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

UniOCTSeg++: Refined Hierarchical Prompt Strategy and Bi-directional Progressive Consistency Learning for Universal Retinal Layer Segmentation in OCT.

IEEE transactions on medical imaging·2026
Same author

TailBoost: Tail-Synthetic Learning for Boosting Long-Tailed Skin Cancer Image Classification.

Sensors (Basel, Switzerland)·2026
Same author

A Mixed Single-Echo and Multiecho MyoFoldstar for Simultaneous Quantification of Myocardial T<sub>1</sub>, T<sub>2</sub>, T<sub>2</sub>*, and Wall Motion.

NMR in biomedicine·2026
Same author

ABI4-HDA9 Module Epigenetically Silences GIG1 to Accumulate Methylglyoxal for Seed Thermoinhibition Response in Arabidopsis thaliana.

Plant, cell & environment·2026
Same author

Energy collaborative optimization of power routing based on PPO and generative adversarial imitation learning.

PloS one·2026
Same author

Author Correction: Polyrotaxane-based supramolecular theranostics.

Nature communications·2026

Related Experiment Video

Updated: Sep 13, 2025

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging
06:08

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

16.9K

SET: Superpixel Embedded Transformer for skin lesion segmentation.

Zhonghua Wang1, Junyan Lyu2, Xiaoying Tang1

  • 1Department of Electronic and Electrical Engineering, Southern University of Science and Technology, Shenzhen, China; Jiaxing Research Institute, Southern University of Science and Technology, Jiaxing, China.

Medical Image Analysis
|July 30, 2025
PubMed
Summary
This summary is machine-generated.

This study introduces Superpixel Embedded Transformer (SET) for improved skin lesion segmentation. SET enhances early skin cancer detection by better capturing lesion context and structure using superpixels.

Keywords:
Ensemble learningSkin lesion segmentationSuperpixelVision transformer

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

523
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

2.9K

Related Experiment Videos

Last Updated: Sep 13, 2025

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging
06:08

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

16.9K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

523
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

2.9K

Area of Science:

  • Computer Vision
  • Medical Image Analysis
  • Artificial Intelligence

Background:

  • Accurate skin lesion segmentation is vital for early skin cancer detection and treatment.
  • Current deep learning models face challenges in capturing global context and maintaining lesion structural integrity.

Purpose of the Study:

  • To introduce the Superpixel Embedded Transformer (SET) for enhanced skin lesion segmentation.
  • To address limitations in capturing global context and structural integrity in existing methods.

Main Methods:

  • Integrated superpixels into the Transformer framework using an Association Embedded Merging & Dispatching (AEM&D) module.
  • Utilized a superpixel bank with varying compactness values for multi-scale information capture.
  • Employed an Ensemble Fusion and Refinery (EFR) module for fusing and refining segmentation results.

Main Results:

  • Demonstrated superior performance compared to state-of-the-art methods on ISIC datasets (2016, 2017, 2018).
  • Ablation studies confirmed the effectiveness of superpixel integration within the Vision Transformer framework.

Conclusions:

  • The proposed SET model significantly improves skin lesion segmentation accuracy.
  • SET's novel approach effectively captures multi-scale features and structural information, advancing diagnostic capabilities.