Classification of bone marrow cells for medical diagnosis of acute leukemia

Abstract

Leukemia is the cancer that starts in the blood cells due to the excess production of immature leucocytes that replace the cells with normal blood cells. Physicians rely on their experience to determine the type and subtype of Leukemia from the blood sample. Mostly people are misdiagnosed when it comes to its subtypes, the error rates can be up to 40% during the classification process. That too depends on the expertise of the physician. This research represents a medical image classifier that classifies Leukemia and its five subtypes mainly, State of the art Deep learning and transfer learning techniques have been used, all of the network architectures are fine-tuned followed by feature extraction. This gives us the motive to automate the classification process so that that a physician can get help in decision making and can get an another opinion. we can get better and accurate results for classification. The proposed methodology better results in accuracy and more time effectual as compared to a hematologists visual classification. Each method is studied separately and different experiments are conducted to evaluate their performances. We have compared our proposed method with previous literature in term of accuracy and number of images in their dataset. Unlike the standard methods, our proposed method was able to achieve high accuracy.