Search

The paper presents results of using a neural network classifier to analyze images of malignant skin lesions obtained using a hyper-spectral camera. Using a three-block neural network of VGG architecture, we conducted the classification of a set of two-dimensional images of melanoma, papilloma and basal cell carcinoma, obtained in the range of 530 – 570 and 600 – 606 nm, characterized by the highest absorption of melanin and hemoglobin. The sufficiency of the inclusion in the training set of two-dimensional images of a limited spectral range is analyzed. The results obtained show significant prospects of using neural network algorithms for processing hyperspectral data for the classification of skin pathologies. With a relatively small set of training data used in the study, the classification accuracy for the three types of neoplasms was as high as 96 %.

A method for type diagnosis of skin cancers was developed based on the localization changes in the spectral intensity of Raman bands in the 13001340 cm^-1 and 16401680 cm^-1 in relation to the intensity of the 1450 cm^-1 in the phase plane. It was shown, based on ex vivo experiments carried out on 28 samples of skin tumors, that the sensitivity of the proposed method is close to absolute value, and the specificity over 90 %. Phase method can be used for the diagnosis of melanoma and basal cell carcinoma in mass screening and monitoring of skin pathologies.