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

Simultaneous tDCS-rTMS stimulation to regulate the language network and improve language ability in Landau-Kleffner syndrome.

Epilepsia open·2025
Same author

BTFormer: Blast transformer for human blastocyst components segmentation.

PloS one·2025
Same author

Dynamic evolution of frontal-temporal network connectivity in temporal lobe epilepsy: A magnetoencephalography study.

Human brain mapping·2024
Same author

The association of magnetoencephalography high-frequency oscillations with epilepsy types and a ripple-based method with source-level connectivity for mapping epilepsy sources.

CNS neuroscience & therapeutics·2023
Same author

Dynamic brain functional network based on EEG microstate during sensory gating in schizophrenia.

Journal of neural engineering·2022
Same author

<i>In Vitro</i> Cell Migration through Three-Dimensional Interfaces of Varying Depths, Widths, and Curvatures on Micropatterned Polymer Surfaces.

ACS applied bio materials·2022

Related Experiment Video

Updated: Nov 9, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

627

SA-Net: A scale-attention network for medical image segmentation.

Jingfei Hu1,2,3,4, Hua Wang1,2,3,4, Jie Wang5

  • 1School of Biological Science and Medical Engineering, Beihang University, Beijing, China.

Plos One
|April 14, 2021
PubMed
Summary

This study introduces the scale-attention deep learning network (SA-Net) for enhanced medical image segmentation. SA-Net effectively captures multi-scale features, improving accuracy in diverse medical imaging applications.

More Related Videos

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
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 9, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

627
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
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 analysis
  • Deep learning for computer vision

Background:

  • Semantic segmentation is crucial for medical image analysis.
  • Conventional U-Net networks are widely used but can be improved.
  • Multi-scale features are important for accurate medical image segmentation.

Purpose of the Study:

  • To propose a novel deep learning network, SA-Net, for improved medical image segmentation.
  • To enhance the learning of multi-scale features in medical images.
  • To achieve more accurate segmentation across various medical imaging datasets.

Main Methods:

  • Developed a scale-attention deep learning network (SA-Net).
  • SA-Net extracts multi-scale features using residual modules.
  • An attention module is incorporated to enforce scale-attention capabilities.

Main Results:

  • SA-Net demonstrated superior performance in medical image segmentation tasks.
  • Achieved excellent results in retinal vessel detection, lung segmentation, artery/vein classification, and blastocyst segmentation.
  • Validated the method's effectiveness across multiple datasets.

Conclusions:

  • SA-Net effectively learns multi-scale features for accurate medical image segmentation.
  • The proposed network offers improved performance over conventional methods.
  • The publicly available code will aid scientific community utilization.