Back to results
US 2024/0201299 A1Published application
Parameterizing an Imaging Sequence
AssigneeSiemens Healthcare GmbH
InventorMario Zeller
Life of this patent
Estimating the term…
Abstract
A method for parameterizing an imaging sequence, including: (a) receiving and/or establishing at least one fixed parameter using a computer unit; and (b) automatically setting at least one further parameter of the imaging sequence using a neural network installed on the computer unit, based on the at least one fixed parameter.
Claims17
A computer-implemented method for parameterizing an imaging sequence of a magnetic resonance system, the method comprising:
- (a) receiving and/or establishing at least one fixed parameter using a computer unit;
- and
- (b) automatically setting at least one further parameter of the imaging sequence using a neural network installed on the computer unit, based on the at least one fixed parameter,
- wherein the neural network is trained to set the at least one further parameter based on the at least one fixed parameter, and wherein in the neural network the parameterization is transferred into a sentence-like structure.
1 more element
A computer-implemented method for training a neural network for parameterizing an imaging sequence of a magnetic resonance system, comprising:
- (a) a computer unit providing a trained neural network for language processing;
- (b) the computer unit providing parameterized imaging sequences comprising different parameter values;
- (c) the computer unit converting the imaging sequences into a sentence-like structure, wherein the sentence-like structure describes the parameter values;
- and
- (d) the computer unit training the neural network for the language processing with the converted imaging sequences.
2 more elements
Dependencies are inferred from the claim text.