PROCESSING OF GRAPHIC DATA BASED ON COMPUTER VISION METHODS IN THE FIELD OF MEDICINE

The article describes segmentation methods used in the analysis of medical images. The advantages and disadvantages of such methods as threshold values, classification, clustering, Markov networks, neural networks, deformable models used in the analysis of magnetic resonance imaging and computed tomography images are considered. The process of developing software technology for processing graphic data using computer vision in the healthcare sector is presented. The stages of design and modeling of the developed system are described. Data processing through image segmentation promotes diagnostic accuracy and close interaction between application users. A database and cross-platform application have also been created that allows you to store a volume of research in the application cloud. Full testing of the created mobile application was carried out. In the healthcare sector, medical image segmentation is becoming an increasingly necessary function for more accurate diagnosis and further verification of the patient’s diagnosis, and therefore, thanks to the timely detection of various diseases, it will be widely used for more rational and targeted treatment, improving the quality of life of the population. When developing the application, data processing was carried out using libraries such as OpenCV, Tensorflow, PyTorch, which facilitate the analysis of graphical data.