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 15, 2026

Magnetic Resonance Derived Myocardial Strain Assessment Using Feature Tracking

Magnetic Resonance Derived Myocardial Strain Assessment Using Feature Tracking

Published on: February 12, 2011

Myocardial border detection from ventriculograms using support vector machines and real-coded genetic algorithms.

Miguel Vera¹, Antonio Bravo, Rubén Medina

¹Laboratorio de Física, Departamento de Ciencias, Universidad de Los Andes-Táchira, San Cristóbal 5001, Venezuela.

Computers in Biology and Medicine

|March 16, 2010

Summary

This study introduces a novel two-step method for left ventricle segmentation in heart angiograms using landmark detection and evolutionary snakes. The approach achieves high accuracy in identifying cardiac structures and offers precise myocardial border estimation.

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

Accessibility Matters: Demonstrating the Critical Role of Mesoporous Pore Dimension on PFAS Adsorption Removal by Amine-Functionalized Surfaces.

Environmental science & technology·2026

Same author

Multi-scale entropy analysis of acoustic emission for gearbox fault severity classification.

Scientific reports·2026

Same author

Climate-Resilient F<sub>3</sub> Progenies of <i>Coffea arabica</i>: Agronomic Traits and Antibiosis to <i>Hypothenemus hampei</i>.

Plants (Basel, Switzerland)·2025

Same author

Systematic Review of Artificial Intelligence and Electrocardiography for Cardiovascular Disease Diagnosis.

Bioengineering (Basel, Switzerland)·2025

Same author

Single Hidden Layer Neural Networks With Random Weights Based on Nondifferentiable Functions.

IEEE transactions on neural networks and learning systems·2025

Same author

Scale-Fractal Detrended Fluctuation Analysis for Fault Diagnosis of a Centrifugal Pump and a Reciprocating Compressor.

Sensors (Basel, Switzerland)·2024

Area of Science:

Medical Imaging
Biomedical Engineering
Computational Cardiology

Background:

Accurate segmentation of the left ventricle is crucial for diagnosing cardiac conditions.
Existing methods may face challenges in precision and automation.

Purpose of the Study:

To develop and validate a robust two-step method for left ventricle segmentation.
To improve the accuracy of myocardial border detection in human heart angiograms.

Main Methods:

Utilized support vector machines (SVMs) with a radial basis function kernel for anatomical landmark detection.
Employed evolutionary snakes, optimized by a real-coded genetic algorithm, for myocardial border contour generation.
Trained SVMs on 31x31 pixel windows, achieving 97.94% recognition during detection.

More Related Videos

Real-Time Cardiac Mapping with a Noninvasive Imageless Electrocardiographic Imaging System

Real-Time Cardiac Mapping with a Noninvasive Imageless Electrocardiographic Imaging System

Published on: April 11, 2025

Related Experiment Videos

Last Updated: Jun 15, 2026

Magnetic Resonance Derived Myocardial Strain Assessment Using Feature Tracking

Magnetic Resonance Derived Myocardial Strain Assessment Using Feature Tracking

Published on: February 12, 2011

Real-Time Cardiac Mapping with a Noninvasive Imageless Electrocardiographic Imaging System

Real-Time Cardiac Mapping with a Noninvasive Imageless Electrocardiographic Imaging System

Published on: April 11, 2025

Main Results:

Achieved 97.94% recognition accuracy in landmark detection with no false positives during training.
Validated the method against manual tracings by cardiologists, with a maximum average contour error of 4.93% across 178 images.
Demonstrated the effectiveness of the evolutionary snakes and genetic algorithm for precise contour optimization.

Conclusions:

The proposed two-step method provides an accurate and automated approach for left ventricle segmentation.
This technique shows significant potential for clinical application in cardiac imaging analysis.
The combination of SVMs and evolutionary snakes offers a powerful tool for biomedical image analysis.