Automatic Detection of Blue-White Veil and Related Structures in Dermoscopy Images - Computer Science > Computer Vision and Pattern RecognitionReport as inadecuate




Automatic Detection of Blue-White Veil and Related Structures in Dermoscopy Images - Computer Science > Computer Vision and Pattern Recognition - Download this document for free, or read online. Document in PDF available to download.

Abstract: Dermoscopy is a non-invasive skin imaging technique, which permitsvisualization of features of pigmented melanocytic neoplasms that are notdiscernable by examination with the naked eye. One of the most importantfeatures for the diagnosis of melanoma in dermoscopy images is the blue-whiteveil irregular, structureless areas of confluent blue pigmentation with anoverlying white -ground-glass- film. In this article, we present a machinelearning approach to the detection of blue-white veil and related structures indermoscopy images. The method involves contextual pixel classification using adecision tree classifier. The percentage of blue-white areas detected in alesion combined with a simple shape descriptor yielded a sensitivity of 69.35%and a specificity of 89.97% on a set of 545 dermoscopy images. The sensitivityrises to 78.20% for detection of blue veil in those cases where it is a primaryfeature for melanoma recognition.



Author: M. Emre Celebi, Hitoshi Iyatomi, William V. Stoecker, Randy H. Moss, Harold S. Rabinovitz, Giuseppe Argenziano, H. Peter Soyer

Source: https://arxiv.org/







Related documents