Model for estimating the heterogeneity of the distribution of globule characteristics in images of skin neoplasms

The problem of skin melanoma diagnostics from digital images of the tumor is considered. Clinical algorithms for detecting skin melanoma are briefly described. An overview of the works devoted to the automated assessment of the asymmetry of the distribution of shape, color, area of globules – important signs of melanoma – is given. A model for estimating the heterogeneity of the distribution of the characteristics of globules on digital images in the skin neoplasms diagnosis is developed and models of signs of heterogeneity of this distribution are proposed. The comparative evaluation of the proposed models was carried out experimentally using a software system developed in C++. The most informative features are identified. The greatest accuracy 93 % in estimating the heterogeneity of the distribution of the characteristics of globules was shown by the sign “the reduced inverse of the greatest frequency of occurrence of the measured areas of globules”. The results obtained can be applied in the development of systems to support medical decision-making in the diagnosis of melanoma.

Download Full-text

A model for the selection of structural elements of lines in digital images in oncodermatology

Izmeritel`naya Tekhnika ◽

10.32446/0368-1025it.2021-6-66-71 ◽

2021 ◽

pp. 66-71

Author(s):

Valentin G. Nikitaev ◽

Alexandr N. Pronichev ◽

Olga B. Tamrazova ◽

Vasily Yu. Sergeev ◽

Ekaterina A. Druzhinina ◽

...

Keyword(s):

Digital Images ◽

Malignant Neoplasm ◽

Skin Neoplasms ◽

Interdisciplinary Cooperation ◽

Medical Decision ◽

Medical Institute ◽

Malignant Neoplasms ◽

Structural Elements ◽

Skin Melanoma ◽

Selection Of

The problem of early diagnosis of one of the most dangerous malignant neoplasms of the skin – melanoma is considered. A model for identifying the structural elements of lines in digital images of skin neoplasms in oncodermatology has been developed. The model is based on adaptive binarization of the original digital dermatoscopic image of skin neoplasms and subsequent operations of dilation, erosion, skeletonization and filtering of false fragments of lines. Test dermatoscopic images of skin neoplasms are visually divided into four groups to conduct the experiment. The optimal parameters of image processing of four groups for the model of selection of structural elements – lines – are experimentally established. The experimentally determined accuracy of the selection of lines was 95 %. The work is the result of interdisciplinary cooperation between dermatologists of the Central Medical Academy of the Presidential Administration of the Russian Federation, the Medical Institute of the Peoples' Friendship University of Russia and specialists in the field of information and measurement systems of the Engineering and Physical Institute of Biomedicine of the National Research Nuclear University “MEPhI”. The proposed model can be used in the development of computer systems to support medical decision – making in the diagnosis of skin melanoma – a dangerous malignant neoplasm.

Download Full-text