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

A support vector machine for decision support in melanoma recognition.

Stephen Gilmore1, Rainer Hofmann-Wellenhof, H Peter Soyer

  • 1Dermatology Research Centre, The University of Queensland, School of Medicine, Princess Alexandra Hospital, Brisbane, Queensland, Australia. s.gilmore1@uq.edu.au

Experimental Dermatology
|July 16, 2010
PubMed
Summary
This summary is machine-generated.

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

The genomic and spatial transcriptomic landscape of seborrheic keratoses.

The Journal of investigative dermatology·2026
Same author

Charting a new melanoma risk factor: Satellite Naevus Prevalence in High-Risk and Population-Based Cohorts.

The Journal of investigative dermatology·2026
Same author

Dermatologists' Perspectives on Referral Systems and Legal Risk: Insights From a National Survey.

The Australasian journal of dermatology·2026
Same author

Spatially Profiling Trace Cytokine Signatures From Microscopically Derived Skin Samples to Probe Skin Disease Inflammation.

Small methods·2026
Same author

Nevus clustering on the back associated with in situ melanoma in a Queensland melanoma high-risk cohort.

The Journal of investigative dermatology·2026
Same author

A tissue multiplexing approach to maximize spatial omics output from pathology specimens.

Frontiers in medicine·2026

Early melanoma diagnosis is crucial for survival. Support vector machine (SVM) technology aids dermatologists by improving melanoma detection accuracy, complementing expert assessment for better clinical decisions.

Area of Science:

  • Dermatology
  • Medical Imaging
  • Machine Learning

Background:

  • Early melanoma diagnosis is vital for reducing mortality and improving patient survival rates.
  • Clinical examination of melanocytic lesions can be challenging, especially for atypical or dysplastic nevi due to structural heterogeneity.
  • Distinguishing difficult cases from melanoma often requires advanced diagnostic tools.

Purpose of the Study:

  • To evaluate the utility of support vector machine (SVM) technology for melanoma diagnosis using digital dermoscopic images.
  • To assess the performance of SVM models in classifying atypical melanocytic lesions.
  • To explore the integration of SVM-based decision support systems into clinical practice.

Main Methods:

  • Utilized a dataset of 199 digital dermoscopic images of excised atypical melanocytic lesions.

Related Experiment Videos

  • Developed and validated support vector machine (SVM) models for melanoma diagnosis.
  • Evaluated model performance using metrics such as sensitivity, specificity, diagnostic odds ratio, and AUC.

    • Main Results:

    • The best validation models achieved an average sensitivity of 0.86 and specificity of 0.72.
    • The top-performing model on the test set demonstrated a sensitivity of 0.89, a diagnostic odds ratio of 14.09, and an AUC of 0.76.
    • The SVM approach offers simple feature extraction and computationally efficient processing.

    Conclusions:

    • SVM technology shows promise as a valuable tool for dermatologists in melanoma diagnosis.
    • Integrating SVM-derived diagnoses with dermatologist assessments can enhance clinical decision-making and reduce the risk of missed melanomas.
    • The SVM model demonstrates favorable generalization and compares well with other algorithms and expert performance.