A computer system for the leukocytes classification in medical images

Abstract

The paper is about the development of a computer system for the white blood cells images classification. Solving the leukocytes classification task makes it possible to diagnose not only the blood diseases, but also a wide range of other diseases, as well as to evaluate the overall state of a person's health. Modern leukocytes classification methods have a fairly large number of shortcomings, which make a problem of finding the most effective method as a tool to solve this task. In our computer system we use the method based on using a trained convolutional neural network as a binary classifier for the leukocytes classification. This study shows the advantages of using this architecture and a deep learning technology to solve the objects classification task in medical digital images. The developed system allows one, in most cases, correctly and with a high speed to determine whether the white blood cell belongs to one of the two classes, which indicates to the possibility of using this system as an auxiliary tool for the blood hematological analysis.