A machine learning method for identifying morphological patterns in reflectance confocal microscopy mosaics of melanocytic skin lesions in-vivo Conference Paper


Authors: Kose, K.; Alessi-Fox, C.; Gill, M.; Dy, J. G.; Brooks, D. H.; Rajadhyaksha, M.
Title: A machine learning method for identifying morphological patterns in reflectance confocal microscopy mosaics of melanocytic skin lesions in-vivo
Conference Title: Photonic Therapeutics and Diagnostics XII
Abstract: We present a machine learning algorithm that can imitate the clinicians qualitative and visual process of analyzing reflectance confocal microscopy (RCM) mosaics at the dermal epidermal junction (DEJ) of skin. We divide the mosaics into localized areas of processing, and capture the textural appearance of each area using dense Speeded Up Robust Feature (SURF). Using these features, we train a support vector machine (SVM) classifier that can distinguish between meshwork, ring, clod, aspecific and background patterns in benign conditions and melanomas. Preliminary results on 20 RCM mosaics labeled by expert readers show classification with 55 â' 81% sensitivity and 81 â' 89% specificity in distinguishing these patterns. © 2016 SPIE.
Keywords: confocal microscopy; algorithms; artificial intelligence; reflectance confocal microscopies; reflection; support vector machines; computer aided diagnosis; learning systems; dermal-epidermal junctions; reectance confocal microscopy; learning algorithms; computer-aided detection and diagnosis; melanocytic skin lesions; supervised classification; supervised learning; machine learning methods; morphological patterns; speeded up robust features
Journal Title Progress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume: 9689
Conference Dates: 2016 Feb 13-14
Conference Location: San Francisco, CA
ISBN: 1605-7422
Publisher: SPIE  
Date Published: 2016-02-29
Start Page: 968908
Language: English
DOI: 10.1117/12.2212978
PROVIDER: scopus
DOI/URL:
Notes: Conference Paper -- Conference code: 121711 -- Export Date: 1 July 2016 -- The Society of Photo-Optical Instrumentation Engineers (SPIE) -- 13 February 2016 through 14 February 2016 -- Source: Scopus
Altmetric
Citation Impact
BMJ Impact Analytics
MSK Authors
  1. Kivanc Kose
    81 Kose