Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 22, 2026

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

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

Published on: July 28, 2023

Retinal image analysis based on mixture models to detect hard exudates.

Clara I Sánchez¹, María García, Agustín Mayo

¹Biomedical Engineering Group, E.T.S. Ingenieros de Telecomunicación, University of Valladolid, Campus Miguel Delibes s/n, Valladolid, Spain. csangut@gmail.com

Medical Image Analysis

|June 23, 2009

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

Advanced Research Institute Scholars' Perspectives on Program Success: A Self-determination Theory Evaluation.

The American journal of geriatric psychiatry : official journal of the American Association for Geriatric Psychiatry·2026

Same author

Dynamics of the microbiota in patients with Clostridioides difficile: Recurrence, treatment, sex, and immunosuppression.

PLoS pathogens·2026

Same author

DDFU-Net: A Deep Decoder-Focused U-Net Model for Retinal Lesion Segmentation.

Annals of biomedical engineering·2026

Same author

Antimicrobial Susceptibility of <i>Clostridioides difficile</i> in Spain: Multicenter Retrospective Cohort Study.

Antibiotics (Basel, Switzerland)·2026

Same author

The real-world economic impact of herpes zoster disease in patients with selected underlying conditions in Spain.

Human vaccines & immunotherapeutics·2026

Same author

An Oral Human Papillomavirus Lesion in a Neonate: A Clinical Case Report.

Journal of paediatrics and child health·2026

An automated method effectively detects hard exudates, an early sign of diabetic retinopathy, from retinal images. This technique aids in early diagnosis and prevention of vision loss.

Area of Science:

Ophthalmology
Medical Imaging
Computer Vision

Background:

Diabetic retinopathy is a leading cause of blindness globally.
Hard exudates are early clinical indicators of diabetic retinopathy.
Accurate detection of hard exudates is crucial for timely intervention.

Purpose of the Study:

To develop and evaluate an automated algorithm for detecting hard exudates in retinal images.
To differentiate hard exudates from other retinal pathologies and artifacts.

Main Methods:

Utilized mixture models for dynamic image thresholding to segment exudates.
Employed edge detection for post-processing to distinguish hard exudates from cotton wool spots and artifacts.
Prospectively assessed algorithm performance on 80 retinal images with varying quality.

More Related Videos

An Acute Retinal Model for Evaluating Blood Retinal Barrier Breach and Potential Drugs for Treatment

An Acute Retinal Model for Evaluating Blood Retinal Barrier Breach and Potential Drugs for Treatment

Published on: September 13, 2016

Related Experiment Videos

Last Updated: Jun 22, 2026

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

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

Published on: July 28, 2023

An Acute Retinal Model for Evaluating Blood Retinal Barrier Breach and Potential Drugs for Treatment

An Acute Retinal Model for Evaluating Blood Retinal Barrier Breach and Potential Drugs for Treatment

Published on: September 13, 2016

Main Results:

Achieved 90.2% sensitivity and 96.8% positive predictive value on a lesion-based criterion.
Demonstrated 100% sensitivity and 90% specificity for image-based classification.
The algorithm showed robust performance across images with variable color, brightness, and quality.

Conclusions:

The proposed automated method accurately detects hard exudates in retinal images.
This algorithm shows significant clinical potential for early diabetic retinopathy diagnosis.
The technique offers a reliable tool for ophthalmologists in managing diabetic retinopathy.