US 12,339,341 B2
Computer-implemented method for determining magnetic resonance images showing different contrasts, magnetic resonance device, computer program and electronically readable storage medium
Thomas Benkert, Neunkirchen am Brand (DE); Marcel Dominik Nickel, Herzogenaurach (DE); and Simon Arberet, Princeton, NJ (US)
Assigned to Siemens Healthineers AG, Erlangen (DE)
Filed by Siemens Healthcare GmbH, Erlangen (DE)
Filed on Feb. 8, 2023, as Appl. No. 18/107,124.
Claims priority of application No. 22155650 (EP), filed on Feb. 8, 2022.
Prior Publication US 2023/0251338 A1, Aug. 10, 2023
Int. Cl. G01R 33/56 (2006.01); G06T 5/70 (2024.01); G06T 11/00 (2006.01)
CPC G01R 33/5608 (2013.01) [G06T 5/70 (2024.01); G06T 11/005 (2013.01); G06T 11/008 (2013.01); G06T 2207/10088 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/30168 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A computer-implemented method for determining magnetic resonance images showing different contrasts in an examination, comprising:
acquiring, using the same acquisition technique, magnetic resonance data sets for each one of a plurality of magnetic resonance images;
reconstructing the magnetic resonance images from their respective magnetic resonance data sets using at least one reconstruction algorithm by performing a de-noising operation,
determining, after the acquisition of the magnetic resonance data sets, a noise strength measure for each contrast associated with each respective one of the magnetic resonance data sets;
selecting, for the de-noising operation, individual de-noising strengths for each contrast depending on each respectively determined noise strength measure,
wherein a first image result for each contrast is obtained from reconstruction steps that are applied before performing the de-noising operation,
wherein the de-noising operation comprises applying a predefined de-noising strength to the first image result to determine a second image result; and
weightedly combining the first image result and the second image result to determine the magnetic resonance image by selecting weights dependent on the noise strength measure for each respective contrast.