- Gazi Mühendislik Bilimleri Dergisi
- Cilt: 9 Sayı: 4 - ICAIAME 2023 Özel Sayı
- Generating Synthetic Images from Real MR Images Using Deep Learning Methods
Generating Synthetic Images from Real MR Images Using Deep Learning Methods
Authors : Ercüment Güvenç, Gürcan Çetin, Mevlüt Ersoy
Pages : 230-239
View : 26 | Download : 51
Publication Date : 2023-12-31
Article Type : Research
Abstract :Different technological methods are utilized today for diagnosing various diseases in tissues and organs within the human body. The most crucial ones among these are Computed Tomography (CT) and Magnetic Resonance (MR) imaging techniques. The process of MR imaging enables the identification of the size and shapes of tumor regions in the body\'s tissues, facilitating experts in determining the type of tumor as well as whether it is benign or malignant. To aid professionals in this regard, several deep learning-based computer software have been developed to accurately pinpoint tumor areas on the tissue. Due to the lack of image data used in deep learning studies, a limitation naturally arises in studies in this field. In order to eliminate the lack of image data in these studies, image augmentation can be performed using deep learning methods as well as data augmentation methods using various image processing techniques. In this study, Generative Adversarial Networks (GAN), a deep learning technique, were employed to duplicate brain MR images and generate synthetic images. After the resulting MR images were made usable by undergoing various pre-processing, similarity rates to real images were calculated using metrics such as Peak Signal-to-Noise Ratio (PSNR), Structural similarity index (SSIM) and Mean Square Error (MSE), and by looking at these rates, realistic images were added to the data set and the data set was expanded.Keywords : Derin Öğrenme, Üretken Çekişmeli Ağlar, Görüntü İşleme