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

Vacuolin-1 inhibits endosomal trafficking and metastasis via CapZβ.

Oncogene·2021
Same author

CTPA pulmonary artery distensibility in assessment of severity of acute pulmonary embolism and right ventricular function.

Medicine·2021
Same author

The complete chloroplast genome of <i>Castanopsis mekongensis</i> A. Camus (Fagaceae).

Mitochondrial DNA. Part B, Resources·2021
Same author

3D images of the silicone implants in capsular contracture after breast augmentation using magnetic resonance imaging with SPACE sequence.

Journal of plastic, reconstructive & aesthetic surgery : JPRAS·2021
Same author

High-efficient liquid exfoliation of 2D metal-organic framework using deep-eutectic solvents.

Ultrasonics sonochemistry·2021
Same author

High-content screening of diterpenoids from Isodon species as autophagy modulators and the functional study of their antiviral activities.

Cell biology and toxicology·2021

Related Experiment Video

Updated: Jun 28, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.8K

Anat-SFSeg: Anatomically-guided superficial fiber segmentation with point-cloud deep learning.

Di Zhang1, Fangrong Zong1, Qichen Zhang1

  • 1School of Airtificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China.

Medical Image Analysis
|April 12, 2024
PubMed
Summary

Accurate superficial white matter segmentation is crucial for brain mapping. Our novel Anatomically-guided Superficial Fiber Segmentation (Anat-SFSeg) framework improves accuracy and shows potential as neuroimaging biomarkers for Alzheimer's disease.

Keywords:
AnatomyDeep learningDiffusion MRIPoint cloudSuperficial white matterTractography

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
Fiber Connections of the Supplementary Motor Area Revisited: Methodology of Fiber Dissection, DTI, and Three Dimensional Documentation
16:23

Fiber Connections of the Supplementary Motor Area Revisited: Methodology of Fiber Dissection, DTI, and Three Dimensional Documentation

Published on: May 23, 2017

11.3K

Related Experiment Videos

Last Updated: Jun 28, 2025

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.8K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
Fiber Connections of the Supplementary Motor Area Revisited: Methodology of Fiber Dissection, DTI, and Three Dimensional Documentation
16:23

Fiber Connections of the Supplementary Motor Area Revisited: Methodology of Fiber Dissection, DTI, and Three Dimensional Documentation

Published on: May 23, 2017

11.3K

Area of Science:

  • Neuroimaging
  • Computational Neuroscience
  • Medical Image Analysis

Background:

  • Diffusion magnetic resonance imaging (dMRI) tractography maps brain structural connectivity.
  • Accurate segmentation of superficial white matter (SWM) is vital but challenging due to its complex U-shaped fiber patterns.

Purpose of the Study:

  • To develop and validate an advanced framework, Anatomically-guided Superficial Fiber Segmentation (Anat-SFSeg), for improved SWM segmentation.
  • To introduce novel metrics for quantifying SWM characteristics and assessing their clinical relevance.

Main Methods:

  • Proposed Anat-SFSeg framework utilizing a novel FiberAnatMap descriptor and a deep learning point-cloud network.
  • Integration of spatial fiber coordinates and multi-level anatomical features for network training.
  • Development of Fiber Anatomical Region Proportion (FARP) and Anatomical Region Fiber Count (ARFC) metrics.

Main Results:

  • Anat-SFSeg achieved superior accuracy on Human Connectome Project (HCP) datasets.
  • Demonstrated excellent generalization capabilities on clinical datasets with varying cognitive impairment levels.
  • ARFC and diffusion tensor metrics revealed significant alterations in Alzheimer's disease (AD) and mild cognitive impairment (MCI) patients, correlating with cognitive decline.

Conclusions:

  • Anat-SFSeg provides a robust and accurate method for SWM segmentation.
  • The developed metrics show promise as neuroimaging biomarkers for AD and potentially other neurological disorders.
  • The framework has broad applicability for studying neurodegenerative, neurodevelopmental, and psychiatric conditions.