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

You might also read

Related Articles

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

Sort by

Same author

Agricultural sustainability monitoring in arid regions using hybrid deep learning and Landsat 8 imagery in Najran City, Saudi Arabia.

Scientific reports·2026

Same author

Neural Efficiency and Attentional Instability in Gaming Disorder: A Task-Based Occipital EEG and Machine Learning Study.

Bioengineering (Basel, Switzerland)·2026

Same author

Hybrid deep learning and optimization-based land use and land cover classification for advancing sustainable agriculture in Najran city, Saudi Arabia.

Scientific reports·2025

Same author

Analyzing histopathological images using fused CNN features based on the geometric active contour method for early diagnosis of lung and colon cancer.

Discover oncology·2025

Same author

Enhanced early skin cancer detection through fusion of vision transformer and CNN features using hybrid attention of EViT-Dens169.

Scientific reports·2025

Same author

Brain tumor segmentation by optimizing deep learning U-Net model.

Technology and health care : official journal of the European Society for Engineering and Medicine·2025

Search research articles

Related Experiment Video

Updated: Apr 1, 2026

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

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

Deep neural network-based robust framework for automated skin lesion segmentation and analysis.

Khlood M Mehdar¹, Toufique A Soomro², Ahmed Ali³

¹Department of Anatomy, Faculty of Medicine, Najran University, Najran, Kingdom of Saudi Arabia.

|March 31, 2026

Summary

This summary is machine-generated.

This study introduces a novel deep neural network for accurate skin lesion segmentation in dermoscopic images. The method enhances early skin cancer detection by improving segmentation accuracy and consistency over existing approaches.

Keywords:

International Skin Imaging Collaboration (ISIC) benchmark datasets Skin lesion segmentation automated skin cancer diagnosis deep neural network (DNN) framework pre-processing and post-processing modules

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

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Related Experiment Videos

Last Updated: Apr 1, 2026

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

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

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

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Area of Science:

Dermatology
Medical Imaging
Artificial Intelligence

Background:

Accurate skin lesion segmentation is crucial for computer-aided diagnosis of skin cancer.
Challenges include variations in lesion appearance, texture, sharpness, and indistinct edges.

Purpose of the Study:

To develop and evaluate a novel deep neural network (DNN)-based approach for robust and accurate skin lesion segmentation.
Utilize advanced pre-processing and post-processing techniques for improved segmentation.

Main Methods:

Integrated a DNN architecture with specialized pre-processing (denoising, normalization) and post-processing (boundary refinement, artifact removal) modules.
Tested on International Skin Imaging Collaboration (ISIC) datasets (2016, 2017, 2018) without extensive data augmentation.
Compared performance against state-of-the-art methods like U-Net, UNet++, and Swin-Unet.

Main Results:

Achieved high Jaccard index scores (e.g., 89.91% for ISIC 2016) and Dice coefficients (e.g., 94.30% for ISIC 2016).
Outperformed U-Net, UNet++, and Swin-Unet in segmentation accuracy, consistency, and computational efficiency.
Demonstrated robust performance across multiple datasets.

Conclusions:

Presents a high-performing, scalable solution for automated skin lesion segmentation.
Effectively addresses segmentation challenges through integrated feature extraction and boundary refinement.
Well-suited for real-world clinical applications in skin cancer diagnosis and management.