Acute lymphoblast leukemia and multiple myeloma classification using neural network and multilevel Otsu thresholding
Dishant Totade, Ashish Shrivastava · Journal of Emerging Technologies and Innovative Research · 2021
Acute Lymphoblast leukemia and multiple Myeloma is a kind of blood cancer that affects the white blood cells. Early diagnosis is very important to prevent the progression of cancer. The main objective of this research paper is to classify the blood cancer from the microscopic image of the patient’s blood smear. Microscopic blood image analysis results in the early diagnosis of leukemia and myeloma with lower cost. It is less costly to use image for diagnosis, compare to the equipment and methods used in the field of Hematology. The aim of this study is to identify, whether the cell belong to leukemia class or myeloma class. For this 30 microscopic images from both classes is used to train the Convolution Neural Network model and Multi Otsu algorithm to extract the cell region of interest. A degree of accuracy 97.72% gives high performance of the proposed method.