Differentiation of Pigmented Skin Lesions Based on Digital Processing of Optical Images
Rimskaya E. N., Schadko A. O., Apollonova I. A., Nikolaev A. P., Briko A. N., Deshin I. A., Bereshnoy P. U., Kudrin K. G., Zaytsev K. I., Tuchin V. V., Reshetov I. V.
Optics and Spectroscopy
Vol.126, Issue5, P. 503-513
Опубликовано: 2019
Тип ресурса: Статья
DOI:10.1134/S0030400X19050230
Аннотация:
Abstract: A method for differentiation of pigmented skin lesions is proposed that is based on digital processing of optical images. The optical images are detected using a digital camera and a standard for its color and spatial calibration. The method involves segmentation and automatic recognition of neoplasms on the basis of five parameters: diameter, area, color, shape, and border sharpness. The analysis reveals clinical features of the lesion, required for diagnosis, and allows for calculating the probability of its malignant transformation. The method proposed was tested on 360 digital images of in vivo skin pigment lesions, including ordinary dysplastic nevi and melanoma. The sensitivity and specificity of the method proved to be 97 and 95[%], respectively. © 2019, Pleiades Publishing, Ltd.
Ключевые слова:
Dermatology; Geometrical optics; Automatic recognition; Clinical features; Dysplastic nevi; Five parameters; Malignant transformations; Pigmented skin lesions; Sensitivity and specificity; Spatial calibration; Image processing
Язык текста: Английский
ISSN: 1562-6911
Rimskaya E. N.
Schadko A. O.
Apollonova I. A.
Nikolaev A. P.
Briko A. N.
Deshin I. A.
Bereshnoy P. U.
Kudrin K. G. Konstantin Gennadyevich 1979-
Zaytsev K. I. Kirill Igorevich 1989-
Tuchin V. V.
Reshetov I. V. Igor` Vladimirovich 1964-
Римскайа Е. Н.
Счадко А. О.
Аполлонова И. А.
Николаев А. П.
Брико А. Н.
Дешин И. А.
Берешноy П. У.
Кудрин К. Г. Константин Геннадьевич 1979-
Зайцев К. И. Кирилл Игоревич 1989-
Тючин В. В.
Решетов И. В. Игорь Владимирович 1964-
Differentiation of Pigmented Skin Lesions Based on Digital Processing of Optical Images
Текст визуальный непосредственный
Optics and Spectroscopy
Pleiades Publishing, Ltd.
Vol.126, Issue5 P. 503-513
2019
Статья
Dermatology Geometrical optics Automatic recognition Clinical features Dysplastic nevi Five parameters Malignant transformations Pigmented skin lesions Sensitivity and specificity Spatial calibration Image processing
Abstract: A method for differentiation of pigmented skin lesions is proposed that is based on digital processing of optical images. The optical images are detected using a digital camera and a standard for its color and spatial calibration. The method involves segmentation and automatic recognition of neoplasms on the basis of five parameters: diameter, area, color, shape, and border sharpness. The analysis reveals clinical features of the lesion, required for diagnosis, and allows for calculating the probability of its malignant transformation. The method proposed was tested on 360 digital images of in vivo skin pigment lesions, including ordinary dysplastic nevi and melanoma. The sensitivity and specificity of the method proved to be 97 and 95[%], respectively. © 2019, Pleiades Publishing, Ltd.