An Efficient Strategy for Blood Diseases Detection Based on Grey Wolf Optimization as Feature Selection and Machine Learning Techniques

Acute Lymphoblastic Leukemia (ALL) is a cancer that infects the blood cells causing development of lymphocytes in large numbers. Diagnostic tests are costly and very time-consuming. It important to diagnose ALL using Peripheral Blood Smear (PBS) images, especially initial screening cases. Several issues affect examination process such as diagnostic error, symptoms, nonspecific nature signs ALL. Therefore, objective this study enforce machine-learning classifiers detection benign or malignant after grey wolf optimization algorithm feature selection. The images have been enhanced by an adaptive threshold improve contrast remove errors. model based on technology which has developed for reduction. Finally, acute lymphoblastic leukemia classified into K-nearest neighbors (KNN), support vector machine (SVM), naïve Bayes (NB), random forest (RF) classifiers. best accuracy, sensitivity, specificity were 99.69%, 99.5%, 99%, respectively, To ensure effectiveness proposed model, comparative results with other classification techniques included.