Real-Time White Blood Cell Classification with YOLO

Abstract

White blood cell (WBC) classification plays a crucial role in diagnosing various hematological conditions, including infections, immune disorders, and leukemia. This study presents an automated approach for WBC detection and classification using the YOLOv5 deep learning model. The system integrates a 1.3 MP microscope camera with a stepper motor-driven platform for real-time imaging and classification. The dataset consists of five WBC types: basophils, eosinophils, lymphocytes, monocytes, and neutrophils, with image enhancement and data augmentation applied to improve model performance. The trained YOLOv5 model achieved a classification accuracy of 92.61% and a validation accuracy of 95.86%, demonstrating high precision and recall in WBC identification. The results indicate that this system can effectively automate WBC analysis, reducing manual effort and improving diagnostic accuracy. This approach has potential applications in clinical hematology, offering a rapid and reliable method for WBC classification.