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

Synthetic data-driven diabetic retinopathy diagnosis with explainable AI: a clinically interpretable framework.

Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie·2026
Same author

Unfolding the diagnostic pipeline of diabetic retinopathy with artificial intelligence: A systematic review.

Survey of ophthalmology·2025
Same author

Morphological Abnormalities Classification of Red Blood Cells Using Fusion Method on Imbalance Datasets.

Microscopy research and technique·2025
Same author

An enumerative pre-processing approach for retinopathy severity grading using an interpretable classifier: a comparative study.

Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie·2024

Related Experiment Video

Updated: Oct 20, 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

3.0K

Deep feed forward neural network-based screening system for diabetic retinopathy severity classification using the

Hemanth Kumar Vasireddi1,2, Suganya Devi K3, Raja Reddy G N V1,4

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

Graefe'S Archive for Clinical and Experimental Ophthalmology = Albrecht Von Graefes Archiv Fur Klinische Und Experimentelle Ophthalmologie
|September 10, 2021
PubMed
Summary

Diabetic retinopathy (DR) screening can be improved with a new deep fuzzy neural network with optimization algorithm (DFNN-LOA) model. This automated system enhances diagnostic accuracy and efficiency for early detection, preventing blindness.

Keywords:
ClassificationDeep feed forward neural network (DFNN)Diabetic retinopathyLion optimization algorithm (LOA)Optic disc (OD) detectionOptimization

More Related Videos

Behavioral Assessment of Visual Function via Optomotor Response and Cognitive Function via Y-Maze in Diabetic Rats
07:41

Behavioral Assessment of Visual Function via Optomotor Response and Cognitive Function via Y-Maze in Diabetic Rats

Published on: October 23, 2020

6.1K
Author Spotlight: Understanding Retinal Vessel Resilience and Disease Progression
04:36

Author Spotlight: Understanding Retinal Vessel Resilience and Disease Progression

Published on: January 12, 2024

1.3K

Related Experiment Videos

Last Updated: Oct 20, 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

3.0K
Behavioral Assessment of Visual Function via Optomotor Response and Cognitive Function via Y-Maze in Diabetic Rats
07:41

Behavioral Assessment of Visual Function via Optomotor Response and Cognitive Function via Y-Maze in Diabetic Rats

Published on: October 23, 2020

6.1K
Author Spotlight: Understanding Retinal Vessel Resilience and Disease Progression
04:36

Author Spotlight: Understanding Retinal Vessel Resilience and Disease Progression

Published on: January 12, 2024

1.3K

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Diabetic retinopathy (DR) is a leading cause of blindness, necessitating regular screenings for early detection.
  • Increasing patient numbers strain ophthalmologists, highlighting the need for efficient automated screening systems.
  • Current DR diagnostic systems often lack optimization algorithms, limiting performance in severity classification.

Purpose of the Study:

  • To develop and evaluate an automated deep fuzzy neural network with optimization algorithm (DFNN-LOA) for DR screening.
  • To improve the speed and accuracy of DR diagnosis and severity classification.
  • To assist ophthalmologists by reducing workload and enhancing diagnostic capabilities.

Main Methods:

  • A five-phase model (DFNN-LOA) was proposed, including pre-processing, optic disc detection, segmentation, feature extraction, and severity classification.
  • The model incorporates an optimization algorithm with hyperparameter tuning to enhance neural network performance.
  • Experimental analysis was conducted using the MESSIDOR dataset.

Main Results:

  • The proposed DFNN-LOA model achieved high performance metrics on the MESSIDOR dataset.
  • Maximum accuracy reached 97.6%, sensitivity 98.4%, specificity 90.7%, F1-score 96.5%, PPV 94.6%, and NPV 97.1%.
  • The results demonstrate the model's superior characteristics for DR detection and severity classification.

Conclusions:

  • The DFNN-LOA model offers a promising automated solution for diabetic retinopathy screening.
  • The integration of an optimization algorithm significantly improves diagnostic performance.
  • This system can aid in early and accurate DR diagnosis, potentially preventing vision loss.