Classification of B-Lymphoblasts against Normal Lymphocytes by Deep Convolutional Neural Network
K. Anilkumar, V. J. Manoj, T.M. Sagi · Soft Computing Research Society eBooks · 2022
Leukemia is a life-threatening ailment and is a non-tumor type of cancer which results in a large number of abnormal white blood cells known as blasts. Image processing and machine learning techniques can be used to help pathologists to detect and classify these cancer cells. The present work tries to classify the blast cells of acute leukemia (B-Lymphoblasts) against healthy lymphocytes by a custom made Deep Convolutional Neural Network (DCNN) developed by the authors and named as LeukNet using an online dataset C-NMC 2019. The LeukNet is able to classify the cancer cells against the healthy cells with an Accuracy of 86.73% without much complicated segmentation and feature extraction. Even though the accuracy is slightly less compared to the related works on the same dataset, the classification model used in the study is comparatively simple.