuracy and rapid throughput. Results are shown for a data set of 395 images with 2-fold validation testing.

MeSH Terms (15)

Algorithms Automation Bayes Theorem Eye Humans Image Interpretation, Computer-Assisted Likelihood Functions Models, Statistical Models, Theoretical Optic Nerve Pattern Recognition, Automated Reproducibility of Results Retina Retinal Diseases Sensitivity and Specificity

Connections (1)

This publication is referenced by other Labnodes entities:

Links