Automated Detection Model in Classification of B-Lymphoblast Cells from Normal B-Lymphoid Precursors in Blood Smear Microscopic Images Based on the Majority Voting Technique

Introduction. Acute lymphoblastic leukemia (ALL) is the most common type of leukemia, a deadly white blood cell disease that impacts human bone marrow. ALL detection in its early stages has always been riddled with complexity and difficulty. Peripheral smear (PBS) examination, method applied at outset diagnosis, time-consuming tedious process largely depends on specialist’s experience. Materials Methods. Herein, fast, efficient, comprehensive model based deep learning (DL) was proposed by implementing eight well-known convolutional neural network (CNN) models for feature extraction all images classification B-ALL lymphoblast normal cells. After evaluating their performance, four best-performing CNN were selected to compose an ensemble classifier combining each classifier’s pretrained capabilities. Results. Due close similarity nuclei cancerous cells, alone had low sensitivity poor performance diagnosing these two classes. The majority voting technique adopted combine models. resulting achieved 99.4, specificity 96.7, AUC 98.3, accuracy 98.5. Conclusion. In classifying cells from can achieve high without operator’s intervention determination. It thus be recommended as extraordinary tool analysis samples digital laboratory equipment assist specialists.