@article{article_1489168, title={Generation of Synthetic Data Using Breast Cancer Dataset and Classification with Resnet18}, journal={Karaelmas Fen ve Mühendislik Dergisi}, volume={14}, pages={74–85}, year={2024}, DOI={10.7212/karaelmasfen.1489168}, author={Aytar, Berin and Gündüç, Semra}, keywords={Çekişmeli üretici ağlar, histopatoloji, ÇÖD-ÇÜA, ResNet18, sentetik veri}, abstract={Since technology is advancing so quickly in the modern era of information, data is becoming an essential resource in many fields. Correct data collection, organization, and analysis make it a potent tool for successful decision-making, process improvement, and success across a wide range of sectors. Synthetic data is required for a number of reasons, including the constraints of real data, the expense of collecting labeled data, and privacy and security problems in specific situations and domains. For a variety of reasons, including security, ethics, legal restrictions, sensitivity and privacy issues, and ethics, synthetic data is a valuable tool, particularly in the health sector. A Deep Learning (DL) model called GAN (Generative Adversarial Networks) has been developed with the intention of generating synthetic data. In this study, the Breast Histopathology dataset was used to generate malignant and benign labeled synthetic patch images using MSG-GAN (Multi-Scale Gradients for Generative Adversarial Networks), a form of GAN, to aid in cancer identification. After that, real and synthetic data were classified in four different ways with Transfer Learning (TL) using the ResNet18 model. In the first classification, real data is used as training and test data and an accuracy rate of 84%, in the second classification, synthetic data is used as training and test data and the accuracy rate is 99%, in the third classification, real data is used as training and synthetic data is used as test data and an accuracy rate of 81%, in the fourth classification, synthetic data is used as training and real data is used as test data and an accuracy rate of 76%. As a result of the study, four different classifications were associated and it was tried to determine whether the synthetic images are similar to the original data and whether they behave like real data.}, number={3}, publisher={Zonguldak Bülent Ecevit Üniversitesi}