A fuzzy based classifier for diagnosis of acute lymphoblastic leukemia using blood smear image processing

Leukemia is a kind of blood disorder and its early diagnosis plays an important role in preventing the rapid progression of the disease. The main objective of the research is how to use fuzzy concepts for deriving a proper classifier for diagnosis of this disorder in microscopic image of a patient's peripheral blood smears. Analysis of blood image usually results in early diagnosis of leukemia with lower costs. Furthermore, disease control and monitoring are possible at later stages using blood images. The use of pictures for diagnosis is less costly in terms of the equipment and material needed to detect the disease in comparison with other methods in the field of Hematology. The aim of this study is to identify characteristics of white blood cells and to detect the type of lymphoblasts using morphology method for the diagnosis of acute lymphoblastic leukemia. A set of 32 blood smears are used in this project and decisions concerning subtype of acute lymphoblastic leukemia are conducted based on the fuzzy system proposed in the paper. A degree of accuracy of 93.75% reflects better high performance of the proposed classifier.