Open AccessDevelopment of neoplastic region selection algorithm based on breast cancer whole slide image
Author(s) -
С.Н. Рябцева,
Vassili Kovalev,
Valery Malyshev,
И. А. Семеник,
М. А. Деревянко,
Roman Moskalenko,
А. С. Довбыш,
Taras Savchenko,
Анатолий Николаевич Романюк
Publication year - 2020
Publication title -
doklady belorusskogo gosudarstvennogo universiteta informatiki i radioèlektroniki
Language(s) - English
Resource type - Journals
eISSN - 2708-0382
pISSN - 1729-7648
DOI - 10.35596/1729-7648-2020-18-8-21-28
Subject(s) - breast cancer , normalization (sociology) , computer science , artificial intelligence , image processing , selection (genetic algorithm) , pattern recognition (psychology) , computer vision , cancer , image (mathematics) , medicine , sociology , anthropology
Analysis of breast cancer whole-slide image is an extremely labor-intensive process. Histological whole slide images have the following features: a high degree of tissue diversity both in one image and between different images, hierarchy, a large amount of graphic information and different artifacts. In this work, pre-processing of breast cancer whole-slide tissue image was carried out, which included normalization of the color distribution and the image area selection. We reduced the operating time of the other algorithms and excluded areas of breast cancer whole-slide tissue with a background to analyze. Also, an algorithm for finding similar neoplastic regions for semi-automatic selection using various image descriptors has been developed and implemented.