Authors: | Bozkurt, A.; Gale, T.; Kose, K.; Alessi-Fox, C.; Brooks, D. H.; Rajadhyaksha, M.; Dy, J. |
Title: | Delineation of skin strata in reflectance confocal microscopy images with recurrent convolutional networks |
Conference Title: | 30th IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW 2017) |
Abstract: | Reflectance confocal microscopy (RCM) is an effective, non-invasive pre-screening tool for cancer diagnosis. However, acquiring and reading RCM images requires extensive training and experience, and novice clinicians exhibit high variance in diagnostic accuracy. Consequently, there is a compelling need for quantitative tools to standardize image acquisition and analysis. In this study, we use deep recurrent convolutional neural networks to delineate skin strata in stacks of RCM images collected at consecutive depths. To perform diagnostic analysis, clinicians collect RCM images at 4-5 specific layers in the tissue. Our model automates this process by discriminating between RCM images of different layers. Testing our model on an expert labeled dataset of 504 RCM stacks, we achieve 87.97% classification accuracy, and a 9-fold reduction in the number of anatomically impossible errors compared to the previous state-of-the-art. © 2017 IEEE. |
Keywords: | image acquisition; diagnostic accuracy; confocal microscopy; image analysis; reflectance confocal microscopies; reflection; computer vision; statistical tests; pattern recognition; classification (of information); neural networks; convolution; convolutional networks; convolutional neural network; deep neural networks; recurrent neural networks; classification accuracy; diagnostic analysis; image acquisition and analysis; quantitative tool |
Journal Title | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops |
Conference Dates: | 2017 Jul 21-26 |
Conference Location: | Honolulu, HI |
ISBN: | 1063-6919 |
Publisher: | IEEE |
Location: | Los Alamitos, CA |
Date Published: | 2017-01-01 |
Start Page: | 777 |
End Page: | 785 |
Language: | English |
DOI: | 10.1109/cvprw.2017.108 |
PROVIDER: | scopus |
DOI/URL: | |
Notes: | ISSN: 2160-7508 -- Conference Paper -- Export Date: 2 November 2017 -- Source: Scopus |