EUVIMEDEUVIMED entdecken
Crossref

DiffGAN: An adversarial diffusion model with local transformer for MRI reconstruction

Xiang Zhao, Tiejun Yang, Bingjie Li, Aolin Yang, Yanghui Yan, Chunxia Jiao

Magnetic Resonance Imaging · 2024

DOI: 10.1016/j.mri.2024.03.017 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Magnetic Resonance Imaging, 2024. Verfasst von Xiang Zhao und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, China. Hauptthemen laut MEDLINE: Anxiety, Artifacts. Die Arbeit wurde bisher 33-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: Department of Science and Technology of Henan Province, Henan University of Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Magnetic resonance imaging (MRI) is non-invasive and crucial for clinical diagnosis, but it has long acquisition time and aliasing artifacts. Accelerated imaging techniques can effectively reduce the scanning time of MRI, thereby decreasing the anxiety and discomfort of patients. Vision Transformer (ViT) based methods have greatly improved MRI image reconstruction, but their computational complexity and memory requirements for the self-attention mechanism grow quadratically with image resolution, which limits their use for high resolution images. In addition, the current generative adversarial networks in MRI reconstruction are difficult to train stably. To address these problems, we propose a Local Vision Transformer (LVT) based adversarial Diffusion model (Diff-GAN) for accelerating MRI reconstruction. We employ a generative adversarial network (GAN) as the reverse diffusion model to enable large diffusion steps. In the forward diffusion module, we use a diffusion process to generate Gaussian mixture distribution noise, which mitigates the gradient vanishing issue in GAN training. This network leverages the LVT module with the local self-attention, which can capture high-quality local features and detailed information. We evaluate our method on four datasets: IXI, MICCAI 2013, MRNet and FastMRI, and demonstrate that Diff-GAN can outperform several state-of-the-art GAN-based methods for MRI reconstruction.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AnxietyArtifactsHumansDiffusionElectric Power SuppliesMagnetic Resonance ImagingImage Processing, Computer-Assisted

Stichwörter der Autor:innen

Diffusion modelGANMRI reconstructionTransformer

Autor:innen und Institutionen

  • School of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, China.
  • School of Artificial Intelligence and Big Data, Henan University of Technology, Zhengzhou 450001, China; Key Laboratory of Grain Information Processing and Control (HAUT), Ministry of Education, Zhengzhou, China; Henan…

Förderung

  • Department of Science and Technology of Henan Province
  • Henan University of Technology

Zitieren

APA

Zhao, X., Yang, T., Li, B., Yang, A., Yan, Y., & Jiao, C. (2024). DiffGAN: An adversarial diffusion model with local transformer for MRI reconstruction. Magnetic Resonance Imaging. https://doi.org/10.1016/j.mri.2024.03.017

Vancouver

Zhao X, Yang T, Li B, Yang A, Yan Y, Jiao C. DiffGAN: An adversarial diffusion model with local transformer for MRI reconstruction. Magnetic Resonance Imaging. 2024. doi:10.1016/j.mri.2024.03.017

BibTeX
@article{Zhao2024,
  author = {Zhao, Xiang and Yang, Tiejun and Li, Bingjie and Yang, Aolin and Yan, Yanghui and Jiao, Chunxia},
  title = {DiffGAN: An adversarial diffusion model with local transformer for MRI reconstruction},
  journal = {Magnetic Resonance Imaging},
  year = {2024},
  doi = {10.1016/j.mri.2024.03.017}
}
Kostenlos starten →