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

Title: A Probabilistic Framework for Content-Based Diagnosis of Retinal Disease

Abstract

Diabetic retinopathy is the leading cause of blindness in the working age population around the world. Computer assisted analysis has the potential to assist in the early detection of diabetes by regular screening of large populations. The widespread availability of digital fundus cameras today is resulting in the accumulation of large image archives of diagnosed patient data that captures historical knowledge of retinal pathology. Through this research we are developing a content-based image retrieval method to verify our hypothesis that retinal pathology can be identified and quantified from visually similar retinal images in an image archive. We will present diagnostic results for specificity and sensitivity on a population of 395 fundus images representing the normal fundus and 14 stratified disease states.

Authors:
 [1];  [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:
944594
DOE Contract Number:
DE-AC05-00OR22725
Resource Type:
Conference
Resource Relation:
Conference: 29th IEEE EMBS Annual International Conference, Lyon,, France, 20070823, 20070823
Country of Publication:
United States
Language:
English
Subject:
59 BASIC BIOLOGICAL SCIENCES; AVAILABILITY; CAMERAS; COMPUTERS; DETECTION; DIAGNOSIS; DISEASES; HYPOTHESIS; PATHOLOGY; PATIENTS; SENSITIVITY; SPECIFICITY

Citation Formats

Tobin Jr, Kenneth William, Abdelrahman, Mohamed A, Chaum, Edward, Muthusamy Govindasamy, Vijaya Priya, and Karnowski, Thomas Paul. A Probabilistic Framework for Content-Based Diagnosis of Retinal Disease. United States: N. p., 2007. Web.
Tobin Jr, Kenneth William, Abdelrahman, Mohamed A, Chaum, Edward, Muthusamy Govindasamy, Vijaya Priya, & Karnowski, Thomas Paul. A Probabilistic Framework for Content-Based Diagnosis of Retinal Disease. United States.
Tobin Jr, Kenneth William, Abdelrahman, Mohamed A, Chaum, Edward, Muthusamy Govindasamy, Vijaya Priya, and Karnowski, Thomas Paul. Mon . "A Probabilistic Framework for Content-Based Diagnosis of Retinal Disease". United States. doi:.
@article{osti_944594,
title = {A Probabilistic Framework for Content-Based Diagnosis of Retinal Disease},
author = {Tobin Jr, Kenneth William and Abdelrahman, Mohamed A and Chaum, Edward and Muthusamy Govindasamy, Vijaya Priya and Karnowski, Thomas Paul},
abstractNote = {Diabetic retinopathy is the leading cause of blindness in the working age population around the world. Computer assisted analysis has the potential to assist in the early detection of diabetes by regular screening of large populations. The widespread availability of digital fundus cameras today is resulting in the accumulation of large image archives of diagnosed patient data that captures historical knowledge of retinal pathology. Through this research we are developing a content-based image retrieval method to verify our hypothesis that retinal pathology can be identified and quantified from visually similar retinal images in an image archive. We will present diagnostic results for specificity and sensitivity on a population of 395 fundus images representing the normal fundus and 14 stratified disease states.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Mon Jan 01 00:00:00 EST 2007},
month = {Mon Jan 01 00:00:00 EST 2007}
}

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:
  • A method for diagnosing diseases having retinal manifestations including retinal pathologies includes the steps of providing a CBIR system including an archive of stored digital retinal photography images and diagnosed patient data corresponding to the retinal photography images, the stored images each indexed in a CBIR database using a plurality of feature vectors, the feature vectors corresponding to distinct descriptive characteristics of the stored images. A query image of the retina of a patient is obtained. Using image processing, regions or structures in the query image are identified. The regions or structures are then described using the plurality of featuremore » vectors. At least one relevant stored image from the archive based on similarity to the regions or structures is retrieved, and an eye disease or a disease having retinal manifestations in the patient is diagnosed based on the diagnosed patient data associated with the relevant stored image(s).« less
  • A prototype Knowledge Based (KB) operator Adviser (OPAD) system has been developed for 100 MW(th) Heavy Water moderated, cooled and Natural Uranium fueled research reactor. The development objective of this system is to improve reliability of operator action and hence the reactor safety at the time of crises as well as normal operation. The jobs performed by this system include alarm analysis, transient identification, reactor safety status monitoring, qualitative fault diagnosis and procedure generation in reactor operation. In order to address safety objectives at various stages of the Operator Adviser (OPAD) system development the Knowledge has been structured using PSAmore » tools/information in an shell environment. To demonstrate the feasibility of using a combination of KB approach with PSA for operator adviser system, salient features of some of the important modules (viz. FUELEX, LOOPEX and LOCAEX) have been discussed. It has been found that this system can serve as an efficient operator support system.« less
  • 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.
  • Probabilistic criteria for abnormality would enhance application of stress-redistribution Tl-201 rotational tomography (tomo) for evaluation of coronary artery disease (CAD). Thus, 91 pts were studied, of whom 45 had angiographic CAD (greater than or equal to 50% coronary narrowing) and 46 were normal (nl). The validity of this model was prospectively tested in the remaining 51 pts (26 nls and 25 with CAD) by comparing the predicted and observed likelihood of CAD in four subgroups (I-IV). In this paper a logistic model is developed and validated that assigns a CAD likelihood to the quantified size of tomograhic myocardial perfusion defects.
  • The increasing use of results from probabilistic risk assessments in the decision-making process makes it ever more important to eliminate simplifications in probabilistic models that might lead to conservative results. One area in which conservative simplifications are often made is modeling the physical interactions that occur during the progression of an accident sequence. This paper demonstrates and compares different approaches for incorporating deterministic models of physical parameters into probabilistic models; parameter range binning, response curves, and integral deterministic models. An example that combines all three approaches in a probabilistic model for the handling of an energetic material (i.e. high explosive,more » rocket propellant,...) is then presented using a directed graph model.« less