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

Acute radiating gluteal pain caused by obturator internus muscle endometriosis.

American journal of obstetrics and gynecology·2026
Same author

The human limbus functions as an instructive epithelial transition zone.

Research square·2026
Same author

Pathological and molecular characterization of a four-component combined small cell lung carcinoma: a case report.

Translational lung cancer research·2026
Same author

The use of the smart eye camera for diagnosing and grading cataract in diabetic and non-diabetic patients in an outpatient setting in Jordan.

International ophthalmology·2026
Same author

YAP1-dependent regulation of cell size in BCAM-positive limbal corneal progenitor cells.

Experimental eye research·2026
Same author

Devising a Coaching Method for a Smartphone-Based Slit-Lamp Microscope and Its Learning Effects: A Pilot Study.

Journal of clinical medicine·2026

Related Experiment Video

Updated: Mar 27, 2026

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders
05:49

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Published on: November 1, 2024

1.3K

Development of a Novel Deep Learning-Based Gaze Estimation Method for Detecting Strabismus.

Midori Watabe1,2, Hiroki Nishimura2,3,4, Rohan J Khemlani2,3

  • 1Chemical Engineering, United World Colleges International School of Asia, Karuizawa, Karuizawa, JPN.

Cureus
|March 26, 2026
PubMed
Summary

A new deep learning algorithm estimates eye alignment using gaze estimation, showing promise for quantifying strabismus. This non-invasive method could offer a practical approach to strabismus assessment.

Keywords:
artificial intelligence in ophthalmologybinocular visiondeep learninggaze estimationstrabismus

More Related Videos

Using an Automated Hirschberg Test App to Evaluate Ocular Alignment
05:40

Using an Automated Hirschberg Test App to Evaluate Ocular Alignment

Published on: March 24, 2020

16.1K
Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior
07:09

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior

Published on: November 14, 2018

11.6K

Related Experiment Videos

Last Updated: Mar 27, 2026

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders
05:49

Author Spotlight: Deciphering Electrical Networks Behind Complex Brain Activities and Disorders

Published on: November 1, 2024

1.3K
Using an Automated Hirschberg Test App to Evaluate Ocular Alignment
05:40

Using an Automated Hirschberg Test App to Evaluate Ocular Alignment

Published on: March 24, 2020

16.1K
Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior
07:09

Gaze in Action: Head-mounted Eye Tracking of Children's Dynamic Visual Attention During Naturalistic Behavior

Published on: November 14, 2018

11.6K

Area of Science:

  • Ophthalmology
  • Computer Vision
  • Artificial Intelligence

Background:

  • Strabismus detection and quantification are crucial for effective treatment.
  • Current methods may be invasive or lack accessibility.
  • Developing novel, quantitative methods for ocular alignment assessment is needed.

Purpose of the Study:

  • To develop and validate a deep learning (DL)-based algorithm for quantitative ocular alignment estimation.
  • To evaluate the algorithm's potential as a novel method for strabismus detection and quantification.
  • To assess the correlation between gaze directions of both eyes in healthy subjects.

Main Methods:

  • A DL gaze-estimation model was applied to video input of ocular positions.
  • The model was trained using computer-generated eye images synthesized with UnityEyes.
  • The algorithm outputs visualizations and estimated gaze angles for both eyes.

Main Results:

  • The algorithm accurately reflected clinical findings in a case of exotropia (estimated deviation: -10.1 degrees left eye).
  • In a subject with no history, estimated gaze deviation was 4.3 degrees right eye and -0.5 degrees left eye.
  • A strong correlation (Spearman's r=0.961-0.965) was found between left and right eye gaze angles in 10 control subjects.

Conclusions:

  • The DL-based gaze estimation algorithm shows potential for quantifying strabismus angles.
  • This non-invasive technique may provide a practical and accessible approach to strabismus assessment.
  • Further validation against clinical standards is required to enhance accuracy and clinical utility.