POSSIBILITIES OF USING NEURAL NETWORKS IN THE DIAGNOSIS OF PNEUMONIA

UDC 004.891
DOI: 10.36871/2618-9976.2022.11.009

Authors

Egor A. Rybko
Graduate of the Department of Information Systems and Technologies, Yaroslavl State Technical University, Yaroslavl, Russia
Elena I. Voevodina
Senior Lecturer of the Department of Information Systems and Technologies, Yaroslavl State Technical University, Yaroslavl, Russia
Alexey D. Burykin
Professor of the Department of Economics and Management, Academy of Labor and Social Relations, Yaroslavl, Russia

Abstract

In this paper, the possibilities of using neural networks and deep learning in the diagnosis of various diseases are considered.
This area is considered on the example of the diagnosis of pneumonia. In the context of the spread of coronovirus infection, the article substantiates the relevance of differentiation of radiographic data to determine different types of pneumonia based on the use of neural networks and deep learning. At the same time, it is emphasized that the algorithm of convolutional neural networks is well suited for a multiclass classification problem or binary classification, which allows solving the problem under consideration.

Keywords

Neural networks, Deep learning, Pneumonia, Information technology, Diagnostics, Convolutional neural network layers, Radiographic data