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

Volumetric texture description and discriminant feature selection for MRI.

Constantino Carlos Reyes-Aldasoro1, Abhir Bhalerao

  • 1Department of Computer Science, Warwick University, Coventry, UK. creyes@dcs.warwick.ac.uk

Information Processing in Medical Imaging : Proceedings of the ... Conference
|September 4, 2004
PubMed
Summary

This study introduces a novel texture classification method for Magnetic Resonance Images (MRI) using sub-band filtering. This approach efficiently analyzes 2D and 3D textures, reducing computational complexity for improved medical image analysis.

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

ConvShareViT: A Vision Transformer-Like Architecture for Free-Space Optical Accelerators.

IEEE transactions on neural networks and learning systems·2026
Same author

Structural complexity of brain regions in mild cognitive impairment and Alzheimer's disease.

Brain and cognition·2026
Same author

Image Matching for UAV Geolocation: Classical and Deep Learning Approaches.

Journal of imaging·2025
Same author

Improving Medical Visual Representation Learning With Pathological-Level Cross-Modal Alignment and Correlation Exploration.

IEEE journal of biomedical and health informatics·2025
Same author

Correction: A subset of neutrophil phagosomes is characterised by pulses of Class I PI3K activity.

Disease models & mechanisms·2025
Same author

SGRRG: Leveraging radiology scene graphs for improved and abnormality-aware radiology report generation.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2025

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Biomedical Engineering

Background:

  • Texture analysis is crucial for Magnetic Resonance Image (MRI) classification.
  • Traditional joint statistics like co-occurrence matrices are computationally intensive, especially for 3D MRI data.
  • Efficient texture classification methods are needed for advanced medical image analysis.

Purpose of the Study:

  • To develop an efficient texture classification strategy for 2D and 3D MRI.
  • To propose a feature selection technique to reduce computational load.
  • To validate the methodology on synthetic, natural, and human knee MRI datasets.

Main Methods:

  • A sub-band filtering technique was developed for texture classification, extendable to 3D.
  • A feature selection method using Bhattacharyya distance was implemented to identify discriminant features.

Related Experiment Videos

  • The methodology was applied to 2D synthetic phantoms, 2D natural textures, and 3D human knee MRI scans.

    • Main Results:

    • The sub-band filtering approach provides an effective method for texture classification in 2D and 3D.
    • The Bhattacharyya distance-based feature selection significantly reduces the number of required features.
    • Quantitative analysis demonstrated the successful application of the method across diverse image types.

    Conclusions:

    • The proposed sub-band filtering and feature selection strategy offers an efficient solution for MRI texture classification.
    • This method enhances the feasibility of complex 3D texture analysis in medical imaging.
    • The technique shows promise for improving the accuracy and efficiency of diagnostic tools utilizing MRI data.