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 Video

Updated: Nov 29, 2025

Smartphone Fundus Photography
05:51

Smartphone Fundus Photography

Published on: July 6, 2017

39.8K

Smartphone-based diabetic macula edema screening with an offline artificial intelligence.

De-Kuang Hwang1,2, Wei-Kuang Yu1,2, Tai-Chi Lin1,2

  • 1Department of Ophthalmology, Taipei Veterans General Hospital, Taipei, Taiwan, ROC.

Journal of the Chinese Medical Association : JCMA
|November 19, 2020
PubMed
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

Systemic bias in medical consensus: how flawed panels and lack of evidence can distort definitions and guidelines: the case of Vogt-Koyanagi-Harada disease : Perspective.

Journal of ophthalmic inflammation and infection·2026
Same author

Age Spectrum of Meibomian Gland Dysfunction: A Cross-Sectional Study.

Cornea·2026
Same author

Non-Infectious Choroiditis Subdivided into Its Diverse Pathophysiological Sub-Groups Is the Best-Known and Most Appropriate Nomenclature to Date for the Reclassification and Diagnosis of Former White Dot Entities.

Diagnostics (Basel, Switzerland)·2026
Same author

Epidemiology and disease patterns of uveitis in Taiwan: A nationwide multicenter analysis.

Journal of the Formosan Medical Association = Taiwan yi zhi·2026
Same author

Evidence and Consensus-Based Imaging Guidelines in Cytomegalovirus Retinitis: Multimodal Imaging in Uveitis (MUV) Task Force - Report 15.

Ophthalmology. Retina·2026
Same author

Short-term efficacy of aflibercept 8 mg in refractory neovascular age-related macular degeneration: a retrospective case series from Taiwan.

BMC ophthalmology·2026

A new smartphone-based artificial intelligence (AI) system can accurately diagnose diabetic macular edema (DME) from optical coherence tomography (OCT) images. This offline AI tool aids in early detection and management of DME, especially in remote areas.

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Diabetic macular edema (DME) is a leading cause of vision loss requiring regular monitoring.
  • Optical coherence tomography (OCT) provides structural data but lacks direct diagnostic capabilities for DME.
  • Artificial intelligence (AI) offers potential for automated diagnosis and treatment guidance in DME.

Purpose of the Study:

  • To develop a smartphone-based, offline AI system for analyzing OCT images.
  • To provide diagnostic suggestions and medical strategies for diabetic patients at risk of DME.
  • To improve accessibility of DME screening and diagnosis.

Main Methods:

  • Retrospective collection of OCT images from DME patients (2008-2018).
  • Development of an AI model using MobileNet architecture for OCT image classification.

More Related Videos

Subjective Refraction Test Using a Smartphone for Vision Screening
05:36

Subjective Refraction Test Using a Smartphone for Vision Screening

Published on: October 18, 2024

1.4K
Author Spotlight: Development of a Smartphone-Enhanced Paper-Based Device for Rapid Dengue NS1 Detection
06:00

Author Spotlight: Development of a Smartphone-Enhanced Paper-Based Device for Rapid Dengue NS1 Detection

Published on: January 26, 2024

1.7K

Related Experiment Videos

Last Updated: Nov 29, 2025

Smartphone Fundus Photography
05:51

Smartphone Fundus Photography

Published on: July 6, 2017

39.8K
Subjective Refraction Test Using a Smartphone for Vision Screening
05:36

Subjective Refraction Test Using a Smartphone for Vision Screening

Published on: October 18, 2024

1.4K
Author Spotlight: Development of a Smartphone-Enhanced Paper-Based Device for Rapid Dengue NS1 Detection
06:00

Author Spotlight: Development of a Smartphone-Enhanced Paper-Based Device for Rapid Dengue NS1 Detection

Published on: January 26, 2024

1.7K
  • Performance evaluation using a confusion matrix.

    • Main Results:

    • The AI system achieved a 90.02% accuracy in diagnosing DME.
    • Performance is comparable to other advanced AI models like InceptionV3 and VGG16.
    • A mobile application was developed for the AI model.

    Conclusions:

    • An AI model was successfully integrated into a mobile device for offline DME diagnosis.
    • The system enables rapid screening for DME risk.
    • This tool can assist non-ophthalmologists in underserved regions.