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

Reply: Accuracy of new-generation and traditional intraocular lens power calculation formulas in pediatric primary implantation.

Journal of cataract and refractive surgery·2026
Same author

Adaptive contour prediction in postoperative OCT imaging using domain-adaptive generative adversarial networks.

Photodiagnosis and photodynamic therapy·2026
Same author

Anisometropia at Age 7 After Bilateral Secondary Intraocular Lens Implantation at 2 to Younger than 6 Years for Pediatric Aphakia: The CCPMOH Report.

Ophthalmology science·2026
Same author

Discussion on "INTACT: A method for integration of longitudinal physical activity data from multiple sources" by Jingru Zhang, Erjia Cui, Hongzhe Li, and Haochang Shou.

Biometrics·2026
Same author

An AI-Based OCT System to Detect Diabetic Macular Edema: A Prospective Validation and Noninferiority Randomized Clinical Trial.

JAMA·2026
Same author

DeepAdapter: a generalisable algorithm integrating self-supervised learning and unsupervised domain adaptation for robust retinopathy of prematurity screening.

The British journal of ophthalmology·2026

Related Experiment Video

Updated: Jul 12, 2025

Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

21.7K

Deep Learning Performance of Ultra-Widefield Fundus Imaging for Screening Retinal Lesions in Rural Locales.

Tingxin Cui1, Duoru Lin1, Shanshan Yu1

  • 1State Key Laboratory of Ophthalmology, Zhongshan Ophthalmic Center, Sun Yat-sen University, Guangdong Provincial Key Laboratory of Ophthalmology and Vision Science, Guangdong Provincial Clinical Research Center for Ocular Diseases, Guangzhou, China.

JAMA Ophthalmology
|October 19, 2023
PubMed
Summary

Deep learning systems (DLSs) show excellent performance in screening for five retinal lesions using ultra-widefield (UWF) fundus images in rural populations. However, factors like image quality and lesion complexity may impact DLS performance, requiring consideration during model development.

More Related Videos

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

2.8K
Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases
07:22

Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases

Published on: March 11, 2016

11.5K

Related Experiment Videos

Last Updated: Jul 12, 2025

Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

21.7K
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

2.8K
Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases
07:22

Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases

Published on: March 11, 2016

11.5K

Area of Science:

  • Ophthalmology and medical imaging analysis
  • Artificial intelligence in healthcare

Background:

  • Retinal diseases are a leading cause of irreversible blindness globally.
  • Early detection of retinal lesions is crucial for preventing vision loss, particularly in underserved rural areas.
  • Ultra-widefield (UWF) fundus imaging offers a broader view of the retina compared to traditional methods.

Purpose of the Study:

  • To evaluate the performance of a deep learning system (DLS) for screening multiple retinal lesions using UWF fundus images in a rural patient population.
  • To explore the feasibility of DLS-based screening in resource-limited rural settings.

Main Methods:

  • A diagnostic study utilizing a pre-developed DLS for screening five specific retinal lesions (exudates/drusen, glaucomatous optic neuropathy, hemorrhage, lattice degeneration/retinal breaks, retinal detachment).
  • Screening was conducted in 24 villages, analyzing 6222 eyes from 3149 participants using UWF fundus images.
  • DLS performance was compared against ophthalmologist analysis and previous model development validation, assessing image quality, lesion proportions, and lesion complexity.

Main Results:

  • The DLS achieved a mean Area Under the Curve (AUC) of 0.918 for detecting five retinal lesions in the rural cohort.
  • Performance was lower than the internal validation stage (AUC 0.998), with increased instances of poor image quality (13.8%) and greater lesion complexity observed in rural images.
  • Significant variations in lesion proportions and increased complexity of lesion composition were noted in the rural screening data compared to the development dataset.

Conclusions:

  • The DLS demonstrates excellent potential as a screening tool for retinal lesions in rural settings using UWF fundus images.
  • Suboptimal image quality, diverse lesion prevalence, and complex lesion presentations in rural populations can affect DLS accuracy.
  • Future DLS development should account for these real-world screening challenges to optimize performance in targeted populations.