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

Notoginsenoside R1 Alleviates Acetaminophen-Induced Liver Injury via MAPK/mTOR-Mediated Autophagy.

The American journal of Chinese medicine·2026
Same author

Predicting dysthyroid optic neuropathy in moderate-to-severe thyroid eye disease: a clinically applicable nomogram.

European thyroid journal·2025
Same author

The Effects of Counter-Ions on Peptide Structure, Activity, and Applications.

Biomolecules·2025
Same author

Antimicrobial Peptides for Skin Wound Healing.

Biomolecules·2025
Same author

Effects of Maternal Iodine Deficiency in Women with Mild Thyroid Dysfunction During Early Pregnancy on Mental and Motor Growth of Their Offspring During Levothyroxine Treatment.

Biological trace element research·2025
Same author

Global, regional, and national burden of gallbladder and biliary tract cancer among adults aged 55 years and older, 2010-2021.

Frontiers in nutrition·2025

Related Experiment Video

Updated: Aug 26, 2025

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.8K

EA-Net: Edge-aware network for brain structure segmentation via decoupled high and low frequency features.

Qian Hu1, Ying Wei2, Xiang Li1

  • 1College of Information Science and Engineering, Northeastern University, Shenyang 110819, China.

Computers in Biology and Medicine
|October 9, 2022
PubMed
Summary

This study introduces an edge-aware network (EA-Net) for improved brain Magnetic Resonance Image (MRI) segmentation. The novel approach enhances diagnostic accuracy by effectively segmenting complex brain structures and their boundaries.

Keywords:
Brain structure segmentationEdge supervisionEdge-aware networkFrequency separationMulti-task learning

More Related Videos

Author Spotlight: Advancing 3D Cytoarchitecture Analysis - Rapid Volumetric Reconstruction of the Human Brain
06:52

Author Spotlight: Advancing 3D Cytoarchitecture Analysis - Rapid Volumetric Reconstruction of the Human Brain

Published on: January 26, 2024

2.3K
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

9.0K

Related Experiment Videos

Last Updated: Aug 26, 2025

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.8K
Author Spotlight: Advancing 3D Cytoarchitecture Analysis - Rapid Volumetric Reconstruction of the Human Brain
06:52

Author Spotlight: Advancing 3D Cytoarchitecture Analysis - Rapid Volumetric Reconstruction of the Human Brain

Published on: January 26, 2024

2.3K
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

9.0K

Area of Science:

  • Medical Imaging
  • Neuroimaging Analysis
  • Artificial Intelligence in Medicine

Background:

  • Accurate brain Magnetic Resonance Image (MRI) segmentation is crucial for diagnosing neuropsychiatric diseases.
  • Existing segmentation methods struggle with blurred boundaries and complex brain structures, limiting diagnostic precision.
  • Enhanced segmentation requires explicit modeling of spatial localization (low-frequency content) and shape appearance (high-frequency edge features).

Purpose of the Study:

  • To develop a novel network, the edge-aware network (EA-Net), for simultaneously segmenting brain structures and detecting object edges in MRI.
  • To improve the extraction of rich feature representations by decoupling low-frequency content and high-frequency edge information.
  • To enhance the robustness and accuracy of brain MRI segmentation, particularly in low-quality and noisy images.

Main Methods:

  • A frequency decoupling (FD) block is proposed to separate low-frequency content and high-frequency edge features within MRI data.
  • An encoder-decoder sub-network processes multi-level information, feeding into the FD block for frequency separation.
  • Distinct optimization mechanisms are applied to low- and high-frequency features, with final fusion for prediction; edge and content masks are extracted using specialized supervisions.

Main Results:

  • The EA-Net demonstrated superior performance compared to state-of-the-art methods on the IBSR and MALC brain MRI T1 scan datasets.
  • Segmentation accuracy, measured by the Dice Similarity Coefficient (DSC) score, was improved by up to 1.31% compared to U-Net variants.
  • The EA-Net exhibited significant robustness and superior performance under various noise disturbances in low-quality MRI scans.

Conclusions:

  • The proposed EA-Net effectively segments brain structures and detects edges by leveraging frequency decoupling, outperforming existing methods.
  • The network's ability to explicitly learn boundary features through specialized supervisions enhances segmentation accuracy and robustness.
  • EA-Net offers a promising advancement for clinical diagnosis and research involving brain MRI analysis, especially in challenging imaging conditions.