Back to all papers

Multi-contrast generation and quantitative MRI using a transformer-based framework with RF excitation embeddings.

December 14, 2025pubmed logopapers

Authors

Nagar D,Ifrah S,Finkelstein A,Vladimirov N,Zaiss M,Perlman O

Affiliations (6)

  • School of Electrical Engineering, Tel Aviv University, Tel Aviv, Israel.
  • School of Biomedical Engineering, Tel Aviv University, Tel Aviv, Israel.
  • Institute of Neuroradiology, University Hospital Erlangen, Friedrich-Alexander Universität Erlangen-Nürnberg, Erlangen, Germany.
  • Department of Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander Universität Erlangen-Nürnberg, Erlangen, Germany.
  • School of Biomedical Engineering, Tel Aviv University, Tel Aviv, Israel. [email protected].
  • Sagol School of Neuroscience, Tel Aviv University, Tel Aviv, Israel. [email protected].

Abstract

Magnetic resonance imaging (MRI) relies on radiofrequency (RF) excitation of proton spin. Clinical diagnosis requires a comprehensive collation of biophysical data via multiple MRI contrasts, acquired using a series of RF sequences that lead to lengthy examinations. Here, we developed a vision transformer-based framework that explicitly utilizes RF excitation information alongside per-subject calibration data (acquired within 28.2 s), to generate a wide variety of image contrasts including fully quantitative molecular, water relaxation, and magnetic field maps. The method was validated across healthy subjects and a cancer patient in two different imaging sites, and proved to be 94% faster than alternative protocols. The transformer-based MRI framework (TBMF) may support the efforts to reveal the molecular composition of the human brain tissue in a wide range of pathologies, while offering clinically attractive scan times.

Topics

Journal Article

Ready to Sharpen Your Edge?

Subscribe to join 7,200+ 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.