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

Serum Iodine Concentration as a Biomarker for Individual Iodine Nutrition and Thyroid Function in Pregnant Women: A Cross-Sectional Study in Hubei Province.

Public health nutrition·2026
Same author

Distinguishing intrinsic and interfacial pyroelectric effects by polarization reversal measurements.

Nature communications·2026
Same author

Single-nucleotide variant profiling in liquid biopsy with RECO-Cas.

Science advances·2026
Same author

SMPD1 modulates malignant progress of osteosarcoma through ferroptosis pathway.

Tissue & cell·2026
Same author

Mean corpuscular Hb and red cell distribution width for early screening of non-anaemic Fe deficiency in children: a retrospective study.

The British journal of nutrition·2026
Same author

BCL6B suppresses acute myeloid leukemia progression by transcriptionally repressing GGT5 and modulating MAPK signaling.

Biology direct·2026

Related Experiment Video

Updated: Dec 16, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.2K

Automatic identification of myopia based on ocular appearance images using deep learning.

Yahan Yang1, Ruiyang Li1, Duoru Lin1

  • 1State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangzhou, China.

Annals of Translational Medicine
|July 4, 2020
PubMed
Summary

This study developed a deep learning system (DLS) for myopia detection in children using ocular images, achieving high accuracy. The DLS shows promise for remote monitoring and reducing the burden of childhood myopia.

Keywords:
Deep learningmyopia

More Related Videos

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

1.2K
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

15.5K

Related Experiment Videos

Last Updated: Dec 16, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.2K
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

1.2K
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

15.5K

Area of Science:

  • Ophthalmology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Myopia is a leading cause of visual impairment in children globally.
  • Current manual screenings are resource-intensive and face challenges in availability and cost.
  • Deep learning and computer vision offer potential for efficient disease screening.

Purpose of the Study:

  • To develop and evaluate a deep learning system (DLS) for myopia detection using ocular appearance images.
  • To assess the DLS performance in a prospective clinical trial.
  • To explore the potential of DLS for large-scale, remote myopia screening in children.

Main Methods:

  • A deep learning system was trained on 2,350 ocular images from children aged 6-18.
  • Myopia was defined as spherical equivalent refraction (SER) ≤-0.5 diopters.
  • Saliency maps and grad-CAMs were used for interpretability; performance was validated in a prospective trial.

Main Results:

  • The DLS achieved an area under the curve (AUC) of 0.9270, with 81.13% sensitivity and 86.42% specificity.
  • The DLS focused on ocular regions, particularly the temporal sclera.
  • In a prospective trial, the DLS outperformed ophthalmologists in sensitivity and specificity.

Conclusions:

  • Deep learning applied to ocular images provides accurate myopia screening in children.
  • The DLS enables remote monitoring of refractive status, aiding in myopia management.
  • This technology can significantly benefit public health by mitigating myopia-associated visual impairment.