| Abstract: |
Leukocytes, also known as white blood cells (WBCs), are an essential component of the immune system that protects the body against infectious illnesses, germs, and viruses. The classification of white blood cells is often used to identify disorders such as AIDS, leukemia, myeloma, and anemia. A significant number of diverse samples, including various forms of Leukocytes, related sub-types, and blood concentration, may lead to complications, making the examination susceptible to human error. In this study, one of the most common neural networks, the convolutional neural network (CNN), is used to identify several kinds of white blood cells, including eosinophil, lymphocyte, monocyte, and neutrophil. We want to identify a quick and effective classification process and collect data on the distribution of white blood cell evidence, which would eventually facilitate the diagnosis of blood-related disorders. Here, we investigate deep learning advancements in white blood cell classification, concentrating on publicly accessible microscopy image datasets of blood samples.
|
