Aarhus University Seal / Aarhus Universitets segl

Torben Ellegaard Lund

Ultra-fast (milliseconds), multi-dimensional RF pulse design with deep learning

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Standard

Ultra-fast (milliseconds), multi-dimensional RF pulse design with deep learning. / Vinding, Mads Sloth; Skyum, Birk; Sangill, Ryan; Lund, Torben Ellegaard.

In: Magnetic Resonance in Medicine, Vol. 82, No. 2, 08.2019, p. 586-599.

Research output: Contribution to journal/Conference contribution in journal/Contribution to newspaperJournal articleResearchpeer-review

Harvard

APA

CBE

MLA

Vancouver

Author

Bibtex

@article{b89e68e7f3ea4f97ae0afda20ee32986,
title = "Ultra-fast (milliseconds), multi-dimensional RF pulse design with deep learning",
abstract = " Purpose: Some advanced RF pulses, like multi-dimensional RF pulses, are often long and require substantial computation time due to a number of constraints and requirements, sometimes hampering clinical use. However, the pulses offer opportunities of reduced-FOV imaging, regional flip-angle homogenization, and localized spectroscopy, e.g., of hyperpolarized metabolites. We propose a novel deep learning approach to ultra-fast design multi-dimensional RF pulses with intention of real-time pulse updates. Methods: The proposed neural network considers input maps of the desired excitation region of interest, and outputs a multi-dimensional RF pulse. The training library is retrieved from a large image database, and the target RF pulses trained upon are calculated with a method of choice. Results: A relatively simple neural network is enough to produce reliable 2D spatial-selective RF pulses of comparable performance to the teaching method. For binary regions of interest, the training library does not need to be vast, hence, re-establishment of the training library is not necessarily cumbersome. The predicted, single-channel pulses were tested numerically and experimentally at 3 T. Conclusion: We demonstrate a relatively effortless training of multi-dimensional RF pulses, based on non-MRI related inputs, but working in an MRI setting still. The prediction time of few milliseconds renders real-time updates of advanced RF pulses possible. ",
keywords = "deep learning, multidimensional RF pulses, neural networks, optimal control theory, EXCITATION, MRI, RECONSTRUCTION",
author = "Vinding, {Mads Sloth} and Birk Skyum and Ryan Sangill and Lund, {Torben Ellegaard}",
year = "2019",
month = aug,
doi = "10.1002/mrm.27740",
language = "English",
volume = "82",
pages = "586--599",
journal = "Magnetic Resonance in Medicine",
issn = "0740-3194",
publisher = "JohnWiley & Sons, Inc.",
number = "2",

}

RIS

TY - JOUR

T1 - Ultra-fast (milliseconds), multi-dimensional RF pulse design with deep learning

AU - Vinding, Mads Sloth

AU - Skyum, Birk

AU - Sangill, Ryan

AU - Lund, Torben Ellegaard

PY - 2019/8

Y1 - 2019/8

N2 - Purpose: Some advanced RF pulses, like multi-dimensional RF pulses, are often long and require substantial computation time due to a number of constraints and requirements, sometimes hampering clinical use. However, the pulses offer opportunities of reduced-FOV imaging, regional flip-angle homogenization, and localized spectroscopy, e.g., of hyperpolarized metabolites. We propose a novel deep learning approach to ultra-fast design multi-dimensional RF pulses with intention of real-time pulse updates. Methods: The proposed neural network considers input maps of the desired excitation region of interest, and outputs a multi-dimensional RF pulse. The training library is retrieved from a large image database, and the target RF pulses trained upon are calculated with a method of choice. Results: A relatively simple neural network is enough to produce reliable 2D spatial-selective RF pulses of comparable performance to the teaching method. For binary regions of interest, the training library does not need to be vast, hence, re-establishment of the training library is not necessarily cumbersome. The predicted, single-channel pulses were tested numerically and experimentally at 3 T. Conclusion: We demonstrate a relatively effortless training of multi-dimensional RF pulses, based on non-MRI related inputs, but working in an MRI setting still. The prediction time of few milliseconds renders real-time updates of advanced RF pulses possible.

AB - Purpose: Some advanced RF pulses, like multi-dimensional RF pulses, are often long and require substantial computation time due to a number of constraints and requirements, sometimes hampering clinical use. However, the pulses offer opportunities of reduced-FOV imaging, regional flip-angle homogenization, and localized spectroscopy, e.g., of hyperpolarized metabolites. We propose a novel deep learning approach to ultra-fast design multi-dimensional RF pulses with intention of real-time pulse updates. Methods: The proposed neural network considers input maps of the desired excitation region of interest, and outputs a multi-dimensional RF pulse. The training library is retrieved from a large image database, and the target RF pulses trained upon are calculated with a method of choice. Results: A relatively simple neural network is enough to produce reliable 2D spatial-selective RF pulses of comparable performance to the teaching method. For binary regions of interest, the training library does not need to be vast, hence, re-establishment of the training library is not necessarily cumbersome. The predicted, single-channel pulses were tested numerically and experimentally at 3 T. Conclusion: We demonstrate a relatively effortless training of multi-dimensional RF pulses, based on non-MRI related inputs, but working in an MRI setting still. The prediction time of few milliseconds renders real-time updates of advanced RF pulses possible.

KW - deep learning

KW - multidimensional RF pulses

KW - neural networks

KW - optimal control theory

KW - EXCITATION

KW - MRI

KW - RECONSTRUCTION

UR - http://www.scopus.com/inward/record.url?scp=85063612801&partnerID=8YFLogxK

U2 - 10.1002/mrm.27740

DO - 10.1002/mrm.27740

M3 - Journal article

C2 - 30927308

VL - 82

SP - 586

EP - 599

JO - Magnetic Resonance in Medicine

JF - Magnetic Resonance in Medicine

SN - 0740-3194

IS - 2

ER -