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

Feature space analysis: effects of MRI protocols.

H Soltanian-Zadeh1, D J Peck

  • 1Department of Diagnostic Radiology, Henry Ford Health System, Detroit, Michigan 48202, USA. hamids@rad.hfh.edu

Medical Physics
|January 5, 2002
PubMed
Summary

This study reveals that while specific tumor zone locations shift with different magnetic resonance imaging (MRI) protocols, overall lesion segmentation remains consistent. This finding impacts brain tumor analysis using optimal feature space methods.

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

A dictionary learning approach for spatio-temporal characterization of absence seizures.

Physiological measurement·2019
Same author

Overlapping brain Community detection using Bayesian tensor decomposition.

Journal of neuroscience methods·2019
Same author

Integrated Analysis of EEG and fMRI Using Sparsity of Spatial Maps.

Brain topography·2016
Same author

K-edge ratio method for identification of multiple nanoparticulate contrast agents by spectral CT imaging.

The British journal of radiology·2013
Same author

Segmentation of Crohn, Lymphangiectasia, Xanthoma, Lymphoid hyperplasia and Stenosis diseases in WCE.

Studies in health technology and informatics·2012
Same author

Directed differential connectivity graph of interictal epileptiform discharges.

IEEE transactions on bio-medical engineering·2010

Area of Science:

  • Medical Imaging
  • Radiology
  • Neuro-oncology

Background:

  • Accurate brain tumor segmentation is crucial for diagnosis and treatment planning.
  • Magnetic resonance imaging (MRI) protocols can influence image characteristics and subsequent analysis.
  • Understanding the impact of different MRI sequences on segmentation is essential for reliable results.

Purpose of the Study:

  • To investigate the relationship between MRI protocols and image segmentation outcomes using an optimal feature space method.
  • To determine how variations in MRI sequences affect the segmentation of brain tumors and surrounding tissues.
  • To assess the consistency of segmentation results across different combinations of MRI protocols.

Main Methods:

  • Patients with brain tumors underwent MRI using various protocols (T1, T2-weighted, FLAIR) on a 1.5 T GE Signa system.

Related Experiment Videos

  • Image volumes were co-registered, and tumor center slices were selected for processing.
  • Optimal feature spaces were generated from different sets of MR images, followed by segmentation into normal tissues and tumor zones.
  • Segmentation results from 27 distinct image sets were compared.

    • Main Results:

    • The locations of segmented tumor zones and their corresponding image regions varied depending on the specific MRI protocols utilized.
    • Despite variations in tumor zone localization, the segmentation of the total lesion volume remained relatively consistent.
    • Segmentation of normal tissues also showed stability across different MRI protocol combinations.

    Conclusions:

    • The choice of MRI protocols impacts the precise localization of segmented tumor sub-regions.
    • The overall brain tumor segmentation, including total lesion and normal tissue delineation, is robust to variations in MRI protocols when using this optimal feature space method.
    • This suggests a degree of reliability in applying this segmentation technique across diverse imaging datasets.