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

Parameter estimation and tissue segmentation from multispectral MR images.

Z Liang1, J R Macfall, D P Harrington

  • 1Dept. of Radiol., State Univ. of New York, Stony Brook, NY.

IEEE Transactions on Medical Imaging
|January 1, 1994
PubMed
Summary
This summary is machine-generated.

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

Effects of early life stress on depression, cognitive performance and brain morphology.

Psychological medicine·2016
Same author

Identification of promoter polymorphisms in the cytochrome P450 CYP6AY1 linked with insecticide resistance in the brown planthopper, Nilaparvata lugens.

Insect molecular biology·2014
Same author

Identification of Chinese herbal medicines by fluorescence microscopy: fluorescent characteristics of medicinal bark.

Journal of microscopy·2014
Same author

Comparison of the effects on glycaemic control and β-cell function in newly diagnosed type 2 diabetes patients of treatment with exenatide, insulin or pioglitazone: a multicentre randomized parallel-group trial (the CONFIDENCE study).

Journal of internal medicine·2014
Same author

Measurements of four-lepton production at the Z resonance in pp collisions at sqrt[s] = 7 and 8 TeV with ATLAS.

Physical review letters·2014
Same author

Concurrent chemoradiotherapy followed by adjuvant chemotherapy compared with concurrent chemoradiotherapy alone for the treatment of locally advanced nasopharyngeal carcinoma: a retrospective controlled study.

Current oncology (Toronto, Ont.)·2014
Same journal

UniOCTSeg++: Refined Hierarchical Prompt Strategy and Bi-directional Progressive Consistency Learning for Universal Retinal Layer Segmentation in OCT.

IEEE transactions on medical imaging·2026
Same journal

Volumetric Functional Ultrasound Imaging in Macaques.

IEEE transactions on medical imaging·2026
Same journal

MUST: Multi-style virtual staining with incomplete pairs.

IEEE transactions on medical imaging·2026
Same journal

BrainCL: Transformer-Based Brain Network Contrastive Learning with Multi-Order Topology and Salience Masking.

IEEE transactions on medical imaging·2026
Same journal

LLM-enhanced Neuron Segmentation and Reconstruction in Complex Mouse Brain Images.

IEEE transactions on medical imaging·2026
Same journal

Matrixed-Spectrum Decomposition Accelerated Linear Boltzmann Transport Equation Solver for Fast Scatter Correction in Multi-Spectral CT.

IEEE transactions on medical imaging·2026
See all related articles

A new statistical method accurately classifies and segments brain tissue types using magnetic resonance imaging (MRI) relaxation times T(1), T(2), and proton density (PD). This approach enhances medical image analysis for better diagnostic capabilities.

Area of Science:

  • Medical Imaging
  • Statistical Modeling
  • Computational Anatomy

Background:

  • Accurate tissue segmentation in magnetic resonance imaging (MRI) is crucial for diagnosing neurological conditions.
  • Existing methods often struggle with precise classification of diverse brain tissue types based on relaxation parameters.
  • Developing robust statistical frameworks for MRI analysis remains an active area of research.

Purpose of the Study:

  • To develop and validate a novel statistical method for classifying tissue types and segmenting corresponding regions in MRI.
  • To leverage multivariate relaxation time data (T(1), T(2), proton density) for improved tissue characterization.
  • To automate the estimation of tissue class parameters and segmentation using advanced algorithms.

Main Methods:

Related Experiment Videos

  • A statistical approach modeling tissue intensity distributions as multivariate likelihood functions.
  • Utilizing a Markov random field prior to characterize piecewise contiguous tissue regions.
  • Employing the expectation-maximization algorithm for maximum likelihood estimation of class parameters.
  • Implementing maximum a posteriori probability for tissue region segmentation based on neighborhood information.
  • Determining the optimal number of tissue classes using the minimum description length criterion.

    • Main Results:

    • The developed method successfully classifies tissue types and segments corresponding regions in T(1), T(2), and proton density-weighted brain MRI.
    • Automatic estimation of tissue class parameters and the number of classes was achieved.
    • Satisfactory segmentation of different brain tissue regions was demonstrated on 1.5 Tesla MRI data.

    Conclusions:

    • The proposed statistical method provides an effective and automated approach for brain tissue segmentation using multi-parametric MRI.
    • This technique holds promise for improving the accuracy and efficiency of neuroimaging analysis.
    • Further applications in clinical diagnostics and research are anticipated.