English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  MRzero: Fully automated invention of MRI sequences using supervised learning

Loktyushin, A., Herz, K., Dang, N., Glang, F., Deshmane, A., Doerfler, A., et al. (submitted). MRzero: Fully automated invention of MRI sequences using supervised learning.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0006-9F0D-A Version Permalink: http://hdl.handle.net/21.11116/0000-0007-51B9-D
Genre: Paper

Files

show Files

Locators

show
hide
Locator:
https://arxiv.org/abs/2002.04265 (Any fulltext)
Description:
-

Creators

show
hide
 Creators:
Loktyushin, A.1, 2, Author              
Herz, K1, 2, Author              
Dang, N, Author
Glang, F1, 2, Author              
Deshmane, A1, 2, Author              
Doerfler, A, Author
Schölkopf, B3, Author              
Scheffler, K1, 2, Author              
Zaiss, M1, 2, Author              
Affiliations:
1Department High-Field Magnetic Resonance, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497796              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497794              
3Dept. Empirical Inference, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1497647              

Content

show
hide
Free keywords: -
 Abstract: Purpose: A supervised learning framework is proposed to automatically generate MR sequences and corresponding reconstruction without human knowledge on MR strategies. This enables a target-based optimization from scratch, as well as exploration of novel and flexible MR sequence strategies. Methods: The entire scanning and reconstruction process is simulated end-to-end in terms of RF events, gradient moment events in x and y, and delay times, acting on the input model spin system given in terms of proton density, T1 and T2, and B0. As proof of concept we use both conventional MR images but also binary masks and T1 maps as a target and optimize from scratch using the loss defined by data fidelity, SAR, and scan time. Results: In a first attempt, MRzero learns all gradient and RF events from zero, and is able to generate the aimed at target image. Appending a neural network layer to the reconstruction module also arbitrary targets were learned successfully. Experiments could be translated to image acquisition at a real system (3T Siemens, PRISMA) and could be verified in measurements of phantoms and the human brain in vivo. Discussion/Conclusion: We have developed a fully automated MR sequence generator based on Bloch equation simulations and supervised learning. While we focus on the method herein, having such a differentiable digital MR twin at hand paves the way to a novel way of generating MR sequence and reconstruction solely governed by the target provided, which can be a certain MR contrast, but the possibilities for targets are limitless, e.g. quantification, segmentation, as well as contrasts of other image modalities.

Details

show
hide
Language(s):
 Dates: 2020-02
 Publication Status: Submitted
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: -
 Degree: -

Event

show

Legal Case

show

Project information

show

Source

show