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 Videos

Interpretable Skin Cancer Identification Using a Hybrid Deep Learning and XAI Framework on HAM10000.

Bhagyashri S Sonune1, R Udaya Kumar1, K Sankar2

  • 1Department of Computer Science, Kalinga University, Raipur 492101, Chhattisgarh, India.

Bioengineering (Basel, Switzerland)
|June 26, 2026
PubMed
Summary

Related Concept Videos

Skin Cancer01:30

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

AI-driven multimodal retinal imaging for early detection and risk stratification of vascular and neurodegenerative diseases.

Graefe's archive for clinical and experimental ophthalmology = Albrecht von Graefes Archiv fur klinische und experimentelle Ophthalmologie·2026
Same author

Substrate-driven optimization of microfluidic aluminum-air fuel cells: a comparative study of glass fiber vs. cellulose paper.

Scientific reports·2026
Same author

Machine learning-assisted paper-based chemiluminescence biosensor for choline quantification in infant milk: toward portable nutritional quality monitoring.

Scientific reports·2026
Same author

Biosensing technologies for foodborne pathogen detection and healthcare: principles, emerging materials, and intelligent platforms.

Mikrochimica acta·2026
Same author

Artificial Intelligence Meets Nail Diagnostics: Emerging Image-Based Sensing Platforms for Non-Invasive Disease Detection.

Bioengineering (Basel, Switzerland)·2026
Same author

From Drops to Decisions: AI/ML-Driven Biofluidics for Clinical Diagnostics and Healthcare Intelligence.

Analytical chemistry·2025
Same journal

Correction: Komatsu et al. Three-Dimensional Visualization and Detection of the Pulmonary Venous-Left Atrium Connection Using Artificial Intelligence in Fetal Cardiac Ultrasound Screening. <i>Bioengineering</i> 2026, <i>13</i>, 100.

Bioengineering (Basel, Switzerland)·2026
Same journal

Comparison of CO<sub>2</sub> Laser and Microdebrider in the Surgical Treatment of Pediatric Recurrent Respiratory Papillomatosis: A Retrospective Analysis.

Bioengineering (Basel, Switzerland)·2026
Same journal

Toward More Translational Tumor Models: Breast dECM-Based 3D Systems Capture Native Microenvironmental Cues.

Bioengineering (Basel, Switzerland)·2026
Same journal

Postural Stability Changes During the 4 Phases of the Half Squat: Kinematics Profile of the Center of Pressure and Center of Mass in High-Performance Weightlifters-A Pilot Study.

Bioengineering (Basel, Switzerland)·2026
Same journal

Definite Implant Position as Novel Readout for Effectiveness of Ridge Preservation Indicates to Beneficial Effect of Combined Treatment with Platelet-Rich Fibrin (PRF) and Xenogenic Biomaterial in Bone Regeneration.

Bioengineering (Basel, Switzerland)·2026
Same journal

Trueness and Precision of Intraoral Scanners for 3D-Printed Orthodontic Models with Attachments: An In Vitro Comparative Study.

Bioengineering (Basel, Switzerland)·2026
See all related articles
This summary is machine-generated.

This study introduces a hybrid deep learning and machine learning framework for skin lesion classification, improving diagnostic accuracy and interpretability. The best model, DenseNet201 with SVM-RBF, achieved 90.88% accuracy, enhancing clinical decision-making.

Area of Science:

  • Dermatology
  • Artificial Intelligence
  • Computer Science

Background:

  • Deep learning shows promise for automated skin lesion classification.
  • Challenges include imbalanced classes and poor model interpretability.
  • Hybrid models combining deep and shallow learning are under-explored.

Purpose of the Study:

  • To evaluate a systematic framework for comparing hybrid models for skin lesion classification.
  • To address performance inconsistencies and improve clinical interpretability.
  • To compare multiple deep feature extractors with classical classifiers using various metrics.

Main Methods:

  • Extracted deep features from DenseNet201, InceptionV3, and EfficientNet-B4.
  • Inputted features into six classical classifiers, creating 18 hybrid models.
Keywords:
cancer detectionconvolutional neural networks (CNNs)deep learning (DL)explainable artificial intelligence (XAI)image analysismachine learning (ML)skin lesion classification

Related Experiment Videos

  • Systematically compared models using metrics like accuracy, macro-F1, and ROC-AUC.
  • Optimized decision thresholds based on macro-F1 score maximization.
  • Applied explainable AI (XAI) techniques (Grad-CAM, LIME, Occlusion Sensitivity) for model interpretation.

    • Main Results:

    • DenseNet201 with SVM-RBF classifier achieved the highest performance (90.88% accuracy, 90.7% macro-precision, 0.921 ROC-AUC).
    • All tested hybrid models were compared using multiple clinically relevant metrics.
    • XAI analysis confirmed that top models focused on lesion-specific areas, indicating clinical plausibility.

    Conclusions:

    • A reproducible hybrid-XAI framework was developed for skin lesion classification.
    • The framework supports transparent and clinically meaningful diagnostic tools.
    • Hybrid models offer a promising approach to overcome limitations of single deep learning classifiers.