Ilona Kuzmina

Clinical evaluation of melanomas and common nevi by spectral imaging.

A clinical trial on multi-spectral imaging of malignant and non-malignant skin pathologies comprising 17 melanomas and 65 pigmented common nevi was performed. Optical density data of skin pathologies were obtained in the spectral range 450–950 nm using the multispectral camera Nuance EX. An image parameter and maps capable of distinguishing melanoma from pigmented nevi were proposed. The diagnostic criterion is based on skin optical density differences at three fixed wavelengths: 540nm, 650nm and 950nm. The sensitivity and specificity of this method were estimated to be 94% and 89%, respectively. The proposed methodology and potential clinical applications are discussed.

Noncontact monitoring of vascular lesion phototherapy efficiency by RGB multispectral imaging

Abstract. A prototype low-cost RGB imaging system consisting of a commercial RGB CMOS sensor, RGB light-emitting diode ring light illuminator, and a set of polarizers was designed and tested for mapping the skin erythema index, in order to monitor skin recovery after phototherapy of vascular lesions, such as hemangiomas and telangiectasias. The contrast of erythema index (CEI) was proposed as a parameter for quantitative characterization of vascular lesions. Skin recovery was characterized as a decrease of the CEI value relative to the value before the treatment. This approach was clinically validated by examining 31 vascular lesions before and after phototherapy.

Contact and contactless diffuse reflectance spectroscopy: potential for recovery monitoring of vascular lesions after intense pulsed light treatment

Optical fiber contact probe diffuse reflectance spectroscopy and remote multispectral imaging methods in the spectral range of 400 to 1100 nm were used for skin vascular malformation assessment and recovery tracing after treatment by intense pulsed light. The results confirmed that oxy-hemoglobin relative changes and the optical density difference between lesion and healthy skin in the spectral region 500 to 600 nm may be successfully used for objective appraisal of the therapy effect. Color redness parameter a* = 2 is suggested as a diagnostic border to distinguish healthy skin and vascular lesions, and as the indicator of phototreatment efficiency. Valuable diagnostic information on large area (>5 mm) lesions and lesions with uncertain borders can be proved by the multispectral imaging method.

Analysis of skin basalioma and melanoma by multispectral imaging

A clinical trial involving multi-spectral imaging of histologically confirmed 8 basaliomas and 30 melanomas was performed. Parametric maps of the melanin index, erythema index and melanoma-nevus differentiation parameter have been constructed and mutually compared. Specific features of basalioma and melanoma images were analyzed and discussed.

Multi-spectral imaging analysis of pigmented and vascular skin lesions: results of a clinical trial

A clinical trial comprising 266 pigmented lesions and 49 vascular lesions has been performed in three Riga clinics by means of multi-spectral imaging analysis. The imaging system Nuance 2.4 (CRI) and self-developed software for mapping of the main skin chromophores were used. The obtained results confirm clinical potential of this technology for non-contact quantitative assessment of skin pathologies.

Study of smartphone suitability for mapping of skin chromophores

RGB (red-green-blue) technique for mapping skin chromophores by smartphones is proposed and studied. Three smartphones of different manufacturers were tested on skin phantoms and in vivo on benign skin lesions using a specially designed light source for illumination. Hemoglobin and melanin indices obtained by these smartphones showed differences in both tests. In vitro tests showed an increment of hemoglobin and melanin indices with the concentration of chromophores in phantoms. In vivo tests indicated higher hemoglobin index in hemangiomas than in nevi and healthy skin, and nevi showed higher melanin index compared to the healthy skin. Smartphones that allow switching off the automatic camera settings provided useful data, while those with “embedded” automatic settings appear to be useless for distant skin chromophore mapping.

Multispectral imaging of pigmented and vascular cutaneous malformations: the influence of laser treatment

The paper investigates influence and efficacy of laser therapy on pigmented and vascular cutaneous malformations by multispectral imaging technique. Parameter mapping of skin pigmented and vascular lesions and monitoring of the laser therapy efficacy are performed by multispectral imaging in wavelength range 450-700nm by scanning step - 10nm. Parameter maps of the oxyhemoglobin deoxyhemoglobin and melanin derived from the images are presented. Possibility of laser therapy efficacy monitoring by comparison of the parameter maps before and after laser treatment has been demonstrated. As both cutaneous pigmented and vascular malformations are commonly found lesions, the parameter mapping would be a valuable method to use routinely.

Melanoma-nevus differentiation by multispectral imaging

A clinical trial on multi-spectral imaging of malignant and non-malignant skin pathologies comprising 22 melanomas and 59 pigmented nevi was performed in Latvian Oncology Center. Analysis of data obtained in the spectral range 450-950 nm using multispectral camera have led to a novel image processing algorithm capable to distinguish melanoma from pigmented nevi and different areas of activity of melanoma. The proposed methodology and potential clinical applications are discussed.

Image quality enhancement for skin cancer optical diagnostics

The research presents image quality analysis and enhancement proposals in biophotonic area. The sources of image problems are reviewed and analyzed. The problems with most impact in biophotonic area are analyzed in terms of specific biophotonic task – skin cancer diagnostics. The results point out that main problem for skin cancer analysis is the skin illumination problems. Since it is often not possible to prevent illumination problems, the paper proposes image post processing algorithm – low frequency filtering. Practical results show diagnostic results improvement after using proposed filter. Along that, filter do not reduces diagnostic results’ quality for images without illumination defects. Current filtering algorithm requires empirical tuning of filter parameters. Further work needed to test the algorithm in other biophotonic applications and propose automatic filter parameter selection.

Evaluation of skin melanoma in spectral range 450-950 nm using principal component analysis

Diagnostic potential of principal component analysis (PCA) of multi-spectral imaging data in the wavelength range 450- 950 nm for distant skin melanoma recognition is discussed. Processing of the measured clinical data by means of PCA resulted in clear separation between malignant melanomas and pigmented nevi.