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

On the use of 3D modeling, reconstruction and printing techniques for the development of a total ossicular replacement prosthesis: a case study of cholesteatoma.

Biomedical materials (Bristol, England)·2025
Same author

STEFF: Spatio-temporal EfficientNet for dynamic texture classification in outdoor scenes.

Heliyon·2024
Same author

Diabetic retinopathy screening through artificial intelligence algorithms: A systematic review.

Survey of ophthalmology·2024
Same author

MedKnee: A New Deep Learning-Based Software for Automated Prediction of Radiographic Knee Osteoarthritis.

Diagnostics (Basel, Switzerland)·2024
Same author

On the Implementation of a Post-Pandemic Deep Learning Algorithm Based on a Hybrid CT-Scan/X-ray Images Classification Applied to Pneumonia Categories.

Healthcare (Basel, Switzerland)·2023
Same author

Identification of the novel SDR42E1 gene that affects steroid biosynthesis associated with the oculocutaneous genital syndrome.

Experimental eye research·2021

Related Experiment Video

Updated: Jul 29, 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

2.8K

Application of Deep Learning Methods in a Moroccan Ophthalmic Center: Analysis and Discussion.

Zineb Farahat1,2, Nabila Zrira1, Nissrine Souissi1

  • 1LISTD Laboratory, Ecole Nationale Supérieure des Mines de Rabat, Rabat 10000, Morocco.

Diagnostics (Basel, Switzerland)
|May 27, 2023
PubMed
Summary

Artificial intelligence (AI) using deep learning (DL) effectively detects early signs of diabetic retinopathy (DR), including hemorrhages and exudates, in fundus images. This AI tool shows high accuracy, aiding in early diagnosis and potentially preventing vision loss.

Keywords:
U-NetYOLOv5artificial intelligenceautomatic screeningdeep learningdiabetic retinopathyexudateshemorrhagesmethod

More Related Videos

VisualEyes: A Modular Software System for Oculomotor Experimentation
10:41

VisualEyes: A Modular Software System for Oculomotor Experimentation

Published on: March 25, 2011

12.8K
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

856

Related Experiment Videos

Last Updated: Jul 29, 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

2.8K
VisualEyes: A Modular Software System for Oculomotor Experimentation
10:41

VisualEyes: A Modular Software System for Oculomotor Experimentation

Published on: March 25, 2011

12.8K
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

856

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Diabetic retinopathy (DR) is a leading cause of vision loss in working-aged adults.
  • Early detection of DR signs like hemorrhages and exudates is crucial for timely intervention.
  • Advancements in AI and DL offer new possibilities for noninvasive medical image analysis.

Purpose of the Study:

  • To develop and evaluate AI-based methods for detecting early signs of diabetic retinopathy (DR).
  • To assess the performance of U-Net for segmentation and YOLOv5 for detection of DR indicators.
  • To compare AI performance against human expert and resident doctor diagnoses.

Main Methods:

  • Applied U-Net deep learning model for segmenting hemorrhages and exudates in color fundus images.
  • Utilized YOLOv5 deep learning model for identifying and localizing hemorrhages and exudates.
  • Collected on-site data from Cheikh Zaïd Foundation's Ophthalmic Center in Rabat.

Main Results:

  • The U-Net segmentation achieved 85% specificity, 85% sensitivity, and an 85% Dice score.
  • The AI detection software identified 100% of diabetic retinopathy signs.
  • Expert doctor detected 99% of DR signs, while a resident doctor detected 84%.

Conclusions:

  • AI, specifically DL models like U-Net and YOLOv5, demonstrates high efficacy in detecting diabetic retinopathy signs.
  • AI-powered computer-aided diagnosis tools can assist clinicians in early DR detection, potentially reducing the burden on healthcare professionals.
  • The developed AI methods show promising results for noninvasive, rapid, and accurate assessment of retinal conditions.