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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Real-time emotion recognition based on EEG signals using a hybrid batch-stream architecture.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Private, non-profit, and plantation: Oil palm smallholders in management-assistance programs vary in socio-demographics, attitudes, and management practices.

PloS one·2025
Same author

Smallholder oil palm plantation sustainability assessment using multi-criteria analysis and unmanned aerial vehicles.

Environmental monitoring and assessment·2023
Same author

Residual Learning: A New Paradigm to Improve Deep Learning-Based Segmentation of the Left Ventricle in Magnetic Resonance Imaging Cardiac Images.

Journal of medical signals and sensors·2021
Same author

A Novel Microaneurysms Detection Method Based on Local Applying of Markov Random Field.

Journal of medical systems·2016
Same author

A novel method based on learning automata for automatic lesion detection in breast magnetic resonance imaging.

Journal of medical signals and sensors·2014

Related Experiment Video

Updated: May 7, 2026

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

8.5K

Ensemble Semi-supervised Frame-work for Brain Magnetic Resonance Imaging Tissue Segmentation.

Reza Azmi1, Boshra Pishgoo, Narges Norozi

  • 1Departments of Computer Engineering, Alzahra University, Tehran, Iran.

Journal of Medical Signals and Sensors
|October 8, 2013
PubMed
Summary

This study introduces an ensemble semi-supervised framework for brain MRI tissue segmentation. This approach improves accuracy by combining multiple improved semi-supervised classifiers, outperforming traditional methods.

Keywords:
Brain magnetic resonance image tissue segmentationMCo_Training classifierensemble semi-supervised frame-workexpectation filtering maximization classifier

More Related Videos

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.8K
High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain
10:06

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain

Published on: May 10, 2012

12.2K

Related Experiment Videos

Last Updated: May 7, 2026

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

8.5K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.8K
High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain
10:06

High-resolution Functional Magnetic Resonance Imaging Methods for Human Midbrain

Published on: May 10, 2012

12.2K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Machine Learning

Background:

  • Accurate brain magnetic resonance imaging (MRI) tissue segmentation is crucial for clinical diagnostics.
  • Supervised methods offer high accuracy but require extensive labeled data, while unsupervised methods lack performance.
  • Semi-supervised learning balances accuracy and data requirements by utilizing both labeled and unlabeled data.

Purpose of the Study:

  • To develop an ensemble semi-supervised framework for enhanced brain MRI tissue segmentation.
  • To introduce improved semi-supervised algorithms, Expectation Filtering Maximization (EFM) and MCo_Training, for increased segmentation accuracy.
  • To evaluate the framework's performance against supervised and individual semi-supervised methods.

Main Methods:

  • An ensemble framework combining multiple semi-supervised classifiers was proposed.
  • Two novel semi-supervised algorithms, EFM and MCo_Training, were developed as improved versions of Expectation Maximization and Co_Training.
  • These improved classifiers, along with a graph-based semi-supervised classifier, formed the ensemble components.

Main Results:

  • The proposed ensemble semi-supervised framework demonstrated superior segmentation performance.
  • The improved EFM and MCo_Training algorithms enhanced segmentation accuracy compared to their base methods.
  • The ensemble approach outperformed both traditional supervised methods and individual semi-supervised classifiers.

Conclusions:

  • Ensemble semi-supervised learning offers a robust and accurate solution for brain MRI tissue segmentation.
  • The developed EFM and MCo_Training algorithms contribute to advancing semi-supervised segmentation techniques.
  • This framework provides a promising direction for improving clinical diagnostic tools through automated image analysis.