Melanoma - skin cancer reviewed

The goal of any imaging methodology used in dermatology is to diagnose melanoma in early stages, because on it depends effectiveness of treatment. Investigations shows, that early diagnosis is more than 90% curable and late is less than 50% [1]. The diagnosis and successful treatment is often supplemented with permanent monitoring of suspicious skin lesions.

Doctor’s diagnosis is reliable, but this procedure takes lots of time, efforts. These routines can be automated. It could save lots of doctor’s time and could help to diagnose more accurate. Besides using computerised means there are good opportunity to store information with diagnostic information in order to use it for further investigations or creation of new methods of diagnosis.

Skin lesion imaging methods

We found that there are number of various imaging methods of skin lesions [2]. The simplest visualisation method is photography. This method gives only top layer skin image. In order to get deeper layer image there is oil immersion used. It reduces reflections of surface and brightens the image of epidermis – the second skin layer.

The different illumination method called epiliuminescence can be used in order to get the image from deeper skin layers. The light is directed straight in to these layers and reflected goes back through lesion giving more information about consistence of light absorbers in these layers. This method of illumination improves diagnosis accuracy up to 10 percent [2].

Other interesting solution of getting more information from skin is using multi spectral photography [2]. There is used narrow frequency band of light illumination. Those images give information about consistence and concentration of absorbers and reflectors in the skin. The idea is that different pigment of skin absorbs different light wave, determining the colour of our skin. When those photos are made with range of light waves, we can calculate the reflectance frequency characteristics of skin. And comparing to normal skin characteristic there can be made diagnostic decisions about skin pigment consistency.

Other imaging method using laser is called CLSM (confocal scanning laser microscopy). It uses red or near infrared low power laser beam to scan skin surface. This beam can be focused in to different deep to get the image of it. The deep is limited to 300µm, because of absorbance [2]. The distance between two layers (axial resolution) can be about 2 – 5 µm. The main disadvantage of this method is complicated acquisition of image from reflected laser beam.

Ultrasound visualisation is usually used to measure depth of melanoma [1]. The other uses of ultrasound are limited by very little tissue differences between normal skin and lesion. If there is no melanoma practically there is no any differences. When doctor diagnoses melanoma, then he uses high frequency ultrasound (over 30 MHz) to measure penetration depth in order to make correct cut during surgery.

In optical coherence tomography is used short near infrared light pulses focused to papillary dermis [2]. Reflected light is combined with reference light that is reflected from mirror system in order to determine the depth of papillary dermis. Measurement of the interference pattern allows determination of the position within the tissue where the light was reflected. Using recent technologies with ultra sort light pulse, the maximum obtained resolution is 2 – 4 µm. Visualisation depth is 1 – 1.5 mm.

The wide variety of methods shows, that there is no best universal visualisation. Some of them are used for different needs, other are very expensive. The choice of method depends on what features of skin lesions is wanted to visualise, and on availability of resources.

Algorithms of skin image processing

Digital dermatoscopic images itself does not provide formal and determined information. To get diagnostic information the digital image processing is used. Commonly used methods are based on geometrical feature extraction from image with lesion. The USA national health institute offers ABCD rule for classification of dermatological images in to benign, suspicious and melanoma [3]. ABCD are the letters of first feature words: A (asymmetry), B (border), C (bolour), D (dermatoscopic structures). According to these four values there are total dermatoscopic value calculated by formula:

N – Not known
Most of those software solutions have some major disadvantages. Firs of all, they are analysing geometrical and structural or colour changes extracted from plain surface picture, which does not contain enough useful information. Analysis is not connected with physical nature of skin image. There are no associations with histological parameters of skin.

Other disadvantage is that diagnostic results do not always support diagnosis decisions. If there is support of databases, then those pictures with diagnostic results are stored and should be used in decisions support algorithms. In now days there is tendency to request past data and knowledge to gain better diagnosis results in future.

Digital dermatoscopic images firstly have to be parameterised for automatic classification. The deep study of skin nature has to be done before to parameterise it. For extraction skin or lesion optical features it is very useful to use multi layer skin model [5].

The most common is four-layer skin model: Stratum Cornea, Epidermis, Papillary dermis and Reticular dermis.

Stratum Corneum is top thin layer, which is a protective layer consisting of keratin-impregnated cells and it varies considerably in thickness. Apart from scattering the light, it is optically neutral.

The epidermis is largely composed of connective tissue. It also contains the melanin producing cells, the melanocytes, and their product, melanin. In this layer there is strong absorption of blue and ultraviolet light. Melanocytes absorb most of this light. It behaves like blue and ultraviolet filter, which characteristics depend on concentration of melanocytes. Within the epidermal layer there is very little scattering, with the small amount that occurs being forward directed. The result is that all light not absorbed by melanin can be considered to pass into the dermis. By this description, epidermis can be characterised by wavelength dependant coefficients: absorption coefficient of melanin mam(l) and melanin concentration cm [5].

Dermis consist of two sub layers: papillary dermis and reticular dermis. Dermis itself consists of collagen fibres and, in contrast to the epidermis; it contains sensors, receptors, blood vessels and nerve ends. In papillary dermis the collagen fibres are thinner and it behaves as highly backscattering layer. Any incident light is backscattered towards surface. Scattering is grater in red spectrum and going greater to infrared. Because infrared is not absorbed by melanin and blood, this part of spectrum is best for assessing thickness of papillary dermis. Papillary dermis can be described by the absorption coefficients for haemoglobin mah(l), the haemoglobin concentration ch, the scatter coefficient for collagen mspd, and the thickness of collagen layer dpd.

Within the reticular dermis, the large size of collagen fibre bundles causes highly forward-directed scattering. Thus any light, which gets to this layer, is passed deeper into the skin and does not contribute to the spectrum remitted from the skin. Reticular dermis can be described by scatter coefficient msrd, and thickness of layer drd.

Model based feature detection methods

The parameters, describing skin pigmentation, can be found by modelling light transport through layered skin model. To implement this model there can be used Kubelka-Munk theory (Egan and Hilgeman, 1979). It calculates the remitted and transmitted light separately for each layer. And using Beer-Lambert theory of light absorption, there can be calculated concentrations of pigments in each layer, when reflectance coefficients are known [5].

This physical interpretation would let mathematically to define the colour changes because of melanin concentration changes in each layer.

The bigger part of melanoma diagnostic information is hidden in dermis. In more than 90 % skin cancer cases the dermal melanin causes melanoma [6].

The biggest problem is to define the melanin concentration in reticular dermis because almost all light is backscattered from papillary dermis and the rest of light is forward scattered into deeper tissues almost without reflection. To solve this problem there should help Beer–Lambert law combined with Monte-Carlo simulation. Monte-Carlo simulation itself requires much of calculations, but combining with Beer–Lambert theory, this time can be significantly reduced. When there are known characteristics of upper layers by using Monte–Carlo simulation there can be calculated optical properties of reticular dermis with adequate probability.

The main equations used in skin modelling calculations are [6]:

d – layer thickness, k ≈ μa – absorption coefficient, s ≈ μs- scattering coefficient of each layer, Ri and Ti – represents reflected and transmitted light intensities in i-th layer of layered system.