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

Characteristics and efficacy of canalith-repositioning maneuvers for benign paroxysmal positional vertigo in very elderly patients.

Acta oto-laryngologica·2026
Same author

[The application of domestic ear molding system in bilateral neonatal congenital ear malformation].

Lin chuang er bi yan hou tou jing wai ke za zhi = Journal of clinical otorhinolaryngology head and neck surgery·2026
Same author

Computational intelligence using nailfold videocapillaroscopy for the prediction of carotid intima-media thickness in rheumatoid arthritis: a cohort-based study.

Rheumatology international·2026
Same author

Condensate-based sequestration enables high-efficiency synthesis of mussel foot protein Mcofp-3.

Applied and environmental microbiology·2026
Same author

miR-494-3p/G6PC/FOXO1 signaling axis drives autophagy-mediated breast cancer progression and predicts poor prognosis.

Cellular signalling·2026
Same author

Complete genome sequence of <i>Methylomonas defluvii</i> YC3 isolated from the cyclic activated sludge system of a banknote printing facility.

Microbiology resource announcements·2026

Related Experiment Video

Updated: Jul 27, 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

2.8K

AMSUnet: A neural network using atrous multi-scale convolution for medical image segmentation.

Yunchou Yin1, Zhimeng Han1, Muwei Jian2

  • 1School of Computer Science and Technology, Ocean University of China, Qingdao, China.

Computers in Biology and Medicine
|June 5, 2023
PubMed
Summary

We developed AMSUnet, a lightweight medical image segmentation model using atrous multi-scale (AMS) convolution. This network achieves superior segmentation performance for various target scales with only 2.62 million parameters.

Keywords:
Attention mechanismConvolutional attentionMedical image processingNeural network

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

447
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.5K

Related Experiment Videos

Last Updated: Jul 27, 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

2.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

447
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.5K

Area of Science:

  • Medical image processing
  • Deep learning for medical imaging
  • Computer vision

Background:

  • Unet and its variants are successful in medical image segmentation.
  • Existing Unet variants often have a large number of parameters, hindering lightweight applications.
  • There is a need for efficient and high-performance medical image segmentation models.

Purpose of the Study:

  • To develop a lightweight and high-performance medical image segmentation network.
  • To introduce a novel network architecture named AMSUnet.
  • To improve segmentation accuracy for diverse target scales.

Main Methods:

  • Developed AMSUnet, a network incorporating atrous multi-scale (AMS) convolution.
  • Constructed a convolutional attention block (AMS) and redesigned the downsampling encoder (AMSE).
  • Integrated a residual attention mechanism (RSC) into skip connections for enhanced feature fusion.

Main Results:

  • AMSUnet achieves superior segmentation performance across small, medium, and large-scale targets.
  • The proposed model is lightweight, requiring only 2.62 million parameters.
  • Experimental results demonstrate the effectiveness of AMSUnet on various datasets.

Conclusions:

  • AMSUnet offers a compelling solution for lightweight and effective medical image segmentation.
  • The integration of AMS convolution and RSC module enhances segmentation accuracy.
  • The model's efficiency and performance make it suitable for diverse medical imaging applications.