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 Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Spinal cord reserve is associated with multi-dimensional clinical resilience in multiple sclerosis.

Journal of neurology·2026
Same author

Leveraging electronic health record data for precision medicine insights: the precision medicine registry at NYU Langone Health.

npj health systems·2026
Same author

A statistical shape model of the human female sacrum: An integrative analysis of form.

Journal of anatomy·2026
Same author

Proteomic-based Aging Clocks and MRI Markers of Cerebral Small Vessel Disease: ARIC and MESA.

medRxiv : the preprint server for health sciences·2026
Same author

Cross-sectional brain volumetric measures and disability outcomes in relapsing-remitting multiple sclerosis.

Journal of neurology·2026
Same author

Did you know? State-of-the-art preprocessing diffusion MRI data can improve tractography.

Brain structure & function·2026

Related Experiment Video

Updated: Mar 3, 2026

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.5K

Semi-automated brain tumor segmentation on multi-parametric MRI using regularized non-negative matrix factorization.

Nicolas Sauwen1,2, Marjan Acou3, Diana M Sima4,5

  • 1Department of Electrical Engineering (ESAT), STADIUS Centre for Dynamical Systems, Signal Processing and Data Analytics, KULeuven, Kasteelpark Arenberg, Leuven, Belgium. nicolas.sauwen@kuleuven.be.

BMC Medical Imaging
|May 6, 2017
PubMed
Summary
This summary is machine-generated.

This study introduces a semi-automated method for brain tumor segmentation using non-negative matrix factorization (NMF) and L1-regularization on multi-parametric MRI. The NMF approach achieves competitive segmentation accuracy for gliomas, improving upon methods without regularization.

Keywords:
Brain tumorsMRINon-negative matrix factorizationSegmentationUnsupervised classification

More Related Videos

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

3.9K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

49.5K

Related Experiment Videos

Last Updated: Mar 3, 2026

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.5K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

3.9K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

49.5K

Area of Science:

  • Radiology
  • Medical Imaging
  • Computational Biology

Background:

  • Glioma segmentation in multi-parametric MRI is challenging due to tumor heterogeneity.
  • Manual segmentation is time-consuming, necessitating automated solutions for clinical practice.

Purpose of the Study:

  • To develop and evaluate a semi-automated framework for brain tumor segmentation.
  • To assess the impact of L1-regularization and multi-parametric MRI data on segmentation accuracy.

Main Methods:

  • A semi-automated segmentation framework based on non-negative matrix factorization (NMF) was developed.
  • L1-regularization was incorporated to enhance spatial consistency and sparseness.
  • The method was applied to multi-parametric MRI data from 21 high-grade glioma patients.

Main Results:

  • Mean Dice-scores of 65% (active tumor), 74% (tumor core), and 80% (whole tumor) were achieved with L1-regularized NMF.
  • Segmentation performance was lower without L1-regularization and when using only conventional MRI data.
  • Robustness was verified through repeated analysis with varied seeding points.

Conclusions:

  • The L1-regularized semi-automated NMF method provides competitive glioma segmentation results.
  • Careful voxel selection is crucial for optimal segmentation outcomes.
  • The framework demonstrates potential for improving clinical workflows in neuro-oncology.