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 of MRI

H Soltanian-Zadeh1, J P Windham, D J Peck

  • 1Department of Diagnostic Radiology, Henry Ford Health System, Detroit, Michigan, USA.

Magnetic Resonance in Medicine
|September 4, 1998
PubMed
Summary

This study introduces a novel MRI feature-space analysis for brain tumors, enhancing tissue segmentation and identification. The method achieves consistent results across patients and sites, aiding in tumor characterization and treatment monitoring.

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

Correction: Neuropilin-1 promotes human glioma progression through potentiating the activity of the HGF/SF autocrine pathway.

Oncogene·2026
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

Outcome of Adult Brain Tumor Consortium (ABTC) prospective dose-finding trials of I-125 balloon brachytherapy in high-grade gliomas: challenges in clinical trial design and technology development when MRI treatment effect and recurrence appear similar.

Journal of radiation oncology·2016
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

Area of Science:

  • Medical Imaging
  • Neuro-oncology
  • Computational Pathology

Background:

  • Accurate brain tumor characterization is crucial for effective treatment.
  • Existing MRI analysis methods can lack consistency across different sites and patients.
  • Distinguishing between tumor components and treatment effects (e.g., radiation necrosis) remains challenging.

Purpose of the Study:

  • To present a novel MRI feature-space image-analysis method for brain tumor studies.
  • To demonstrate the method's ability to achieve patient-to-patient and site-to-site consistency.
  • To validate the method's utility in tissue identification, segmentation, and quantitative measurement.

Main Methods:

  • Acquisition of multi-sequence MRI data (T1- and T2-weighted) from 10 brain tumor patients.

Related Experiment Videos

  • Application of a proprietary algorithm to transform MRI data into an orthonormal feature space.
  • Comparison of image-derived segmentation results with histopathological analysis of biopsy samples.

    • Main Results:

    • The method successfully segmented normal brain tissues (white matter, gray matter, CSF) and various tumor components (tumor, cyst, edema, necrosis, infiltrated tumor).
    • Image analysis results showed strong agreement with biopsy findings.
    • Comparison of pre- and post-treatment feature spaces revealed changes indicative of radiation necrosis, differentiating it from residual tumor.

    Conclusions:

    • The developed MRI feature-space analysis method provides a consistent and reliable tool for brain tumor characterization.
    • The method facilitates accurate segmentation and identification of normal tissues, tumor zones, and treatment-related changes.
    • This approach holds significant potential for improving diagnostic accuracy and monitoring treatment response in neuro-oncology.