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

Epidemiology of childhood tuberculosis and factors associated with unsuccessful treatment outcomes in Tigray, Ethiopia: a ten-year retrospective cross sectional study.

BMC public health·2019
Same author

Prevalence and Rates of New Diagnosis and Missed Diagnosis of Diabetes Mellitus among 35-74-year-old Residents in Urban Communities in Southwest China.

Biomedical and environmental sciences : BES·2019
Same author

Insights into the degradation and detoxication mechanisms of aqueous capecitabine in electrochemical oxidation process.

Chemosphere·2019
Same author

Resolving electrical stimulus triggered molecular binding and force modulation upon thrombin-aptamer biointerface.

Journal of colloid and interface science·2019
Same author

Effect of periodic temperature shock on nitrogen removal performance and microbial community structure in plug-flow microaerobic sludge blanket.

Chemosphere·2019
Same author

Central Nervous System Complications after Allogeneic Hematopoietic Stem Cell Transplantation in Children.

Acta haematologica·2019

Related Experiment Video

Updated: May 16, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

331

Grouped multi-scale vision transformer for medical image segmentation.

Zexuan Ji1, Zheng Chen2, Xiao Ma1

  • 1School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, 210094, China.

Scientific Reports
|April 1, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces Grouped Multi-Scale Attention (GMSA) and Inter-Scale Attention (ISA) for advanced medical image segmentation. These methods improve the modeling of complex structures and achieve state-of-the-art results in clinical diagnosis.

Keywords:
Channel groupMedical image segmentationMulti-scaleSelf-attentionTransformer

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

2.6K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.7K

Related Experiment Videos

Last Updated: May 16, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

331
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

2.6K
A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.7K

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Artificial Intelligence

Background:

  • Medical image segmentation is crucial for diagnosis and research.
  • Convolutional Neural Networks (CNNs) have limitations in capturing long-range dependencies.
  • Vision Transformers (ViTs) show promise but struggle with multi-scale variations.

Purpose of the Study:

  • To enhance multi-scale feature representation in medical image segmentation.
  • To improve the modeling of complex anatomical structures.
  • To achieve state-of-the-art performance in medical image segmentation.

Main Methods:

  • Proposing Grouped Multi-Scale Attention (GMSA) for enhanced multi-scale feature representation.
  • Introducing Inter-Scale Attention (ISA) for effective cross-scale feature fusion.
  • Utilizing Vision Transformers (ViTs) with novel attention mechanisms.

Main Results:

  • GMSA enhances multi-scale feature representation by grouping channels and applying self-attention at different scales.
  • ISA facilitates cross-scale feature fusion, improving segmentation accuracy.
  • The proposed model achieves state-of-the-art results on Synapse, ACDC, and ISIC2018 datasets.

Conclusions:

  • The novel GMSA and ISA mechanisms significantly improve medical image segmentation.
  • The model effectively captures multi-scale variations and long-range dependencies.
  • This approach advances the capabilities of Vision Transformer-based medical image segmentation.