Abstract:

The human immune system's white blood cells (WBCs) guard against infection and shield the body from potentially harmful substances. WBCs are mainly composed of neutrophils, eosinophils, basophils, monocytes, and lymphocytes, each of which makes up a different proportion and has a particular job to do[1]. They differ in terms of texture, colour, size, and morphology. In order to count the different types of white blood cells as part of a complete blood count (CBC) test, which is used to assess a person's health, a clinical laboratory is typically used. Deep learning has enabled the fast and accurate classification of blood film images using a variety of algorithms. Detecting and classifying WBC kinds in blood is done automatically with computer assistance. This method attempts to classify WBCs using the latent features of their images. The methodology used in this system is Convolutional Neural Networks, a kind of ANN that is most frequently employed to analyse visual images

Description:

CBC, CNN, Eosinophil, Lymphocyte, Monocyte, Neutrophil