# US 2024/0201299 A1 · Parameterizing an Imaging Sequence

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2024/0201299 A1
- Document ID: US20240201299A1
- Status: Published application
- Kind: A1
- Application number: 18/520,935
- Filed: 2023-11-28
- Published: 2024-06-20
- Earliest claimed: 2022-12-14
- Assignees: Siemens Healthcare GmbH
- Applicants: Siemens Healthcare GmbH
- Inventors: Mario Zeller
- Web page: https://patentgrep.com/patent/US20240201299A1

## CPC

- G01R 33/543: {Control of the operation of the MR system, e.g. setting of acquisition parameters prior to or during MR data acquisition, dynamic shimming, use of one or more scout images for scan plane prescription (G01R33/546 takes precedence)}
- G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12)

## 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.

## Claims

### Claim 1

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.

### Claim 2 (depends on 1)

The computer-implemented method as claimed in claim 1,
wherein the neural network is a pre-trained neural network for language processing which has been adapted using training with parameters of imaging sequences for an automatic parameterization.

### Claim 3 (depends on 1)

The computer-implemented method as claimed in claim 1,
wherein in an intermediate step, the at least one fixed parameter is transferred by the computer unit into an incomplete sentence-like structure and is then passed to the neural network for setting the at least one further parameter,
wherein the sentence-like structure is incomplete in that parts in the sentence-like structure which relate to the at least one further parameter are lacking, and
wherein the neural network enhances the incomplete sentence-like structure and in this manner determines the at least one further parameter.

### Claim 4 (depends on 1)

The computer-implemented method as claimed in claim 1,
wherein the computer unit comprises a database with specified parameter values for the parameters of the imaging sequence with fixed step sizes between individual parameter values and/or has access to this database, and
wherein the method further comprises:
(c) following the setting of the at least one further parameter by the neural network, rounding the parameter set by the neural network to the nearest specified parameter value.

### Claim 5 (depends on 1)

The computer-implemented method as claimed in claim 1,
wherein after receiving and/or establishing the at least one fixed parameter, the computer unit fetches at least one parameter from an imaging device that is to be used as at least one hardware-related parameter, and
wherein using the neural network, the at least one further parameter is set based on the at least one fixed parameter and the at least one hardware-related parameter.

### Claim 6 (depends on 1)

The computer-implemented method as claimed in claim 1,
wherein a user fixes the at least one parameter by selecting and amending a parameter from an existing imaging sequence,
wherein the neural network sets the at least one further parameter in that it adapts the remaining parameters of the existing imaging sequence based on the amended parameter, and
wherein the neural network is trained to adapt the remaining parameters.

### Claim 7 (depends on 1)

The computer-implemented method as claimed in claim 1,
wherein the fixed parameter is an amended imaging technique in an existing imaging sequence.

### Claim 8 (depends on 1)

The computer-implemented method as claimed in claim 1,
wherein the fixed parameter is a task of omitting a precondition that is needed for execution of an existing imaging sequence, and
wherein the neural network adapts the parameters of the existing imaging sequence such that the imaging sequence functions without the precondition that is not present.

### Claim 9 (depends on 1)

The computer-implemented method as claimed in claim 1,
wherein the fixed parameter is fixed in that a user specifies that it is to be optimized in a specified manner, and
wherein the neural network adapts the at least one further parameter in such a way that the fixed parameter is optimized in the specified manner.

### Claim 10 (depends on 1)

The computer-implemented method as claimed in claim 1,
wherein a user fixes all the parameters with exception of a designation of the imaging sequence and/or wherein all the parameters with the exception of the designation of the imaging sequence are received or established as fixed parameters using the computer unit,
wherein the neural network automatically sets a designation as a further parameter based on the parameters and their effect, and
wherein the designation includes information regarding properties of the imaging sequence.

### Claim 11 (depends on 1)

The computer-implemented method as claimed in claim 1, automatically setting at least all the remaining parameters of the imaging sequence using the neural network installed on the computer unit, based on the at least one fixed parameter.

### Claim 12 (depends on 1)

The computer-implemented method as claimed in claim 1, wherein the neural network is trained to adapt the remaining parameters based on specified imaging sequences which vary in the at least one parameter.

### Claim 13 (depends on 1)

The computer-implemented method as claimed in claim 1,
wherein the fixed parameter is fixed in that a user specifies that it is to be optimized by minimizing the parameter value.

### Claim 14 (depends on 1)

A non-transitory computer-readable data storage device on which a computer program is stored which, when it is executed on a computer, causes the computer to carry out the method as claimed in claim 1.

### Claim 15 (depends on 1)

A magnetic resonance system for imaging, comprising:
a computer unit operable to receive at least one fixed parameter of an imaging sequence and/or to establish at least one fixed parameter, wherein the imaging sequence includes a number of parameters,
wherein the computer unit comprises a neural network and is also operable to set at least one further parameter of the imaging sequence using the neural network 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 the computer unit is configured to carry out the method as claimed in claim 1.

### Claim 16 (depends on 15)

The system as claimed in claim 15, wherein the computer unit is operable to set all the remaining parameters of the imaging sequence using the neural network based on the at least one fixed parameter.

### Claim 17

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.
