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

Advanced CNN Deep Learning Model for Diabetic Retinopathy Classification.

Noor Ali Sadek1, Ziad Tarik Al-Dahan2, Suzan Amana Rattan3

  • 1Department of Biomedical Engineering, Al-Nahrain University, Baghdad, Iraq.

Journal of Biomedical Physics & Engineering
|June 15, 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

Effects of fluoroquinolone antibiotics on extracellular matrix-related phenotypes in tendon cells.

Scientific reports·2026
Same author

Corneal epithelial mapping after accelerated corneal cross-linking: early remodeling patterns.

International ophthalmology·2026
Same author

Transcriptional Control of Hepatocellular Carcinoma Cells Aggressiveness by AAV2/8-Mediated Delivery of Human Centenarian-Associated SIRT6 N308K/A313S.

Cancers·2026
Same author

The impact of type 2 diabetes on tendon material properties and locomotor function in the db/db mouse.

Experimental physiology·2026
Same author

Refractive Errors and Vision Problems in Autistic Children: Insights into Parental Awareness in Iraq.

Journal of autism and developmental disorders·2025
Same author

Regional quantification of glycosaminoglycans and their association with collagen fibril ultrastructure in the sclera following enzymatic degradation.

Journal of the mechanical behavior of biomedical materials·2025
Same journal

Occupational Exposure to Blue Light Emitted from Neonatal Phototherapy Devices Alters the Sleep Quality of NICU Nurses.

Journal of biomedical physics & engineering·2026
Same journal

Diagnosing Epilepsy using Entropy Measures and Embedding Parameters of EEG Signals.

Journal of biomedical physics & engineering·2026
Same journal

<i>In Vitro</i> Radiosensitizing Effects of Urtica Dioica Leaf Aqueous Extract on the Killing of U87MG Glioblastoma Cell Line.

Journal of biomedical physics & engineering·2026
Same journal

Bacterial Adaptation to Radiofrequency Electromagnetic Fields Based on Experiences from Ionizing Radiation.

Journal of biomedical physics & engineering·2026
Same journal

Determining the Correlation and Effect of Rectal and Bladder Volume Change in Shift of Planning Target Volume and Calculating Planning Target Volume Margin with Van Herk Formula in Prostate Cancer Tomotherapy.

Journal of biomedical physics & engineering·2026
Same journal

Neural Changes in Patients with Post-Traumatic Anosmia: Insights from Resting-State fMRI.

Journal of biomedical physics & engineering·2026
See all related articles
This summary is machine-generated.

This study developed a deep learning system for early Diabetic Retinopathy (DR) detection. Logistic regression models achieved high accuracy, offering a promising tool for preventing vision loss in diabetes patients.

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Diabetic Retinopathy (DR) is a growing global complication of Diabetes Mellitus (DM).
  • Early detection and treatment of DR are crucial to prevent vision loss.
  • Deep Learning (DL) offers potential for early DR grading and risk reduction.

Purpose of the Study:

  • To develop a low-cost, fast, and accurate automated system using DL for early DR detection and classification.
  • To utilize DL techniques for grading DR severity from retina fundus images.
  • To aid clinicians in reducing patient vision loss risk.

Main Methods:

  • A cross-sectional study utilizing three DL models: Convolutional Neural Networks (CNNs), decision tree, and logistic regression.
  • Categorization of DR severity across three distinct datasets: Iraqi, Indian Diabetic Retinopathy Image Dataset (IDRiD), and Eyepacs.
Keywords:
CNNDecision TreesDeep LearningDiabetic RetinopathyEyePACSIDRiDIraqi DatasetLogistic Regression

Related Experiment Videos

  • Comparative analysis of model performance on clinical datasets.

    • Main Results:

    • Logistic regression demonstrated the highest accuracy across all datasets (99% to 99.4%).
    • The Iraqi dataset yielded the highest accuracy with the logistic regression model.
    • Decision tree models showed the lowest accuracy, ranging from 95.2% to 96.0%.

    Conclusions:

    • Logistic regression is the most effective DL model for DR classification.
    • Automated DR detection systems using DL can significantly improve diagnostic accuracy.
    • This approach supports timely intervention to preserve patient vision.