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

Visual field interpretation with a personal computer based neural network

E Mutlukan1, D Keating

  • 1Tennent Institute of Ophthalmology, University of Glasgow, UK.

Eye (London, England)
|January 1, 1994
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

Cross-reactive anti-prophage antibodies and bacterial heteroresistance implicated in phage therapeutic failure.

Nature medicine·2026
Same author

Optimizing Pre-Operative Clinical Staging in Resectable Non-Small Cell Lung Cancer (NSCLC): A Retrospective Cohort Study.

Thoracic cancer·2025
Same author

Cognitive decrements in 1991 Gulf War veterans: associations with Gulf War illness and neurotoxicant exposures in the Boston Biorepository, Recruitment, and Integrative Network (BBRAIN) cohorts.

Environmental health : a global access science source·2023
Same author

UK and Ireland survey of MPharm student and staff experiences of mental health curricula, with a focus on Mental Health First Aid.

Journal of pharmaceutical policy and practice·2021
Same author

Boston biorepository, recruitment and integrative network (BBRAIN): A resource for the Gulf War Illness scientific community.

Life sciences·2021
Same author

A treatment algorithm for couples with unexplained infertility based on sperm chromatin assessment.

Journal of assisted reproduction and genetics·2018
Same journal

Traumatic intravitreal egg-shaped hematoma.

Eye (London, England)·2026
Same journal

Rare ocular triad: Goldenhar syndrome with Duane retraction syndrome and optic disc pit.

Eye (London, England)·2026
Same journal

AS-OCT demonstration of anterior capsular delamination in unilateral true exfoliation.

Eye (London, England)·2026
Same journal

Spaceflight-associated neuro-ocular syndrome (SANS): expert consensus on diagnosis and management.

Eye (London, England)·2026
Same journal

Temporal perceptual training enhances visual acuity in adult amblyopia: a single-case study.

Eye (London, England)·2026
Same journal

A window of opportunity: tear cytokine profiles in chronic ocular graft-versus-host disease.

Eye (London, England)·2026
See all related articles

A neural network can accurately interpret visual field test data from PC-based video-campimeters like CATS and CAMEC. This technology aids non-experts in diagnosing visual field defects, improving accessibility in community clinics.

Area of Science:

  • Ophthalmology
  • Computer Science
  • Artificial Intelligence

Background:

  • Computer Assisted Touch Screen (CATS) and Computer Assisted Moving Eye Campimeter (CAMEC) are PC-based video-campimeters offering results comparable to conventional devices.
  • These systems utilize static stimuli on cathode ray tubes for visual field testing.

Purpose of the Study:

  • To design and evaluate a neural network for classifying visual field data from PC-based video-campimeters.
  • To facilitate diagnostic interpretation of visual field test results by non-experts in clinical settings.

Main Methods:

  • A three-layer backpropagation neural network was developed with 110 input units, 40 hidden units, and 27 output units.
  • The network was trained on 540 simulated visual field patterns (normal, glaucomatous, neuro-ophthalmic defects) for up to 20,000 cycles.

Related Experiment Videos

  • Performance was assessed using a test set of 135 simulated fields and a genuine set of 300 fields (100 neurological, 200 glaucomatous).

    • Main Results:

    • The neural network achieved a classification accuracy of 91-97% with simulated data.
    • Accuracy with genuine clinical data ranged from 65% to 100% for neurological and glaucomatous defects.
    • The system demonstrated high potential for reliable visual field defect classification.

    Conclusions:

    • Neural networks integrated into PC-based video-campimeters can enable accurate interpretation of visual field test results.
    • This technology has the potential to support correct diagnoses in non-specialist clinics and community settings.
    • Automated interpretation can enhance the accessibility and efficiency of visual field testing.