Automatic Acute Lymphoblastic Leukemia Detection and Comparative Analysis from Images

In this era, surrounded by numerous technologies, medical sector has seen a lot of advancement through implementing various autonomous systems to identify different types of diseases. In this paper, a framework for identification of Acute Lymphoblastic Leukemia from the microscopic image of white blood cell is proposed. Microscopic images are at first carefully preprocessed to prepare them for classification. In addition, four different machine learning algorithms, namely, Random Forest (RF), Support Vector Machine (SVM), Logistic Regression (LR), and Decision Tree (DT) are applied and respective results are analyzed to provide a comparison between these algorithms in terms of different performance metrics. After a thorough comparison, it is observed that the SVM works well to classify and identify the Acute Lymphoblastic cell which is responsible for Leukemia cancer.