Search research articles

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

Segmentation of the right ventricular myocardial infarction in multi-centre cardiac magnetic resonance images.

Medical image analysis·2025

Same author

Segmentation of the Left Ventricle and Its Pathologies for Acute Myocardial Infarction After Reperfusion in LGE-CMR Images.

IEEE transactions on medical imaging·2025

Same author

Research on Autonomous Vehicle Path Planning Algorithm Based on Improved RRT* Algorithm and Artificial Potential Field Method.

Sensors (Basel, Switzerland)·2024

Same author

Segmentation of Pericardial Adipose Tissue in CMR Images: A Benchmark Dataset MRPEAT and a Triple-Stage Network 3SUnet.

IEEE transactions on medical imaging·2023

Same author

MR-Forest: A Deep Decision Framework for False Positive Reduction in Pulmonary Nodule Detection.

IEEE journal of biomedical and health informatics·2019

Same author

Accurate airway centerline extraction based on topological thinning using graph-theoretic analysis.

Bio-medical materials and engineering·2014

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: Oct 4, 2025

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

MR brain tissue classification based on the spatial information enhanced Gaussian mixture model.

Zijian Bian

Technology and Health Care : Official Journal of the European Society for Engineering and Medicine

|February 6, 2022

Summary

This summary is machine-generated.

This study introduces an improved Gaussian mixture model for automated brain tissue classification in MRI scans. The new method offers robust and efficient segmentation of cerebrospinal fluid, gray matter, and white matter, outperforming existing techniques.

Keywords:

Brain tissue classification Gaussian mixture model entropy weighting spatial information

More Related Videos

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

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

Published on: January 7, 2019

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Related Experiment Videos

Last Updated: Oct 4, 2025

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Large-scale Reconstructions and Independent, Unbiased Clustering Based on Morphological Metrics to Classify Neurons in Selective Populations

Published on: February 15, 2017

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

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

Published on: January 7, 2019

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

Area of Science:

Medical Imaging Analysis
Neuroscience
Computational Biology

Background:

Automated classification of T1-weighted MRI brain scans into cerebrospinal fluid, gray matter, and white matter is crucial for neurodegenerative disease research.
Manual segmentation is time-consuming; thus, automated methods like Gaussian mixture models are preferred.
Existing Gaussian mixture models face challenges with computational cost and parameter selection, especially with imaging artifacts like noise and inhomogeneity.

Purpose of the Study:

To present an improved Gaussian mixture model-based method for enhanced brain tissue classification.
To address the limitations of existing methods regarding computational complexity and robustness to imaging defects.

Main Methods:

Formulated individual voxel intensity using a standard mixture model.
Incorporated spatial weightings to capture local tissue characteristics.
Developed a 'lite' and robust implementation using a dedicated entropy term and Expectation-Maximization algorithm for parameter estimation.
Utilized the Maximum a Posteriori criterion for voxel-wise tissue assignment.

Main Results:

The proposed method achieved averaged Dice coefficients ranging from 66.41-87.42% for cerebrospinal fluid, 80.57-85.35% for gray matter, and 83.17-85.63% for white matter on simulated and real MR scans.
Validation demonstrated the method's effectiveness in segmenting brain tissues.

Conclusions:

The developed method proves effective and reliable for brain tissue classification, even in the presence of imaging defects.
It offers an improvement over existing Gaussian mixture model-based approaches for neuroimaging analysis.