Automatic Recognition of Acute Myelogenous Leukemia in Blood Microscopic Images Using K-means Clustering and Support Vector Machine

Abstract

Acute myelogenous leukemia (AML) is a subtype of acute leukemia, which is characterized by the accumulation of myeloid blastsin the bone marrow. Careful microscopic examination of stained blood smear or bone marrow aspirate is still the most significantdiagnostic methodology for initial AML screening and considered as the first step toward diagnosis. It is time-consuming and dueto the elusive nature of the signs and symptoms of AML; wrong diagnosis may occur by pathologists. Therefore, the need forautomation of leukemia detection has arisen. In this paper, an automatic technique for identification and detection of AML andits prevalent subtypes, i.e., M2–M5 is presented. At first, microscopic images are acquired from blood smears of patients withAML and normal cases. After applying image preprocessing, color segmentation strategy is applied for segmenting white bloodcells from other blood components and then discriminative features, i.e., irregularity, nucleus-cytoplasm ratio, Hausdorff dimension,shape, color, and texture features are extracted from the entire nucleus in the whole images containing multiple nuclei. Images areclassified to cancerous and noncancerous images by binary support vector machine (SVM) classifier with 10-fold cross validationtechnique. Classifier performance is evaluated by three parameters, i.e., sensitivity, specificity, and accuracy. Cancerous images arealso classified into their prevalent subtypes by multi-SVM classifier. The results show that the proposed algorithm has achieved anacceptable performance for diagnosis of AML and its common subtypes. Therefore, it can be used as an assistant diagnostic toolfor pathologists.