An unsupervised machine learning method for delineating stratum corneum in reflectance confocal microscopy stacks of human skin in vivo Conference Paper
| Authors: | Bozkurt, A.; Kose, K.; Fox, C. A.; Dy, J.; Brooks, D. H.; Rajadhyaksha, M. |
| Editors: | Mandelis, A.; Choi, B.; Wong, B. J. F.; Ilgner, J. F.; Marcu, L.; Skala, M. C.; Kollias, N.; Zeng, H.; Kang, H. W.; Tearney, G. J.; Gregory, K. W.; Campagnola, P. J. |
| Title: | An unsupervised machine learning method for delineating stratum corneum in reflectance confocal microscopy stacks of human skin in vivo |
| Conference Title: | Photonic Therapeutics and Diagnostics XII |
| Abstract: | Study of the stratum corneum (SC) in human skin is important for research in barrier structure and function, drug delivery, and water permeability of skin. The optical sectioning and high resolution of reflectance confocal microscopy (RCM) allows visual examination of SC non-invasively. Here, we present an unsupervised segmentation algorithm that can automatically delineate thickness of the SC in RCM images of human skin in-vivo. We mimic clinicians visual process by applying complex wavelet transform over non-overlapping local regions of size 16 x 16 μm called tiles, and analyze the textural changes in between consecutive tiles in axial (depth) direction. We use dual-tree complex wavelet transform to represent textural structures in each tile. This transform is almost shift-invariant, and directionally selective, which makes it highly efficient in texture representation. Using DT-CWT, we decompose each tile into 6 directional sub-bands with orientations in ±15, 45, and 75 degrees and a low-pass band, which is the decimated version of the input. We apply 3 scales of decomposition by recursively transforming the low-pass bands and obtain 18 bands of different directionality at different scales. We then calculate mean and variance of each band resulting in a feature vector of 36 entries. Feature vectors obtained for each stack of tiles in axial direction are then clustered using spectral clustering in order to detect the textural changes in depth direction. Testing on a set of 15 RCM stacks produced a mean error of 5.45±1.32 μm, compared to the "ground truth" segmentation provided by a clinical expert reader. © 2016 SPIE. |
| Keywords: | confocal microscopy; artificial intelligence; reflectance confocal microscopies; reflection; stratum corneum; image segmentation; spectral clustering; clustering algorithms; wavelet transforms; learning systems; reectance confocal microscopy; unsupervised segmentation; partial discharges; complex wavelet transforms; dual-tree complex wavelet transform; texture representation; unsupervised machine learning |
| Journal Title | Proceedings of SPIE |
| Volume: | 9689 |
| Conference Dates: | 2016 Feb 13-14 |
| Conference Location: | San Francisco, CA |
| ISBN: | 0277-786X |
| Publisher: | SPIE |
| Date Published: | 2016-05-18 |
| Start Page: | 96890Z |
| Language: | English |
| DOI: | 10.1117/12.2213036 |
| 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
-
222Rajadhyaksha -
81Kose
Related MSK Work