Anatomical skin segmentation in reflectance confocal microscopy with weak labels

Hames, Samuel C., Ardigo, Marco, Soyer, H. Peter, Bradley, Andrew P. and Prow, Tarl W. (2016). Anatomical skin segmentation in reflectance confocal microscopy with weak labels. In: 2015 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2015. International Conference on Digital Image Computing: Techniques and Applications, DICTA 2015, Adelaide, Australia, (1-8). 23-25 November 2015. doi:10.1109/DICTA.2015.7371231


Author Hames, Samuel C.
Ardigo, Marco
Soyer, H. Peter
Bradley, Andrew P.
Prow, Tarl W.
Title of paper Anatomical skin segmentation in reflectance confocal microscopy with weak labels
Conference name International Conference on Digital Image Computing: Techniques and Applications, DICTA 2015
Conference location Adelaide, Australia
Conference dates 23-25 November 2015
Convener IEEE
Proceedings title 2015 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2015
Place of Publication Piscataway, NJ, United States
Publisher Institute of Electrical and Electronics Engineers
Publication Year 2016
Year available 2016
Sub-type Fully published paper
DOI 10.1109/DICTA.2015.7371231
Open Access Status Not Open Access
ISBN 9781467367950
Start page 1
End page 8
Total pages 8
Collection year 2017
Language eng
Abstract/Summary Reflectance confocal microscopy (RCM) allows in-vivo microscopic examination of human skin and is emerging as a powerful tool for a wide range of dermatological problems. Clinical use of RCM is limited by the need for trained experts to interpret images and the lack of supporting tools for quantitative evaluation of the images, especially in large datasets. The first task in understanding RCM images is to understand and produce a segmentation of the anatomical strata of human skin. This work presents such an algorithm using only weak supervision, in the form of labels for whole en-face sections, to learn a per pixel segmentation of a complete RCM depth stack. Using a bag-of-features representation for image appearance, and a conditional random field model for strata labels through the depth of the skin, a structured support vector machine was trained to label individual pixels. The approach was developed and tested on a dataset of 308 depth stacks from 54 volunteers, consisting of 16,144 total en-face sections. This approach accurately classified 85.7% of sections in the test set, and was able to detect underlying changes in the skin strata thickness with age.
Keyword Reflectance confocal microscopy (RCM)
Confocal microscopy
Dermatology
Segmentation
Anatomical strata
Human skin
Algorithm
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status UQ

 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Tue, 03 May 2016, 01:57:26 EST by System User on behalf of Learning and Research Services (UQ Library)