# US 12,111,374 B2 · Computer-implemented magnetic resonance image optimisation method

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

- Number: US 12,111,374 B2
- Document ID: US12111374B2
- Status: Granted
- Kind: B2
- Application number: 17/729,482
- Filed: 2022-04-26
- Published: 2022-11-03
- Granted: 2024-10-08
- Earliest claimed: 2021-04-29
- Assignees: Siemens Healthineers AG
- Applicants: Siemens Healthineers AG
- Inventors: Raphael Tomi-Tricot; Radhouene Neji
- Web page: https://patentgrep.com/patent/US12111374B2

## CPC

- G01R 33/5608: {Data processing and visualization specially adapted for MR, e.g. for feature analysis and pattern recognition on the basis of measured MR data, segmentation of measured MR data, edge contour detection on the basis of measured MR data, for enhancing measured MR data in terms of signal-to-noise ratio by means of noise filtering or apodization, for enhancing measured MR data in terms of resolution by means for deblurring, windowing, zero filling, or generation of gray-scaled images, colour-coded images or images displaying vectors instead of pixels (image data processing or generation, in general G06T)}
- G01R 33/445: {MR involving a non-standard magnetic field B0, e.g. of low magnitude as in the earth's magnetic field or in nanoTesla spectroscopy, comprising a polarizing magnetic field for pre-polarisation, B0 with a temporal variation of its magnitude or direction such as field cycling of B0 or rotation of the direction of B0, or spatially inhomogeneous B0 like in fringe-field MR or in stray-field imaging}
- G01R 33/56563: {caused by a distortion of the main magnetic field B0, e.g. temporal variation of the magnitude or spatial inhomogeneity of B0 (G01R33/56509, G01R33/56518, G01R33/56536 take precedence)}
- G01R 33/5659: {caused by a distortion of the RF magnetic field, e.g. spatial inhomogeneities of the RF magnetic field (G01R33/56509, G01R33/56518, G01R33/56536 take precedence)}
- G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12)

## Abstract

A computer-implemented magnetic resonance image optimisation method is disclosed. An image of an object is mapped using a static magnetic field and divided into a plurality of voxels. Each voxel is represented in a Euclidean n-dimensional space, where n≥3, and clustered by grouping together voxels having similar characteristics to create homogenous clusters. The centre or centroid of each cluster is determined, and used, or the voxel closest to either the centre or the centroid is used, as a super-voxel in an optimisation procedure. An optimised diagnostic image of the object is then generated.

## Claims

### Claim 1

A computer-implemented magnetic resonance image optimisation method, comprising:
mapping an image of an object obtained using a static magnetic field and an incident radio frequency signal by dividing the image into identically sized three-dimensional voxels, dimensions of the identically sized three-dimensional voxels being determined by a desired mapping resolution;
representing each voxel in a Euclidean n-dimensional space, where n≥3, each voxel having a voxel location represented by at least a two-dimensional position and at least one voxel characteristic represented by at least one further dimension;
clustering the Euclidean n-dimensional space by grouping together voxels having similar voxel characteristics to create homogenous clusters;
determining a centre or centroid of each cluster;
using either the determined centre or centroid of each cluster, or the voxel closest to the determined centre or centroid, as a super-voxel in an optimisation procedure; and
generating an optimised diagnostic image of the object,
wherein each voxel characteristic includes at least one of a local transmit magnetic field amplitude induced by the incident RF signal at the voxel location or a local static magnetic field amplitude at a respective voxel location.

### Claim 2 (depends on 1)

The method as claimed in claim 1, wherein each voxel location is represented by a two-dimensional position having x and y coordinates.

### Claim 3 (depends on 1)

The method as claimed in claim 1, wherein each voxel location is represented by a three-dimensional position having x, y and z coordinates.

### Claim 4 (depends on 1)

The method as claimed in claim 1, wherein in response to each voxel characteristic including the local transmit magnetic field amplitude induced by the incident RF signal at the voxel location, the step of clustering comprises partitioning the identically sized three-dimensional voxels into super voxels based on a nearest mean transmit magnetic field amplitude of one of the super voxels.

### Claim 5 (depends on 1)

The method as claimed in claim 1, wherein in response to each voxel characteristic including the local static magnetic field amplitude at the respective voxel location, the step of clustering comprises partitioning the identically sized three-dimensional voxels into super voxels based on a nearest magnetic field amplitude of one of the super voxels.

### Claim 6 (depends on 1)

The method as claimed in claim 1, wherein the clustering is performed using a k-means algorithm.

### Claim 7 (depends on 1)

The method as claimed in claim 1, wherein the mapping includes,
obtaining the image using one of a circularly polarised field, an RF shimming technique, a homogenisation technique or a Direct Signal Control technique.

### Claim 8 (depends on 1)

The method as claimed in claim 1, wherein the optimisation procedure further comprises:
using at least one weighting parameter derived from tracking a cardinality of the clusters.

### Claim 9 (depends on 8)

The method as claimed in claim 8, wherein the at least one weighting parameter comprises a size of the cluster the super-voxel is derived from.

### Claim 10

A data processing system adapted to optimise a magnetic resonance image, comprising:
at least one processor configured to cause the data processing system to,
map an image of an object obtained using a static magnetic field and an incident radio frequency (RF) signal by dividing the image into identically sized three-dimensional voxels, dimensions of the identically sized three-dimensional voxels being determined by a desired mapping resolution;
represent each voxel in a Euclidean n-dimensional space, where n≥3, each voxel having a voxel location represented by at least a two-dimensional position and at least one voxel characteristic represented by at least one further dimension;
cluster the Euclidean n-dimensional space by grouping together voxels having similar voxel characteristics to create homogenous clusters;
determine a centre or centroid of each cluster;
use either the determined centre or centroid of each cluster, or the voxel closest to the determined centre or centroid as a super-voxel in an optimisation procedure; and
generate an optimised diagnostic image of the object,
wherein each voxel characteristic includes at least one of a local transmit magnetic field amplitude induced by the incident RF signal at the voxel location or a local static magnetic field amplitude at a respective voxel location.

### Claim 11 (depends on 1)

A non-transitory computer readable medium comprising instructions that, when executed by a computer, cause the computer to perform the method of claim 1.