Robust technique for the detection of Acute Lymphoblastic Leukemia

The counting and classification of blood cells helps in diagnosing a vast number of blood diseases. One type of hematological neoplasia which is most common among those blood diseases is Acute Lymphoblastic Leukemia (ALL) and it mostly occurs in the age group of 3-7. The characterization of ALL is done by rapid and uncontrolled growth of immature leukemic cells (also named as blast cells) mainly in bone marrow and lymphoid organs. The primary step in the diagnosis of ALL is the morphological analysis of the bone marrow and blood smear under the microscope. Valuable information is provided by the features extracted from the blood cells for the confirmation of the diagnosis. Nowadays, this is performed manually by experienced operators. The process have numerous drawbacks, such as non-standard accuracy, dependency on the operator skills and time consuming too. A computerized system will be helpful for the analysis of stained microscopic images of the blood cells for quantitative examination. This paper demonstrates a method using morphological operations in MATLAB to segment images and compare between different classifiers to perfectly diagnose the presence of ALL in blood smear.