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

A fully automated comparative microaneurysm digital detection system

M J Cree1, J A Olson, K C McHardy

  • 1Department of Bio-medical Physics and Bio-engineering, University of Aberdeen, Foresterhill, UK.

Eye (London, England)
|January 1, 1997
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

Tissue pharmacokinetics and pharmacodynamics of AmBisome® (L-AmBis) in uninfected and infected animals and their effects on dosing regimens.

Journal of liposome research·2017
Same author

Identification of a 10/10 matched donor for patients with an uncommon haplotype is unlikely.

HLA·2017
Same author

Modelling the cost-effectiveness of adopting risk-stratified approaches to extended screening intervals in the national diabetic retinopathy screening programme in Scotland.

Diabetic medicine : a journal of the British Diabetic Association·2016
Same author

Use of computer decision support in an antimicrobial stewardship program (ASP).

Applied clinical informatics·2015
Same author

Toxicity and efficacy differences between liposomal amphotericin B formulations in uninfected and Aspergillus fumigatus infected mice.

Medical mycology·2015
Same author

Response to Dr Clearkin.

Eye (London, England)·2014
Same journal

Determinants of regression kinetics in observed stage 3 retinopathy of prematurity without plus disease.

Eye (London, England)·2026
Same journal

Oculomics and the NHS: A UK opportunity to translate eye-derived biomarkers into population health.

Eye (London, England)·2026
Same journal

Long-term follow-up and outcomes of a Diabetic Eye Screening Programme in patients aged 80 with no diabetic eye disease at baseline: should we be routinely screening this cohort?

Eye (London, England)·2026
Same journal

Real world experience with faricimab in switched neovascular AMD and evaluation of reloading versus interval matching regimes.

Eye (London, England)·2026
Same journal

"When the lens drew a continent: a cartographic clue to Alport syndrome".

Eye (London, England)·2026
Same journal

Infographic: efficacy and safety of teprotumumab in patients with thyroid eye disease of long duration and low disease activity.

Eye (London, England)·2026
See all related articles

A new automated system accurately quantifies microaneurysms in retinal images, offering objective and repeatable detection for diabetic retinopathy studies.

Area of Science:

  • Ophthalmology
  • Medical Image Analysis
  • Computer Vision

Background:

  • Diabetic retinopathy is a leading cause of vision loss.
  • Accurate quantification of microaneurysms is crucial for monitoring disease progression.
  • Current methods for microaneurysm detection can be subjective and time-consuming.

Purpose of the Study:

  • To develop and validate a fully automated digital image processing system for quantifying microaneurysms in fluorescein angiograms.
  • To compare the performance of the automated system with human clinicians in microaneurysm detection.

Main Methods:

  • Development of an automated computer processing system for retinal image analysis.
  • System includes image registration, region-of-interest selection, microaneurysm detection, and serial image comparison.

Related Experiment Videos

  • Training and testing of the microaneurysm detector using a database of diabetic patient images.

    • Main Results:

    • The automated microaneurysm detector achieved 82% sensitivity with 2.0 false-positives per image during training.
    • On an independent test set, the detector achieved 82% sensitivity with 5.7 false-positives per image.
    • Clinician performance, based on ROC curves, showed 3.2 false-positives per image at 82% sensitivity.

    Conclusions:

    • The developed computer system reliably detects microaneurysms in digitised fluorescein angiograms.
    • The system offers advantages of objectivity, repeatability, speed, and full automation for microaneurysm quantification.
    • This automated approach has the potential to improve the monitoring and management of diabetic retinopathy.