A review on machine learning techniques for acute leukemia classification

Acute leukemia is a malignant disease characterized by an excess of immature white blood cells, which proliferate in the circulatory system and replace healthy blood cells. These abnormal cells cause that the body exposure to diseases, affecting a large proportion of the world's population. Acute leukemia is categorized into two types and ten subtypes. Hence, early detection of the particular class of acute leukemia helps to provide patients with adequate treatment. In recent years, studies have focused on the development of automatic methods to detect and classify acute leukemia and its subtypes as an alternative tool to aid in diagnosis. Among these studies, machine learning techniques have gained much attention and shown success. This chapter aims at providing an overview of the most recent advances in the use of machine learning techniques to classify acute leukemia, by examining the different stages involved in this task, such as image preprocessing, feature extraction, and classification. This chapter includes a brief analysis of these trends, emphasizing current issues and possible challenges in this area.