Blood Cell Cancer Detection Method Based Classification Using CNN Algorithm

Conventional identification of blood disorders based on visual inspection of blood smears through microscope is time consuming, error-prone and is limited by hematologist's physical acuity.Therefore, an automated optical image processing system is required to support clinical decision-making.Leukemia is a type of cancer, characterized by an anomalous production of immature, abnormally-shaped white blood cells (WBC) called "blasts".Leukemia is a white blood cells-(WBC-) related illness affecting the bone marrow and/or blood.A quick, safe, and accurate early-stage diagnosis of leukemia plays a key role in curing and saving patients' lives.Diagnosis is typically carried out by analysing the white blood cells via the microscope of the blood smear.Numerous machine learning algorithms have been developed to identify different diseases, e.g., leukemia and to provide the high number of mis-classification error rate.So To implement a deep learning algorithm to classify the microscope images for White Blood count analysis.The WBC differential count system contained two modules: the detection model and the classification model.The raw bone marrow smear images were first processed by the detection module, through which all the WBCs were detected from red blood cells, blood platelets, staining impurities and so on.Then, the detected cells were used as input for the classification module.The classification module contained two stages.In the first stage, we discriminated the uncountable cells including crush cells, degenerated cells and so on, which are not used in the diagnosis of leukemia.In the second stage, the countable WBCs were submitted for multi-class differentiation using the Convolutional neural network algorithm.