Medical MR Image Synthesis using DCGAN

• Published in: 2022 First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT) pp. 01 - 04
• Main Authors: Divya, S, Suresh, L Padma, John, Ansamma
• Format: Conference Proceeding
• Language: English
• Published: IEEE 16.02.2022
• Subjects: brain tumor; Computational modeling; Computer architecture; Computer vision; Focusing; GAN; Generative adversarial networks; Image synthesis; Magnetic resonance imaging; medical image processing; MRI; synthetic data
• DOI: 10.1109/ICEEICT53079.2022.9768647

Generative Adversarial Networks (GANs) have been extensively gained considerable attention since 2014. Irrefutably saying, their most remarkable success has been made in domains such as computer vision and medical image processing. Despite the noteworthy success attained to date, applying GANs to real world problems still posses significant challenges, one among which is diversity of image generation and detection of fake images from real ones. Focusing on the extend to which various GAN models have made headway against these challenges, this study provides an overview of DCGAN architecture and its application as a synthetic data generator and act an a binary classifier, which detects real or fake images using brain tumorous Magnetic Resonance Imaging (MRI) dataset.