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

Experimental verification of asymmetric transmission in continuous omega-shaped metamaterials.

RSC advances·2022
Same author

Dual-mode subwavelength trapping by plasmonic tweezers based on V-type nanoantennas.

Optics letters·2019
Same author

Enhanced asymmetric transmissions attributed to the cavity coupling hybrid resonance in a continuous omega-shaped metamaterial.

Optics express·2018
Same author

Super-radiating manipulation of a nano-emitter by active toroidal metamaterials.

Scientific reports·2017
Same author

Optical force enhancement and annular trapping by plasmonic toroidal resonance in a double-disk metastructure.

Optics express·2016
Same author

Clinical application of a novel computer-aided detection system based on three-dimensional CT images on pulmonary nodule.

International journal of clinical and experimental medicine·2015

Related Experiment Video

Updated: Nov 3, 2025

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

3.1K

Learning U-Net Based Multi-Scale Features in Encoding-Decoding for MR Image Brain Tissue Segmentation.

Jiao-Song Long1, Guang-Zhi Ma1, En-Min Song1

  • 1School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan 430074, China.

Sensors (Basel, Switzerland)
|June 2, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces an improved U-Net model for brain MRI segmentation, enhancing accuracy in identifying tissues like gray matter (GM) and cerebrospinal fluid (CSF). The novel network effectively addresses limitations in standard models for precise diagnostic applications.

Keywords:
brain tissue segmentationmagnetic resonance imagesmulti-branch dense predictionmulti-branch outputmulti-branch poolingmulti-scale feature learning

More Related Videos

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

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.8K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.8K

Related Experiment Videos

Last Updated: Nov 3, 2025

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

3.1K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.8K
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.8K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Neuroscience

Background:

  • Accurate brain tissue segmentation in MRI is crucial for diagnosis, treatment planning, and monitoring neurological conditions.
  • Convolutional Neural Networks (CNNs), particularly U-Net, are widely used for MR image segmentation due to their high-precision feature generation.
  • Standard U-Net performance is limited by variable target shapes and information loss during down-sampling/up-sampling operations.

Purpose of the Study:

  • To propose a novel network that enhances U-Net's capability for accurate brain MRI segmentation.
  • To address the limitations of information loss and variable target shapes in existing models.
  • To improve the extraction of multi-scale features and localization accuracy in brain MRI segmentation.

Main Methods:

  • Introduction of spatial and channel dimensions-based multi-scale feature information extractors into the U-Net framework.
  • Development of a multi-branch pooling (MP) module for the encoding part to extract rich multi-scale features.
  • Design of a multi-branch dense prediction (MDP) module and a multi-branch output structure for the decoding part to enhance localization and edge preservation.

Main Results:

  • The proposed network demonstrated higher accuracy in segmenting brain tissues across MRbrainS13, IBSR18, and ISeg2017 datasets.
  • Achieved superior performance compared to the leading 2018 method for segmenting gray matter (GM) and cerebrospinal fluid (CSF).
  • The enhanced feature extraction and localization capabilities led to more accurate edge-preserving prediction maps.

Conclusions:

  • The novel network effectively extracts multi-scale features and improves localization for precise brain MRI segmentation.
  • The proposed method offers a significant advancement over existing techniques, particularly for GM and CSF segmentation.
  • This tool holds promise for improving diagnostic applications in neurology, including brain MRI segmentation and disease diagnosis.