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

PCOSFusionNet: Hybrid Deep Feature Fusion Network for PCOS Classification from Ultrasound Images of Ovaries.

Ultrasonic imaging·2026
Same author

DiabeRules: a transparent rule based expert system for managing diabetes.

Health information science and systems·2025
Same author

Sentiment analysis: A survey on design framework, applications and future scopes.

Artificial intelligence review·2023
Same author

A novel centroid based sentence classification approach for extractive summarization of COVID-19 news reports.

International journal of information technology : an official journal of Bharati Vidyapeeth's Institute of Computer Applications and Management·2023
Same author

Early detection of Parkinson disease using stacking ensemble method.

Computer methods in biomechanics and biomedical engineering·2022
Same author

A critical review on diagnosis of diabetic retinopathy using machine learning and deep learning.

Multimedia tools and applications·2022

Related Experiment Video

Updated: Aug 19, 2025

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

Detection of Diabetic Retinopathy using Convolutional Neural Networks for Feature Extraction and Classification

Dolly Das1, Saroj Kumar Biswas1, Sivaji Bandyopadhyay1

  • 1Department of Computer Science and Engineering, National Institute of Technology Silchar, Cachar, Silchar, Assam 788010 India.

Multimedia Tools and Applications
|December 5, 2022
PubMed
Summary

Diabetic Retinopathy (DR) detection is improved using deep learning models. EfficientNetB4 demonstrated optimal performance in identifying DR from fundus images, offering a reliable automated diagnostic tool.

Keywords:
Convolutional Neural NetworkDeep LearningDiabetic RetinopathyFundus imageImage classification

More Related Videos

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

604
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

2.9K

Related Experiment Videos

Last Updated: Aug 19, 2025

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
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

604
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

2.9K

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Diabetic Retinopathy (DR) is a diabetes complication causing retinal damage and potential blindness.
  • Manual DR diagnosis is time-consuming, resource-dependent, and often unreliable.
  • Deep Learning (DL) offers automated solutions for DR detection from fundus images.

Purpose of the Study:

  • To comprehensively evaluate 26 state-of-the-art Deep Learning (DL) networks for Diabetic Retinopathy (DR) detection.
  • To identify the most optimal and reliable DL model for DR classification from fundus images.
  • To compare the performance and overfitting characteristics of various DL architectures.

Main Methods:

  • A comprehensive model utilizing 26 DL networks was developed.
  • Networks were trained and evaluated on the Kaggle EyePACS fundus image dataset.
  • Performance metrics including training and validation accuracy were assessed.

Main Results:

  • EfficientNetB4 emerged as the most optimal DL algorithm for DR detection.
  • EfficientNetB4 achieved 99.37% training accuracy and 79.11% validation accuracy.
  • ResNet50 exhibited the highest overfitting, while Inception V3 showed the lowest.

Conclusions:

  • DL models, particularly EfficientNetB4, show significant promise for automated DR diagnosis.
  • Automated systems can overcome limitations of manual DR detection.
  • Further research can refine DL models for improved DR screening and management.