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

Analysis of skin line pattern for lesion classification.

Zhishun She1, Peter J Fish

  • 1School of Informatics, University of Wales, Dean Street, Bangor, LL57 1UT, UK.

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)
|January 22, 2003
PubMed
Summary

Analyzing skin pattern disruption in optical images can help differentiate malignant melanoma from benign lesions. A new, computationally inexpensive method effectively measures skin line direction and variation for improved diagnostic accuracy.

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

Lesion classification using 3D skin surface tilt orientation.

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)·2012
Same author

Skin pattern analysis for lesion classification using local isotropy.

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)·2011
Same author

Combination of features from skin pattern and ABCD analysis for lesion classification.

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)·2007
Same author

Simulation and analysis of optical skin lesion images.

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)·2006
Same author

Time-scale removal of "wall thump" in Doppler ultrasound signals: a simulation study.

IEEE transactions on ultrasonics, ferroelectrics, and frequency control·2004
Same author

Enhancement of lesion classification using divergence, curl and curvature of skin pattern.

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)·2004

Area of Science:

  • Dermatology
  • Medical Imaging
  • Computational Pathology

Background:

  • Skin lesion pattern disruption differs between malignant and benign types.
  • Optical imaging of skin patterns offers potential diagnostic value.
  • Previous methods for measuring skin pattern disruption were computationally intensive.

Purpose of the Study:

  • To develop a simpler, computationally low-cost method to measure skin pattern disruption for lesion classification.
  • To assess the effectiveness of analyzing skin line direction and variation for distinguishing malignant melanoma from benign lesions.

Main Methods:

  • Skin patterns extracted using high-pass filtration and adaptive anisotropic filtering.
  • Skin line direction and variance estimated via local image gradient matrix.

Related Experiment Videos

  • Classification based on the difference in line direction and variation across lesion boundaries.

    • Main Results:

    • Excellent separation of malignant melanoma and benign naevi observed in a 2D feature space.
    • Receiver Operating Characteristic (ROC) plot analysis yielded an area of 0.88.
    • The developed method demonstrated high accuracy in distinguishing lesion types.

    Conclusions:

    • Local skin line direction and variation are effective features for differentiating malignant melanoma from benign lesions.
    • The proposed image analysis method is both effective and computationally efficient.
    • This approach offers a promising, low-cost tool for diagnostic feature sets in skin lesion analysis.