US 11,815,576 B2
Method for correcting object specific inhomogeneities in an MR imaging system
Birgi Tamersoy, Erlangen (DE); Boris Mailhe, Plainsboro, NJ (US); Vivek Singh, Princeton, NJ (US); Ankur Kapoor, Plainsboro, NJ (US); and Mariappan S. Nadar, Plainsboro, NJ (US)
Assigned to Siemens Healthcare GmbH, Erlangen (DE)
Filed by Siemens Healthcare GmbH, Erlangen (DE)
Filed on Mar. 21, 2022, as Appl. No. 17/699,619.
Claims priority of application No. 21168347 (EP), filed on Apr. 14, 2021.
Prior Publication US 2022/0334204 A1, Oct. 20, 2022
Int. Cl. G01R 33/3875 (2006.01); G06N 20/00 (2019.01); G01R 33/44 (2006.01); G01R 33/56 (2006.01)
CPC G01R 33/3875 (2013.01) [G01R 33/443 (2013.01); G01R 33/5608 (2013.01); G06N 20/00 (2019.01)] 15 Claims
OG exemplary drawing
 
1. A method for correcting object specific in-homogeneities in an MR imaging system, the method comprising:
determining prescan information available at the MR imaging system, the prescan information comprising at least an object geometry of an object located in the MR imaging system from which an MR image is to be generated, the object geometry determined from image data of the object acquired using an optical camera, the prescan information not including a B1 map of the MR imaging system with the object being present in the MR imaging system,
applying the prescan information to a trained machine learning module provided at the MR imaging system, the trained machine learning module determining and generating shimming information as output,
applying the shimming information to a shimming module of the MR imaging system, wherein the shimming module uses the shimming information in order to generate a corrected magnetic field B0.