MRzero - Automated discovery of MRI sequences using supervised learning

Loktyushin A, Herz K, Dang N, Glang F, Deshmane A, Weinmüller S, Dörfler A, Scholkopf B, Scheffler K, Zaiss M (2021)

Publication Type: Journal article

Publication year: 2021

Journal

Magnetic Resonance in Medicine Wiley

DOI: 10.1002/mrm.28727

Abstract

Purpose A supervised learning framework is proposed to automatically generate MR sequences and corresponding reconstruction based on the target contrast of interest. Combined with a flexible, task-driven cost function this allows for an efficient exploration of novel MR sequence strategies.

Authors with CRIS profile

Simon Weinmüller Department of Neuroradiology Arnd Dörfler Department of Neuroradiology

Involved external institutions

Max Planck Institute for Intelligent Systems (MPI-IS) / Max-Planck-Institut für Intelligente Systeme DE Germany (DE) Max-Planck-Institut für biologische Kybernetik / Max Planck Institute for Biological Cybernetics DE Germany (DE)

How to cite

APA:

Loktyushin, A., Herz, K., Dang, N., Glang, F., Deshmane, A., Weinmüller, S.,... Zaiss, M. (2021). MRzero - Automated discovery of MRI sequences using supervised learning. Magnetic Resonance in Medicine. https://doi.org/10.1002/mrm.28727

MLA:

Loktyushin, A., et al. "MRzero - Automated discovery of MRI sequences using supervised learning." Magnetic Resonance in Medicine (2021).

BibTeX: Download