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

Response to the Letter to the Editor Entitled "A Missing Genomic Dimension: The Small but Central Mitochondrial Genome in Diabetic Kidney Disease Genetics".

Kidney international reports·2026
Same author

A Structured Review of Deep Learning Approaches and Image-Preprocessing Techniques for Automated Contact Allergy Patch Test Interpretation.

Medical sciences (Basel, Switzerland)·2026
Same author

The Complementary Role of Optical Coherence Tomography and Fluorescein Angiography in Diagnosing and Monitoring Retinal Vascular Status in Susac Syndrome: Two Case Reports.

Reports (MDPI)·2026
Same author

Growth patterns in patients with congenital adrenal hyperplasia analyzed by the QEPS growth model.

Frontiers in endocrinology·2026
Same author

DNA Oxidation and Expression of Repair Enzymes in Organ- Cultured Human Limbal Epithelium.

International journal of molecular sciences·2026
Same author

Deep Optic Nerve Head Structural Alterations in Adults with Cystic Fibrosis.

Journal of clinical medicine·2026

Related Experiment Video

Updated: Aug 2, 2025

Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases
07:22

Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases

Published on: March 11, 2016

11.5K

Automatic Detection of Microaneurysms in Fundus Images Using an Ensemble-Based Segmentation Method.

Vidas Raudonis1, Arturas Kairys1, Rasa Verkauskiene2

  • 1Automation Department, Kaunas University of Technology, 51368 Kaunas, Lithuania.

Sensors (Basel, Switzerland)
|April 13, 2023
PubMed
Summary

A new method automatically detects microaneurysms in eye images using deep learning. This approach shows high accuracy for early diabetic retinopathy detection.

Keywords:
diabetic retinopathy (DR)encoder-decoder deep neural networkimage segmentationmicroaneurysms (MAs)

More Related Videos

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

2.8K
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.4K

Related Experiment Videos

Last Updated: Aug 2, 2025

Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases
07:22

Quantitative Fundus Autofluorescence for the Evaluation of Retinal Diseases

Published on: March 11, 2016

11.5K
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

2.8K
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.4K

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Diabetic retinopathy is a leading cause of vision loss.
  • Early detection of microaneurysms is crucial for timely treatment.
  • Automated analysis of retinal images can improve diagnostic efficiency.

Purpose of the Study:

  • To present a novel method for automatic microaneurysm detection in color fundus images.
  • To evaluate the performance of an ensemble deep learning model for this task.

Main Methods:

  • The method involves breaking fundus images into smaller patches.
  • Segmentation models, including U-Net, ResNet34-UNet, and UNet++, are used for inference.
  • A final segmentation map is reconstructed from the output patches.

Main Results:

  • The ensemble-based deep learning model achieved a Dice score of 0.95.
  • The model obtained an Intersection over Union (IoU) value of 0.91.
  • The ensemble model outperformed individual network architectures.

Conclusions:

  • The proposed ensemble-based model demonstrates high accuracy in microaneurysm detection.
  • This method holds significant potential for the early detection of diabetic retinopathy.
  • Automated analysis can aid in clinical screening and patient management.