System and method for providing at least one parameter for a magnetic resonance scan
AssigneeSiemens Healthcare GmbH
InventorsGudrun Ruyters, Johann Sukkau, Michael Wullenweber
Life of this patent
Estimating the term…
Abstract
A method and a system for providing parameters of a resonance frequency spectrum of a magnetic resonance scan. The system includes: an input interface for receiving a resonance frequency spectrum of a magnetic resonance scan and a computing device configured to implement a trained machine learning algorithm. The trained machine learning algorithm is trained to receive the resonance frequency spectrum received by the input interface as its input and to generate as its output a set of parameters of the resonance frequency spectrum. The system further includes an output interface configured to output the generated set of parameters.
Claims20
A system for providing at least one parameter for a magnetic resonance scan, the system comprising:
- an input interface configured to receive a resonance frequency spectrum of the magnetic resonance scan;
- a computing device configured to implement a trained machine learning algorithm, wherein the trained machine learning algorithm is trained to input the resonance frequency spectrum and generate the at least one parameter comprising at least a water resonance frequency value;
- and
- an output interface configured to output at least the water resonance frequency value.
A computer-implemented method for providing at least one parameter for a magnetic resonance scan, the method comprising:
- receiving a resonance frequency spectrum of the magnetic resonance scan;
- applying a trained machine learning algorithm to the received resonance frequency spectrum, the trained machine learning algorithm configured to output the at least one parameter comprising at least a water resonance frequency value when input the resonance frequency spectrum;
- and
- outputting at least the water resonance frequency value generated by the trained machine learning algorithm.
A non-transitory computer-readable data storage medium that stores machine-readable instructions executable by at least one processor for providing at least one parameter for a magnetic resonance scan, the machine-readable instructions comprising:
- receiving a resonance frequency spectrum of the magnetic resonance scan;
- applying a trained machine learning algorithm to the received resonance frequency spectrum, the trained machine learning algorithm configured to output the at least one parameter comprising at least a water resonance frequency value when input the resonance frequency spectrum;
- and
- outputting at least the water resonance frequency value generated by the trained machine learning algorithm.
Dependencies are inferred from the claim text.