Aarhus University Seal / Aarhus Universitets segl

Torben Ellegaard Lund

DeepControl: 2DRF pulses facilitating B1+ inhomogeneity and B0 off-resonance compensation in vivo at 7 T

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

Standard

DeepControl: 2DRF pulses facilitating B1+ inhomogeneity and B0 off-resonance compensation in vivo at 7 T. / Vinding, Mads Sloth; Aigner, Christoph Stefan; Schmitter, Sebastian; Lund, Torben Ellegaard.

In: Magnetic Resonance in Medicine, Vol. 85, No. 6, 06.2021, p. 3308-3317.

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

Harvard

APA

CBE

MLA

Vancouver

Author

Vinding, Mads Sloth ; Aigner, Christoph Stefan ; Schmitter, Sebastian ; Lund, Torben Ellegaard. / DeepControl: 2DRF pulses facilitating B1+ inhomogeneity and B0 off-resonance compensation in vivo at 7 T. In: Magnetic Resonance in Medicine. 2021 ; Vol. 85, No. 6. pp. 3308-3317.

Bibtex

@article{0544d14fa84a4f6c944f32a01e94c1f9,
title = "DeepControl: 2DRF pulses facilitating B1+ inhomogeneity and B0 off-resonance compensation in vivo at 7 T",
abstract = "PURPOSE: Rapid 2DRF pulse design with subject-specific B 1 + inhomogeneity and B0 off-resonance compensation at 7 T predicted from convolutional neural networks is presented.METHODS: The convolution neural network was trained on half a million single-channel transmit 2DRF pulses optimized with an optimal control method using artificial 2D targets, B 1 + and B0 maps. Predicted pulses were tested in a phantom and in vivo at 7 T with measured B 1 + and B0 maps from a high-resolution gradient echo sequence.RESULTS: Pulse prediction by the trained convolutional neural network was done on the fly during the MR session in approximately 9 ms for multiple hand-drawn regions of interest and the measured B 1 + and B0 maps. Compensation of B 1 + inhomogeneity and B0 off-resonances has been confirmed in the phantom and in vivo experiments. The reconstructed image data agree well with the simulations using the acquired B 1 + and B0 maps, and the 2DRF pulse predicted by the convolutional neural networks is as good as the conventional RF pulse obtained by optimal control.CONCLUSION: The proposed convolutional neural network-based 2DRF pulse design method predicts 2DRF pulses with an excellent excitation pattern and compensated B 1 + and B0 variations at 7 T. The rapid 2DRF pulse prediction (9 ms) enables subject-specific high-quality 2DRF pulses without the need to run lengthy optimizations.",
keywords = "2DRF pulses, 7 T, artificial intelligence, deep learning, optimal control",
author = "Vinding, {Mads Sloth} and Aigner, {Christoph Stefan} and Sebastian Schmitter and Lund, {Torben Ellegaard}",
note = "{\textcopyright} 2021 International Society for Magnetic Resonance in Medicine.",
year = "2021",
month = jun,
doi = "10.1002/mrm.28667",
language = "English",
volume = "85",
pages = "3308--3317",
journal = "Magnetic Resonance in Medicine",
issn = "0740-3194",
publisher = "JohnWiley & Sons, Inc.",
number = "6",

}

RIS

TY - JOUR

T1 - DeepControl: 2DRF pulses facilitating B1+ inhomogeneity and B0 off-resonance compensation in vivo at 7 T

AU - Vinding, Mads Sloth

AU - Aigner, Christoph Stefan

AU - Schmitter, Sebastian

AU - Lund, Torben Ellegaard

N1 - © 2021 International Society for Magnetic Resonance in Medicine.

PY - 2021/6

Y1 - 2021/6

N2 - PURPOSE: Rapid 2DRF pulse design with subject-specific B 1 + inhomogeneity and B0 off-resonance compensation at 7 T predicted from convolutional neural networks is presented.METHODS: The convolution neural network was trained on half a million single-channel transmit 2DRF pulses optimized with an optimal control method using artificial 2D targets, B 1 + and B0 maps. Predicted pulses were tested in a phantom and in vivo at 7 T with measured B 1 + and B0 maps from a high-resolution gradient echo sequence.RESULTS: Pulse prediction by the trained convolutional neural network was done on the fly during the MR session in approximately 9 ms for multiple hand-drawn regions of interest and the measured B 1 + and B0 maps. Compensation of B 1 + inhomogeneity and B0 off-resonances has been confirmed in the phantom and in vivo experiments. The reconstructed image data agree well with the simulations using the acquired B 1 + and B0 maps, and the 2DRF pulse predicted by the convolutional neural networks is as good as the conventional RF pulse obtained by optimal control.CONCLUSION: The proposed convolutional neural network-based 2DRF pulse design method predicts 2DRF pulses with an excellent excitation pattern and compensated B 1 + and B0 variations at 7 T. The rapid 2DRF pulse prediction (9 ms) enables subject-specific high-quality 2DRF pulses without the need to run lengthy optimizations.

AB - PURPOSE: Rapid 2DRF pulse design with subject-specific B 1 + inhomogeneity and B0 off-resonance compensation at 7 T predicted from convolutional neural networks is presented.METHODS: The convolution neural network was trained on half a million single-channel transmit 2DRF pulses optimized with an optimal control method using artificial 2D targets, B 1 + and B0 maps. Predicted pulses were tested in a phantom and in vivo at 7 T with measured B 1 + and B0 maps from a high-resolution gradient echo sequence.RESULTS: Pulse prediction by the trained convolutional neural network was done on the fly during the MR session in approximately 9 ms for multiple hand-drawn regions of interest and the measured B 1 + and B0 maps. Compensation of B 1 + inhomogeneity and B0 off-resonances has been confirmed in the phantom and in vivo experiments. The reconstructed image data agree well with the simulations using the acquired B 1 + and B0 maps, and the 2DRF pulse predicted by the convolutional neural networks is as good as the conventional RF pulse obtained by optimal control.CONCLUSION: The proposed convolutional neural network-based 2DRF pulse design method predicts 2DRF pulses with an excellent excitation pattern and compensated B 1 + and B0 variations at 7 T. The rapid 2DRF pulse prediction (9 ms) enables subject-specific high-quality 2DRF pulses without the need to run lengthy optimizations.

KW - 2DRF pulses

KW - 7 T

KW - artificial intelligence

KW - deep learning

KW - optimal control

UR - http://www.scopus.com/inward/record.url?scp=85099917300&partnerID=8YFLogxK

U2 - 10.1002/mrm.28667

DO - 10.1002/mrm.28667

M3 - Journal article

C2 - 33480029

VL - 85

SP - 3308

EP - 3317

JO - Magnetic Resonance in Medicine

JF - Magnetic Resonance in Medicine

SN - 0740-3194

IS - 6

ER -