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 Concept Videos

Skin Cancer01:30

Skin Cancer

5.7K
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...
5.7K

You might also read

Related Articles

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

Sort by
Same author

A clinical decision support system for skin cancer classification using fractional gooseneck barnacle-enabled ensemble classifier.

Computational biology and chemistry·2025
See all related articles

Related Experiment Video

Updated: Jan 7, 2026

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
09:37

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

Published on: August 18, 2022

2.8K

EnsembleSkinNet: a transfer learning-based framework for efficient skin cancer detection with explainable AI

Srilakshmi Cherukuri1, Srisailapu D Vara Prasad1

  • 1Department of Computer Science and Engineering, GITAM Deemed to be University, Hyderabad, India.

Frontiers in Oncology
|December 31, 2025
PubMed
Summary

EnsembleSkinNet, an explainable AI framework, enhances skin cancer diagnosis by fusing multiple deep learning models. This approach improves accuracy and reliability, leading to earlier detection and better clinical outcomes for skin lesions.

Keywords:
convolutional neural networks (CNNs)deep learningensemble learningexplainable AIskin cancer detectiontransfer learning

More Related Videos

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging
06:08

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

17.2K

Related Experiment Videos

Last Updated: Jan 7, 2026

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
09:37

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

Published on: August 18, 2022

2.8K
Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging
06:08

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

17.2K

Area of Science:

  • Artificial Intelligence
  • Medical Imaging
  • Computational Biology

Background:

  • Skin cancer is a prevalent and dangerous disease, making early diagnosis crucial for effective treatment.
  • Deep learning, particularly Convolutional Neural Networks (CNNs), shows promise in AI-driven skin lesion classification.
  • Limitations in single CNN models include reduced generalization due to variations in lesion appearance and image quality.

Purpose of the Study:

  • To develop an explainable ensemble deep learning framework for robust skin image classification.
  • To enhance the reliability and generalization capabilities of AI models in diagnosing skin lesions.
  • To improve early detection rates and clinical confidence in AI-based skin cancer diagnosis.

Main Methods:

  • EnsembleSkinNet framework utilizes softmax-weighted spectrum fusion of pre-trained CNNs (M-VGG16, ResNet50, Inception V3, DenseNet201).
  • Employs transfer learning, fine-tuning, and Bayesian hyperparameter optimization for improved classification performance.
  • Evaluated using five-fold cross-validation on the HAM10000 dataset and external validation on the ISIC 2020 dataset.

Main Results:

  • Achieved high accuracy (98.32%) on the HAM10000 dataset with excellent precision, recall, and F1-score.
  • Demonstrated strong cross-domain generalization with 96.84% accuracy and 0.983 AUC on the ISIC 2020 dataset.
  • Grad-CAM explainability analysis showed 93.6% agreement with dermatologist annotations, indicating clinical relevance.

Conclusions:

  • EnsembleSkinNet offers a reproducible, interpretable, and clinically applicable framework for AI-based skin cancer diagnosis.
  • The ensemble approach enhances robustness and reliability, reducing false negatives for critical skin cancers like melanoma.
  • This AI framework can improve early detection rates and boost diagnostic confidence in clinical settings.