Share Email Print

Proceedings Paper

A machine learning method for identifying morphological patterns in reflectance confocal microscopy mosaics of melanocytic skin lesions in-vivo
Author(s): Kivanc Kose; Christi Alessi-Fox; Melissa Gill; Jennifer G. Dy; Dana H. Brooks; Milind Rajadhyaksha
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper 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 − 81% sensitivity and 81 − 89% specificity in distinguishing these patterns.

Paper Details

Date Published: 29 February 2016
PDF: 8 pages
Proc. SPIE 9689, Photonic Therapeutics and Diagnostics XII, 968908 (29 February 2016); doi: 10.1117/12.2212978
Show Author Affiliations
Kivanc Kose, Memorial Sloan-Kettering Cancer Ctr. (United States)
Christi Alessi-Fox, Caliber Imaging and Diagnostics, Inc. (United States)
Melissa Gill, Skin Medical Research and Diagnostics (United States)
Jennifer G. Dy, Northeastern Univ. (United States)
Dana H. Brooks, Northeastern Univ. (United States)
Milind Rajadhyaksha, Memorial Sloan-Kettering Cancer Ctr. (United States)

Published in SPIE Proceedings Vol. 9689:
Photonic Therapeutics and Diagnostics XII
Hyun Wook Kang; Guillermo J. Tearney M.D.; Melissa C. Skala; Bernard Choi; Andreas Mandelis; Brian J. F. Wong M.D.; Justus F. Ilgner M.D.; Nikiforos Kollias; Paul J. Campagnola; Kenton W. Gregory M.D.; Laura Marcu; Haishan Zeng, Editor(s)

© SPIE. Terms of Use
Back to Top