Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

DeepVBM: A fully automatic and efficient voxel-based morphometry via deep learning-based segmentation and registration methods.

Magnetic resonance imaging·2026

Same author

Human Proteoglycan Linkage Region Glycosyltransferases are Dimeric and Show Unexpected Specificities.

Angewandte Chemie (International ed. in English)·2025

Same author

Preclinical Pharmacokinetic, Pharmacodynamic, and Safety Profile of OBI-992: A Novel TROP2-Targeted Antibody-Drug Conjugate.

Molecular cancer therapeutics·2025

Same author

Referenceless reduction of spin-echo echo-planar imaging distortion with generative displacement mapping.

Magnetic resonance in medicine·2025

Same author

Preclinical evaluation of a novel antibody-drug conjugate OBI-992 for Cancer therapy.

Scientific reports·2025

Same author

Reducing polypharmacy through deprescribing in the emergency department.

Medicine·2025

Search research articles

Related Experiment Video

Updated: Aug 20, 2025

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

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

Published on: November 30, 2022

Deriving a robust deep-learning model for subcortical brain segmentation by using a large-scale database:

Jenn-Shiuan Weng¹, Teng-Yi Huang¹

¹Department of Electrical Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan.

NMR in Biomedicine

|November 24, 2022

Summary

A new U-Net based method for subcortical brain segmentation achieves high accuracy and reproducibility without extensive preprocessing. This convolutional neural network approach offers a faster alternative to FreeSurfer for clinical applications.

Keywords:

MRI segmentation deep learning subcortical brain structures

More Related Videos

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

A Standardized Pipeline for Examining Human Cerebellar Grey Matter Morphometry using Structural Magnetic Resonance Imaging

A Standardized Pipeline for Examining Human Cerebellar Grey Matter Morphometry using Structural Magnetic Resonance Imaging

Published on: February 4, 2022

Related Experiment Videos

Last Updated: Aug 20, 2025

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

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

Published on: November 30, 2022

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

A Standardized Pipeline for Examining Human Cerebellar Grey Matter Morphometry using Structural Magnetic Resonance Imaging

A Standardized Pipeline for Examining Human Cerebellar Grey Matter Morphometry using Structural Magnetic Resonance Imaging

Published on: February 4, 2022

Area of Science:

Neuroimaging
Artificial Intelligence
Medical Image Analysis

Background:

Accurate subcortical brain segmentation is crucial for clinical applications.
Existing methods often require extensive preprocessing, increasing analysis time.

Purpose of the Study:

To develop and evaluate a novel, efficient convolutional neural network (CNN)-based method for subcortical brain segmentation.
To assess the necessity of preprocessing steps, reproducibility, and volumetric accuracy of the proposed method.

Main Methods:

A U-Net based CNN was trained on a large dataset of 7039 T1-weighted MRI scans.
The optimized model, MX_RW, was evaluated for preprocessing necessity, cross-institutional/longitudinal reproducibility, and volumetric accuracy.
Performance was compared against FreeSurfer.

Main Results:

The MX_RW model achieved high performance (Dice: 0.809, CV: 4.6%, PCC: 0.979), comparable to FreeSurfer (Dice: 0.798, CV: 5.6%, PCC: 0.973).
MX_RW demonstrated robustness across institutions and time, without requiring complex preprocessing like intensity normalization or registration.
Computation time was significantly reduced, with MX_RW completing segmentation in under 5 seconds per dataset.

Conclusions:

The MX_RW method provides an accurate, reproducible, and significantly faster alternative for subcortical brain segmentation.
Its efficiency makes it suitable for time-restricted clinical applications, offering a competitive option to established tools like FreeSurfer.