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

Multi-spectral brain tissue segmentation using automatically trained k-Nearest-Neighbor classification.

Henri A Vrooman1, Chris A Cocosco, Fedde van der Lijn

  • 1Department of Radiology, Erasmus MC, P.O. Box 1738, Rotterdam, The Netherlands. h.vrooman@erasmusmc.nl

Neuroimage
|June 19, 2007
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

The Associations Between Intracranial Stenosis, Brain Amyloid-beta, and Cognition in a Memory Clinic Sample.

Alzheimer disease and associated disorders·2022
Same author

Diabetes and hypertension are related to amyloid-beta burden in the population-based Rotterdam Study.

Brain : a journal of neurology·2022
Same author

Classification of Skull Shape Deformities Related to Craniosynostosis on 3D Photogrammetry.

The Journal of craniofacial surgery·2022
Same author

UCSQ Method Applied on 3D Photogrammetry: Non-Invasive Objective Differentiation Between Synostotic and Positional Plagiocephaly.

The Cleft palate-craniofacial journal : official publication of the American Cleft Palate-Craniofacial Association·2022
Same author

A Diffusion Tensor Imaging Analysis of Frontal Lobe White Matter Microstructure in Trigonocephaly Patients.

Pediatric neurology·2022
Same author

Cerebral cortex maldevelopment in syndromic craniosynostosis.

Developmental medicine and child neurology·2021
Same journal

Segmentation of the parasagittal dura mater on multi-center 3D-FLAIR MRI.

NeuroImage·2026
Same journal

Spatial frequency channels implement a mental ruler in spatial vision.

NeuroImage·2026
Same journal

Exploring the Link Between Intravoxel Incoherent Motion Measured Brain Diffusivity During Wakefulness and Sleep Macrostructure in the Elderly.

NeuroImage·2026
Same journal

Closed-loop adaptation of transcranial magnetic stimulation intensity with electroencephalography feedback.

NeuroImage·2026
Same journal

Volumetric postmortem MRI of the medial temporal lobe in Alzheimer's disease and related disorders: methodological advances and implications for in vivo biomarker development.

NeuroImage·2026
Same journal

Neural responses to equity and inequity when receiving vicarious rewards for self and charity during adolescence.

NeuroImage·2026
See all related articles

A new automated method for brain tissue classification using k-Nearest-Neighbor (kNN) eliminates manual labeling. Non-rigid registration with a tissue probability atlas automates kNN training, achieving accurate and robust segmentation of gray matter, white matter, and CSF.

Area of Science:

  • Neuroimaging
  • Medical Image Analysis
  • Computational Neuroscience

Background:

  • Manual labeling for k-Nearest-Neighbor (kNN) brain tissue classification in MR data is time-consuming and laborious.
  • Automating this training process is crucial for efficient and scalable neuroimaging analysis.

Purpose of the Study:

  • To develop and validate a fully automated kNN training procedure for brain tissue classification.
  • To compare the accuracy and robustness of the automated method against conventional manual training and rigid registration-based training.

Main Methods:

  • Automated kNN training via non-rigid registration of MR data with a tissue probability atlas.
  • Selection of reliable training samples through a post-processing step.
  • Segmentation of gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) in 12 datasets and robustness evaluation on 59 subjects.

Related Experiment Videos

Main Results:

  • The automated non-rigid registration method significantly outperformed rigid registration-based training.
  • Automated and manually trained kNN classifiers showed comparable results, with differences not exceeding inter-observer variability.
  • High similarity indices (0.93 for CSF, 0.92 for GM, 0.92 for WM) were achieved, demonstrating accurate segmentation.

Conclusions:

  • The developed fully automated, non-rigid registration-based kNN method provides accurate and robust brain tissue segmentation.
  • This automated approach can potentially replace laborious manual segmentation, making brain tissue classification more feasible.
  • The method offers a significant advancement in automated neuroimaging analysis.