Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Automated keratoconus screening with corneal topography analysis

N Maeda1, S D Klyce, M K Smolek

  • 1Lions Eye Research Laboratories, LSU Eye Center, New Orleans 70112.

Investigative Ophthalmology & Visual Science
|May 1, 1994
PubMed
Summary

An automated system accurately detects keratoconus from corneal topography maps, improving upon subjective visual inspection. This computer-assisted videokeratoscopy method aids in distinguishing keratoconus from other corneal conditions.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Analyzing Data from Experiments in which the Outcome is Time to an Event.

Nutritional neuroscience·2016
Same author

Analysis of Data that is in the Form of Categories.

Nutritional neuroscience·2016
Same author

Analysis of Data that is in the Form of Categories Part II: Beyond the 2*2 Contingency Table-Partitioning Chi-Square Tests.

Nutritional neuroscience·2016
Same author

A Description of the Appropriate Use of Student's t-Test.

Nutritional neuroscience·2016
Same author

The Analysis of Variance (ANOVA).

Nutritional neuroscience·2016
Same author

Infra-red recording with the cathode ray oscilloscope.

Nature·2010

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Computer Science

Background:

  • Corneal topography analysis is crucial for diagnosing various eye conditions.
  • Visual inspection of corneal maps is subjective and can lead to diagnostic variability.
  • Objective, quantitative methods are needed for accurate classification of corneal abnormalities.

Purpose of the Study:

  • To develop and validate an automated system for differentiating keratoconus from other corneal conditions using computer-assisted videokeratoscopy.
  • To establish a quantitative classification method for abnormal topographic patterns.

Main Methods:

  • A classification tree combined with a linear discriminant function was employed.
  • Eight indices from TMS-1 videokeratoscope data were analyzed.

Related Experiment Videos

  • A training set of 100 corneas and a validation set of 100 corneas with diverse diagnoses were used.

    • Main Results:

    • The system achieved 100% sensitivity and 97% accuracy in detecting keratoconus in the training set.
    • In the validation set, sensitivity was 89% and accuracy was 96%, with one false positive in a transplanted cornea.
    • The system demonstrated high specificity (96-99%) in distinguishing keratoconus.

    Conclusions:

    • The developed automated system effectively screens for clinical keratoconus.
    • This quantitative approach enhances the objective interpretation of corneal topographic maps.
    • The system shows potential for improving diagnostic accuracy in ophthalmology.