The examination of the dermis/epidermis junction (DEJ) is clinically important for skin cancer diagnosis. Reflectance
confocal microscopy (RCM) is an emerging tool for detection of skin cancers in vivo. However, visual localization of
the DEJ in RCM images, with high accuracy and repeatability, is challenging, especially in fair skin, due to low contrast,
heterogeneous structure and high inter- and intra-subject variability. We recently proposed a semi-automated algorithm
to localize the DEJ in z-stacks of RCM images of fair skin, based on feature segmentation and classification. Here we
extend the algorithm to dark skin. The extended algorithm first decides the skin type and then applies the appropriate
DEJ localization method. In dark skin, strong backscatter from the pigment melanin causes the basal cells above the
DEJ to appear with high contrast. To locate those high contrast regions, the algorithm operates on small tiles (regions)
and finds the peaks of the smoothed average intensity depth profile of each tile. However, for some tiles, due to
heterogeneity, multiple peaks in the depth profile exist and the strongest peak might not be the basal layer peak. To
select the correct peak, basal cells are represented with a vector of texture features. The peak with most similar features
to this feature vector is selected. The results show that the algorithm detected the skin types correctly for all 17 stacks
tested (8 fair, 9 dark). The DEJ detection algorithm achieved an average distance from the ground truth DEJ surface of
around 4.7μm for dark skin and around 7-14μm for fair skin.
Optical Coherence Tomography (OCT) is a non-invasive imaging modality that acquires cross sectional images of tissue
in-vivo. It accelerates skin diagnosis by eliminating invasive biopsy and laborious histology in the process.
Dermatologists have widely used it for looking at morphology of skin diseases such as psoriasis, dermatitis, basal cell
carcinoma etc. Skin scientists have also successfully used it for looking at differences in epidermal thickness and its
underlying structure with respect to age, body sites, ethnicity, gender, and other related factors.
Similar to other in-vivo imaging systems, OCT images suffer from a high degree of speckle and noise content, which
hinders examination of tissue structures. Most of the previous work in OCT segmentation of skin was done manually.
This compromised the quality of the results by limiting the analyses to a few frames per area.
In this paper, we discuss a region growing method for automatic identification of the upper and lower boundaries of the
epidermis in living human skin tissue. This image analysis method utilizes images obtained from a frequency-domain
OCT. This system is high-resolution and high-speed, and thus capable of capturing volumetric images of the skin in
short time. The three-dimensional (3D) data provides additional information that is used in the segmentation process to
help compensate for the inherent noise in the images. This method not only provides a better estimation of the epidermal
thickness, but also generates a 3D surface map of the epidermal-dermal junction, from which underlying topography can
be visualized and further quantified.
The appearance and color distribution of skin are important characteristics that affect the human perception of health and vitality. Dermatologists and other skin researchers often use color and appearance to diagnose skin conditions and monitor the efficacy of procedures and treatments. Historically, most skin color and chromophore measurements have been performed using reflectance spectrometers and colorimeters. These devices acquire a single measurement over an integrated area defined by an aperture, and are therefore poorly suited to measure the color of pigmented lesions or other blemishes. Measurements of spots smaller than the aperture will be washed out with background, and spots that are larger may not be adequately sampled unless the blemish is homogenous.
Recently, multispectral imaging devices have become available for skin imaging. These devices are designed to image regions of skin and provide information about the levels of endogenous chromophores present in the image field of view. This data is presented as four images at each measurement site including RGB color, melanin, collagen, and blood images. We developed a robust segmentation technique that can segment skin blemishes in these images and provide more precise values of melanin, blood, and collagen by only analyzing the segmented region of interest. Results from hundreds of skin images show this to be a robust automated segmentation technique over a range of skin tones and shades.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.