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

Correction: Resilient back-propagation machine learning-based classification on fundus images for retinal microaneurysm detection.

International ophthalmology·2026
Same author

YOLOv8's advancements in tuberculosis identification from chest images.

Frontiers in big data·2024
See all related articles

Related Experiment Video

Updated: Jul 2, 2025

An Acute Retinal Model for Evaluating Blood Retinal Barrier Breach and Potential Drugs for Treatment
09:33

An Acute Retinal Model for Evaluating Blood Retinal Barrier Breach and Potential Drugs for Treatment

Published on: September 13, 2016

7.2K

Resilient back-propagation machine learning-based classification on fundus images for retinal microaneurysm

S Steffi1, W R Sam Emmanuel2

  • 1Department of Computer Science, Nesamony Memorial Christian College Affiliated to Manonmaniam Sundaranar University, Abishekapatti, Tirunelveli, Tamil Nadu, 627012, India. steffis992@gmail.com.

International Ophthalmology
|February 17, 2024
PubMed
Summary

This study introduces a novel, non-invasive method for detecting retinal microaneurysms using fundus scans. The approach achieves high accuracy, aiding in early diabetic retinopathy diagnosis.

Keywords:
Adaptive thresholdingFundus imageGradientMachine learningRetinal microaneurysms

More Related Videos

Monitoring Dynamic Growth of Retinal Vessels in Oxygen-Induced Retinopathy Mouse Model
10:32

Monitoring Dynamic Growth of Retinal Vessels in Oxygen-Induced Retinopathy Mouse Model

Published on: April 2, 2021

3.5K
Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

21.6K

Related Experiment Videos

Last Updated: Jul 2, 2025

An Acute Retinal Model for Evaluating Blood Retinal Barrier Breach and Potential Drugs for Treatment
09:33

An Acute Retinal Model for Evaluating Blood Retinal Barrier Breach and Potential Drugs for Treatment

Published on: September 13, 2016

7.2K
Monitoring Dynamic Growth of Retinal Vessels in Oxygen-Induced Retinopathy Mouse Model
10:32

Monitoring Dynamic Growth of Retinal Vessels in Oxygen-Induced Retinopathy Mouse Model

Published on: April 2, 2021

3.5K
Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

21.6K

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Machine Learning

Background:

  • Early detection of diabetic retinopathy relies on identifying retinal microaneurysms.
  • Traditional retinography struggles with the small size and poor differentiation of microaneurysms.
  • Fluorescein angiography improves detection but is too invasive for routine screening.

Purpose of the Study:

  • To develop a novel, non-invasive method for detecting retinal microaneurysms from fundus images.
  • To leverage circular reference-based shape features (CR-SF) and radial gradient-based texture features (RG-TF).

Main Methods:

  • Extracting CR-SF and RG-TF from candidate microaneurysms.
  • Utilizing a back-propagation machine learning algorithm for training.
  • Comparing extracted features from test images to classify microaneurysm presence.

Main Results:

  • The method was evaluated on four diverse datasets (MESSIDOR, Diaretdb1, e-ophtha-MA, ROC).
  • Achieved high performance metrics: 98.01% accuracy, 98.74% sensitivity, 97.12% specificity, and 91.72% AUC.
  • Demonstrated significant potential for automated microaneurysm detection.

Conclusions:

  • The proposed fundus scan-based approach effectively detects retinal microaneurysms.
  • The non-invasive technique offers high accuracy and sensitivity.
  • This method shows promise for routine diabetic retinopathy screening and related conditions.