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

Harmonizing regional cancer registry data to facilitate Germany-wide epidemiological analyses.

International journal of medical informatics·2026
Same author

Quantification of amyotrophic lateral sclerosis (ALS) disease accumulation with T1-weighted high-resolution magnetic resonance imaging: validation in an independent cohort.

Journal of neurology·2026
Same author

RetCond: A Conditional Diffusion Model for Self-Explanatory Multi-Class Fundus Image Classification.

Journal of medical systems·2026
Same author

The Relationship Between Inhibitory Control of Attention and fMRI Functional Connectivity in Children With and Without ADHD.

Journal of attention disorders·2026
Same author

Combining federated learning and travelling model boosts performance and opens opportunities for digital health equity.

NPJ digital medicine·2026
Same author

Task-aware multiple instance learning for stress detection from facial video data.

Journal of affective disorders·2026

Related Experiment Video

Updated: Apr 20, 2026

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

49.8K

Extra tree forests for sub-acute ischemic stroke lesion segmentation in MR sequences.

Oskar Maier1, Matthias Wilms2, Janina von der Gablentz3

  • 1Institute of Medical Informatics, University of Lübeck, Germany; Graduate School for Computing in Medicine and Live Science, University of Lübeck, Germany.

Journal of Neuroscience Methods
|December 3, 2014
PubMed
Summary

Accurate brain lesion segmentation after stroke is crucial for understanding brain function. This new method uses magnetic resonance (MR) imaging and an Extra Tree forest for reproducible, automated lesion identification, improving upon manual methods.

Keywords:
Extra tree forestMulti-spectral MRIRandom forestSegmentationSub-acute ischemic stroke lesionWhite matter lesion

More Related Videos

Endovascular Perforation Model for Subarachnoid Hemorrhage Combined with Magnetic Resonance Imaging MRI
06:30

Endovascular Perforation Model for Subarachnoid Hemorrhage Combined with Magnetic Resonance Imaging MRI

Published on: December 16, 2021

4.6K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

41.1K

Related Experiment Videos

Last Updated: Apr 20, 2026

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

49.8K
Endovascular Perforation Model for Subarachnoid Hemorrhage Combined with Magnetic Resonance Imaging MRI
06:30

Endovascular Perforation Model for Subarachnoid Hemorrhage Combined with Magnetic Resonance Imaging MRI

Published on: December 16, 2021

4.6K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

41.1K

Area of Science:

  • Neuroimaging
  • Medical Image Analysis
  • Computational Neuroscience

Background:

  • Accurate segmentation of brain lesions in magnetic resonance (MR) images is essential for analyzing the relationship between brain structure and function post-stroke.
  • Manual delineation, the current standard, is labor-intensive and prone to significant observer variability.

Purpose of the Study:

  • To develop an automatic and reproducible method for segmenting sub-acute ischemic stroke lesions in MR images.
  • To evaluate the performance of the proposed method against existing techniques.

Main Methods:

  • A novel approach utilizing an Extra Tree forest framework for voxel-wise classification.
  • Employing intensity-derived image features, with a focus on multi-spectral MR imaging variants.

Main Results:

  • The fluid attenuated inversion recovery (FLAIR) sequence was found to be both necessary and sufficient for effective segmentation.
  • Incorporating features from T1-weighted and diffusion-weighted sequences further enhanced accuracy; other sequences were detrimental.
  • The method achieved a Dice coefficient of 0.65 on 37 clinical cases, outperforming previous methods.

Conclusions:

  • The developed approach is highly effective in differentiating new stroke lesions from other white matter pathologies using FLAIR sequences alone.
  • Its accuracy and ability to handle diverse pathologies make it suitable for automated screening of large MR scan databases for neuropsychological studies.
  • Detailed analysis of feature importance and statistical dependencies was performed.