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 Experiment Videos

Review of MR image segmentation techniques using pattern recognition

J C Bezdek1, L O Hall, L P Clarke

  • 1Division of Computer Science, University of West Florida, Pensacola 32514.

Medical Physics
|July 1, 1993
PubMed
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

An Assessment of Imaging Informatics for Precision Medicine in Cancer.

Yearbook of medical informatics·2017
Same author

Automatic section thickness determination using an absolute gradient focus function.

Journal of microscopy·2012
Same author

A Convergence Theorem for the Fuzzy ISODATA Clustering Algorithms.

IEEE transactions on pattern analysis and machine intelligence·2012
Same author

Curvature and tangential deflection of discrete arcs: a theory based on the commutator of scatter matrix pairs and its application to vertex detection in planar shape data.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

Efficient Implementation of the Fuzzy c-Means Clustering Algorithms.

IEEE transactions on pattern analysis and machine intelligence·2011
Same author

The Reference Image Database to Evaluate Response to therapy in lung cancer (RIDER) project: a resource for the development of change-analysis software.

Clinical pharmacology and therapeutics·2008
Same journal

Decomposition-based harmonization for quantitative PET imaging across scanners and radiotracers.

Medical physics·2026
Same journal

Development and evaluation of an in vivo dose-based monitoring system for electron FLASH radiation therapy.

Medical physics·2026
Same journal

A novel optical respiratory gating system with a hybrid phase-amplitude algorithm for spot-scanning proton therapy.

Medical physics·2026
Same journal

Gamma Knife treatment planning using knowledge-based reinforcement learning.

Medical physics·2026
Same journal

Development and characterization of a novel, small animal external beam irradiator using a clinical high dose rate brachytherapy source.

Medical physics·2026
Same journal

Deep learning-based dose prediction for MR-guided prostate SIB: Supporting rapid feasibility assessment and adaptive editing margin selection.

Medical physics·2026
See all related articles

This review examines nine magnetic resonance (MR) image segmentation techniques, finding that both supervised and unsupervised methods require human input for clinical use. Fuzzy c-means and k-nearest neighbor rules show promise for faster, more accurate MR image segmentation.

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Biomedical Engineering

Background:

  • Magnetic Resonance (MR) image segmentation is crucial for medical diagnosis and treatment planning.
  • Existing segmentation techniques vary in complexity, accuracy, and computational requirements.
  • Clinical utility of MR image segmentation relies on minimizing human intervention while maximizing accuracy.

Purpose of the Study:

  • To review and compare nine distinct MR image segmentation techniques.
  • To identify the strengths and weaknesses of various segmentation approaches.
  • To highlight promising avenues for future development in MR image segmentation.

Main Methods:

  • Categorization of reviewed methods into four groups: c-means, maximum likelihood, neural networks, and k-nearest neighbor rules.

Related Experiment Videos

  • Discussion of both supervised and unsupervised segmentation schemes.
  • Analysis of techniques based on underlying statistical assumptions and their applicability to MR image data.

    • Main Results:

    • Supervised methods like Feedforward Neural Networks (FF/NN) and k-nearest neighbor (k-nn) rules show promise.
    • Unsupervised methods, particularly fuzzy c-means clustering and connectionist techniques, demonstrate significant potential.
    • Maximum likelihood techniques are sensitive to training region selection; statistical distribution-based methods are less promising.
    • k-nn is identified as the fastest technique reviewed.

    Conclusions:

    • Both supervised and unsupervised MR image segmentation require human interaction for clinical results.
    • Unsupervised techniques, especially fuzzy c-means and connectionist approaches, offer promising results but need speed improvements.
    • Future research should focus on parallelization, optimization for speed, dynamic cluster validity, and improved initialization strategies.