US 11,721,049 B2
Method for generating at least one image dataset and one reference image dataset, data carrier, computer program product, and magnetic resonance system
Gregor Koerzdoerfer, Erlangen (DE); and Mathias Nittka, Baiersdorf (DE)
Assigned to Siemens Healthcare GmbH, Erlangen (DE)
Filed by Siemens Healthcare GmbH, Erlangen (DE)
Filed on Nov. 23, 2020, as Appl. No. 17/101,480.
Claims priority of application No. 19212159 (EP), filed on Nov. 28, 2019.
Prior Publication US 2021/0166447 A1, Jun. 3, 2021
Int. Cl. G06T 11/00 (2006.01); G01R 33/48 (2006.01); G01R 33/56 (2006.01); G06N 3/084 (2023.01)
CPC G06T 11/008 (2013.01) [G01R 33/482 (2013.01); G01R 33/4824 (2013.01); G01R 33/5608 (2013.01); G06N 3/084 (2013.01); G06T 11/005 (2013.01); G06T 11/006 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A method for generating at least one image dataset and one reference image dataset of an examination object from at least two raw datasets, the method comprising:
providing a first raw dataset that is recorded using a magnetic resonance system, the first raw dataset including measurement signals at a plurality of readout points in k-space, wherein the readout points lie on a first k-space trajectory;
providing a second raw dataset that is recorded using the same magnetic resonance system and on the same examination object as the first raw dataset, the second raw dataset including measurement signals at a plurality of readout points in k-space, wherein the readout points lie on a second k-space trajectory different from the first k-space trajectory;
reconstructing a plurality of image datasets from the first raw dataset, wherein a separate equalization coefficient set is used before reconstruction of each image dataset of the plurality of image datasets, wherein each of the corresponding equalization coefficient sets defines a phase shift of the phases of the measurement signals of the first raw dataset in k-space;
reconstructing a reference image dataset from the second raw dataset;
comparing the reference image data set with each image dataset of the plurality of image datasets to generate respective similarity values; and
selecting the image dataset with a greatest similarity value of the respective similarity values.