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

Shape analysis for classification of malignant melanoma.

E Claridge1, P N Hall, M Keefe

  • 1School of Computer Science, University of Birmingham, Edgbaston, UK.

Journal of Biomedical Engineering
|May 1, 1992
PubMed
Summary

Computer analysis of mole shape can help distinguish melanoma from benign lesions. Quantitative measures of shape and border irregularity achieved 91% sensitivity and 69% specificity in classifying these skin tumors.

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

Mn-porphyrins in a four-helix bundle participate in photo-induced electron transfer with a bacterial reaction center.

Photosynthesis research·2023
Same author

Identification of amino acid residues in a proton release pathway near the bacteriochlorophyll dimer in reaction centers from Rhodobacter sphaeroides.

Photosynthesis research·2022
Same author

A bound iron porphyrin is redox active in hybrid bacterial reaction centers modified to possess a four-helix bundle domain.

Photochemical & photobiological sciences : Official journal of the European Photochemistry Association and the European Society for Photobiology·2021
Same author

Dermoscopy for melanoma detection and triage in primary care: a systematic review.

BMJ open·2019
Same author

My Teaching Partner-Secondary: A video-based coaching model.

Theory into practice·2017
Same author

Measurements of limb oedema in chronic venous disease: A review.

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)·2016

Area of Science:

  • Dermatology
  • Medical Imaging
  • Computational Analysis

Background:

  • Melanoma, a malignant skin tumor, has an excellent prognosis if detected and surgically removed early.
  • Distinguishing benign pigmented lesions from melanoma is crucial, with shape irregularity being a key indicator.
  • Both patients and clinicians face challenges in consistently identifying mole shape irregularity.

Purpose of the Study:

  • To develop and apply computer image analysis methods for quantifying mole shape irregularity.
  • To derive objective measures of shape parameters used in melanoma assessment.
  • To evaluate the effectiveness of these quantitative measures in classifying melanomas.

Main Methods:

  • Utilized computer image analysis to derive quantitative measures of lesion shape and border.

Related Experiment Videos

  • Employed a 'bulkiness' measure for overall lesion shape.
  • Applied two fractal dimension measures (structural and textural) to assess border irregularity.

    • Main Results:

    • The developed computer image analysis methods were applied to silhouettes of 43 melanomas and 45 benign lesions.
    • A combination of quantitative measures achieved 91% sensitivity in correctly classifying melanomas.
    • The classification achieved 69% specificity for benign lesions.

    Conclusions:

    • Computer-derived quantitative measures of shape and border irregularity can aid in distinguishing melanoma.
    • Objective assessment of mole morphology using image analysis shows promise for improved melanoma detection.
    • This approach offers a potential tool to support dermatologists in melanoma diagnosis.