A new acute leukaemia-automated classification system

Abstract

Acute leukaemia is a type of cancer that affects the blood and the bone marrow. Detection and classification of white blood cells is a challenge in image processing, as manual data analysis is time-consuming and most often it is not accurate. Research in this area is essential because a fully automated classifier tool can prove to be an effective ancillary tool for physicians. The goal of this article is to develop a new whole image system that performs automated classification of peripheral blood smear images of acute lymphoblastic leukaemia containing multiple nuclei. This is a key difference of our system from other commonly used systems. For this purpose, we tested the commonly used features in other systems in order to get the most relevant features for our system. Also, we included a new, so-called cell energy, colour feature. In order to evaluate the performance of our system, we used multiple cross-validation methods. Experimental results show that the proposed system is efficient and effective in classification acute leukaemia cells in blood smear images.