Deep Learning for Classifying of White Blood Cancer

Abstract

Automated classification of cells is an essential but challenging task for computer vision with significant biomedical advantages. Numerous studies have attempted to construct a cell classifier based on artificial intelligence using label-free cellular images obtained from an optical microscope in recent years. While these studies showed promising results, different cell types' biological complexity could not be represented by such classifiers. However, it is well-known that intracellular actin filaments are significantly modified in terms of the malignant cell. This is believed to be closely linked to tumor cells' distinctive growth characteristics, their tendency to invade tissues around them, and metastasize. It is also more beneficial to identify various cell types based on their biological activities using an automated technique. This paper shows the differentiation between normal White Blood Cells and cancer, which can provide new knowledge on malignant changes and be used as an additional diagnostic marker. Since human eyes can not observe the features, we proposed the application of a convolutional neural network (CNN) based on malignant and normal WBCs classification. The Inception- V3Cnn model was validated on various WBCs normal and malignant cell images on regular normal and blood cancer cell lines with differing aggression levels. The study showed that CNN performed better in accuracy and efficiency than a human expert in the cell classification system