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

Screening for diabetic retinopathy using computer based image analysis and statistical classification.

B M Ege1, O K Hejlesen, O V Larsen

  • 1Virtual Centre for Health Informatics, Department of Medical Informatics and Image Analysis, Aalborg University, Fredrik Bajers Vej 7D, DK-9220, Aalborg East, Denmark. bme@vision.auc.dk

Computer Methods and Programs in Biomedicine
|June 6, 2000
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

Impacts of a Clinical Quality Registry on Lung Cancer Quality Measures: A Retrospective Observational Study of the Victorian Lung Cancer Registry.

Clinical oncology (Royal College of Radiologists (Great Britain))·2025
Same author

CXD101 and nivolumab in patients with metastatic microsatellite-stable colorectal cancer (CAROSELL): a multicentre, open-label, single-arm, phase II trial.

ESMO open·2022
Same author

Digital intervention increases influenza vaccination rates for people with diabetes in a decentralized randomized trial.

NPJ digital medicine·2021
Same author

ESMO's new strategic plan: our society's road to the future of oncology.

Annals of oncology : official journal of the European Society for Medical Oncology·2020
Same author

Predicting changes in the status of patient-reported outcome measures after Birmingham Hip Resurfacing: an observational cohort study with a median follow-up of ten years.

The bone & joint journal·2019
Same author

The outcome and survival of metal-on-metal hip resurfacing in patients aged less than 50 years: a prospective observational cohort study with minimum ten-year follow-up.

The bone & joint journal·2019
Same journal

SynTME: A tumor microenvironment-aware, pharmacology-inspired multi-stage framework for drug synergy prediction.

Computer methods and programs in biomedicine·2026
Same journal

MMFVS-Net: A triple-symmetric cross-attention network for multimodal optical image fusion and high-accuracy virtual staining of breast cancer tissues.

Computer methods and programs in biomedicine·2026
Same journal

A novel Milstein-stochastic epidemiologically-informed neural network for approaching epidemic dynamics: Application to Mpox disease.

Computer methods and programs in biomedicine·2026
Same journal

Accounting for approximation errors using surrogate-based parameter estimation of cardiac mechanics digital twins.

Computer methods and programs in biomedicine·2026
Same journal

Facial iPPG heatmap patterns based on period-aware autoencoder show association with carotid atherosclerosis towards non-contact hemodynamic assessment.

Computer methods and programs in biomedicine·2026
Same journal

Explainable machine learning models predict liver fibrosis risk and outcome in the general population: Development and multi-cohort external validation.

Computer methods and programs in biomedicine·2026
See all related articles

Early detection of diabetic retinopathy using digital imaging and automated analysis can prevent blindness. A Mahalanobis classifier showed promising results in identifying key indicators like microaneurysms and hemorrhages.

Area of Science:

  • Ophthalmology
  • Medical Imaging
  • Computer Science

Background:

  • Diabetic retinopathy is a leading cause of blindness in Europe.
  • Early diagnosis and treatment can prevent vision loss in over 50% of cases.
  • Digital imaging facilitates screening and monitoring of diabetic retinopathy.

Purpose of the Study:

  • To develop an automated analysis tool for digital retinal images in diabetic retinopathy screening.
  • To evaluate the performance of different statistical classifiers for detecting diabetic retinopathy features.

Main Methods:

  • Development of an automated analysis system for digital retinal images.
  • Testing of Bayesian, Mahalanobis, and KNN statistical classifiers.
  • Evaluation on a dataset of 134 retinal images.

Related Experiment Videos

Main Results:

  • The Mahalanobis classifier achieved the highest sensitivity in detecting diabetic retinopathy features.
  • Sensitivity rates for microaneurysms, hemorrhages, exudates, and cotton wool spots were 69%, 83%, 99%, and 80%, respectively.

Conclusions:

  • Automated analysis of digital retinal images shows potential for early diabetic retinopathy detection.
  • The Mahalanobis classifier demonstrates effectiveness in identifying key pathological signs.
  • This technology can aid in preventing blindness through timely diagnosis and treatment.