Metal artifact reduction in computed tomography images based on developed generative adversarial neural network

• DOI: 10.1016/j.imu.2021.100573
• Publication Date: 2021-04-21T04:44:41Z
• Authors: Goli Khaleghi; Mohammad Hosntalab; Mahdi Sadeghi; Reza Reiazi; Seied Rabi Mahdavi
• Keywords: Artifact (error); Generative adversarial network

Metal artifacts are one of the major issues encountered in computed tomography (CT) images since they may make distinguishing healthy and tumor organs computing dose distribution through radiotherapy very difficult. Accordingly, designing generative adversarial neural networks (GANs) will help reduce metal artifacts. Training validating with without were simulated MATLAB. Then, these used as input data for GAN, while CT 30 patients head neck cancer testing GAN. Finally, quality metrics denoised compared those noisy images. The dental implant have shown more improvement oral cavity area (16.81%), which is important treatment planning. Simulated validation GAN's ability artifact reduction. Moreover, GAN was affected by density position Corrected allow us to improve