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

Hierarchical Deep Learning Framework for Skin Disease and Cancer Classification Performance Enhancement.

Chanapa Chaitan1, Sasithorn Tengjongdee1, Suejit Pechprasarn1,2

  • 1College of Biomedical Engineering, Rangsit University, Pathum Thani 12000, Thailand.

Sensors (Basel, Switzerland)
|May 13, 2026
PubMed
Summary
This summary is machine-generated.

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

Sensing Mechanisms of Rough Plasmonic Surfaces for Protein Binding of Surface Plasmon Resonance Detection.

Sensors (Basel, Switzerland)·2023
Same author

Analysis of Deep Learning-Based Phase Retrieval Algorithm Performance for Quantitative Phase Imaging Microscopy.

Sensors (Basel, Switzerland)·2022
Same author

Generalized figure of merit for plasmonic dip measurement-based surface plasmon resonance sensors.

Biomedical optics express·2022
Same author

Cuff-Less Blood Pressure Prediction from ECG and PPG Signals Using Fourier Transformation and Amplitude Randomization Preprocessing for Context Aggregation Network Training.

Biosensors·2022
Same author

Analysis of the surface plasmon resonance interferometric imaging performance of scanning confocal surface plasmon microscopy.

Biomedical optics express·2022
Same author

Analysis of Effects of Surface Roughness on Sensing Performance of Surface Plasmon Resonance Detection for Refractive Index Sensing Application.

Sensors (Basel, Switzerland)·2021
Same journal

RETRACTED: Zhang et al. A Novel Framework for Reconstruction and Imaging of Target Scattering Centers via Wide-Angle Incidence in Radar Networks. <i>Sensors</i> 2025, <i>25</i>, 6802.

Sensors (Basel, Switzerland)·2026
Same journal

Enhancing Unsupervised Multi-Source Domain Adaptation for Person Re-Identification via Mixture of Experts and Graph-Based Relation.

Sensors (Basel, Switzerland)·2026
Same journal

Development of an Instrumented Glove for Palmar Pressure Assessment in Kayakers.

Sensors (Basel, Switzerland)·2026
Same journal

Development and Experimental Validation of an Autonomous IoT-Based Monitoring System for Real-Time Water Quality Assessment in the Amazon River.

Sensors (Basel, Switzerland)·2026
Same journal

Semi-Supervised Adversarial Learning Framework for Controller Area Network Bus Intrusion Detection.

Sensors (Basel, Switzerland)·2026
Same journal

Smart Optimization Method for Safety Signs in Innovative Manufacturing Environments Integrating Industrial Field IoT Sensors and Knowledge Graphs.

Sensors (Basel, Switzerland)·2026
See all related articles

A new hierarchical model significantly improves skin cancer classification accuracy. This approach uses multiple binary classifiers, achieving an 82.62% recall, a substantial increase for better clinical decision support.

Area of Science:

  • Dermatology and Medical Imaging
  • Artificial Intelligence in Healthcare
  • Computer Vision

Background:

  • Skin cancer diagnosis relies on visual inspection, which requires expert dermatologists and faces challenges with similar-looking lesions.
  • Accurate classification of skin conditions, encompassing both benign and malignant types, is crucial for timely and effective treatment.

Purpose of the Study:

  • To address the complexity of classifying multiple skin lesion images by developing a hierarchical binary classification model.
  • To enhance the performance and reduce the task complexity compared to conventional single multi-class classification models.

Main Methods:

  • Four convolutional neural network (CNN) models (MobileNetV2, EfficientNet-B0, ResNet-18, ResNet-50) were evaluated.
  • A hierarchical binary classification approach was proposed and compared against traditional multi-class classification methods.
Keywords:
convolutional neural networksdeep learninghierarchical binary classificationmulti-class classificationskin cancer

Related Experiment Videos

  • Recall was prioritized as the primary evaluation metric to minimize false negatives in skin lesion classification.

    • Main Results:

    • The proposed hierarchical model achieved a recall of 82.62%, a 22.35% increase over the best single model (MobileNetV2 at 60.27%).
    • Significant improvements were observed across other metrics: accuracy (+25.46%), precision (+17.21%), F1-score (+21.34%), balanced accuracy (+12.69%), specificity (+3.03%), and G-mean (+14.25%).
    • The hierarchical approach demonstrated superior performance in correctly identifying both positive and negative cases, reducing misclassification rates.

    Conclusions:

    • The hierarchical binary classification model offers a significant performance improvement for classifying skin lesion images.
    • Using recall as a selection criterion effectively identifies suitable CNN models within the hierarchical framework.
    • The enhanced model generalizability shows potential for broad applicability in clinical decision-support systems for dermatology.