Performance Comparision of Classification of Chronic Leukaemia Cell Types Using Artificial Neural Network

摘要

Leukaemia is classified by how quickly it progresses. Acute leukaemia is fast-growing and can overrun the body within a few weeks or months. By contrast, chronic leukaemia is slow-growing and progressively worsens over years. In chronic leukaemia, the blood-forming cells eventually mature, or differentiate, but they are not "normal." Chronic Myelogenous Leukaemia (CML) and Chronic Lymphocytic Leukaemia (CLL) were considered for the study. Back Propagation Neural network (BPN) and Modified Back Propagation Network (MBPN) were used as a classifier for the classification process. Back propagation provides a computationally efficient method for changing the weights in a feed forward networks, with differentiable activation function units, to learn a training set of inputs-outputs. Comparison of performance of classification accuracy was carried out. The effectiveness of the classification system is tested with the total of 91 samples collected from 13 patients. The evaluated results demonstrate that our method outperformed the existing systems with an accuracy of 98%.