Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Skin Cancer

Skin Cancer

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...

You might also read

Related Articles

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

Sort by

Same author

Feasibility and preliminary validation of an autonomous robotic ultrasound system for thyroid nodule screening: a pilot prospective study.

Journal of medical ultrasonics (2001)·2026

Same author

Quantitative transcriptomic and metabolic analyses reveal the roles of RpoS and Crp in the acid resistance system 1 in <i>Escherichia coli</i>.

Microbiology spectrum·2026

Same author

Complete Fuzzy Knowledge Representation With Knowledge Graph Embedding.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

Acetylation-mediated regulation of ALV viral proteins: Implications for retroviral inhibition.

PLoS pathogens·2026

Same author

Overview of Short Peptides for Hair Loss.

Biomedicines·2026

Same author

Chinese Society of Pediatric Anesthesiology Guideline for Pediatric Sedation (2025).

Paediatric anaesthesia·2026

Search research articles

Related Experiment Video

Updated: Jun 9, 2025

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

A Bi-Directionally Fused Boundary Aware Network for Skin Lesion Segmentation.

Feiniu Yuan, Yuhuan Peng, Qinghua Huang

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society

|October 23, 2024

Summary

This summary is machine-generated.

This study introduces the Bi-directionally Fused Boundary Aware Network (BiFBA-Net) for improved skin lesion segmentation. The novel network effectively fuses Convolutional Neural Network (CNN) and Transformer features, enhancing boundary detection for lesions of all sizes.

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

Related Experiment Videos

Last Updated: Jun 9, 2025

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

Area of Science:

Medical Image Analysis
Artificial Intelligence in Dermatology
Computer Vision

Background:

Accurate segmentation of skin lesions is challenging due to variations in shape, boundaries, and scale.
Convolutional Neural Networks (CNNs) excel at local feature extraction, while Transformers capture global context but lack spatial detail.
Existing methods struggle to effectively combine the strengths of both CNNs and Transformers for precise lesion boundary delineation.

Purpose of the Study:

To develop an advanced deep learning model for accurate and robust skin lesion segmentation.
To overcome the limitations of individual CNN and Transformer models in capturing both local and global features.
To improve the discrimination of small, blurred, or irregularly shaped skin lesions and enhance boundary accuracy.

Main Methods:

Proposed a novel Bi-directionally Fused Boundary Aware Network (BiFBA-Net) incorporating a dual-encoding structure.
Introduced a Bi-directional Attention Gate (Bi-AG) for effective crosswise feature fusion between CNN and Transformer encoders.
Implemented a progressive decoding structure with a Boundary Aware Decoder (BAD) utilizing residual connections and Reverse Attention (RA) for refined boundary segmentation.

Main Results:

BiFBA-Net achieved superior segmentation accuracy compared to existing methods on public datasets.
The network demonstrated significantly improved perception of lesion boundaries, effectively handling small and large lesions.
BiFBA-Net successfully alleviated over-segmentation of small lesions and under-segmentation of large ones.

Conclusions:

The proposed BiFBA-Net effectively integrates complementary features from CNNs and Transformers through bi-directional attention fusion.
The Boundary Aware Decoder significantly enhances the precision of skin lesion segmentation, particularly at the boundaries.
BiFBA-Net represents a promising advancement in automated skin lesion analysis, offering improved diagnostic potential.