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

Topology-aware multiclass segmentation of the Circle of Willis from MRA and CTA images.

Computers in biology and medicine·2026
Same author

Erratum: Strategies to combine 3D vasculature and brain CTA with deep neural networks: Application to LVO.

iScience·2026
Same author

Multi-atlas Parcellation in the Presence of Lesions: Application to Multiple Sclerosis.

Patch-based techniques in medical imaging : 4th international workshop, Patch-MI 2018, held in conjunction with MICCAI 2018, Granada, Spain, September 20, 2018 : proceedings. Patch-MI (Workshop) (4th : 2018 : Granada, Spain)·2025
Same author

Deep learning framework for vertebral heart size and cardiothoracic ratio estimation in dogs and cats using thoracic radiographs.

Frontiers in veterinary science·2025
Same author

DeepISLES: a clinically validated ischemic stroke segmentation model from the ISLES'22 challenge.

Nature communications·2025
Same author

Deep learning to predict progression independent of relapse activity at a first demyelinating event.

Brain communications·2025

Related Experiment Video

Updated: Dec 17, 2025

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

3.5K

A fully automated pipeline for brain structure segmentation in multiple sclerosis.

Sandra González-Villà1, Arnau Oliver2, Yuankai Huo3

  • 1Institute of Computer Vision and Robotics, University of Girona, Ed. P-IV, Campus Montilivi, University of Girona, 17003 Girona, Spain; Electrical Engineering, Vanderbilt University, Nashville, TN 37235, USA.

Neuroimage. Clinical
|June 26, 2020
PubMed
Summary

This study presents an automated pipeline for robust brain structure segmentation in multiple sclerosis (MS) patients, overcoming challenges posed by lesions. The new method ensures accurate volume measurements regardless of lesion mask variations.

Keywords:
Brain structuresLabel fusionMRIMulti-atlasMultiple sclerosis lesionsParcellationSegmentation

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

9.3K
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

40.7K

Related Experiment Videos

Last Updated: Dec 17, 2025

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

3.5K
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

9.3K
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

40.7K

Area of Science:

  • Neuroimaging
  • Medical Image Analysis
  • Computational Neuroscience

Background:

  • Accurate brain structure volume measurement is crucial for multiple sclerosis (MS) patient monitoring and treatment evaluation.
  • Manual segmentation methods for brain structures are prone to variability, impacting reproducibility.
  • Existing automated segmentation methods struggle with the aberrant intensities caused by MS lesions.

Purpose of the Study:

  • To develop and validate a fully automated pipeline for reproducible brain structure segmentation in MS patients.
  • To improve segmentation accuracy in the presence of MS lesions by reformulating label fusion strategies.
  • To assess the robustness of the automated pipeline against variations in lesion mask acquisition.

Main Methods:

  • Integration of reformulated state-of-the-art label fusion strategies into an automated pipeline.
  • Inclusion of pre-processing steps: inhomogeneity correction and intensity normalization.
  • Combination with an automated lesion segmentation method and analysis using both manual and automatic lesion masks.

Main Results:

  • Original label fusion methods showed significant volume differences when using manual versus automatic lesion masks.
  • The proposed automated pipeline demonstrated robustness, yielding no significant volume differences regardless of lesion mask type.
  • Specific volume changes observed with original methods include decreases in cerebrospinal fluid and increases in white and gray matter.

Conclusions:

  • The developed automated pipeline provides robust and reproducible brain structure segmentation in MS patients.
  • The pipeline effectively mitigates the impact of MS lesions on segmentation accuracy.
  • This advancement is critical for reliable disease follow-up and treatment evaluation in multiple sclerosis.