Open AccessДифференциация пигментных новообразований кожи на основе цифровой обработки оптических изображений-=SUP=-*-=/SUP=-
Author(s) -
Е.Н. Римская,
А.О. Щадько,
Irina A. Apollonova,
Александр Петрович Николаев,
Andrey Briko,
I. A. Deshin,
П.Ю. Бережной,
Konstantin G. Kudrin,
К.И. Зайцев,
Valery V. Tuchin,
Igor V. Reshetov
Publication year - 2019
Publication title -
žurnal tehničeskoj fiziki
Language(s) - English
Resource type - Journals
eISSN - 1726-748X
pISSN - 0044-4642
DOI - 10.21883/os.2019.05.47657.6-19
Subject(s) - artificial intelligence , segmentation , calibration , computer science , computer vision , pattern recognition (psychology) , physics , quantum mechanics
A method for differentiation of pigmented skin neoplasms based on digital processing of optical images has been proposed. The optical images are detected using a digital camera and an etalon for its color and spatial calibration. The method implies segmentation and automatic differentiation of neoplasms based on 5 parameters –the diameter, area, color, shape and smoothness of margins of the neoplasm. It reveals clinical features of the neoplasm, required for diagnosis, and allows for calculating a probability of the neoplasms malignizaion. The proposed method has been verified using 360 imaging of pigmented neoplasms of the skin in vivo; among them: ordinary, dysplastic nevi of the skin and skin melanoma. The observed sensitivity and specificity of the proposed technique are 97% and 95%, correspondingly.