Automation of Blood Microscopy Image Processing

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.