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

Title: Locating the Optic Nerve in Retinal Images: Comparing Model-Based and Bayesian Decision Methods

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 is criminator 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.

Authors:
 [1];  [1];  [1];  [1]
  1. ORNL
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE; Work for Others (WFO)
OSTI Identifier:
962591
DOE Contract Number:
DE-AC05-00OR22725
Resource Type:
Conference
Resource Relation:
Conference: 28th Annual Inter. Conf. of the IEEE Engineering in Medicine and Biology Society, New York, NY, USA, 20060830, 20060903
Country of Publication:
United States
Language:
English
Subject:
60 APPLIED LIFE SCIENCES; ACCURACY; NERVES; EYES; RETINA; IMAGES; DETECTION; MEASURING METHODS; COMPARATIVE EVALUATIONS

Citation Formats

Karnowski, Thomas Paul, Tobin Jr, Kenneth William, Muthusamy Govindasamy, Vijaya Priya, and Chaum, Edward. Locating the Optic Nerve in Retinal Images: Comparing Model-Based and Bayesian Decision Methods. United States: N. p., 2006. Web.
Karnowski, Thomas Paul, Tobin Jr, Kenneth William, Muthusamy Govindasamy, Vijaya Priya, & Chaum, Edward. Locating the Optic Nerve in Retinal Images: Comparing Model-Based and Bayesian Decision Methods. United States.
Karnowski, Thomas Paul, Tobin Jr, Kenneth William, Muthusamy Govindasamy, Vijaya Priya, and Chaum, Edward. Sun . "Locating the Optic Nerve in Retinal Images: Comparing Model-Based and Bayesian Decision Methods". United States. doi:.
@article{osti_962591,
title = {Locating the Optic Nerve in Retinal Images: Comparing Model-Based and Bayesian Decision Methods},
author = {Karnowski, Thomas Paul and Tobin Jr, Kenneth William and Muthusamy Govindasamy, Vijaya Priya and Chaum, Edward},
abstractNote = {In this work we compare two methods for automatic optic nerve (ON) localization in retinal imagery. The first method uses a Bayesian decision theory is criminator 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.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Sun Jan 01 00:00:00 EST 2006},
month = {Sun Jan 01 00:00:00 EST 2006}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:
  • The detection of the optic nerve in retina images is a key element of detecting the anatomical structure of the retina. In this work we report on the fusion of two complementary optic nerve detection methods. The methods are complementary in the sense that they use different fundamental queues for locating the optic nerve. By fusing the methods through applying simple distance-based threshold, a confidence level may be assigned to the quality of the optic nerve detection. In a practical screening system this metric can be used to determine if the images should be immediately reviewed by a physician ormore » if further automatic processing is feasible. We report on the results for two different data sets and show that the use of the threshold improves detection quality.« less
  • The frequency spectral characteristics, bias and variance of images reconstructed from real Positron Emission Tomography (PET) data have been studied. Feasible images obtained from statistically based reconstruction methods have been compared to Filtered Backprojection (FBP) images. Feasible images have been described as those images that are compatible with the measured data by consideration of the Poisson nature of the emission process. The results show that the spectral characteristics of reconstructions obtained by statistically based methods are at least as good as those obtained by the FBP methods. With some exceptions, statistically based reconstructions do not exhibit abnormal amounts of bias.more » The most significant difference between the two groups of reconstructions is in the image variance, where the statistically based methods yield substantially smaller variances in the regions with smaller image intensity than the FBP images. 14 refs., 12 figs., 3 tabs.« less
  • The authors describe conjugate gradient algorithms for reconstruction of transmission and emission PET images. The reconstructions are based on a Bayesian formulation, where the data are modeled as a collection of independent Poisson random variables and the image is modeled using a Markov random field. A conjugate gradient algorithm is used to compute a maximum a posteriori (MAP) estimate of the image by maximizing over the posterior density. To ensure nonnegativity of the solution, a penalty function is used to convert the problem to one of unconstrained optimization. Preconditioners are used to enhance convergence rates. These methods generally achieve effectivemore » convergence in 15--25 iterations. Reconstructions are presented of an [sup 18]FDG whole body scan from data collected using a Siemens/CTI ECAT931 whole body system. These results indicate significant improvements in emission image quality using the Bayesian approach, in comparison to filtered backprojection, particularly when reprojections of the MAP transmission image are used in place of the standard attenuation correction factors.« less
  • Discontinuity detection is an important component in many fields: Image recognition, Digital signal processing, and Climate change research. Current methods shortcomings are: Restricted to one- or two-dimensional setting, Require uniformly spaced and/or dense input data, and Give deterministic answers without quantifying the uncertainty. Spectral methods for Uncertainty Quantification with global, smooth bases are challenged by discontinuities in model simulation results. Domain decomposition reduces the impact of nonlinearities and discontinuities. However, while gaining more smoothness in each subdomain, the current domain refinement methods require prohibitively many simulations. Therefore, detecting discontinuities up front and refining accordingly provides huge improvement to the currentmore » methodologies.« less