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

Conf Proc IEEE Eng Med Biol Soc. 2006:2006:4436-9. doi: 10.1109/IEMBS.2006.259406.

Abstract

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.

Publication types

  • Research Support, N.I.H., Extramural
  • Research Support, U.S. Gov't, Non-P.H.S.

MeSH terms

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