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

Influence of MRI acquisition protocols and image intensity normalization methods on texture classification.

G Collewet1, M Strzelecki, F Mariette

  • 1Cemagref, Rennes, France. guylaine.collewet@cemagref.fr

Magnetic Resonance Imaging
|February 20, 2004
PubMed
Summary

Texture analysis of soft cheese using MRI is sensitive to acquisition protocols and normalization methods. Limiting gray level dynamics to +/- 3sigma significantly improved classification accuracy for cheese ripening stages.

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

[HLA-B58.01 and allopurinol hypersensitivity renal vasculitis in a Chinese patient].

La Revue de medecine interne·2022
Same author

A global non-invasive methodology for the phenotyping of potato under water deficit conditions using imaging, physiological and molecular tools.

Plant methods·2021
Same author

FGF receptor genes and breast cancer susceptibility: results from the Breast Cancer Association Consortium.

British journal of cancer·2014
Same author

Direct vertebral artery access for the endovascular treatment of basilar artery aneurysms.

Interventional neuroradiology : journal of peritherapeutic neuroradiology, surgical procedures and related neurosciences·2012
Same author

Quantification of muscle, subcutaneous fat and intermuscular fat in pig carcasses and cuts by magnetic resonance imaging.

Meat science·2011
Same author

Estimation of poultry breastmeat yield: magnetic resonance imaging as a tool to improve the positioning of ultrasonic scanners.

Meat science·2011

Area of Science:

  • Medical Imaging
  • Food Science
  • Image Analysis

Background:

  • Texture analysis quantifies image spatial variations, offering insights into structures.
  • Magnetic resonance imaging (MRI) texture analysis is sensitive to acquisition conditions and normalization methods.

Purpose of the Study:

  • To investigate the influence of MRI acquisition protocols and gray level normalization on texture analysis for soft cheese classification.
  • To determine the optimal normalization method for discriminating between young and old soft cheese based on texture features.

Main Methods:

  • Proton density and T(2)-weighted MR images of 32 soft cheese samples (16 young, 16 old) were acquired at 0.2 T.
  • Four gray level normalization methods were applied: original, same maximum, same mean, and dynamics limited to micro +/- 3sigma.

Related Experiment Videos

  • Texture descriptors were computed using co-occurrence matrix, run length matrix, gradient matrix, autoregressive model, and wavelet transform, followed by 1-nearest neighbor classification.

    • Main Results:

    • The best classification performance was achieved using gray level normalization with dynamics limited to micro +/- 3sigma.
    • This normalization method enhanced the differences between the two cheese ripening classes.
    • Both normalization techniques and acquisition protocols significantly impacted classification effectiveness and parameter selection.

    Conclusions:

    • Normalization methods and MR acquisition protocols critically influence the performance of texture analysis in soft cheese.
    • Evaluating sensitivity to these factors is essential for reliable texture analysis in MRI studies.