A Cloud-Based Machine Learning Approach for Blood Cell Classification using YOLOv5

Abstract

Checking blood cell counts is crucial for diagnosing health issues. Traditionally, this involves manually counting cells under a microscope, a slow and tiring process. This research explores a new method using machine learning. A machine learning approach for automatic identification and counting of three types of blood cells using ‘you only look once’ (YOLO) object detection and classification algorithm. YOLO framework has been trained with a modified configuration BCCD Dataset of blood smear image to automatically identify and count red blood cells, white blood cells, and platelets. Moreover, this study with other convolutional neural network architectures considering architecture complexity, reported accuracy, and running time with this framework and compare the accuracy of the models for blood cells detection. Overall, the computer-aided system of detection and counting enables us to count blood cells from smear images in less than a second, which is useful for practical applications. Among the state-of-the-arts object detection algorithms such as regions with convolutional neural network (R-CNN), you only look once (YOLO), we chose YOLO framework which is about three times faster than Faster R-CNN with VGG-16 architecture. YOLO uses a single neural network to predict bounding boxes and class probabilities directly from the full image in one evaluation. We retrained YOLO framework to automatically identify and count RBCs, WBCs, and platelets from blood smear images. Also, the trained model has been tested with images from another dataset to observe the precision and accuracy to be around 95% with the recall-confidence to be 0.99.