A Bozkurt1, K Kose2, C Alessi-Fox3, J G Dy1, D H Brooks1, M Rajadhyaksha2. 1. Electrical and Computer Engineering Department, Northeastern University, Boston, MA, USA. 2. Dermatology Service, Memorial Sloan Kettering Cancer Center, New York, NY, USA. 3. Caliber Imaging and Diagnostics, Rochester, NY, USA.
Abstract
BACKGROUND: Measuring the thickness of the stratum corneum (SC) in vivo is often required in pharmacological, dermatological, and cosmetological studies. Reflectance confocal microscopy (RCM) offers a non-invasive imaging-based approach. However, RCM-based measurements currently rely on purely visual analysis of images, which is time-consuming and suffers from inter-user subjectivity. METHODS: We developed an unsupervised segmentation algorithm that can automatically delineate the SC layer in stacks of RCM images of human skin. We represent the unique textural appearance of SC layer using complex wavelet transform and distinguish it from deeper granular layers of skin using spectral clustering. Moreover, through localized processing in a matrix of small areas (called 'tiles'), we obtain lateral variation of SC thickness over the entire field of view. RESULTS: On a set of 15 RCM stacks of normal human skin, our method estimated SC thickness with a mean error of 5.4 ± 5.1 μm compared to the 'ground truth' segmentation obtained from a clinical expert. CONCLUSION: Our algorithm provides a non-invasive RCM imaging-based solution which is automated, rapid, objective, and repeatable.
BACKGROUND: Measuring the thickness of the stratum corneum (SC) in vivo is often required in pharmacological, dermatological, and cosmetological studies. Reflectance confocal microscopy (RCM) offers a non-invasive imaging-based approach. However, RCM-based measurements currently rely on purely visual analysis of images, which is time-consuming and suffers from inter-user subjectivity. METHODS: We developed an unsupervised segmentation algorithm that can automatically delineate the SC layer in stacks of RCM images of human skin. We represent the unique textural appearance of SC layer using complex wavelet transform and distinguish it from deeper granular layers of skin using spectral clustering. Moreover, through localized processing in a matrix of small areas (called 'tiles'), we obtain lateral variation of SC thickness over the entire field of view. RESULTS: On a set of 15 RCM stacks of normal human skin, our method estimated SC thickness with a mean error of 5.4 ± 5.1 μm compared to the 'ground truth' segmentation obtained from a clinical expert. CONCLUSION: Our algorithm provides a non-invasive RCM imaging-based solution which is automated, rapid, objective, and repeatable.
Authors: S Koller; M Wiltgen; V Ahlgrimm-Siess; W Weger; R Hofmann-Wellenhof; E Richtig; J Smolle; A Gerger Journal: J Eur Acad Dermatol Venereol Date: 2010-08-23 Impact factor: 6.166
Authors: Sila Kurugol; Kivanc Kose; Jennifer G Dy; Dana H Brooks; Milind Rajadhyaksha; Brian Park Journal: J Invest Dermatol Date: 2014-09-03 Impact factor: 8.551