Rigid motion-resolved B1+ prediction using deep learning for real-time parallel-transmission pulse design

Plumley, Alix, Watkins, Luke, Treder, Matthias ORCID: https://orcid.org/0000-0001-5955-2326, Liebig, Patrick, Murphy, Kevin ORCID: https://orcid.org/0000-0002-6516-313X and Kopanoglu, Emre ORCID: https://orcid.org/0000-0001-8982-4441 2022. Rigid motion-resolved B1+ prediction using deep learning for real-time parallel-transmission pulse design. Magnetic Resonance in Medicine 87 (5) , pp. 2254-2270. 10.1002/mrm.29132

Preview

PDF - Published Version Available under License Creative Commons Attribution. Download (2MB) | Preview

Abstract

Purpose Tailored parallel-transmit (pTx) pulses produce uniform excitation profiles at 7 T, but are sensitive to head motion. A potential solution is real-time pulse redesign. A deep learning framework is proposed to estimate pTx urn:x-wiley:07403194:media:mrm29132:mrm29132-math-0003 distributions following within-slice motion, which can then be used for tailored pTx pulse redesign. Methods Using simulated data, conditional generative adversarial networks were trained to predict urn:x-wiley:07403194:media:mrm29132:mrm29132-math-0004 distributions in the head following a displacement. Predictions were made for two virtual body models that were not included in training. Predicted maps were compared with ground-truth (simulated, following motion) B1 maps. Tailored pTx pulses were designed using B1 maps at the original position (simulated, no motion) and evaluated using simulated B1 maps at displaced position (ground-truth maps) to quantify motion-related excitation error. A second pulse was designed using predicted maps (also evaluated on ground-truth maps) to investigate improvement offered by the proposed method. Results Predicted urn:x-wiley:07403194:media:mrm29132:mrm29132-math-0005 maps corresponded well with ground-truth maps. Error in predicted maps was lower than motion-related error in 99% and 67% of magnitude and phase evaluations, respectively. Worst-case flip-angle normalized RMS error due to motion (76% of target flip angle) was reduced by 59% when pulses were redesigned using predicted maps. Conclusion We propose a framework for predicting urn:x-wiley:07403194:media:mrm29132:mrm29132-math-0006 maps online with deep neural networks. Predicted maps can then be used for real-time tailored pulse redesign, helping to overcome head motion–related error in pTx.

Item Type:	Article
Date Type:	Publication
Status:	Published
Schools:	Computer Science & Informatics Physics and Astronomy Psychology Cardiff University Brain Research Imaging Centre (CUBRIC)
Subjects:	Q Science > Q Science (General) Q Science > QC Physics
Additional Information:	This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, providedthe original work is properly cited
Publisher:	Wiley
ISSN:	0740-3194
Funders:	The Wellcome Trust, The Engineering and Physical Sciences Research Council, The Rabin Ezra Scholarship Trust
Date of First Compliant Deposit:	4 January 2022
Date of Acceptance:	3 December 2021
Last Modified:	06 Sep 2023 19:02
URI:	https://orca.cardiff.ac.uk/id/eprint/146340

Citation Data

Cited 1 time in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item