BelSU scientists will help doctors identify patients with COVID-19 by using artificial brain

Doctors use chest x-rays as the basic method for identifying patients with COVID-19. In order to optimize and speed up the process of processing and analysis of the obtained X-ray images, BelSU scientists have developed and “trained” a special ultra-precise neural network. The research was carried out at the Department for Information Systems Mathematical Support and Software financed by the grant of the Russian Foundation for Fundamental Research.

According to Vladimir Mikhelev, the Associate Professor of BelSU Department for Information Systems Mathematical Support and Software, the ultra-precise neural networks provide an effective solution for detecting COVID-19 cases based on medical images. After “training” the neural network was tested to prove high efficiency in identifying patients with COVID-19 based on medical images.

Andrey Miroshnichenko, a postgraduate student of Department for Information Systems Mathematical Support and Software involved in development of the neural network, said that the research team will proceed with the work in this direction in order to enhance the training quality of the model, improve the training approach and modify the method in order to detect the classification of positive COVID-19 image results.