Automatic Classification of White Blood Cells Using Pre-Trained Deep Models

White blood cells (WBCs), which are part of the immune system, help our body fight infections and other diseases. Certain diseases can cause to produce fewer WBCs than it needs. For this reason, great importance in field medical imaging. Artificial intelligence-based computer systems assist experts analysis WBCs. In study, an approach is proposed for automatic classification over five different classes using a pre-trained model. ResNet-50, VGG-19, MobileNet-V3-Small models were trained with ImageNet weights. training, validation, testing processes models, public dataset containing 16,633 images not having even class distribution was used. While ResNet-50 model reached 98.79% accuracy, VGG-19 98.19% highest accuracy rate 98.86%. When predictions examined, seen that affected by dominance classify least sampled correctly. classified high deep learning models. Experts effectively use process analyzing