Detection and Classification of Leukemia using Machine Learning

Abstract

Abstract—Leukemia is a haematological malignancy characterized by the abnormal proliferation of cancerous cells inside the bone marrow, resulting in the disruption of normal blood cell production. It induces a rise in the number of leukocytes. Leukemia is characterized by an aberrant proliferation of white blood cells. Leukemia is a heterogeneous disease characterized by the presence of several subtypes. Certain forms of leukemia have been observed to impact the paediatric population. Adults can be affected by several forms of leukemia. Leukemia is categorized according to the progressive elevation of white blood cell counts. There are two main classifications of leukemia, namely Acute leukemia and Chronic leukemia. When the rate of progression is gradual, individuals are diagnosed with chronic leukemia. Acute leukemia is characterized by a rapid proliferation of white blood cells. These two categories are further subdivided into two distinct subtypes for each form of leukemia. Our models were constructed using a customized version of the VGG13 architecture. The VGG13 architecture is a widely used Convolutional Neural Network (CNN) model that consists of many layers. The object recognition model is considered to be innovative. The models are utilized to categorize the microscopic blood smear images provided as input into three distinct categories: Acute Lymphocytic Leukemia or normal cells. The model achieves 92% accuracy in classifying ALL cells assisting automated identification of leukemic cells. Keywords— leukemia detection, leukemia classification, VGG, CNN, Acute leukemia