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

A deep phenotyping study in mouse and iPSC models to understand the role of oligodendroglia in optic neuropathy in Wolfram syndrome.

Acta neuropathologica communications·2024
Same author

Deep learning based MLC aperture and monitor unit prediction as a warm start for breast VMAT optimisation.

Physics in medicine and biology·2023
Same author

Rare and New Mutations of B-Globin in Azari Population of Iran, a Considerable Diversity.

Balkan journal of medical genetics : BJMG·2023
Same author

Clinical evaluation of a deep learning model for segmentation of target volumes in breast cancer radiotherapy.

Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology·2022
Same author

Interobserver variability in organ at risk delineation in head and neck cancer.

Radiation oncology (London, England)·2021
Same author

Relationship Between Early Functional and Structural Brain Developments and Brain Injury in Preterm Infants.

Cerebellum (London, England)·2021

Related Experiment Video

Updated: Mar 12, 2026

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

4.0K

Comparison of unsupervised classification methods for brain tumor segmentation using multi-parametric MRI.

N Sauwen1, M Acou2, S Van Cauter3

  • 1KU Leuven, Department of Electrical Engineering (ESAT), STADIUS Centre for Dynamical Systems, Signal Processing and Data Analytics, Leuven, Belgium; iMinds, Department of Medical Information Technologies, Belgium.

Neuroimage. Clinical
|November 5, 2016
PubMed
Summary
This summary is machine-generated.

Accurate tumor segmentation in high-grade gliomas (HGGs) is crucial for patient care. A novel hierarchical non-negative matrix factorization method using multi-parametric MRI (MP-MRI) significantly improved segmentation performance on diverse datasets.

Keywords:
1H MRSI, proton magnetic resonance spectroscopic imagingADC, apparent diffusion coefficientCho, total cholineClusteringCre, total creatineDKI, diffusion kurtosis imagingDSC-MRI, dynamic susceptibility-weighted contrast-enhanced magnetic resonance imagingDTI, diffusion tensor imagingDWI, diffusion-weighted imagingFA, fractional anisotropyFCM, fuzzy C-means clusteringFLAIR, fluid-attenuated inversion recoveryGBM, glioblastoma multiformeGMM, Gaussian mixture modellingGliomaGlx, glutamine + glutamateGly, glycineHALS, hierarchical alternating least squaresHGG, high-grade gliomaLGG, low-grade gliomaLac, lactateLip, lipidsMD, mean diffusivityMK, mean kurtosisMP-MRI, multi-parametric magnetic resonance imagingMulti-parametric MRINAA, N-acetyl-aspartateNMF, non-negative matrix factorizationNNLS, non-negative linear least-squaresNon-negative matrix factorizationPWI, perfusion-weighted imagingROI, region of interestSC, spectral clusteringSPA, successive projection algorithmSegmentationT1c, contrast-enhanced T1UZ Gent, University hospital of GhentUZ Leuven, University hospitals of LeuvenUnsupervised classificationcMRI, conventional magnetic resonance imaginghNMF, hierarchical non-negative matrix factorizationmI, myo-inositolrCBV, relative cerebral blood volume

More Related Videos

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

9.6K
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

49.6K

Related Experiment Videos

Last Updated: Mar 12, 2026

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

4.0K
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

9.6K
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

49.6K

Area of Science:

  • Radiology
  • Oncology
  • Medical Imaging

Background:

  • High-grade gliomas (HGGs) present significant segmentation challenges due to tumor heterogeneity.
  • Accurate tumor delineation is vital for treatment planning, prognosis, and patient follow-up.
  • Conventional MRI (cMRI) is standard, but advanced modalities offer enhanced characterization.

Purpose of the Study:

  • To compare unsupervised classification methods for HGG segmentation using multi-parametric MRI (MP-MRI).
  • To evaluate the performance of MP-MRI data, including cMRI, DWI, MRSI, and PWI, for automated tumor segmentation.

Main Methods:

  • Utilized two independent MP-MRI datasets from different hospitals with varying acquisition protocols.
  • Applied and compared several unsupervised classification algorithms for HGG segmentation.
  • Focused on a hierarchical non-negative matrix factorization (H-NMF) variant previously developed for MP-MRI segmentation.

Main Results:

  • The hierarchical non-negative matrix factorization variant demonstrated superior performance across both datasets.
  • Achieved the highest mean Dice-scores for segmenting pathological tissue classes.
  • Confirmed the effectiveness of the H-NMF approach for MP-MRI based tumor segmentation.

Conclusions:

  • The proposed hierarchical non-negative matrix factorization method offers robust and accurate segmentation of high-grade gliomas.
  • MP-MRI data, when analyzed with advanced unsupervised methods, enhances tumor segmentation capabilities.
  • This approach holds promise for improving clinical management of HGG patients.