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 Experiment Video

Updated: Jun 6, 2026

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

MSGU-Net: a lightweight multi-scale ghost U-Net for image segmentation.

Hua Cheng1, Yang Zhang1, Huangxin Xu2,3

  • 1Chengdu Civil Aviation Information Technology Co., Ltd, Chengdu, China.

Frontiers in Neurorobotics
|January 21, 2025
PubMed
Summary

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

Acoustic Non-Abelian Topological Insulator Induced by Artificial SU(2) Gauge Fields.

Physical review letters·2026
Same author

COP9 signalosome 8 mediated autophagy drives proliferation, invasion, and metastasis in pancreatic ductal adenocarcinoma.

Biochemical and biophysical research communications·2026
Same author

Integrating physiological and transcriptomic analyses reveal the role of LrDREB2B in thermotolerance of Lycoris radiata.

Plant science : an international journal of experimental plant biology·2026
Same author

Biological effects of selenium on Hypnum plumaeforme and the underlying mechanisms mediated by physiology and microbiome.

Ecotoxicology and environmental safety·2026
Same author

Photonic Intrinsic Chiral Flatband With Tailorable Quality Factor and Circular Dichroism.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Janus Silica Microspheres-Reinforced Polymer-Based Composite Encapsulation Films with Enhanced Barrier and Mechanical Properties.

ACS applied materials & interfaces·2026

A new lightweight multi-scale Ghost U-Net (MSGU-Net) offers efficient image segmentation. This model significantly reduces computational costs and parameters while achieving superior performance on benchmark datasets.

Area of Science:

  • Computer Vision
  • Deep Learning
  • Medical Image Analysis

Background:

  • U-Net architectures are prevalent for image segmentation tasks.
  • Existing models often face challenges with computational efficiency and parameter overhead.
  • High-quality object mask generation is crucial for accurate segmentation.

Purpose of the Study:

  • To propose a lightweight multi-scale Ghost U-Net (MSGU-Net) for efficient image segmentation.
  • To enhance object mask generation quality and reduce computational demands.
  • To enable deployment on resource-constrained intelligent devices and mobile platforms.

Main Methods:

  • Integration of a pyramid structure (SPP-Inception) and ghost module for multi-scale information fusion.
  • Incorporation of efficient local attention (ELA) and attention gate mechanisms to identify regions of interest (ROI).
Keywords:
SPP-InceptionU-Netimage segmentationlightweight neural networkmulti-scale

More Related Videos

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

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Related Experiment Videos

Last Updated: Jun 6, 2026

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

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

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

  • Comparative analysis against state-of-the-art networks on ISIC2017 and ISIC2018 datasets.

    • Main Results:

    • MSGU-Net achieves superior segmentation performance compared to baseline U-Net.
    • Significant reduction in parameter (96.08%) and computation costs (92.59%).
    • Effective merging of multi-scale features from low-level, high-level, and decoder masks.

    Conclusions:

    • MSGU-Net provides an efficient and high-quality solution for image segmentation.
    • The proposed architecture demonstrates considerable potential for deployment on mobile and intelligent devices.
    • The model offers a balance between performance and computational efficiency.