Meeting Banner
Abstract #2628

Deep learning accelerated Sandwich for 3D multi-channel B1+ mapping at 7T in less than 10 seconds

Natalia Pato Montemayor1,2,3, Jocelyn Philippe1,2,3, James L. Kent4, Aaron Hess4, Antoine Klauser1, Emilie Sleight5,6, Lina Bacha1,2,3, Tommaso Di Noto1,2,3, Bénédicte Maréchal1,2,3, Patrick A. Liebig7, Jürgen Herrler7, Dominik Nickel7, Robin M. Heidemann7, Jean-Philippe Tiran2,3, Tobias Kober7, Tom Hilbert1,2,3, Thomas Yu1,2,3, and Gian Franco Piredda1
1Advanced Clinical Imaging Technology, Siemens Healthineers International AG, Lausanne, Switzerland, 2LTS5, Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland, 3Department of Radiology, Centre Hospitalier Universitaire Vaudois (CHUV) and University of Lausanne (UNIL), Lausanne, Switzerland, 4Wellcome Centre for Integrative Neuroimaging, FMRIB, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom, 5CIBM Centre for Biomedical Imaging, Geneva, Switzerland, 6Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland, 7Siemens Healthineers AG, Erlangen, Germany

Synopsis

Keywords: AI/ML Image Reconstruction, High-Field MRI, B1+ mapping, 7T

Motivation: Online multi-channel B1+ mapping is essential in ultra-high field MRI for individual optimization of parallel transmit pulses.

Goal(s): To rapidly and accurately estimate multi-channel B1+ maps at 7T.

Approach: A deep learning reconstruction was implemented for accelerating the Sandwich sequence. The approach was validated by comparing the estimated 3D B1+ maps of five subjects with the fully sampled acquisitions and conventional compressed sensing reconstructions.

Results: The proposed deep learning method generates accurate 3D multi-channel B1+ maps in under 10 seconds, with an RMSE of 3.6$$$\,$$$±$$$\,$$$1.4° for a target flip angle of 90°.

Impact: This study demonstrates a deep learning-based method for rapid B1+ mapping in ultra-high field MRI, significantly reducing acquisition time to under 10 seconds while maintaining accuracy. The approach enhances the efficiency of parallel transmission, facilitating clinical applications at 7T.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords