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: Mar 19, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Retinal vessel segmentation in colour fundus images using Extreme Learning Machine.

Chengzhang Zhu¹, Beiji Zou¹, Rongchang Zhao¹

¹School of Information Science and Engineering, Central South University, Changsha, China; Mobile Health Ministry of Education-China Mobile Joint Laboratory, Changsha, China.

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society

|June 13, 2016

Summary

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

The heat-ramp method to study regulated cell death in a pathogenic yeast Cryptococcus neoformans.

Methods in cell biology·2026

Same author

Genome Wide Pleiotropic Analysis Reveals Shared Genetic Architecture and Pathological Basis Between Retinitis Pigmentosa and Relevant Ocular Comorbidities.

Seminars in ophthalmology·2026

Same author

ANIMATE: Unsupervised Attributed Graph Anomaly Detection with Masked Graph Transformers.

Sensors (Basel, Switzerland)·2026

Same author

DCPS modulates TDP-43-linked neurodegeneration through P-body-mediated RNA decay.

Neuron·2026

Same author

The Role of Viral Infection and Microbial Dysbiosis in Glaucoma: From Pathogenesis to Therapeutic Strategies.

Viruses·2026

Same author

Micropulse Transscleral Cyclophotocoagulation in Refractory Glaucoma: Two-year Results of a Prospective Multicenter Study.

Clinical ophthalmology (Auckland, N.Z.)·2026

This study introduces a fast Extreme Learning Machine (ELM) method for retinal vessel segmentation. The technique achieves high accuracy, aiding in ophthalmic diagnosis and real-time disease screening.

Area of Science:

Ophthalmology
Medical Imaging
Computer Vision

Background:

Retinal vessel attributes are crucial for diagnosing systemic conditions and eye diseases.
Accurate segmentation of retinal vasculature is essential for clinical analysis.

Purpose of the Study:

To propose a supervised method using Extreme Learning Machine (ELM) for efficient and accurate retinal vessel segmentation.
To evaluate the method's performance on public and new retinal image databases.

Main Methods:

Extraction of 39-D discriminative feature vectors per pixel, including local, morphological, phase congruency, Hessian, and divergence features.
Utilizing a matrix of feature vectors and manual labels as input for the ELM classifier.
Implementing an optimization step to remove small, isolated regions from the segmented vasculature.

Keywords:

Colour fundus image Computer-aided diagnosis Feature extraction Retinal vessel segmentation Supervised learning

More Related Videos

Using Retinal Imaging to Study Dementia

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

Deep Vascular Imaging in the Eye with Flow-Enhanced Ultrasound

Deep Vascular Imaging in the Eye with Flow-Enhanced Ultrasound

Published on: October 4, 2021

Related Experiment Videos

Last Updated: Mar 19, 2026

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Using Retinal Imaging to Study Dementia

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

Deep Vascular Imaging in the Eye with Flow-Enhanced Ultrasound

Deep Vascular Imaging in the Eye with Flow-Enhanced Ultrasound

Published on: October 4, 2021

Main Results:

The proposed ELM method demonstrated significantly faster segmentation compared to existing techniques on the DRIVE database.
Achieved high performance metrics: average accuracy (0.9607), sensitivity (0.7140), and specificity (0.9868).
Exhibited speed and robustness on the RIS database, indicating practical applicability.

Conclusions:

The developed supervised ELM method provides a fast and accurate approach for retinal vessel segmentation.
The technique shows potential for real-time computer-aided diagnosis and screening of eye diseases.
High accuracy and robustness suggest its utility in clinical settings for analyzing retinal vasculature.