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

4.0K
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...
4.0K

You might also read

Related Articles

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

Sort by
Same author

Cooling-Triggered Release of Celecoxib from Implantable Alginate-Soluplus Composite Devices.

ACS biomaterials science & engineering·2025
Same author

Polymeric Nanoparticles Enable Targeted Visualization of Drug Delivery in Breast Cancer.

Molecular pharmaceutics·2025
Same author

Using The Cancer Genome Atlas from cBioPortal to Develop Genomic Datasets for Machine Learning Assisted Cancer Treatment.

bioRxiv : the preprint server for biology·2025
Same author

Polymeric Micellar Nanoparticles Enable Image-guided Drug Delivery in Solid Tumors.

bioRxiv : the preprint server for biology·2024
Same author

Ferroptosis Inhibitors Suppress Prostaglandin Synthesis in Lipopolysaccharide-Stimulated Macrophages.

ACS chemical biology·2023
Same author

Discovery of a Redox-Activatable Chemical Probe for Detection of Cyclooxygenase-2 in Cells and Animals.

ACS chemical biology·2022

Related Experiment Video

Updated: Jun 18, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K

Machine Learning Approaches for Skin Neoplasm Diagnosis.

Abu Asaduzzaman1, Christian C Thompson1, Md Jashim Uddin2

  • 1Wichita State University, College of Engineering, Wichita, Kansas 67260, United States.

ACS Omega
|August 5, 2024
PubMed
Summary

Machine learning significantly improves skin cancer diagnosis accuracy. Techniques like generative adversarial networks (GANs) and synthetic minority oversampling technique (SMOTE) enhance computer-aided diagnosis (CADx) systems for better skin neoplasm classification.

More Related Videos

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

2.3K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K

Related Experiment Videos

Last Updated: Jun 18, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K
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

2.3K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K

Area of Science:

  • Dermatology and Medical Imaging
  • Artificial Intelligence in Healthcare
  • Computational Pathology

Background:

  • Traditional skin neoplasm diagnosis methods like physical exams and biopsies are often time-consuming and prone to errors.
  • Machine learning (ML) demonstrates potential in accurately classifying skin images, distinguishing between conditions like melanoma and melanocytic nevi.
  • Existing computer-aided diagnosis (CADx) systems require enhancement for improved diagnostic performance in dermatology.

Purpose of the Study:

  • To investigate and enhance machine learning approaches for improving the performance of CADx systems in diagnosing skin diseases.
  • To evaluate the effectiveness of generative adversarial networks (GANs) and data balancing techniques in improving skin image classification accuracy.
  • To compare the performance of various ML models, including LDA, SVM, CNN, and ensemble methods, for skin neoplasm diagnosis.

Main Methods:

  • Utilized exploratory data analysis (EDA) for data normalization to prevent model overfitting.
  • Applied Synthetic Minority Oversampling Technique (SMOTE) to address class imbalances within the dataset.
  • Employed a generative adversarial network (GAN) discriminator to identify and remove artificial images.
  • Trained and evaluated Linear Discriminant Analysis (LDA), Support Vector Machine (SVM), Convolutional Neural Network (CNN), and an ensemble CNN-SVM model on the HAM10000 dataset.

Main Results:

  • Initial accuracies for LDA, SVM, CNN, and ensemble CNN-SVM were 49%, 72%, 77%, and 79%, respectively.
  • After applying GAN (discriminator) and SMOTE, accuracies improved significantly: LDA (76%), SVM (83%), CNN (87%), and ensemble CNN-SVM (94%).
  • The ensemble CNN-SVM model achieved the highest accuracy of 94% post-enhancement, demonstrating superior performance.

Conclusions:

  • Machine learning models, particularly the ensemble CNN-SVM, show substantial promise in enhancing CADx systems for skin neoplasm diagnosis.
  • Data preprocessing techniques, including GANs and SMOTE, are crucial for improving the accuracy and robustness of ML models in medical image analysis.
  • Further research will explore additional ML models and datasets to advance automated skin disease diagnosis.