Automated Detection of Leukemia and Counting RBCs Using Image Processing Technique

A form of cancer known as leukemia affects the bone marrow, which makes an excessive number of aberrant white blood cells (or WBCs) that are not functioning normally. The leukemia diagnosis is typically done by a trained expert who visually observes unique features and determines the type of cancer. This paper presents a system that can automatically detect leukemia in microscopic images of blood and classify them as normal or abnormal (with leukemia). By using models that can discriminate between red blood cells and other cellular components, which have been trained on annotated datasets, the method reduces false positives and increases diagnosis accuracy. There are several benefits to the automated red blood cell counting technique described in this study, including speed, precision, and repeatability. This technology advances hematological diagnostics by using machine learning and image processing to enable faster and more accurate blood cell analysis in clinical and research contexts.