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: May 31, 2026

LipidUNet-Machine Learning-Based Method of Characterization and Quantification of Lipid Deposits Using iPSC-Derived Retinal Pigment Epithelium
06:16

LipidUNet-Machine Learning-Based Method of Characterization and Quantification of Lipid Deposits Using iPSC-Derived Retinal Pigment Epithelium

Published on: July 28, 2023

Automated drusen detection in retinal images using analytical modelling algorithms.

André D Mora1, Pedro M Vieira, Ayyakkannu Manivannan

  • 1Center of Technologies and Systems, Uninova, Campus da FCT-UNL, 2829-516 Caparica, Portugal. atbdm@fct.unl.pt

Biomedical Engineering Online
|July 14, 2011
PubMed
Summary

This study introduces Automatic Drusen Deposits Detection and quantification in Retinal Images (AD3RI), an automated method for analyzing drusen in Age-Related Macular Degeneration (ARMD). AD3RI offers reproducible and accurate drusen quantification, outperforming traditional methods.

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

European survey on laser safety management in medical settings.

Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB)·2026
Same author

Beyond Snoring: Unexpected Presentation of Obstructive Sleep Apnea.

Cureus·2026
Same author

Multiple mask and boundary scoring R-CNN with cGAN data augmentation for bladder tumor segmentation in WLC videos.

Artificial intelligence in medicine·2024
Same author

Colorimetric Detection of SARS-CoV-2 Using Plasmonic Biosensors and Smartphones.

ACS applied materials & interfaces·2022
Same author

Detection of bladder cancer with feature fusion, transfer learning and CapsNets.

Artificial intelligence in medicine·2022
Same author

Multi-pathology detection and lesion localization in WCE videos by using the instance segmentation approach.

Artificial intelligence in medicine·2021

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Computer Vision

Background:

  • Drusen are key indicators in ageing macula and exudative Age-Related Macular Degeneration (ARMD).
  • Manual drusen evaluation in retinal images is time-consuming and lacks reproducibility.
  • Quantitative analysis of drusen is crucial for ARMD monitoring.

Purpose of the Study:

  • To develop and validate an automated methodology for drusen detection and quantification in retinal images.
  • To compare the performance of the automated method against expert grading and a standard thresholding technique.

Main Methods:

  • Developed Automatic Drusen Deposits Detection and quantification in Retinal Images (AD3RI) using digital image processing.
  • Implemented image pre-processing for illumination correction and contrast normalization.

Related Experiment Videos

Last Updated: May 31, 2026

LipidUNet-Machine Learning-Based Method of Characterization and Quantification of Lipid Deposits Using iPSC-Derived Retinal Pigment Epithelium
06:16

LipidUNet-Machine Learning-Based Method of Characterization and Quantification of Lipid Deposits Using iPSC-Derived Retinal Pigment Epithelium

Published on: July 28, 2023

  • Employed gradient-based segmentation and Modified Gaussian function fitting for drusen detection and modeling.

    • Main Results:

    • AD3RI demonstrated high agreement with expert grading (Intraclass Correlation Coefficient: 0.92).
    • The method achieved high reproducibility (Coefficient of Variation: 28.8%) compared to manual methods.
    • AD3RI showed superior performance over the Global Threshold method in specificity and kappa coefficient.

    Conclusions:

    • AD3RI provides accurate and reproducible drusen quantification, comparable to expert evaluations.
    • The automated method offers significant advantages for the evaluation and follow-up of ARMD.
    • AD3RI outperforms traditional thresholding methods, offering a more reliable tool for clinical use.