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: Oct 12, 2025

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

2.5K

Generative Adversarial Network Image Synthesis Method for Skin Lesion Generation and Classification.

Freedom Mutepfe1, Behnam Kiani Kalejahi1,2, Saeed Meshgini2

  • 1Department of Computer Science and Engineering, School of Science and Engineering, Khazar University, Baku, Azerbaijan.

Journal of Medical Signals and Sensors
|November 25, 2021
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Skin Cancer01:30

Skin Cancer

4.9K
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...
4.9K

You might also read

Related Articles

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

Sort by
Same author

Multimodal deep learning for papillary thyroid carcinoma diagnosis using ultrasound and cytology.

BMC medical imaging·2026
Same author

Hybrid Neural Network Architecture for Automated Liver and Tumor Segmentation Using Ensemble Learning on CT Images.

Biomimetics (Basel, Switzerland)·2026
Same author

Smart Logistics Model for Supply Chain Management via Brain-Inspired Geometric Deep Networks.

Biomimetics (Basel, Switzerland)·2026
Same author

Deep Learning-Based Automatic Segmentation of Ischemic Stroke Lesions in CT Perfusion Imaging.

Biomimetics (Basel, Switzerland)·2026
Same author

Developing an Artificial Intelligence Solution to Autosegment the Edentulous Maxillary Bone for Implant Planning.

European journal of dentistry·2026
Same author

GAN-Based Cross-Modality Brain MRI Synthesis: Paired Versus Unpaired Training and Comparison with Diffusion and Transformer Models.

Biomimetics (Basel, Switzerland)·2026
Same journal

Predicting Theta/Alpha Neurofeedback Success through Psychological and Personality Profiles: A Hybrid Approach Using Multilayer Perceptron and Elastic Net Models.

Journal of medical signals and sensors·2026
Same journal

Efficient Techniques Based on Sparse Representation for Classifying High-dimensional Multiclass Microarray Data.

Journal of medical signals and sensors·2026
Same journal

Supervised Volumetric Segmentation of White and Gray Matter from Brain Positron Emission Tomography Images Using Magnetic Resonance Labels.

Journal of medical signals and sensors·2026
Same journal

Effective Connectivity-based Unsupervised Channel Selection Method for Electroencephalography.

Journal of medical signals and sensors·2026
Same journal

Enhancement of Digital Mammography Images Using Neutrosophic Divergence Score Based on Intuitionistic Fuzzy Entropy.

Journal of medical signals and sensors·2026
Same journal

Monitoring the Adverse Implications of Coronavirus 2019-induced Pulmonary Complications on Patients' Respiratory Capacity and Physical Abilities with Moderate and Severe Signs during Interval Follow-up.

Journal of medical signals and sensors·2026
See all related articles

This study developed an automated machine learning model for skin cancer detection, achieving 93.5% accuracy. The model aids dermatologists in classifying skin lesions for earlier cancer diagnosis and treatment.

Area of Science:

  • Artificial Intelligence
  • Medical Imaging
  • Computational Biology

Background:

  • Early cancer detection is crucial but current methods like visual examination and biopsy are time-consuming and error-prone.
  • Automated machine learning models are essential for rapid diagnoses and timely cancer treatment.
  • Improving skin lesion classification accuracy can significantly aid dermatologists in cancer management.

Purpose of the Study:

  • To establish a fully automatic model for assisting dermatologists in skin cancer handling.
  • To enhance skin lesion classification accuracy using advanced computational techniques.
  • To develop a reliable tool for early detection and diagnosis of skin cancer.

Main Methods:

  • Implementation of a Deep Convolutional Generative Adversarial Network (DCGAN) using Keras.
Keywords:
DCGANdermoscopypretrainingskin lesion

Related Experiment Videos

Last Updated: Oct 12, 2025

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

2.5K
  • Incorporation of image filtering and enhancement algorithms, such as bilateral filters, for improved feature detection.
  • Hyperparameter optimization, including adjustments to learning rate and Adam optimization momentum, to stabilize GAN training and improve performance.
  • Binary classification of skin lesions into benign and malignant categories.
  • Evaluation using metrics like Receiver Operating Characteristic - Area Under the Curve (ROC-AUC) and confusion matrix.

    • Main Results:

    • The DCGAN model generated realistic skin lesions during experimentation.
    • Fine-tuning of network parameters led to a significant improvement in classification accuracy.
    • An overall test accuracy of 93.5% was achieved for skin lesion classification.
    • The model demonstrated effective feature detection and extraction capabilities.

    Conclusions:

    • The developed classification model offers spatial intelligence for potential future cancer risk prediction.
    • Challenges remain in generating high-fidelity synthetic images comparable to real samples.
    • Comparing classification methods is difficult due to the use of non-public datasets in some studies.