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 Experiment Video

Updated: Jun 15, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K

Enhancing Melanoma Diagnosis with Advanced Deep Learning Models Focusing on Vision Transformer, Swin Transformer, and

Serra Aksoy1, Pinar Demircioglu2,3, Ismail Bogrekci3

  • 1Institute of Computer Science, Ludwig Maximilian University of Munich (LMU), Oettingenstrasse 67, 80538 Munich, Germany.

Dermatopathology (Basel, Switzerland)
|August 27, 2024
PubMed
Summary

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

Deep Learning-Based Evaluation of Maxillary Dental Midline Deviation on Orthodontic Frontal Photographs.

Bioengineering (Basel, Switzerland)·2026
Same author

An Explainable Web-Based Diagnostic System for Alzheimer's Disease Using XRAI and Deep Learning on Brain MRI.

Diagnostics (Basel, Switzerland)·2025
Same author

SeruNet-MS: A Two-Stage Interpretable Framework for Multiple Sclerosis Risk Prediction with SHAP-Based Explainability.

Neurology international·2025
Same author

A Web-Deployed, Explainable AI System for Comprehensive Brain Tumor Diagnosis.

Neurology international·2025

Early detection of aggressive melanoma is crucial. Advanced deep learning models, particularly ConvNeXt, show high accuracy in classifying benign and malignant skin lesions from dermoscopic images, improving diagnostic efficiency.

Area of Science:

  • Dermatology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Melanoma is an aggressive skin cancer requiring early detection for improved survival rates.
  • Accurate diagnosis of melanoma from dermoscopic images is challenging but vital for timely treatment.
  • Current diagnostic methods can be enhanced by advanced computational approaches.

Purpose of the Study:

  • To evaluate the efficacy of deep learning models, including ConvNeXt, Vision Transformer (ViT) Base-16, and Swin Transformer V2 Small (Swin V2 S), for melanoma classification.
  • To enhance the accuracy and efficiency of diagnosing benign versus malignant melanoma using dermoscopic images.
  • To identify the most effective deep learning architecture for early melanoma detection.

Main Methods:

  • Utilized a dataset of 13,900 uniformly sized dermoscopic images from Kaggle.
Keywords:
ConvNeXtSwin TransformerViTbenign and malignant tumorsmedical imaging

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

379
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

2.7K

Related Experiment Videos

Last Updated: Jun 15, 2025

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

1.8K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

379
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

2.7K
  • Preprocessed images to standardize inputs for deep learning models.
  • Compared the performance of ConvNeXt, ViT Base-16, and Swin V2 S models in classifying melanoma.

    • Main Results:

    • ConvNeXt achieved the highest diagnostic accuracy at 91.5%.
    • ConvNeXt demonstrated balanced precision and recall for benign (90.45%, 92.8%) and malignant (92.61%, 90.2%) cases.
    • ConvNeXt achieved F1-scores of 91.61% for benign and 91.39% for malignant cases.

    Conclusions:

    • Deep learning, especially hybrid architectures like ConvNeXt, shows significant potential for accurate melanoma diagnosis.
    • ConvNeXt offers a promising tool for improving early melanoma detection through automated image analysis.
    • Further research into advanced AI models can enhance medical image analysis in dermatology.