White Blood Cell Image Generation using Deep Convolutional Generative Adversarial Network

Abstract

White blood cells (WBCs) are a crucial component of the human immune system in medicine. The traditional method of white blood cell classification is to segment the cells, extract features, and then classify them. Insufficient data or unbalanced samples can also cause a low classification accuracy of a deep learning model used for medical diagnosis. The deep convolutional generative adversarial network (DCGAN) is the base of this study and is employed to produce images. The experiment show that the model gives 99.44% accuracy for generation of WBC blood cell image.