Development of the architecture of a computer aided diagnosis system in medicine

Abstract

With the development of information technology, automation of various production processes is an urgent task, and medical diagnostics is no exception. In recent decades, artificial intelligence and information technology have been widely used in computer diagnostic systems. However, as technology advances, so do the challenges. Not every system is optimized and fast, and traditional methods are fading into the background. Often, systems do not use cloud technologies and have unoptimized architectures. This all affects their performance and, accordingly, is an urgent problem. The study analyzes the methods used in computer diagnostic systems and compares them in terms of advantages and disadvantages. The scientific works related to computer diagnostic systems in medicine for specific tasks are analyzed. The existing architectures of computer diagnostic systems are analyzed, which made it possible to identify the use of consistent approaches to diagnosis. Based on the analyzed data, the purpose, objectives, object and subject of the study are determined. A new architecture has been developed that uses the capabilities of U-Net for image segmentation and convolutional neural networks for medical image classification. The developed architecture is designed to increase the speed and automation of diagnostic processes through the use of neural networks and, accordingly, reduce human intervention. The scientific novelty of the developed architecture lies in the parallel execution of medical image segmentation and classification tasks, which gives a potential increase in data processing speed, and in the availability of an image generator, which solves the problem of lack of test data for model training.