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

Normal brain volume measurements using multispectral MRI segmentation

M Vaidyanathan1, L P Clarke, C Heidtman

  • 1Department of Radiology, University of South Florida, Tampa, Florida, USA.

Magnetic Resonance Imaging
|January 1, 1997
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

Prevention of delayed avulsion.

British dental journal·2023
Same author

An Assessment of Imaging Informatics for Precision Medicine in Cancer.

Yearbook of medical informatics·2017
Same author

Amelogenesis imperfecta associated with dental follicular-like hamartomas and generalised gingival enlargement.

European archives of paediatric dentistry : official journal of the European Academy of Paediatric Dentistry·2013
Same author

Automatic section thickness determination using an absolute gradient focus function.

Journal of microscopy·2012
Same author

Rhabdomyomatous mesenchymal hamartoma of the tongue.

BMJ case reports·2012
Same author

Intrapulse temporal and wavelength shifts of a high-power 2.1-µm Ho:YAG laser and their potential influence on atmospheric lidar measurements.

Applied optics·2010
Same journal

Incremental diagnostic value of microstructural time-dependent diffusion MRI in differentiating PCNSL from glioblastoma over conventional MRI.

Magnetic resonance imaging·2026
Same journal

Enhanced motion compensation for free-breathing dynamic contrast-enhanced MRI with GROG-facilitated bunch phase encoding and Golden angle radial sampling.

Magnetic resonance imaging·2026
Same journal

The allegory of the cave: 10 years of AI shadows in radiology.

Magnetic resonance imaging·2026
Same journal

Conversion of 3 T liver, spleen, pancreas, and kidney R2* measurements to 1.5 T R2* equivalents: Validation of a theoretical framework.

Magnetic resonance imaging·2026
Same journal

Cine-derived mitral annular relaxation velocity for detection of preclinical left ventricular diastolic dysfunction.

Magnetic resonance imaging·2026
Same journal

Bone marrow fat fraction and R2* in sickle cell disease: Associations with hemolysis, iron metabolism, and disease severity.

Magnetic resonance imaging·2026
See all related articles

The semisupervised fuzzy c-means (SFCM) method offers reproducible brain tissue and cerebrospinal fluid volume measurements. SFCM demonstrated superior stability and accuracy compared to the k-nearest neighbor (kNN) classifier.

Area of Science:

  • Neuroimaging
  • Medical Image Analysis
  • Computational Biology

Background:

  • Accurate and reproducible measurement of brain tissue and cerebrospinal fluid (CSF) volumes is crucial for neurological research and clinical diagnosis.
  • Segmentation methods are essential for quantifying these volumes from medical images, but their reproducibility can be affected by various factors.

Purpose of the Study:

  • To evaluate the performance and reproducibility of a supervised k-nearest neighbor (kNN) classifier and a semisupervised fuzzy c-means (SFCM) clustering method for segmenting normal brain tissues and CSF.
  • To assess the stability of these segmentation methods across different conditions, including operator variability, imaging session repeats, subject variations, and imaging parameters.

Main Methods:

  • The study compared a k-nearest neighbor (kNN) classifier and a semisupervised fuzzy c-means (SFCM) clustering method for brain tissue and CSF segmentation.

Related Experiment Videos

  • Segmentation performance was evaluated based on reproducibility during repeat imaging sessions, inter-subject variability, and operator influence on training data selection.
  • Variability was assessed across different tissue types and imaging parameters.

    • Main Results:

    • The semisupervised fuzzy c-means (SFCM) method exhibited high reproducibility, with less than 3% variability during repeat imaging sessions.
    • Intraobserver and interobserver reproducibility for SFCM were below 4% for soft tissues and 6% for CSF.
    • The k-nearest neighbor (kNN) segmentation method showed higher variability compared to the SFCM method across all evaluated conditions.
    • Absolute brain matter and CSF volumes varied significantly between subjects (9% to 13%).

    Conclusions:

    • The semisupervised fuzzy c-means (SFCM) clustering method provides a stable and reproducible approach for quantifying normal brain tissue and cerebrospinal fluid volumes.
    • SFCM demonstrates superior performance over the k-nearest neighbor (kNN) classifier in terms of reproducibility and stability in neuroimaging segmentation.
    • The findings highlight the importance of method selection for reliable volumetric analysis in neuroscience research.