Abstract: Blood smear samples are microscopic preparations of blood cells that serve as a valuable tool in medical diagnostics. By spreading a thin layer of blood onto a glass slide, staining it, and examining it under a microscope, healthcare professionals can gain essential insights into various physiological and pathological conditions. These samples allow for the visualization and characterization of different types of blood cells, including red blood cells, platelets, and white blood cells (WBCs). The classification and identification of WBCs in blood smear samples play a crucial role in diagnosing and monitoring infectious, hematologic, and immune disorders. This review paper focuses on the development and evaluation of an automated system for identifying and classifying different types of white blood cells in blood smear images. The manual process of WBC classification is labor-intensive, time-consuming, and subject to inter-observer variability. In response to these challenges, researchers have increasingly explored automated approaches that employ image processing techniques and machine learning algorithms. These automated systems aim to enhance the efficiency, accuracy, and consistency of WBC classification.
Keywords: WBC, White Blood Cells, Classification Algorithms, CNN.
|
DOI:
10.17148/IJARCCE.2023.125287
