Histogram-Based Decision Support System for Extraction and Classification of Leukemia in Blood Smear Images

An abnormality that develops in white blood cells is called leukemia. The diagnosis of leukemia made possible by microscopic investigation the smear periphery. Prior training necessary to complete morphological examination for diagnosis. This paper proposes a Histogram Threshold Segmentation Classifier (HTsC) decision support system. proposed HTsC evaluated based on color and brightness variation dataset images. Arithmetic operations are used crop nucleus automated approximation. White Blood Cell (WBC) segmentation calculated using active contour model determine contrast between image regions transfer approach. Through entropy-adaptive mask generation, WBCs accurately detect circularity region identification nucleus. addressed cytoplasm variations size shape concerning addition rotation operations. Variation WBC imaging characteristics depends cytoplasmic nuclear regions. computation features nuclei classify classification performed with conventional machine-learning techniques integrated deep-learning regression classifier. designed classifier comprises binary lymphocytes, monocytes, neutrophils, eosinophils, abnormalities WBCs. identifies abnormal activity WBC, considering features. It exhibits higher accuracy value 99.6% when combined other classifiers. comparative analysis expressed an overall 98%, which approximately 3%–12% than technique.