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

The influence of the elastic modulus of the plaque in carotid artery on the computed results of FFR<sub>CT</sub>.

Computer methods in biomechanics and biomedical engineering·2020
Same author

Double-Color Lanthanide Metal-Organic Framework Based Logic Device and Visual Ratiometric Fluorescence Water Microsensor for Solid Pharmaceuticals.

Analytical chemistry·2019
Same author

LUCAT1 contributes to MYRF-dependent smooth muscle cell apoptosis and may facilitate aneurysm formation via the sequestration of miR-199a-5p.

Cell biology international·2019
Same author

Comprehensive investigation of key biomarkers and pathways in hepatitis B virus-related hepatocellular carcinoma.

Journal of Cancer·2019
Same author

Effects of a 3D-printed orthosis compared to a low-temperature thermoplastic plate orthosis on wrist flexor spasticity in chronic hemiparetic stroke patients: a randomized controlled trial.

Clinical rehabilitation·2019
Same author

Two new species of the primitively segmented spider genus <i>Liphistius</i> Schiödte, 1849 (Mesothelae, Liphistiidae) from Myanmar.

ZooKeys·2019

Related Experiment Video

Updated: Sep 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

2.9K

Warp-based edge feature reinforcement network for medical image segmentation.

Xin Fan1, Xiaojing Kang2, Shengwei Tian3,4

  • 1School of Information Science and Engineering, Xinjiang University, Urumqi, China.

Medical Physics
|July 23, 2022
PubMed
Summary

This study introduces EFR-Net, a novel deep learning model for medical image segmentation. EFR-Net enhances edge detection and context exploration, outperforming existing methods in accuracy and efficiency for various medical imaging tasks.

Keywords:
edge reinforcementmedical imagemultiscale feature fusionsemantic segmentation

More Related Videos

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

488
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

2.6K

Related Experiment Videos

Last Updated: Sep 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

2.9K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

488
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

2.6K

Area of Science:

  • Medical Image Analysis
  • Deep Learning
  • Computer Vision

Background:

  • Accurate medical image segmentation is crucial for diagnosing life-threatening diseases.
  • Challenges in segmentation include fuzzy edges and background similarity, leading to under/over-segmentation.

Purpose of the Study:

  • To develop a novel deep learning model for improved medical image segmentation.
  • To address challenges of fuzzy edges and background similarity in medical images.

Main Methods:

  • Proposed a novel edge features-reinforcement (EFR) module using relative frequency changes for edge information extraction.
  • Introduced a multiscale context exploration (MCE) module for fusing multiscale features and capturing channel/spatial correlations.
  • Constructed EFR-Net by integrating EFR and MCE modules into an encoder-decoder architecture.

Main Results:

  • EFR-Net achieved high Dice Similarity Coefficients (DSCs) on four diverse datasets: DRIVE (81.61%), CVC-ClinicDB (92.87%), ISIC2018 (89.87%), and Aorta-CT (96.98%).
  • The model demonstrated superior performance compared to current mainstream segmentation methods.
  • Polyp segmentation DSC saw a significant increase of 3.87%.

Conclusions:

  • EFR-Net surpasses current mainstream segmentation methods in quantitative and qualitative evaluations.
  • The EFR module effectively enhances edge prediction in color and CT images.
  • The proposed modules are versatile and can be integrated into other architectures for broader applications.