Web application for diagnosis of COVID-19 by X-ray images
Students Name: Hlova Denys Hryhorovych
Qualification Level: magister
Speciality: Computer Systems and Networks
Institute: Institute of Computer Technologies, Automation and Metrology
Mode of Study: full
Academic Year: 2022-2023 н.р.
Language of Defence: англійська
Abstract: The goal of the work is to diagnose COVID-19 based on available CT images based on machine learning methods. The object of research is the process of medical diagnosis of diseases using artificial intelligence and machine learning methods. The subject of research is convolutional neural networks for pattern recognition on X-ray and CT images. The work consists of five sections. In the first section, an analysis of the subject area is carried out, namely, an analysis of the relevance of the problem. An analysis of existing analogues and publications was carried out, and the main areas of application of neural networks for diagnosing diseases were determined, and the task of the thesis was set. In the second chapter, the problem of image processing for the diagnosis of respiratory diseases based on radiology is formulated. In the third section, the selection of software was made and the process of creating a neural network was described. A comparison of the NASNet algorithm and VGG-16 using image enhancement algorithms was carried out. The fourth chapter describes the implementation of the web application. The fifth chapter describes the economic feasibility of app development during the COVID-19 pandemic. The total volume of work is 93 pages. The master’s thesis contains 14 figures, 3 tables and references to 64 sources. Keywords: database, table, web server, web interface, respiratory disease, coronavirus, generation module, work plan, x-ray image, computer tomography, x-ray, neural networks, convolutional neural networks, U-Net, COVID.