Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jan 16, 2026

Author Spotlight: An Automated Method for Assessing Visual Acuity in Infants and Toddlers Using an Eye-Tracking System

Author Spotlight: An Automated Method for Assessing Visual Acuity in Infants and Toddlers Using an Eye-Tracking System

Published on: March 17, 2023

Evaluating Text-to-Image Generation in Pediatric Ophthalmology.

Sarah Jong¹, Qais A Dihan^2,3, Mohamed M Khodeiry⁴

¹The College of Medicine, Jones Eye Institute, University of Arkansas for Medical Sciences, Little Rock, Arkansas.

Journal of Pediatric Ophthalmology and Strabismus

|September 26, 2025

Summary

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

Utilization of anterior segment optical coherence tomography in childhood glaucoma: A systematic review.

Survey of ophthalmology·2026

Same author

Phosphodiesterase Type-5 Inhibitors and Glaucoma.

International ophthalmology clinics·2026

Same authorSame journal

Evaluating Large Language Models to Improve Spanish Patient Education on Childhood Glaucoma.

Journal of pediatric ophthalmology and strabismus·2026

Same author

Association between Glucagon-like Peptide-1 Receptor Agonist Use and Nonarteritic Anterior Ischemic Optic Neuropathy with Optic Disc Drusen.

Ophthalmology·2026

Same author

Public interest in retinal detachment in the United States: a Google Trends analysis.

International journal of retina and vitreous·2026

Same author

Immunohistochemical clinicopathologic correlation and OCT analysis of idiopathic and secondary epiretinal membrane specimens.

International journal of ophthalmology·2026

Artificial intelligence (AI) image generators struggle to accurately depict pediatric eye conditions. While AI text generation is high-quality, it requires simplification for readability, making it a useful, though imperfect, educational supplement.

Area of Science:

Ophthalmology
Artificial Intelligence
Medical Imaging
Medical Education

Background:

The increasing use of artificial intelligence (AI) in medicine necessitates evaluating its accuracy and utility.
AI-generated medical imagery and text require rigorous assessment for clinical and educational applications.
Pediatric ophthalmology presents unique challenges for accurate visual representation due to subtle pathologies.

Purpose of the Study:

To compare the quality and accuracy of AI-generated images of pediatric ophthalmology pathologies against human illustrations.
To assess the readability, quality, and accuracy of AI-generated textual information accompanying these images.

Main Methods:

A cross-sectional comparative study utilized DALL·E 3 and Gemini Advanced to generate images and text for nine common pediatric ophthalmology pathologies.

More Related Videos

Using an Automated Hirschberg Test App to Evaluate Ocular Alignment

Using an Automated Hirschberg Test App to Evaluate Ocular Alignment

Published on: March 24, 2020

$Subjective Refraction Test Using a Smartphone for Vision Screening$

Subjective Refraction Test Using a Smartphone for Vision Screening

Published on: October 18, 2024

Related Experiment Videos

Last Updated: Jan 16, 2026

Author Spotlight: An Automated Method for Assessing Visual Acuity in Infants and Toddlers Using an Eye-Tracking System

Author Spotlight: An Automated Method for Assessing Visual Acuity in Infants and Toddlers Using an Eye-Tracking System

Published on: March 17, 2023

Using an Automated Hirschberg Test App to Evaluate Ocular Alignment

Using an Automated Hirschberg Test App to Evaluate Ocular Alignment

Published on: March 24, 2020

$Subjective Refraction Test Using a Smartphone for Vision Screening$

Subjective Refraction Test Using a Smartphone for Vision Screening

Published on: October 18, 2024

AI-generated images were evaluated for anatomical and pathological accuracy, artifacts, and color.

Textual responses were assessed for quality (helpfulness, truthfulness, harmlessness) and readability (SMOG, Flesch-Kincaid Grade Level).

Main Results:

AI-generated images demonstrated poor quality and pathological accuracy, significantly inferior to human-illustrated controls.
AI-generated textual information (from ChatGPT-4o and Gemini Advanced) was of high quality but exhibited low readability (SMOG scores 8.2-8.5, FKGL 8.9-9.3).
Text-to-image generators (TTIs) were found to be inadequate for generating accurate pediatric ophthalmology images.

Conclusions:

Current text-to-image generators are insufficient for creating accurate visual depictions of pediatric ophthalmology conditions.
AI-generated text offers high-quality, accurate information but requires simplification to achieve optimal user readability.
AI tools may serve as supplemental resources in medical education, provided their outputs are carefully curated for accuracy and accessibility.