Information technology for image data processing based on hybrid neural networks using geometric features

Abstract. Progress in computing technology has led to a steady increase in computing power, resulting in an exponential growth in the amount of data that needs to be processed. In particular, the enhanced performance of automated systems enables the storage and analysis of large volumes of medical data with high speed and accuracy. Modern medicine is characterized by a significant increase in the information load, necessitating complex processing and in-depth analysis to support clinical decision-making. Information technology plays a pivotal role in ensuring efficient processing of these large datasets, contributing to the accuracy and speed of diagnosis, as well as the effectiveness of subsequent patient treatment. The purpose of this article is to develop and study information technology for processing graphic data based on hybrid neural networks using geometric features of image objects. The paper proposes advanced machine learning methods, deep neural network architectures, and specialized tools for processing graphic data, such as OpenCV, TensorFlow, and others. The data processing workflow during the validation of the proposed methods and architectures included several stages: data pre-processing, model training, and thorough testing of the results. The developed information technology demonstrates a significant improvement in the accuracy of graphic data classification. Experimental studies have shown that the proposed approach ensures efficient processing of large volumes of biomedical data, as evidenced by the high accuracy and speed of analysis. In particular, the accuracy of pathology classification using hybrid neural networks increased by more than 11% compared to the results obtained using classical methods. The practical value of the developed technology lies in its high potential for use in the field of machine vision, including enhancing the efficiency of diagnosis and treatment of patients in the medical field. It can be integrated into modern decision support systems, providing more accurate and faster processing of medical images.