US 11,885,862 B2
Deep learning based magnetic resonance imaging (MRI) examination acceleration
Sudhanya Chatterjee, Bangalore (IN); Dattesh Shanbhag, Bangalore (IN); and Suresh Joel, Bangalore (IN)
Assigned to GE Precision Healthcare LLC, Wauwatosa, WI (US)
Filed by GE Precision Healthcare LLC, Wauwatosa, WI (US)
Filed on Oct. 28, 2020, as Appl. No. 17/083,074.
Prior Publication US 2022/0128640 A1, Apr. 28, 2022
Int. Cl. G01R 33/56 (2006.01); A61B 5/055 (2006.01); G06T 7/00 (2017.01); G01R 33/48 (2006.01); G01R 33/483 (2006.01); G06F 18/22 (2023.01)
CPC G01R 33/5608 (2013.01) [A61B 5/055 (2013.01); G01R 33/4818 (2013.01); G01R 33/4835 (2013.01); G06F 18/22 (2023.01); G06T 7/0012 (2013.01); G06T 2207/10088 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A method of magnetic resonance imaging (MRI) examination acceleration, the method comprising:
acquiring at least one fully sampled reference k-space data of a subject;
acquiring a plurality of partial k-space data of the subject;
grafting the plurality of partial k-space data with the at least one fully sampled reference k-space data to generate a grafted k-space data for accelerated examination; and
wherein grafting the plurality of partial k-space data with the fully sampled k-space data is carried out before a deep learning (DL) module-based reconstruction of the grafted data.