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

Revisiting the role of structural connectivity-based parcellation in thalamic nuclei segmentation: Benchmarking against recent state-of-the-art methods.

PloS one·2026
Same author

Cardiac Magnetic Resonance Scan Efficiency.

Magnetic resonance imaging clinics of North America·2026
Same author

Adiabatic Pulse Shape Influence on the Orientation Dependence of T<sub>1ρ</sub> Relaxation.

Magnetic resonance in medicine·2026
Same author

Robust thalamic nuclei segmentation using spectral clustering of fiber orientation distributions.

PloS one·2026
Same author

Imaging in Movement Disorders: A Clinician's Perspective on Novel Applications.

Seminars in neurology·2025
Same author

A deep learning framework for comprehensive segmentation of deep grey nuclei.

medRxiv : the preprint server for health sciences·2025

Related Experiment Video

Updated: Dec 11, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

685

Automated thalamic nuclei segmentation using multi-planar cascaded convolutional neural networks.

Mohammad S Majdi1, Mahesh B Keerthivasan2, Brian K Rutt3

  • 1Department of Electrical and Computer Engineering, University of Arizona, Tucson, AZ, United States of America.

Magnetic Resonance Imaging
|August 24, 2020
PubMed
Summary
This summary is machine-generated.

This study introduces a rapid convolutional neural network for segmenting thalamic nuclei, improving accuracy across various conditions and field strengths. The method aids in understanding neurological diseases like multiple sclerosis by detecting thalamic atrophy.

Keywords:
Clinical analysisConvolutional neural networkThalamic nuclei segmentationWhite-matter-nulled MPRAGE

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

3.2K
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

Related Experiment Videos

Last Updated: Dec 11, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

685
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

3.2K
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

Area of Science:

  • Neuroimaging
  • Artificial Intelligence
  • Medical Image Analysis

Background:

  • Accurate segmentation of thalamic nuclei is crucial for understanding neurological disorders.
  • Existing methods may lack speed or accuracy across different patient groups and imaging parameters.

Purpose of the Study:

  • To develop a fast and accurate convolutional neural network (CNN) for segmenting thalamic nuclei.
  • To optimize a single network for diverse datasets including healthy controls, multiple sclerosis (MS), and essential tremor (ET) patients, across 3T and 7T MRI.

Main Methods:

  • A modified residual U-Net architecture was employed in a cascaded multi-planar scheme.
  • Segmentation was performed on conventional and white-matter-nulled (WMn) MPRAGE MRI data.
  • Ground truth labels were generated using manual delineation guided by the Morel histological atlas.

Main Results:

  • The CNN achieved segmentation in under a minute, outperforming state-of-the-art methods for ET patients.
  • Statistically significant improvements in Dice similarity coefficient and VSI were observed for specific nuclei.
  • The method demonstrated robustness to image noise and comparable performance across 3T and 7T data.

Conclusions:

  • The developed CNN-based segmentation method is fast, accurate, and versatile across different diseases and field strengths.
  • It shows significant potential for advancing the understanding of thalamic nuclei's role in neurological diseases.
  • Clinical utility was confirmed by detecting thalamic atrophy in MS patients.