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 4, 2026

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

An automated framework to classify skin lesions using Multi-Head Self Attention Layer-based Vision Transformers.

Sahil Faizal1, Charu Anant Rajput1, Manas Ranjan Prusty2

  • 1School of Computer Science and Engineering, Vellore Institute of Technology, Chennai, India.

Frontiers in Artificial Intelligence
|May 21, 2026
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

CA<sup>2</sup>PNet: a context-aware multi-scale architecture with adaptive attention and progressive dilated convolutions for biomedical image segmentation.

Frontiers in artificial intelligence·2026
Same author

An attention-augmented lightweight convolutional framework for fine-grained plant leaf disease classification.

Frontiers in plant science·2026
Same author

Training Indoor and Scene-Specific Semantic Segmentation Models to Assist Blind and Low Vision Users in Activities of Daily Living.

IEEE open journal of engineering in medicine and biology·2025
Same author

Advanced IoT-integrated parking systems with automated license plate recognition and payment management.

Scientific reports·2025
Same author

Time-frequency transformation integrated with a lightweight convolutional neural network for detection of myocardial infarction.

BMC medical imaging·2024
Same author

A single NLR gene confers resistance to leaf and stripe rust in wheat.

Nature communications·2024

This study introduces a novel AI model for classifying nine types of skin lesions, achieving 93.22% accuracy. The system utilizes Vision Transformer for feature extraction, aiding in early skin cancer detection.

Area of Science:

  • Dermatology and Artificial Intelligence
  • Medical Image Analysis

Background:

  • Skin lesions are common, and early detection of malignant types is crucial for combating skin cancer.
  • Automated classification systems for diverse skin lesion categories remain limited.

Purpose of the Study:

  • To develop an automated system for classifying skin lesion images into nine distinct categories.
  • To enhance early detection and classification of potentially malignant skin lesions.

Main Methods:

  • Utilized contrast stretching for image enhancement and Region of Interest (ROI) segmentation.
  • Implemented Vision Transformer (ViT) for novel feature extraction in skin lesion detection.
  • Employed a multi-layer perceptron (MLP) for multinomial classification.
Keywords:
Multi-Head Self Attention LayerVision Transformerscontrast stretchingmulti-layer perceptronskin lesion detection

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

Related Experiment Videos

Last Updated: Jun 4, 2026

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

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

Main Results:

  • Achieved a high training accuracy of 98%.
  • Attained a testing accuracy of approximately 93.22% across nine lesion classes.
  • Demonstrated robust performance in classifying diverse skin lesion types.

Conclusions:

  • The proposed AI model shows significant potential for accurate skin lesion classification.
  • The model's scalability suggests future applications in broader diagnostic contexts.
  • This advancement marks a milestone in automated dermatological diagnostics.