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

A Robust Intelligent CNN Model Enhanced with Gabor-Based Feature Extraction, SMOTE Balancing, and Adam Optimization

Asri Mulyani1,2, Muljono1, Purwanto1

  • 1Faculty of Computer Science, Universitas Dian Nuswantoro, Semarang 50131, Indonesia.

Journal of Imaging
|May 26, 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

NCT-CXR: Enhancing Pulmonary Abnormality Segmentation on Chest X-Rays Using Improved Coordinate Geometric Transformations.

Journal of imaging·2025
Same author

Genetic Algorithm-based Convolutional Neural Network Feature Engineering for Optimizing Coronary Heart Disease Prediction Performance.

Healthcare informatics research·2024
Same author

Participation, not penalties: Community involvement and equitable governance contribute to more effective multiuse protected areas.

Science advances·2022
Same author

Recognizing peripheral ecosystems in marine protected areas: A case study of golden jellyfish lakes in Raja Ampat, Indonesia.

Marine pollution bulletin·2020
Same author

Integrating impact evaluation in the design and implementation of monitoring marine protected areas.

Philosophical transactions of the Royal Society of London. Series B, Biological sciences·2015
Same author

Prediction models for early risk detection of cardiovascular event.

Journal of medical systems·2012
This summary is machine-generated.

A novel Robust Intelligent CNN Model (RICNN) enhances diabetic retinopathy (DR) classification by integrating Gabor filters for microvascular pattern detection. This AI approach shows improved accuracy in identifying DR severity levels.

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Diabetic retinopathy (DR) is a primary cause of vision loss globally.
  • Accurate, automated DR severity classification is crucial for timely intervention.
  • Standard Convolutional Neural Networks (CNNs) face challenges in detecting subtle microvascular changes characteristic of DR.

Purpose of the Study:

  • To develop an improved deep learning model for multi-grade diabetic retinopathy classification.
  • To enhance the model's ability to identify fine, high-frequency microvascular patterns.
  • To improve the sensitivity and accuracy of automated DR diagnosis.

Main Methods:

  • Proposed a Robust Intelligent CNN Model (RICNN) integrating Gabor filters for texture feature extraction.
Keywords:
Gabor filterclassificationdeep learningdiabetic retinopathyfeature extractionintelligent decision supportmedical image

Related Experiment Videos

  • Implemented feature-level fusion by concatenating Gabor features with CNN representations.
  • Utilized Synthetic Minority Oversampling Technique (SMOTE) for data balancing and the Adam optimizer for training.
  • Applied Gabor filters for orientation- and frequency-sensitive preprocessing.

    • Main Results:

    • The RICNN achieved 89% accuracy, 88.75% precision, 89% recall, and 89% F1-score on the Messidor dataset.
    • Demonstrated high AUC values: 97% for Severe DR and 99% for Proliferative DR.
    • The Gabor-enhanced approach significantly outperformed traditional LBP and Color Histogram methods.

    Conclusions:

    • The proposed RICNN effectively classifies diabetic retinopathy severity by capturing critical microvascular details.
    • Texture-aware Gabor enhancement offers a significant advantage over other feature extraction techniques for DR analysis.
    • The model shows strong potential for clinical decision support systems in ophthalmology.