The paper presents the results of the development and research of algorithms for analyzing images obtained by blood microscopy using computer vision technologies. The objects of the study are images of erythrocytes deformed in the shear flow. The deformability of erythrocytes largely determines the nature of blood microcirculation and therefore is directly related to the diagnosis and treatment of many diseases. At the current moment image analysis of the evaluation of blood cells deformations is usually performed visually by medical technicians. To automate the image processing process various technologies were investigated. As a result, a new computer vision approach for rapid and accurate recognition of erythrocytes deformed in shear flow is presented. The developed algorithms use image binarization and a neural network based on the U-Net architecture for separated erythrocytes, and a neural network based on the StarDist architecture for their conglomerates. We present the results of the algorithms on real lood microscopy images, compare their performance and discuss the practical applications in medical diagnostics. Evaluation of the distribution of erythrocytes by deformability will provide additional diagnostic and scientific information for medical research. Automation of image analysis of deformed images will increase the accuracy and simultaneously reduce the time and cost of tests, leading to a better patient treatment.

No abstract

No abstract

Automation of medical image processing aims to create a universal tool for the purposes of medical diagnostics in the field of microscopy of cells and tissues. The authors of the paper have collected large databases of various digital microscopy images that allow to automate the processes of medical research using computer vision technologies, improve the quality of image analysis and provide a set of diagnostic information for decision making. For this purpose, a software package with a user-friendly interface has been developed that allows visualizing the results of detection of microobjects in images, determining their number and size, calculating the values of universal numerical parameters of the detected objects, creating a distribution of numerical parameter values in the form of histograms and diagrams, displaying the results in a user-friendly form, and saving the analysis results for further research. It is possible to analyze the dynamics of biomedical processes using a set of images. The modular architecture of the developed software package allows to extend its functionality, add new modules to solve biomedical problems and visualize the results of image processing. The paper presents the results of image processing of blood microscopy to determine its parameters, which include the characteristics of erythrocytes, platelets, and blood cell aggregation processes. In addition, the automated image processing system is suitable for solving problems of microscopy image analysis in other application areas.

Biomedical research is of great importance in modern medicine. The development of an interface for the intellectualization of medical research in microscopy is a relevant and practically significant task, since the creation of an effective and user-friendly UX/UI system design makes it possible to work out the existing business logic and analyze the existing data security problems. In developing the interface, it was investigated how to improve the quality, simplicity and usability of the laboratory information system (LIS) by medical researchers in order to simplify the work of medical staff and increase the speed of their work in daily tasks. The influence of the target group analysis on the design of quality systems is studied and the LIS user portrait is created; the process of UI interface design for the developed system of medical images analysis is presented, the justification of the adopted stylistic solutions is made. The created interface was tested on a target group represented by the employees of one of the branches of Nika Spring multidisciplinary clinics. The novelty of the solution lies in the development of a UX/UI design for the LIS, which has no counterpart on the market.