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

Deep learning in glaucoma referral: Performance assessment using a real-world setting.

Acta ophthalmologica·2026
Same author

The Quest for Automated Pediatric Sleep Scoring: Are We There Yet?

Sleep·2026
Same author

Modeling day-long ECG signals to predict heart failure risk with explainable AI.

NPJ digital medicine·2026
Same author

Update on the structure-function relationship in glaucoma.

Survey of ophthalmology·2026
Same author

Glaucoma drainage devices as a novel treatment option in the management of recurrent iris cysts.

European journal of ophthalmology·2026
Same author

Outcomes of Ab Interno 63 µm vs. 45 µm XEN<sup>®</sup> Gel Stent in Open-Angle Glaucoma: A Five-Year Follow-Up Study.

Journal of clinical medicine·2026

Related Experiment Video

Updated: Jul 27, 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

FundusQ-Net: A regression quality assessment deep learning algorithm for fundus images quality grading.

Or Abramovich1, Hadas Pizem2, Jan Van Eijgen3

  • 1The Faculty of Biomedical Engineering, Technion-IIT, Haifa, Israel.

Computer Methods and Programs in Biomedicine
|June 7, 2023
PubMed
Summary

A new deep learning (DL) model, FundusQ-Net, accurately estimates the quality of fundus images for diagnosing eye diseases. This automated tool aids in faster and more reliable detection of conditions like glaucoma and diabetic retinopathy.

Keywords:
Deep learningFundus imageQuality assessmentSemi supervised learning

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K
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 27, 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
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K
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
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Ophthalmological conditions like glaucoma, diabetic retinopathy, and age-related macular degeneration are leading causes of vision loss.
  • Accurate diagnosis relies on high-quality fundus images, necessitating automated quality assessment tools.

Purpose of the Study:

  • To develop a novel fundus image quality scale.
  • To create a deep learning (DL) model for automated fundus image quality estimation.

Main Methods:

  • A DL regression model (Inception-V3) was trained using 89,947 fundus images from six databases.
  • 1245 images were graded by ophthalmologists, and the remaining were used for pre-training and semi-supervised learning.
  • The model, FundusQ-Net, was evaluated on internal and external test sets.

Main Results:

  • FundusQ-Net achieved a mean absolute error of 0.61 on an internal test set.
  • The model demonstrated 99% accuracy in binary classification on the external DRIMDB database.

Conclusions:

  • The developed algorithm offers a robust solution for automated fundus image quality grading.
  • This tool can enhance the efficiency and reliability of diagnosing major ophthalmological pathologies.