Share Email Print

Proceedings Paper

Deep learning based classification of morphological patterns in RCM to guide noninvasive diagnosis of melanocytic lesions (Conference Presentation)
Author(s): Kivanc Kose; Alican Bozkurt; Setareh Ariafar; Christi A. Alessi-Fox; Melissa Gill; Jennifer G. Dy; Dana H. Brooks; Milind Rajadhyaksha

Paper Abstract

In this study we present a deep learning based classification algorithm for discriminating morphological patterns that appear in RCM mosaics of melanocytic lesions collected at the dermal epidermal junction (DEJ). These patterns are classified into 6 distinct types in the literature: background, meshwork, ring, clod, mixed, and aspecific. Clinicians typically identify these morphological patterns by examination of their textural appearance at 10X magnification. To mimic this process we divided mosaics into smaller regions, which we call tiles, and classify each tile in a deep learning framework. We used previously acquired DEJ mosaics of lesions deemed clinically suspicious, from 20 different patients, which were then labelled according to those 6 types by 2 expert users. We tried three different approaches for classification, all starting with a publicly available convolutional neural network (CNN) trained on natural image, consisting of a series of convolutional layers followed by a series of fully connected layers: (1) We fine-tuned this network using training data from the dataset. (2) Instead, we added an additional fully connected layer before the output layer network and then re-trained only last two layers, (3) We used only the CNN convolutional layers as a feature extractor, encoded the features using a bag of words model, and trained a support vector machine (SVM) classifier. Sensitivity and specificity were generally comparable across the three methods, and in the same ranges as our previous work using SURF features with SVM . Approach (3) was less computationally intensive to train but more sensitive to unbalanced representation of the 6 classes in the training data. However we expect CNN performance to improve as we add more training data because both the features and the classifier are learned jointly from the data. *First two authors share first authorship.

Paper Details

Date Published: 19 April 2017
PDF: 1 pages
Proc. SPIE 10037, Photonics in Dermatology and Plastic Surgery, 100370C (19 April 2017); doi: 10.1117/12.2253076
Show Author Affiliations
Kivanc Kose, Memorial Sloan-Kettering Cancer Ctr. (United States)
Alican Bozkurt, Northeastern Univ. (United States)
Setareh Ariafar, Memorial Sloan-Kettering Cancer Ctr. (United States)
Christi A. Alessi-Fox, Caliber Imaging & 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. 10037:
Photonics in Dermatology and Plastic Surgery
Bernard Choi; Haishan Zeng; Nikiforos Kollias, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?