Synthetic Skin Cancer Image Data Generation Using Generative Adversarial Neural Network

Authors : Burak BEYNEK, Şebnem BORA, Vedat EVREN, Aybars UGUR

Pages : 147-150

View : 74 | Download : 7

Publication Date : 2021-11-30

Article Type : Conference Paper

Abstract :In this study, synthetic data generating method using generative adversarial neural network insert ignore into journalissuearticles values(GAN); for the skin cancer types malignant melanoma and basal-cell carcinoma is presented. GAN is a neural network where two synthetic networks compete. The generator attempts to generate data similar to those measured and the discriminator attempts to classify data as dummy or real. Using medical data in studies is a difficult task due to legal and ethical restrictions. Most of the available data is classified because of patient consent and available data in most cases is not labeled, low quality and/or low quantity. Recent GAN systems can generate labeled high quantity data without any personal discriminative information. In this paper, we used skin cancer images in The International Skin Imaging Collaboration insert ignore into journalissuearticles values(ISIC); database that have been used for discriminator training. To test our generated images applicability in the medical field studies we have conducted a Turing test with medical experts in various medical fields. Our results indicate that the generated data obtained with our method is a valuable alternative for real medical data.
Keywords : Deep Learning, Generative Adversarial Networks, Image generation, Medical Image Analysis, Skin Lesion

ORIGINAL ARTICLE URL