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

Computer processing of visual data. II. Automated pattern analysis of glaucomatous visual fields

W M Hart

    Archives of Ophthalmology (Chicago, Ill. : 1960)
    |January 1, 1981
    PubMed
    Summary
    This summary is machine-generated.

    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

    Indirect treatment comparison of belatacept versus tacrolimus from a systematic review of immunosuppressive therapies for kidney transplant patients.

    Current medical research and opinion·2016
    Same author

    The cost-effectiveness of solifenacin vs. trospium in the treatment of patients with overactive bladder in the German National Health Service.

    Journal of medical economics·2014
    Same author

    An incidence model of the cost of advanced prostate cancer in Spain.

    Journal of medical economics·2013
    Same author

    Analysis of lactic acid with a modification of the Conway microdiffusion unit.

    Federation proceedings·2010
    Same author

    Hydration properties of excised cornea and factors responsible for transparency.

    Archives of ophthalmology (Chicago, Ill. : 1929)·2010
    Same author

    Hydration and transparency of cornea.

    American journal of ophthalmology·2010

    Machine algorithms can automatically detect glaucomatous defects in visual field tests. These algorithms use pattern analysis to identify typical glaucomatous visual field loss with high sensitivity.

    Area of Science:

    • Ophthalmology
    • Medical Informatics
    • Computer Science

    Background:

    • Glaucoma diagnosis relies on identifying characteristic visual field defects.
    • Manual analysis of visual field records can be time-consuming and subjective.
    • Automated methods offer potential for consistent and efficient defect detection.

    Purpose of the Study:

    • To develop and evaluate machine algorithms for automated detection and characterization of glaucomatous defects.
    • To assess the sensitivity and specificity of these algorithms in identifying visual field abnormalities.

    Main Methods:

    • Utilized elementary pattern analysis techniques to describe visual field contours with graphic and type-descriptive features.
    • Employed a hierarchical structure of logical tests for intermediate and higher-level diagnostic conclusions.

    Related Experiment Videos

  • Developed decision procedures specifically for common glaucomatous visual field loss patterns.

    • Main Results:

    • The developed machine algorithms demonstrated very high sensitivity in detecting glaucomatous defects.
    • Analysis was applied to a large dataset of visual field records with diverse glaucomatous defects.
    • Algorithm specificity was found to be dependent on the typicality of the observed visual field loss patterns.

    Conclusions:

    • Automated machine algorithms show significant promise for the sensitive detection of glaucomatous visual field defects.
    • The accuracy of specificity is influenced by adherence to expected patterns of glaucomatous visual field loss.
    • Further refinement may be needed to improve specificity for atypical defect presentations.