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 Videos

Automated diabetic retinopathy grading and screening using deep learning.

Ahmed M Nashaat Ali Rady1, Mohamed A Azim2,3, Ahmed AbdelMoety4

  • 1Department of Ophthalmology, Kazan Federal University, Cairo Branch, Cairo, Egypt.

International Journal of Retina and Vitreous
|July 1, 2026
PubMed
Summary

Related Concept Videos

Diabetic Retinopathy01:27

Diabetic Retinopathy

DefinitionDiabetic retinopathy is a microvascular complication of diabetes affecting the retinal blood vessels.Risk FactorsDiabetic retinopathy is present in almost all individuals with type 1 diabetes and more than 60% of those with type 2 diabetes after two decades of disease.The risk increases with poor glycemic control, hypertension, dyslipidemia, smoking, pregnancy, and puberty.Although cataracts and glaucoma are also more frequent in people with diabetes, retinopathy remains the leading...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Comparative evaluation of deep learning architectures for microbial colony classification in microbiological imaging.

BMC microbiology·2026
Same author

EfficientNet-driven deep learning for accurate detection of faults in photovoltaic cells.

PloS one·2026
Same author

Comparative analysis of deep learning architectures in solar power prediction.

Scientific reports·2025
Same author

Predicting cancer risk using machine learning on lifestyle and genetic data.

Scientific reports·2025
Same author

ResNet-based image processing approach for precise detection of cracks in photovoltaic panels.

Scientific reports·2025
Same author

Comparative analysis of machine learning techniques for temperature and humidity prediction in photovoltaic environments.

Scientific reports·2025

This study developed a Deep Learning pipeline for diabetic retinopathy (DR) grading and screening. The pipeline shows promise for accurate DR detection and classification, aiding resource-limited settings.

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Diabetic Retinopathy (DR) is a leading cause of vision loss.
  • Automated DR detection and grading are crucial for timely intervention.
  • Resource-limited settings require scalable and accurate screening tools.

Purpose of the Study:

  • To develop and benchmark a Deep Learning (DL) pipeline for automated detection and five-level grading of Diabetic Retinopathy (DR).
  • To create a high-performance binary screening endpoint (DR vs. No DR) for scalable use in resource-limited settings.

Main Methods:

  • Utilized a publicly available dataset of 3,500 color fundus photographs graded using the International Clinical Diabetic Retinopathy (ICDR) scale.
  • Applied a standardized workflow across eight Convolutional Neural Network (CNN) architectures, including transfer learning strategies.
Keywords:
Artificial intelligence in ophthalmologyBinary classificationDeep learningDiabetic retinopathyMedical image analysisMulti-class classification

Related Experiment Videos

  • Employed a 70/20/10 train/validation/test split with data augmentation and class-balanced sampling.

    • Main Results:

    • For five-class grading, VGG16 achieved the highest accuracy (0.7686), while EfficientNetV2B2 yielded the best macro AUROC (0.9158).
    • Misclassifications were primarily between adjacent severity levels.
    • For binary DR screening, modern backbones achieved accuracy ≥0.94, with AUROC ≈0.982-0.990 and AUPRC ≈0.987-0.992.

    Conclusions:

    • The developed DL pipeline offers robust multiclass DR grading and highly discriminative binary screening.
    • Operating-point calibration supports sensitivity- or specificity-oriented triage.
    • The pipeline can enhance teleophthalmology and task-shifted DR screening programs to reduce preventable vision loss.