Development of a system for analyzing X-ray images using computer vision and deep learning algorithms
Students Name: Baranetskyi Mykhailo-Sviatoslav Vasylovych
Qualification Level: magister
Speciality: Informatively-Instrumentation Technologies in Roboticotekhnic
Institute: Institute of Computer Technologies, Automation and Metrology
Mode of Study: full
Academic Year: 2024-2025 н.р.
Language of Defence: ukrainian
Abstract: The essence of the project is the development and implementation of a web service for disease classification based on chest X-ray images. The service employs modern computer vision algorithms and deep learning techniques to analyze medical images and detect pathologies. The developed web service has a well-defined architecture that includes a neural network for image analysis, a server-side component for request processing, and a database for storing results. The system provides users with high diagnostic accuracy. During the development process, the choice of neural network models was substantiated, hyperparameters were configured, and training was conducted on real-world data from the open-source NIH Chest X-rays dataset. The models performance was evaluated, and the entire service was thoroughly tested. Object of research: disease classification based on chest X-ray images using machine learning. Subject of research: a web service that implements machine learning models for analyzing and training on X-ray images. Purpose of research: to develop a web service for automatic disease classification with high accuracy that is accessible and convenient for users. The successful completion of this project resulted in a fully functional web service capable of automatically analyzing chest X-ray images to detect potential diseases. The service leverages modern deep learning models trained on a large dataset, ensuring a high level of accuracy. It has potential for further expansion, including integration with medical information systems, the creation of APIs for functionality access by other applications, and the addition of new features such as recommendations based on analysis results. Keywords: web service, computer vision, X-ray images, deep learning, disease classification.