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 Concept Videos

You might also read

Related Articles

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

Sort by
Same author

Diagnostic Performance of the Mayo ATTR-CM Score in Diverse Populations: Comparison With the AMY Score.

JACC. Advances·2026
Same author

Diagnostic Performance Evaluation of Clinical and Artificial Intelligence Risk Models in Patients Referred for Cardiac Amyloidosis Testing.

Journal of the American Society of Echocardiography : official publication of the American Society of Echocardiography·2026
Same author

Diagnostic Performance and Interpreter Experience of 1-Hour Versus 3-Hour <sup>99m</sup>Tc-HMDP Cardiac Amyloid Radionuclide Imaging: A Prospective, Blinded Comparison.

Circulation. Cardiovascular imaging·2025
Same author

Comparative performance of <sup>99m</sup>Tc-pyrophosphate vs. <sup>99m</sup>Tc-hydroxymethylene diphosphonate for cardiac amyloid radionuclide imaging.

Journal of nuclear cardiology : official publication of the American Society of Nuclear Cardiology·2025
Same author

Healthspan-lifespan gap differs in magnitude and disease contribution across world regions.

Communications medicine·2025
Same author

3D facial reconstruction refines 60-4 visual field assessment.

The British journal of ophthalmology·2025

Related Experiment Video

Updated: Aug 20, 2025

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
12:49

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

12.9K

Predicting 60-4 visual field tests using 3D facial reconstruction.

Sepideh Jamali Dogahe1, Armin Garmany2, Seyedmostafa Sadegh Mousavi1

  • 1Department of Ophthalmology, Mayo Clinic, Rochester, Minnesota, USA.

The British Journal of Ophthalmology
|November 25, 2022
PubMed
Summary

An artificial intelligence platform accurately predicts visual field defects using facial contours. This technology may improve the clinical use of 60-4 visual field tests by accounting for facial structure impacts.

Keywords:
diagnostic tests/investigationfield of visionglaucoma

More Related Videos

Three-Dimensional Reconstruction of Orbital Fractures
08:18

Three-Dimensional Reconstruction of Orbital Fractures

Published on: May 16, 2025

294
Topographical Estimation of Visual Population Receptive Fields by fMRI
06:02

Topographical Estimation of Visual Population Receptive Fields by fMRI

Published on: February 3, 2015

9.3K

Related Experiment Videos

Last Updated: Aug 20, 2025

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells
12:49

A Method for 3D Reconstruction and Virtual Reality Analysis of Glial and Neuronal Cells

Published on: September 28, 2019

12.9K
Three-Dimensional Reconstruction of Orbital Fractures
08:18

Three-Dimensional Reconstruction of Orbital Fractures

Published on: May 16, 2025

294
Topographical Estimation of Visual Population Receptive Fields by fMRI
06:02

Topographical Estimation of Visual Population Receptive Fields by fMRI

Published on: February 3, 2015

9.3K

Area of Science:

  • Ophthalmology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • 60-4 visual field tests are underutilized due to concerns about facial contour interference.
  • Facial structure is a suspected factor influencing visual field defect detection.

Purpose of the Study:

  • To develop and validate an AI-driven platform for predicting visual field defects based on facial structure.
  • To assess the platform's ability to account for facial contour effects in 60-4 visual field testing.

Main Methods:

  • Utilized optical coherence tomography, 60-4 Swedish interactive thresholding algorithm visual field tests, and photography in healthy subjects.
  • Employed a convolutional neural network (CNN) for 3D facial reconstruction and prediction of visual field defects.
  • Evaluated model performance using sensitivity, specificity, precision, accuracy, and F1-scores.

Main Results:

  • The AI platform achieved high overall accuracy (97%±3% right eye, 96%±3% left eye) in predicting visual field defects.
  • The model demonstrated strong performance in the inferior nasal field, with F1-scores of 76%±20% (right) and 70%±29% (left).
  • Convolutional neural network (CNN) successfully predicted facial contour-dependent defects in 30 healthy participants.

Conclusions:

  • A CNN-enhanced platform can predict 60-4 visual field defects based on facial contour in healthy individuals.
  • This pilot study demonstrates the potential of AI to address limitations in visual field testing.
  • Further research using this platform could elucidate the precise influence of facial anatomy on visual field results.