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

Multispectral magnetic resonance image analysis using principal component and linear discriminant analysis.

Han Witjes1, Mark Rijpkema, Marinette van der Graaf

  • 1Laboratory for Analytical Chemistry, University of Nijmegen, Toernooiveld 1, 6525 ED Nijmegen, The Netherlands.

Journal of Magnetic Resonance Imaging : JMRI
|January 24, 2003
PubMed
Summary

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

Predicting tumour and organ dose in α-radiopharmaceutical therapy: a <sup>89</sup>Zr-based dosimetric approach for <sup>225</sup>Ac.

European journal of nuclear medicine and molecular imaging·2026
Same author

Tumour-targeted fluorescence-guided surgery in gastrointestinal cancer: A systematic review of preclinical and clinical research.

Clinical and translational medicine·2026
Same author

An Integrated Nonclinical and Clinical Risk Assessment of the Effects of Investigational ATRi Tuvusertib on QTc Interval in Patients With Solid Tumors.

Clinical and translational science·2026
Same author

Exposure-Response Analysis of Donidalorsen for the Treatment of Hereditary Angioedema.

Clinical and translational science·2025
Same author

Improving magnetic field homogeneity in prostate MR imaging and spectroscopy using an add-on local external shim coil array.

Magma (New York, N.Y.)·2025
Same author

The diagnostic value of controlled attenuation parameter (CAP) and magnetic resonance imaging derived proton density fat fraction (MRI-PDFF) for the evaluation of intestinal failure-associated liver steatosis among adult chronic intestinal failure patients.

Clinical nutrition ESPEN·2025

This study combined multispectral magnetic resonance (MR) images from different patients. The analysis successfully differentiated healthy brain tissue from tumors and even distinguished between tumor types, aiding radiologists in objective image comparison.

Area of Science:

  • Medical Imaging
  • Radiology
  • Computational Analysis

Background:

  • Multispectral magnetic resonance (MR) imaging offers rich diagnostic information.
  • Integrating data from multiple patients presents computational challenges.
  • Objective comparison of complex imaging data is crucial for accurate diagnosis.

Purpose of the Study:

  • To investigate the feasibility of combining multispectral MR images from different patients into a unified data matrix.
  • To develop a method for objective comparison of brain tumor characteristics across individuals.

Main Methods:

  • Applied principal component analysis (PCA) and linear discriminant analysis (LDA) to multispectral MR images of 12 brain tumor patients.
  • Included T1-weighted, T2-weighted, proton-density-weighted, gadolinium-enhanced T1-weighted images, and relative regional cerebral blood volume (rCBV) maps.

Related Experiment Videos

  • Utilized a combined data matrix for comparative analysis.

    • Main Results:

    • Clustering of similar multispectral image regions and scattering of dissimilar regions within a single plot.
    • Successful discrimination between healthy and tumorous brain regions using both PCA and LDA.
    • LDA demonstrated capability in differentiating between oligodendrogliomas and astrocytomas.
    • Partial success in identifying unknown tumor types using discriminant analysis.

    Conclusions:

    • The developed method facilitates easier and more objective comparison of multispectral MR images across different patients.
    • This approach can serve as a valuable tool for radiologists in clinical practice.
    • Enhances the diagnostic utility of multispectral MR imaging for brain tumors.