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

White Matter Perivascular Space Burden in Children With Autism Spectrum Disorder and Typically Developing Controls: An Automated Quantitative MRI Study.

Journal of magnetic resonance imaging : JMRI·2026
Same author

Serial prenatal MRI evaluation of valacyclovir-treated vs untreated fetuses with congenital cytomegalovirus (cCMV) infection.

European radiology·2026
Same author

Neuroradiological patterns and prognostic implications in type I Alexander disease.

Molecular genetics and metabolism·2026
Same author

Short-Term Developmental Trajectories of Dorsal-Ventral Pathways and Their Relationships with First-Grade Learning.

bioRxiv : the preprint server for biology·2026
Same author

An Examination of Task-Evoked fMRI Data Processing in Functional Connectivity.

Journal of neuroscience research·2026
Same author

Human white matter tracts aligned with canonical functional brain networks.

bioRxiv : the preprint server for biology·2026

Related Experiment Video

Updated: Sep 4, 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

2.8K

DBB - A Distorted Brain Benchmark for Automatic Tissue Segmentation in Paediatric Patients.

Gabriele Amorosino1, Denis Peruzzo2, Daniela Redaelli3

  • 1NeuroInformatics Laboratory (NILab), Bruno Kessler Foundation (FBK), Trento, Italy; Center for Mind and Brain Sciences (CIMeC), University of Trento, Italy.

Neuroimage
|July 17, 2022
PubMed
Summary

This study benchmarks supervised learning for brain tissue segmentation in distorted MR images. Data-driven methods show promise for improving accuracy in clinical cases with altered brain anatomy.

Keywords:
BenchmarkBrain malformationBrain tissue segmentationMachine learningMagnetic resonance imaging (MRI)Supervised learning

More Related Videos

Three-Dimensional Shape Modeling and Analysis of Brain Structures
05:33

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

7.2K
Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease
09:06

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Published on: June 9, 2018

12.2K

Related Experiment Videos

Last Updated: Sep 4, 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

2.8K
Three-Dimensional Shape Modeling and Analysis of Brain Structures
05:33

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

7.2K
Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease
09:06

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Published on: June 9, 2018

12.2K

Area of Science:

  • Neuroimaging
  • Computational Neuroscience
  • Medical Image Analysis

Background:

  • T1-weighted MRI provides macro-scale human brain morphology, crucial for segmentation of anatomical structures.
  • Automated brain tissue segmentation methods often rely on anatomical priors, leading to high accuracy in healthy individuals but reduced performance with severe lesions or distorted anatomy.
  • Emerging evidence suggests data-driven, supervised learning approaches can be more robust to brain structure alterations, even when trained on healthy data.

Purpose of the Study:

  • To establish a benchmark for investigating improvements in distorted brain tissue segmentation using supervised learning.
  • To define the task and propose a quantitative evaluation metric for fair comparison of segmentation methods.
  • To facilitate open research into robust brain segmentation techniques for clinical applications.

Main Methods:

  • Development of a benchmark dataset including T1-weighted MR images and brain tissue labels from healthy individuals for training.
  • Inclusion of a test set comprising individuals with severe brain distortions.
  • Formulation of a precise task definition and a quantitative evaluation metric for performance assessment.

Main Results:

  • The benchmark supports open investigation into supervised learning for improved segmentation of distorted brain tissues.
  • The study provides openly published data and code on the BrainLife platform for reproducible research.
  • Empirical evidence suggests data-driven approaches can enhance segmentation robustness in the presence of brain structural alterations.

Conclusions:

  • Supervised learning offers a promising avenue for improving brain tissue segmentation accuracy in cases of severe lesions and distorted anatomy.
  • The benchmark and open data facilitate reproducible research and development of more robust automated segmentation tools for clinical neuroscience.
  • This work contributes to advancing the reliability of brain image analysis in patient populations with complex neurological conditions.