A Robust Feature Extraction and Selection Method for the Recognition of Lymphocytes versus Acute Lymphoblastic Leukemia

Abstract

An essential part of the diagnosis and treatment of leukemia is the visual examination of the patient's peripheral blood smear under the microscope. Morphological changes in the white blood cells are commonly used to determine the nature of the malignant cells, namely blasts. Manual techniques are labor intensive slow, subjected to error and costly. A computerized system can be used as an aiding tool for the specialist in order to improve and accelerate the morphological analysis process. This paper presents and application of feature extraction, selection and cell classification to the recognition and differentiation of normal lymphocytes versus abnormal lymphoblast cells on the image of peripheral blood smears. This is considered as a very useful procedure in the initial treatment process of leukemia patients. A computerized recognition system has been developed, and the results of its numerical verification are presented and discussed. The methodology demonstrates that the application of pattern recognition is a powerful tool for the differentiation of normal lymphocytes and acute lymphoblastic leukemia, leading to the improvement in the early effective treatment for leukemia.