Application of neural network for automatic classification of leukocytes

Abstract

Differential blood count is one of the most frequently used diagnostic methods in medicine. An algorithm for leukocytes classification represents the crucial part of any device for the automatic compilation of a differential blood count. This paper demonstrates a new algorithm for the automatic classification of leukocytes based on neural networks and digital image processing. The results of the algorithm testing show a high sensitivity of the algorithm in leukocyte detection, as well as classification accuracy of 86%. © 2006 IEEE.