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

Advancing workpiece dimension measurement: Integrating AI-based edge detection with machine vision and coordinate measuring systems.

PloS one·2026

Same author

AI Advancements in Healthcare: Medical Imaging and Sensing Technologies.

Bioengineering (Basel, Switzerland)·2025

Same author

New Gait Representation Maps for Enhanced Recognition in Clinical Gait Analysis.

Bioengineering (Basel, Switzerland)·2025

Same author

HIRD-Net: An Explainable CNN-Based Framework with Attention Mechanism for Diabetic Retinopathy Diagnosis Using CLAHE-D-DoG Enhanced Fundus Images.

Life (Basel, Switzerland)·2025

Same author

A graph attention network-based multi-agent reinforcement learning framework for robust detection of smart contract vulnerabilities.

Scientific reports·2025

Same author

Human pose estimation in physiotherapy fitness exercise correction using novel transfer learning approach.

PeerJ. Computer science·2025

Search research articles

Related Experiment Video

Updated: Jun 6, 2025

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

A Unified Multi-Task Learning Model with Joint Reverse Optimization for Simultaneous Skin Lesion Segmentation and

Mohammed A Al-Masni¹, Abobakr Khalil Al-Shamiri², Dildar Hussain¹

¹Department of Artificial Intelligence and Data Science, College of AI Convergence, Sejong University, Seoul 05006, Republic of Korea.

Bioengineering (Basel, Switzerland)

|November 27, 2024

Summary

This summary is machine-generated.

This study introduces a unified multi-task learning method for improved skin cancer classification and segmentation from dermoscopy images, enhancing diagnostic accuracy in automated systems.

Keywords:

classification joint reverse optimization multi-task learning segmentation skin cancer

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

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

Related Experiment Videos

Last Updated: Jun 6, 2025

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

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

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

Area of Science:

Dermatology and Medical Imaging
Artificial Intelligence in Healthcare
Computational Pathology

Background:

Automated skin cancer diagnosis using dermoscopy images faces challenges from lesion variability and image quality issues.
Accurate classification and segmentation of skin lesions are crucial for effective automated diagnostic systems.
Existing single-task learning approaches for classification or segmentation show limitations.

Purpose of the Study:

To develop a unified multi-task learning strategy for concurrent skin lesion classification and segmentation.
To enhance the performance of both classification and segmentation tasks by leveraging their inherent correlation.
To address challenges posed by diverse lesion shapes and fuzzy dermoscopy image characteristics.

Main Methods:

A unified multi-task learning network was proposed, integrating joint reverse learning for feature sharing and task balance.
The method concurrently performs skin lesion abnormality classification and lesion boundary segmentation.
The approach was evaluated on two public datasets: ISIC 2016 and PH².

Main Results:

The multi-task learning approach significantly improved segmentation performance, achieving Dice Similarity Coefficients (DSC) of 89.48% (ISIC 2016) and 88.81% (PH²).
Classification performance was enhanced, with F1 scores increasing from 78.26% to 82.07% on ISIC 2016 and 82.38% to 85.50% on PH², compared to baseline ResNet50.
Experimental findings demonstrated superior diagnostic capability over single-task learning strategies.

Conclusions:

The proposed unified multi-task learning strategy effectively enhances both skin lesion classification and segmentation.
Joint reverse learning facilitates mutual enhancement between classification and segmentation tasks.
This approach shows significant potential for improving automated skin tumor screening and analysis in clinical settings.