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 Video

Updated: Apr 23, 2026

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

6.0K

Automatic exudate detection by fusing multiple active contours and regionwise classification.

Balazs Harangi1, Andras Hajdu1

  • 1Faculty of Informatics, University of Debrecen, POB 12, 4010 Debrecen, Hungary.

Computers in Biology and Medicine
|September 26, 2014
PubMed
Summary
This summary is machine-generated.

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

Novel common target genes for breast cancer and colorectal cancer: a Mendelian randomization and spatial transcriptomics study.

Discover oncology·2025
Same author

The microbiome in cancer.

iMeta·2025
Same author

Space Dentistry Combined With Remote and AI Technologies, a Necessity for Long-Term Stays: Thoughts of US Astronauts' Unexpected Stay.

Oral diseases·2025
Same author

Improving Cell Detection and Tracking in Microscopy Images Using YOLO and an Enhanced DeepSORT Algorithm.

Sensors (Basel, Switzerland)·2025
Same author

A Hybrid Compact Convolutional Transformer with Bilateral Filtering for Coffee Berry Disease Classification.

Sensors (Basel, Switzerland)·2025
Same author

Generation of Synthetic Non-Homogeneous Fog by Discretized Radiative Transfer Equation.

Journal of imaging·2025

This study introduces an automated method for detecting exudates in retinal images. The approach accurately segments lesions and outperforms existing algorithms for improved diabetic retinopathy screening.

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Computer Vision

Background:

  • Diabetic retinopathy is a leading cause of vision loss, characterized by lesions like exudates in retinal images.
  • Accurate detection and segmentation of exudates are crucial for timely diagnosis and treatment of diabetic retinopathy.
  • Current automated methods for exudate detection face challenges in precise segmentation and classification.

Purpose of the Study:

  • To develop and validate a robust, automated method for detecting and segmenting exudates in digital fundus images.
  • To improve the accuracy of exudate detection and classification compared to existing state-of-the-art algorithms.
  • To provide a tool that aids in the early diagnosis and management of diabetic retinopathy.

Main Methods:

  • A three-stage approach involving candidate extraction using grayscale morphology, precise contour segmentation with active contours, and classification of exudates.
Keywords:
Active contour methodContours combinationDiabetic retinopathy screeningExudate detectionMultiple pre-processingRegion-wise classification

More Related Videos

Automated Detection and Analysis of Exocytosis
13:28

Automated Detection and Analysis of Exocytosis

Published on: September 11, 2021

3.1K

Related Experiment Videos

Last Updated: Apr 23, 2026

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
09:16

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

6.0K
Automated Detection and Analysis of Exocytosis
13:28

Automated Detection and Analysis of Exocytosis

Published on: September 11, 2021

3.1K
  • Utilizing diverse pre-processing methods to generate multiple contour candidates for enhanced segmentation accuracy.
  • Employing a region-wise classifier with a Naïve-Bayes algorithm, optimized by adaptive boosting, for false candidate removal.

    • Main Results:

    • The proposed method achieved high accuracy in both segmenting exudate regions and detecting exudates at the image level.
    • Quantitative evaluations on publicly available datasets demonstrated superior performance compared to several state-of-the-art exudate detection algorithms.
    • The adaptive boosting technique effectively optimized the Naïve-Bayes classifier, improving the overall detection accuracy.

    Conclusions:

    • The developed automated method offers a promising solution for accurate exudate detection in digital fundus images.
    • This approach has the potential to significantly aid ophthalmologists in the diagnosis and monitoring of diabetic retinopathy.
    • The method's strong performance suggests its applicability in clinical settings for automated retinal image analysis.