Image-based control of skin melanin texture

Calibration and segmentation of skin areas in hyperspectral imaging for the needs of dermatology

INTRODUCTION

Among the currently known imaging methods, there exists hyperspectral imaging. This imaging fills the gap in visible light imaging with conventional, known devices that use classical CCDs. A major problem in the study of the skin is its segmentation and proper calibration of the results obtained. For this purpose, a dedicated automatic image analysis algorithm is proposed by the paper's authors.

MATERIAL AND METHOD

The developed algorithm was tested on data acquired with the Specim camera. Images were related to different body areas of healthy patients. The resulting data were anonymized and stored in the output format, source dat (ENVI File) and raw. The frequency λ of the data obtained ranged from 397 to 1030 nm. Each image was recorded every 0.79 nm, which in total gave 800 2D images for each subject. A total of 36'000 2D images in dat format and the same number of images in the raw format were obtained for 45 full hyperspectral measurement sessions. As part of the paper, an image analysis algorithm using known analysis methods as well as new ones developed by the authors was proposed. Among others, filtration with a median filter, the Canny filter, conditional opening and closing operations and spectral analysis were used. The algorithm was implemented in Matlab and C and is used in practice.

RESULTS

The proposed method enables accurate segmentation for 36'000 measured 2D images at the level of 7.8%. Segmentation is carried out fully automatically based on the reference ray spectrum. In addition, brightness calibration of individual 2D images is performed for the subsequent wavelengths. For a few segmented areas, the analysis time using Intel Core i5 CPU RAM M460@2.5GHz 4GB does not exceed 10 s.

CONCLUSIONS

The obtained results confirm the usefulness of the applied method for image analysis and processing in dermatological practice. In particular, it is useful in the quantitative evaluation of skin lesions. Such analysis can be performed fully automatically without operator's intervention.

Retrieving skin properties from in vivo spectral reflectance measurements

A previously developed inverse method was applied to in vivo normal-hemispherical spectral reflectance measurements taken on the inner and outer forearm as well as the forehead of healthy white Caucasian and black African subjects. The inverse method was used to determine the thickness and melanin concentration in the epidermis, dermal blood volume fraction and oxygen saturation, and skin's spectral scattering coefficient. It was established that changes in melanin concentration due to racial difference and tanning, and differences in epidermal thickness and blood volume with anatomical location were detectable. The retrieved values were also consistent with independent measurements reported in the literature. The same method could be used for optical diagnosis of pathologies affecting the structure and pigmentation of human skin.

Rapid and accurate estimation of blood saturation, melanin content, and epidermis thickness from spectral diffuse reflectance

We present a method to determine chromophore concentrations, blood saturation, and epidermal thickness of human skin from diffuse reflectance spectra. Human skin was approximated as a plane-parallel slab of variable thickness supported by a semi-infinite layer corresponding to the epidermis and dermis, respectively. The absorption coefficient was modeled as a function of melanin content for the epidermis and blood content and oxygen saturation for the dermis. The scattering coefficient and refractive index of each layer were found in the literature. Diffuse reflectance spectra between 490 and 620 nm were generated using Monte Carlo simulations for a wide range of melanosome volume fraction, epidermal thickness, blood volume, and oxygen saturation. Then, an inverse method was developed to retrieve these physiologically meaningful parameters from the simulated diffuse reflectance spectra of skin. A previously developed accurate and efficient semiempirical model for diffuse reflectance of two layered media was used instead of time-consuming Monte Carlo simulations. All parameters could be estimated with relative root-mean-squared error of less than 5% for (i) melanosome volume fraction ranging from 1% to 8%, (ii) epidermal thickness from 20 to 150 mum, (iii) oxygen saturation from 25% to 100%, (iv) blood volume from 1.2% to 10%, and (v) tissue scattering coefficient typical of human skin in the visible part of the spectrum. A similar approach could be extended to other two-layer absorbing and scattering systems.

Image-based control of skin translucency

We propose a method for skin translucency control of facial images. This is one of the important tasks in the reproduction of posters, TV commercials, movies, and so on. As the first step of processing, we extract the component maps of melanin, hemoglobin, and shading from skin color images by using our conventional method. The extracted shading component is controlled to change the translucency of the skin by simple kernel operations for the component. The efficiency for the change of translucency is confirmed by using the images of numerical and optical skin phantoms. The method is also applied into the real skin color image with the consideration of each component, and realistic change of skin translucency was observed from the resultant images synthesized by the proposed method.