Linear discriminant analysis of dermoscopic parameters for the differentiation of early melanomas from Clark naevi

Hiroshi Oka, Masaru Tanaka, Seiichiro Kobayashi, Giuseppe Argenziano, H. Peter Soyer, Takeji Nishikawa

Research output: Contribution to journalArticlepeer-review

Abstract

As a first step to develop a screening system for pigmented skin lesions, we performed digital discriminant analyses between early melanomas and Clark naevi. A total of 59 cases of melanoma, including 23 melanoma in situ and 36 thin invasive melanomas (Breslow thickness ≤ 0.75 mm), and 188 clinically equivocal, histopathologically diagnosed Clark naevi were used in ou study. After calculating 62 mathematical variables related to the colour, texture, asymmetry and circularity based on the dermoscopic findings of the pigmented skin lesions, we performed multivariate stepwise discriminant analysis using these variables to differentiate melanomas from naevi. The sensitivities and specificities of our model were 94.4 and 98.4%, respectively, for discriminating between melanomas (Breslow thickness ≤ 0.75 mm) and Clark naevi, and 73.9 and 85.6%, respectively, for discriminating between melanoma in situ and Clark naevi. Our algorithm accurately discriminated invasive melanomas from Clark naevi, but not melanomas in situ from Clark naevi.

Original languageEnglish
Pages (from-to)131-134
Number of pages4
JournalMelanoma Research
Volume14
Issue number2
DOIs
Publication statusPublished - Apr 2004

Keywords

  • Clark naevus
  • Dermoscopy
  • Digital diagnosis
  • Discriminant analysis
  • Malignant melanoma

ASJC Scopus subject areas

  • Cancer Research
  • Dermatology

Fingerprint Dive into the research topics of 'Linear discriminant analysis of dermoscopic parameters for the differentiation of early melanomas from Clark naevi'. Together they form a unique fingerprint.

Cite this