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

Computer recognition of skin structures using discriminant and cluster analysis.

Josef Smolle1

  • 1Department of Dermatology, Division of Analytical-Morphological Dermatology, University of Graz, Graz, Austria.

Skin Research and Technology : Official Journal of International Society for Bioengineering and the Skin (ISBS) [And] International Society for Digital Imaging of Skin (ISDIS) [And] International Society for Skin Imaging (ISSI)
|June 29, 2001
PubMed
Summary

Discriminant and cluster analysis accurately interpret skin images by analyzing digital features. These computational methods offer a reliable, unbiased approach for identifying skin structures automatically.

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

Management and Outcomes of Sternoclavicular Joint Infections: A Retrospective Study.

Journal of clinical medicine·2025
Same author

Hyperbaric oxygen (HBO<sub>2</sub>) therapy in thermal burn injury revisited. Pressure does matter. Review.

Undersea & hyperbaric medicine : journal of the Undersea and Hyperbaric Medical Society, Inc·2024
Same author

Measuring the global mechanical properties of the human thorax: Costo-vertebral articulation.

Journal of biomechanics·2024
Same author

Immediate and Long-Term Effects of Hyperbaric Oxygenation in Patients with Long COVID-19 Syndrome Using SF-36 Survey and VAS Score: A Clinical Pilot Study.

Journal of clinical medicine·2023
Same author

The Prognostic Long-Term Impact of Chronic Obstructive Pulmonary Disease and Postoperative Mucostasis in Patients with Curatively Resected Non-Small Cell Lung Cancer.

Cells·2023
Same author

Covid-19 mortality and local burden of infectious diseases: A worldwide country-by-country analysis.

Journal of infection and public health·2022

Area of Science:

  • Dermatology
  • Computational Biology
  • Image Analysis

Background:

  • Automated analysis of complex tissues, like skin, is challenging due to difficulties in recognizing specialized structures.
  • Current computer-based methods often struggle with the intricate details present in skin imagery.

Purpose of the Study:

  • To evaluate the effectiveness of discriminant and cluster analysis for interpreting digital skin images.
  • To develop a more objective and automated system for skin structure identification.

Main Methods:

  • Digital skin images (microscopic, dermatoscopic, clinical) were dissected into uniform elements.
  • Grey level, color, and texture features were extracted from each element.
  • Elements were classified using interactive discriminant analysis and automated hierarchical cluster analysis (Ward method).

Related Experiment Videos

Main Results:

  • The system demonstrated high reproducibility in detecting diverse skin structures.
  • Discriminant analysis achieved 98-100% correct reclassification of interactively classified elements.
  • The Ward method, after feature selection, provided optimal automated classification results across different image sources.

Conclusions:

  • Discriminant and cluster analysis show significant potential for objective, user-independent skin structure measurement.
  • These computational techniques can enhance the accuracy and reliability of dermatological image analysis.
  • The developed methods are applicable across various imaging modalities of skin specimens.