US 12,340,443 B2
Method and apparatus for accelerated acquisition and artifact reduction of undersampled MRI using a k-space transformer network
Chang Gao, Los Angeles, CA (US); John Paul Finn, Los Angeles, CA (US); and Xiaodong Zhong, Oak Park, CA (US)
Assigned to Siemens Healthineers AG, Forchheim (DE); and The Regents of the University of California, Oakland, CA (US)
Filed by Siemens Healthineers AG, Forchheim (DE); and The Regents of the University of California, Oakland, CA (US)
Filed on Sep. 23, 2022, as Appl. No. 17/934,618.
Claims priority of provisional application 63/363,320, filed on Apr. 21, 2022.
Prior Publication US 2023/0342993 A1, Oct. 26, 2023
Int. Cl. G06T 11/00 (2006.01); G01R 33/48 (2006.01)
CPC G06T 11/005 (2013.01) [G01R 33/4818 (2013.01); G06T 11/006 (2013.01); G01R 33/4824 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A system for recreating images from undersampled MRI image data comprising:
an MRI imaging system comprising a plurality of magnets and RF coils configured to acquire undersampled radial MRI k-space data comprising acquired radial lines; and
a processor and memory configured to execute software instructions that implement one or more transformer networks that is trained to predict additional projected radial MRI k-space data from the undersampled radial MRI k-space data and to generate MRI images from the additional projected radial MRI k-space data and undersampled radial MRI k-space data,
wherein the one or more transformer networks includes three independent transformer networks, each transformer network of the three independent transformer networks configured to predict a number of radial lines of k-space data equal to a number of the acquired radial lines.