AUTOMATIC DETECTION AND CLASSIFICATION OF ACUTE LYMPHOBLASTIC LEUKEMIA USING CONVOLUTION NEURAL NETWORK

Abstract

Acute lymphoblastic leukaemia (ALL) incited death has been recorded in the ten most perilous mortality reason for humans. The root cause of this is the slow ALL detection. Detection of ALL on time can save precious lives. Automatic detection and classification of ALL in blood smear images can improve the accuracy of ALL detection and speed up the clinical decisions of haematologist’s and medical experts. It is difficult and time-consuming to detect and differentiate acute lymphoblastic leukaemia in blood smear images. As a result, both patients and medical professionals should have access to high-quality clinical decision support for acute lymphoblastic leukaemia. In this article, we developed a novel method for classifying and detecting ALL using support vector machine (SVM) and convolution neural network (CNN). In the proposed study, CNN features are initially retrieved using the Alex-Net Model after lymphocyte detection. The detected cell is then divided into two categories using SVM: normal and malignant. To demonstrate the technique's importance and effectiveness, it is compared with state of the art methods.