Back to all papers

Magnetic resonance image processing transformer for general accelerated image restoration.

November 17, 2025pubmed logopapers

Authors

Shen G,Li M,Anderson S,Farris CW,Zhang X

Affiliations (9)

  • Department of Mechanical Engineering, Boston University, Boston, MA, 02215, USA.
  • Photonics Center, Boston University, Boston, MA, 02215, USA.
  • Chobanian & Avedisian School of Medicine, Boston University Medical Campus, Boston, MA, 02118, USA.
  • Department of Mechanical Engineering, Boston University, Boston, MA, 02215, USA. [email protected].
  • Photonics Center, Boston University, Boston, MA, 02215, USA. [email protected].
  • Department of Electrical & Computer Engineering, Boston University, Boston, MA, 02215, USA. [email protected].
  • Department of Biomedical Engineering, Boston University, Boston, MA, 02215, USA. [email protected].
  • Division of Materials Science & Engineering, Boston University, Boston, MA, 02215, USA. [email protected].
  • Rafik B. Hariri Institute for Computing and Computational Science & Engineering, Boston University, Boston, MA, 02215, USA. [email protected].

Abstract

Recent advancements in deep learning have enabled the development of generalizable models that achieve state-of-the-art performance across various imaging tasks. Vision Transformer (ViT)-based architectures, in particular, have demonstrated strong feature extraction capabilities when pre-trained on large-scale datasets. In this work, we introduce the Magnetic Resonance Image Processing Transformer (MR-IPT), a ViT-based image-domain framework designed to enhance the generalizability and robustness of accelerated MRI restoration. Unlike conventional deep learning models that require separate training for different acceleration factors, MR-IPT is pre-trained on a large-scale dataset encompassing multiple undersampling patterns and acceleration settings, enabling a unified framework. By leveraging a shared transformer backbone, MR-IPT effectively learns universal feature representations, allowing it to generalize across diverse restoration tasks. Extensive experiments demonstrate that MR-IPT outperforms both CNN-based and existing transformer-based methods, achieving superior quality across varying acceleration factors and sampling masks. Moreover, MR-IPT exhibits strong robustness, maintaining high performance even under unseen acquisition setups, highlighting its potential as a scalable and efficient solution for accelerated MRI. Our findings suggest that transformer-based general models can significantly advance MRI restoration, offering improved adaptability and stability compared to traditional deep learning approaches.

Topics

Journal Article

Ready to Sharpen Your Edge?

Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.

We respect your privacy. Unsubscribe at any time.