Approximate lesion localization in dermoscopy images

M. Emre Celebi, Hitoshi Iyatomi, Gerald Schaefer, William V. Stoecker

Research output: Contribution to journalArticle

Abstract

Background: Dermoscopy is one of the major imaging modalities used in the diagnosis of melanoma and other pigmented skin lesions. Because of the difficulty and subjectivity of human interpretation, automated analysis of dermoscopy images has become an important research area. Border detection is often the first step in this analysis. Methods: In this article, we present an approximate lesion localization method that serves as a preprocessing step for detecting borders in dermoscopy images. In this method, first the black frame around the image is removed using an iterative algorithm. The approximate location of the lesion is then determined using an ensemble of thresholding algorithms. Results: The method is tested on a set of 428 dermoscopy images. The localization error is quantified by a metric that uses dermatologist-determined borders as the ground truth. Conclusion: The results demonstrate that the method presented here achieves both fast and accurate localization of lesions in dermoscopy images.

Original languageEnglish
Pages (from-to)314-322
Number of pages9
JournalSkin research and technology
Volume15
Issue number3
Early online date11 Jul 2009
DOIs
Publication statusPublished - Aug 2009

Keywords

  • border detection
  • dermoscopy
  • skin cancer
  • thresholding

Fingerprint Dive into the research topics of 'Approximate lesion localization in dermoscopy images'. Together they form a unique fingerprint.

Cite this