A computational intelligence system for cell classification

Artificial neural networks were used to classify blood cells. Compared with existing methods, neural networks are more accurate, efficient, adaptable and information-rich. The implementation of the system in a PC/Windows NT environment using image processing technology and database management allows for a variety of features to be extracted and a variety of training algorithms to be used. In this preliminary study, blood cell images are segmented to individual cells. Features for individual cells, including size, color content and shape related moments, are extracted and used as inputs to a multilayer neural network. Backpropagation and ALOPEX training algorithms were used to train the neural network. After less than 2000 training iterations using 95 training sets, the system recognized three kinds of blood cell in a correctness percentage of 100%. This module provides a platform to build a more sophisticated computational intelligent system for cell classification for clinical use.