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

Skin Cancer01:30

Skin Cancer

5.7K
Skin cancer is a type of cancer that occurs when there is an abnormal growth of skin cells, usually triggered by damage to the DNA within the skin cells. It is primarily caused by exposure to ultraviolet (UV) radiation from the sun or artificial sources like tanning beds. Skin cancer is the most common type of cancer worldwide, and its incidence continues to rise.
Basal Cell Carcinoma (BCC): BCC is the most common type of skin cancer, accounting for about 80% of cases. It typically develops in...
5.7K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Usnic acid inhibits colorectal cancer liver metastasis by targeting CRYAB phosphorylation and inducing ferroptosis.

Cell communication and signaling : CCS·2026
Same author

Chiral π-conjugated polymer films <i>via</i> kinetically controlled dip-coating for circularly polarized light information encoding.

Nanoscale·2026
Same author

Experimental Investigation on the Rock-Breaking Efficiency of High-Pressure Jet Drill Rod Perforation in Sandstone Roof.

ACS omega·2026
Same author

The Role of Thioredoxin in Mitigating Ammonia-Induced Oxidative Stress in Nile Tilapia (<i>Oreochromis niloticus</i>).

Animals : an open access journal from MDPI·2026
Same author

Carbide-Os Interactions Enhance Deuterium Evolution and Electrolytic Hydrogen Isotope Separation Efficiency.

ACS applied materials & interfaces·2026
Same author

An integrated approach to mining layout design for compound-hazards mines with coordinated rockburst and water inrush control.

Scientific reports·2026

Related Experiment Video

Updated: Jan 8, 2026

SCAnED - An Open-source Skin Segmentation Macro for Semi-automated Cell and Nuclei Detection in Epidermal and Dermal Skin Compartments
06:34

SCAnED - An Open-source Skin Segmentation Macro for Semi-automated Cell and Nuclei Detection in Epidermal and Dermal Skin Compartments

Published on: August 8, 2025

499

EASNet: Edge-aware Segmentation Network for Skin Lesion Segmentation with Boundary-aware and Frequency Attention

Junwei Yu1, Yuhe Xia2, Jianping Li2

  • 1School of Artificial Intelligence and Big Data, Henan University of Technology, Zhengzhou, 450001, China. yujunwei@126.com.

Interdisciplinary Sciences, Computational Life Sciences
|December 12, 2025
PubMed
Summary

A new deep learning model, EASNet, improves skin cancer detection by analyzing lesion boundaries and frequency features. This advanced segmentation network offers more precise clinical assessment for dermatological image analysis.

Keywords:
Boundary-driven criss-cross attentionFrequency-domain transformHybrid lossSkin 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

3.3K
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

3.1K

Related Experiment Videos

Last Updated: Jan 8, 2026

SCAnED - An Open-source Skin Segmentation Macro for Semi-automated Cell and Nuclei Detection in Epidermal and Dermal Skin Compartments
06:34

SCAnED - An Open-source Skin Segmentation Macro for Semi-automated Cell and Nuclei Detection in Epidermal and Dermal Skin Compartments

Published on: August 8, 2025

499
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

3.3K
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

3.1K

Area of Science:

  • Dermatology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Cutaneous malignancies are globally prevalent, necessitating improved diagnostic tools.
  • Current deep learning models struggle with complex lesion boundaries and frequency features in dermoscopy images.

Purpose of the Study:

  • To introduce EASNet, an edge-aware segmentation network for enhanced dermatological image analysis.
  • To overcome limitations of existing convolutional neural network (CNN) approaches in segmenting complex skin lesions.

Main Methods:

  • EASNet integrates frequency-domain analysis using Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT).
  • It employs a Boundary-Driven Criss-Cross (BDCC) attention mechanism for spatial dependency learning.
  • A hybrid loss function ensures accurate boundary supervision during training.

Main Results:

  • EASNet demonstrated competitive performance on ISIC2017 and ISIC2018 datasets.
  • The network achieved high precision in lesion segmentation and boundary clarity.
  • Positional consistency in segmentation was also significantly improved.

Conclusions:

  • EASNet advances dermatological image analysis by combining frequency and boundary information.
  • This network provides a reliable tool for precise clinical assessment of skin lesions.
  • The findings support the development of improved therapeutic strategies for cutaneous malignancies.