Brain MRI motion artifact reduction using 3D conditional generative adversarial networks on simulated motion

2021 ◽  
Author(s):  
Mina Ghaffari ◽  
Kamlesh Pawar ◽  
Ruth Oliver
Keyword(s):  
Brain Mri ◽  
Motion Artifact ◽  
Generative Adversarial Networks ◽  
Artifact Reduction ◽  
Adversarial Networks ◽  
Simulated Motion

scholarly journals Usefulness of a Metal Artifact Reduction Algorithm in Digital Tomosynthesis Using a Combination of Hybrid Generative Adversarial Networks

Diagnostics ◽  
2021 ◽  
Vol 11 (9) ◽  
pp. 1629
Author(s):  
Tsutomu Gomi ◽  
Rina Sakai ◽  
Hidetake Hara ◽  
Yusuke Watanabe ◽  
Shinya Mizukami
Keyword(s):  
Radiation Dose ◽  
Dose Reduction ◽  
Gumbel Distribution ◽  
Radiation Dose Reduction ◽  
Generative Adversarial Networks ◽  
Artifact Reduction ◽  
Metal Artifact ◽  
Digital Tomosynthesis ◽  
The Novel ◽  
Adversarial Networks

In this study, a novel combination of hybrid generative adversarial networks (GANs) comprising cycle-consistent GAN, pix2pix, and (mask pyramid network) MPN (CGpM-metal artifact reduction [MAR]), was developed using projection data to reduce metal artifacts and the radiation dose during digital tomosynthesis. The CGpM-MAR algorithm was compared with the conventional filtered back projection (FBP) without MAR, FBP with MAR, and convolutional neural network MAR. The MAR rates were compared using the artifact index (AI) and Gumbel distribution of the largest variation analysis using a prosthesis phantom at various radiation doses. The novel CGpM-MAR yielded an adequately effective overall performance in terms of AI. The resulting images yielded good results independently of the type of metal used in the prosthesis phantom (p < 0.05) and good artifact removal at 55% radiation-dose reduction. Furthermore, the CGpM-MAR represented the minimum in the model with the largest variation at 55% radiation-dose reduction. Regarding the AI and Gumbel distribution analysis, the novel CGpM-MAR yielded superior MAR when compared with the conventional reconstruction algorithms with and without MAR at 55% radiation-dose reduction and presented features most similar to the reference FBP. CGpM-MAR presents a promising method for metal artifact and radiation-dose reduction in clinical practice.

scholarly journals Inner-ear augmented metal artifact reduction with simulation-based 3D generative adversarial networks

2021 ◽  
Vol 93 ◽  
pp. 101990
Author(s):  
Zihao Wang ◽  
Clair Vandersteen ◽  
Thomas Demarcy ◽  
Dan Gnansia ◽  
Charles Raffaelli ◽  
...  
Keyword(s):  
Inner Ear ◽  
Generative Adversarial Networks ◽  
Artifact Reduction ◽  
Metal Artifact ◽  
Metal Artifact Reduction ◽  
Adversarial Networks ◽  
Simulation Based

scholarly journals Super-Resolution and Inpainting with Degraded and Upgraded Generative Adversarial Networks

2020 ◽  
Author(s):  
Yawen Huang ◽  
Feng Zheng ◽  
Danyang Wang ◽  
Junyu Jiang ◽  
Xiaoqian Wang ◽  
...  
Keyword(s):  
Medical Image ◽  
Missing Values ◽  
Brain Mri ◽  
Image Inpainting ◽  
Super Resolution ◽  
Poor Performance ◽  
Independent Learning ◽  
Generative Adversarial Networks ◽  
Image Degradation ◽  
Adversarial Networks

Image super-resolution (SR) and image inpainting are two topical problems in medical image processing. Existing methods for solving the problems are either tailored to recovering a high-resolution version of the low-resolution image or focus on filling missing values, thus inevitably giving rise to poor performance when the acquisitions suffer from multiple degradations. In this paper, we explore the possibility of super-resolving and inpainting images to handle multiple degradations and therefore improve their usability. We construct a unified and scalable framework to overcome the drawbacks of propagated errors caused by independent learning. We additionally provide improvements over previously proposed super-resolution approaches by modeling image degradation directly from data observations rather than bicubic downsampling. To this end, we propose HLH-GAN, which includes a high-to-low (H-L) GAN together with a low-to-high (L-H) GAN in a cyclic pipeline for solving the medical image degradation problem. Our comparative evaluation demonstrates that the effectiveness of the proposed method on different brain MRI datasets. In addition, our method outperforms many existing super-resolution and inpainting approaches.

scholarly journals SegSRGAN: Super-resolution and segmentation using generative adversarial networks — Application to neonatal brain MRI

2020 ◽  
Vol 120 ◽  
pp. 103755 ◽  
Author(s):  
Quentin Delannoy ◽  
Chi-Hieu Pham ◽  
Clément Cazorla ◽  
Carlos Tor-Díez ◽  
Guillaume Dollé ◽  
...  
Keyword(s):  
Brain Mri ◽  
Super Resolution ◽  
Generative Adversarial Networks ◽  
Neonatal Brain ◽  
Adversarial Networks
Sign in / Sign up

Export Citation Format

Share Document