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

Motion-compensated implicit neural modeling for 3D multiparametric quantitative MRI.

Medical image analysis·2026
Same author

Myelin-driven structural network redundancy underlies cognition in cerebral small vessel disease.

Alzheimer's research & therapy·2026
Same author

Sub-voxel QSM reveals the mechanism linking substantia nigra iron and temporal diamagnetism to PD gait.

NPJ Parkinson's disease·2026
Same author

Integrated Multi-Omics Analysis of Coagulation Dysregulation and Immune Pathway Alterations in 10-Gene Pig-to-Monkey Liver Xenotransplantation: A Case Report.

Xenotransplantation·2026
Same author

Cortical folding and thickness characteristics of gray matter in fetuses with non-severe ventriculomegaly.

BMC pediatrics·2026
Same author

Integrative Advances in Pig Genomics: From Reference Assemblies and Evolutionary History to the Mechanistic Dissection of Key Traits.

Biology·2026

Related Experiment Video

Updated: Oct 10, 2025

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging
11:03

High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging

Published on: November 10, 2015

9.5K

DeepQSMSeg: A Deep Learning-based Sub-cortical Nucleus Segmentation Tool for Quantitative Susceptibility Mapping.

Yonghang Guan, Xiaojun Guan, Jingjing Xu

    Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference
    |December 11, 2021
    PubMed
    Summary

    DeepQSMSeg accurately segments deep gray matter structures from QSM images using deep learning. This tool aids in neurodegenerative disease assessment and research by providing rapid and reliable segmentation of brain nuclei.

    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

    9.1K
    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

    3.0K

    Related Experiment Videos

    Last Updated: Oct 10, 2025

    High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging
    11:03

    High-resolution In Vivo Manual Segmentation Protocol for Human Hippocampal Subfields Using 3T Magnetic Resonance Imaging

    Published on: November 10, 2015

    9.5K
    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

    9.1K
    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

    3.0K

    Area of Science:

    • Neuroimaging
    • Medical Image Analysis
    • Artificial Intelligence in Medicine

    Background:

    • Deep brain nuclei are implicated in neurodegenerative diseases.
    • Accurate segmentation of these structures is crucial for aging and disease assessment.
    • Quantitative Susceptibility Mapping (QSM) is an emerging MRI technique for studying deep gray matter (DGM) nuclei.

    Purpose of the Study:

    • To develop an automated deep learning tool, DeepQSMSeg, for segmenting five pairs of DGM structures from QSM images.
    • To evaluate the precision, speed, and reliability of the proposed segmentation method.

    Main Methods:

    • A 3D encoder-decoder fully convolutional neural network architecture was employed.
    • Spatial and channel attention modules were integrated into the network.
    • A combination of Dice loss and focal loss was used to handle class imbalance.

    Main Results:

    • DeepQSMSeg achieved precise, rapid, and reliable segmentation of DGM structures from QSM images.
    • The average Dice coefficient reached 0.872±0.053, with a Hausdorff distance of 2.644±2.917 mm.
    • The tool's reliability was confirmed using an age-related susceptibility development model.

    Conclusions:

    • DeepQSMSeg offers an accurate and automated solution for segmenting sub-cortical regions in QSM.
    • This tool can reduce the workload for radiologists and accelerate research and clinical translation in aging and neurodegenerative disease studies.