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

Feature Selection and Pedestrian Detection Based on Sparse Representation.

PloS one·2015
Same author

[A report of odontogenic cutaneous fistula on external nose].

Zhonghua er bi yan hou tou jing wai ke za zhi = Chinese journal of otorhinolaryngology head and neck surgery·2015
See all related articles

Related Experiment Video

Updated: Jun 21, 2025

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

2.4K

ELA-Net: An Efficient Lightweight Attention Network for Skin Lesion Segmentation.

Tianyu Nie1, Yishi Zhao2,3, Shihong Yao1

  • 1School of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, China.

Sensors (Basel, Switzerland)
|July 13, 2024
PubMed
Summary

We developed an efficient lightweight attention network (ELANet) for accurate skin lesion segmentation. ELANet balances high performance with a small model size, ideal for medical devices.

Keywords:
attention mechanismdeep learninglightweight networkmedical image processingskin lesion segmentation

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

2.7K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

385

Related Experiment Videos

Last Updated: Jun 21, 2025

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

2.4K
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

2.7K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

385

Area of Science:

  • Medical image analysis
  • Computer vision
  • Artificial intelligence in dermatology

Background:

  • Lightweight skin lesion segmentation is crucial for integrating AI into medical devices.
  • Existing lightweight models struggle with accuracy on complex skin lesion images.

Purpose of the Study:

  • To propose an efficient lightweight attention network (ELANet) for skin lesion segmentation.
  • To improve accuracy while maintaining a small model footprint for clinical applications.

Main Methods:

  • Utilized a bilateral residual module (BRM) with dual attention mechanisms for enhanced feature extraction.
  • Employed multi-scale attention fusion (MAF) to integrate global information and improve segmentation.
  • Stacked multiple BRMs for efficient processing of input data.

Main Results:

  • Achieved 89.87% mIoU on ISIC2016, 81.85% on ISIC2017, and 82.87% on ISIC2018.
  • Maintained a small parameter count of 0.459 M, demonstrating excellent lightness.
  • Outperformed existing segmentation methods in terms of accuracy and efficiency.

Conclusions:

  • ELANet offers a superior balance between accuracy and model lightness for skin lesion segmentation.
  • The proposed network is suitable for deployment on resource-constrained medical devices.
  • This approach advances the potential for AI-driven dermatological diagnostics.