Meretskyi M. Web service for diagnosing lung diseases by X-ray images

This thesis consists of 66 pages, 17 illustrations, 12 formulas, 9 literary sources. Key words: neural network, online service, python, pneumonia, x-ray.

In the diploma project, a new method for diagnosing lung disease on the basis of X-ray images was conducted. The design of the neural network architecture is developed. The model was trained to recognize viral and bacterial pneumonia in X-rays. An online service was developed that provides real-time, convenient and easy access to the capabilities of the neural network. As a result of the study, a ready-made solution for modern diagnostics was developed on the basis of latest neural network technology. The purpose of the work is to investigate the high-precision method of diagnosing lung diseases on the basis of X-ray images. Also, to development an online interface for easy access in real time and documentation for it.


The object of the study is the human chest, in particular the lungs. Subject of research - methods of diagnostics based on non-network technologies. Scientific novelty - the newest diagnostic method of lung disease on the basis of X-ray images.

Research advisor: R. Galagan


All Diploma Thesis

ПСНК КПІ ім. Ігоря Сікорського, 2017