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

Detection of solid pigment in dermatoscopy images using texture analysis.

Anantha Murali1, William V. Stoecker, Randy H. Moss

  • 1D2 Technologies, Santa Barbara, CA, Stoecker & Associates, Rolla, and Dermatology M173, University of Missouri Health Sciences Center, MO and Department of Electrical and Computer Engineering, University of Missouri-Rolla, Rolla, MO, USA.

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

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

The 5 P's of Pyoderma Gangrenosum

Journal of drugs in dermatology : JDDยท2019
See all related articles

This study developed an automated method using texture analysis to detect solid pigment in dermatoscopic images. The presence of solid pigment, particularly in the periphery, shows promise in differentiating benign from malignant pigmented lesions.

Area of Science:

  • Dermatology
  • Medical Imaging
  • Computational Pathology

Background:

  • Epiluminescence microscopy (ELM), or dermoscopy, reveals subsurface features of pigmented lesions.
  • Solid pigment, a dark structureless area, is a key ELM feature.
  • Distinguishing benign from malignant pigmented lesions requires identifying subtle features.

Purpose of the Study:

  • To develop an algorithm for automatic detection of solid pigment using texture analysis.
  • To assess the utility of solid pigment detection in classifying pigmented lesions.

Main Methods:

  • A texture-based algorithm utilizing Neighboring Gray Level Dependence Matrix (NGLDM) was developed.
  • Optimal parameters (d and a) for NGLDM were determined experimentally.
  • The algorithm was tested on 37 pigmented lesion images.

Related Experiment Videos

Main Results:

  • The NGLDM large number emphasis (N2) effectively detected solid pigment.
  • Solid pigment was identified in 9 out of 37 lesions; no melanomas lacked this feature.
  • A novel index based on peripheral solid pigment successfully differentiated benign from malignant lesions, with one exception (Spitz nevus).

Conclusions:

  • Texture analysis can detect significant dermatoscopic features in digital images.
  • A new index shows potential for distinguishing benign from malignant pigmented lesions.
  • Further validation on a larger dataset is required.