ABSTRACT
Microscopic blood cell analysis is an important methodology for medical diagnosis, and complete blood cell counts (CBCs) are one of the routine tests operated in hospitals to evaluate overall health condition. Results of the CBCs include amounts of red blood cells (RBCs), white blood cells (WBCs), and platelets in a unit blood sample. It is possible to diagnose diseases such as anemia, dengue, COVID-19, etc., when the numbers or shapes of RBCs become abnormal. The percentage of WBCs is one of the important indicators of many severe illnesses such as infection and cancer. Some symptoms like normal or reduced WBC count, or reduced lymphocyte count in the early stages of the COVID-19 onset suspected and confirmed cases. Doctors often use these as criteria to monitor the general health conditions and recovery stages of the patients in the hospital. However, many hospitals are relying on the traditional method of manually counting blood cells using hemocytometer along with other laboratory equipment's and chemical compounds, which is a time-consuming and tedious task, while some are using expensive hematology analyzers to perform these tests. Machine learning based automated identification of COVID-19 infection cells using microscopic section images can help to reduce the time consumed in traditional ways. Detection of blood cells by a patient's blood mark microscopic examination using different techniques of image processing can support fast and effective detection of infection. This chapter is ready to cover latest computational techniques that support blood cell microscopic images-based COVID-19 infection detection.
