# US 12,178,650 B2 · Systems and methods for guiding the acquisition of an ultrasound image

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

- Number: US 12,178,650 B2
- Document ID: US12178650B2
- Status: Granted
- Kind: B2
- Application number: 17/285,379
- Filed: 2019-10-14
- Published: 2021-11-04
- Granted: 2024-12-31
- Earliest claimed: 2018-10-15
- Assignees: Koninklijke Philips N.V.
- Applicants: Koninklijke Philips N.V.
- Inventors: Laurence Rouet; Cybèle Ciofolo-Veit; Thierry Lefevre; Caroline Denise Francoise Raynaud; Cristian Lorenz; Tobias Klinder; Nicole Schadewaldt; Alexander Schmidt-Richberg
- Web page: https://patentgrep.com/patent/US12178650B2

## CPC

- A61B 8/483: {involving the acquisition of a 3D volume of data}
- A61B 8/0866: {involving foetal diagnosis; pre-natal or peri-natal diagnosis of the baby}
- A61B 8/4245: {involving determining the position of the probe, e.g. with respect to an external reference frame or to the patient}
- A61B 8/461: {Displaying means of special interest}
- A61B 8/469: {for selection of a region of interest}
- A61B 8/5223: {for extracting a diagnostic or physiological parameter from medical diagnostic data (for algorithms to analyse biomedical images G06T7/0012)}
- A61B 8/523: {for generating planar views from image data in a user selectable plane not corresponding to the acquisition plane}
- A61B 8/466: {adapted to display 3D data}
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)

## Abstract

The invention provides a method for guiding the acquisition of an ultrasound image. A 3D ultrasound image is acquired by an ultrasound probe at a first position and an anatomical structure is identified within the 3D ultrasound image. A target imaging plane is estimated based on the identified anatomical structure and it is determined whether the target imaging plane is present within the 3D ultrasound image. If the target imaging plane is present, a displacement between a central plane of the 3D ultrasound image and the target plane is determined. If the displacement is below a predetermined threshold, the target imaging plane is extracted and if the displacement is above the predetermined threshold, an instruction to acquire a 3D ultrasound image with the ultrasound probe at a second position, different from the first position, is generated based on the displacement. The invention further provides a method for estimating a target imaging plane. A central plane of a 3D ultrasound image is obtained, wherein the central plane contains at least part of an anatomical structure and abounding box is generated around the anatomical structure. The bounding box is divided into a grid having a plurality of grid points and, for each grid point; an offset is estimated between the central plane and the target imaging plane. Finally, coordinates of the target imaging plane are estimated based on the offset for each grid point of the bounding box.

## Claims

### Claim 1

A method for guiding the acquisition of an ultrasound image, the method comprising:
acquiring a 3D ultrasound image by controlling an ultrasound probe at a first position;
identifying an anatomical structure within the 3D ultrasound image;
estimating a target imaging plane based on the identified anatomical structure;
determining that the target imaging plane is present within the 3D ultrasound image;
determining a displacement between a central plane of the 3D ultrasound image and the target plane; and
if the displacement is below a predetermined threshold, extracting the target imaging plane from the 3D ultrasound image; or
if the displacement is above the predetermined threshold, generating an instruction to acquire another 3D ultrasound image with the ultrasound probe at a second position, different from the first positon, based on the displacement.

### Claim 2 (depends on 1)

A method as claimed in claim 1, wherein the estimation of the target imaging plane comprises:
obtaining the central plane of the 3D ultrasound image, wherein the central plane contains at least part of the anatomical structure;
generating a bounding box around the anatomical structure in the central plane;
dividing the bounding box into a grid having a plurality of grid points;
for each grid point of the plurality of grid points, estimating an offset between the central plane and the target imaging plane; and
estimating coordinates of the target imaging plane based on the offset for each grid point of the bounding box.

### Claim 3 (depends on 2)

A method as claimed in claim 2, wherein the estimation of the offset comprises applying a multi-resolution neural network to the central plane.

### Claim 4 (depends on 3)

A method as claimed in claim 3, wherein the applying of the multi-resolution neural network comprises:
generating a first image patch from the central plane, wherein the first image patch has a first resolution;
generating a second image patch from the central plane, wherein the second image patch has a second resolution, lower than the first resolution;
extracting a first feature map from the first image patch and a second feature map from the second image patch;
combining the first feature map with the second feature map; and
generating an output layer based on the combined maps, wherein the output layer comprises the offset for each grid point.

### Claim 5 (depends on 1)

A method as claimed in claim 1, wherein the identifying of the anatomical structure comprises segmenting the anatomical structure.

### Claim 6 (depends on 1)

A method as claimed in claim 1, wherein the displacement comprises one or more of:
a translation; and
a rotation.

### Claim 7 (depends on 1)

A method as claimed in claim 1, wherein the instruction comprises one or more of:
a visual instruction; and
an audible instruction.

### Claim 8 (depends on 7)

A method as claimed in claim 7, wherein the visual instruction comprises one or more of:
a schematic based instruction; and
a 3D volume based instruction.

### Claim 9 (depends on 1)

A method as claimed in claim 1, wherein the method further comprises performing biometric analysis on the acquired target imaging plane.

### Claim 10 (depends on 1)

A computer program product implemented in a non-transitory computer readable medium, comprising computer program code means which is adapted, when said computer program product is run on an ultrasound imaging system, to implement the method of claim 1.

### Claim 11

An ultrasound imaging system, the system comprising:
an ultrasound probe adapted to acquire a 3D ultrasound image when located at a first position;
a processor, wherein the processor is adapted to:
identify an anatomical structure within the 3D ultrasound image;
estimate a target imaging plane based on the identified anatomical structure;
determine if the target imaging plane is present within the 3D ultrasound image;
if the target imaging plane is present, determine a displacement between a central plane of the 3D ultrasound image and the target plane; and
if the displacement is below a predetermined threshold, extract the target imaging plane from the 3D ultrasound image; or
if the displacement is above the predetermined threshold, generate an instruction to acquire another 3D ultrasound image with the ultrasound probe at a second position, different from the first positon, based on the displacement.

### Claim 12 (depends on 11)

A system as claimed in claim 11, wherein the processor is further adapted to:
obtain the central plane of the 3D ultrasound image, wherein the central plane contains at least part of the anatomical structure;
generate a bounding box around the anatomical structure in the central plane;
divide the bounding box into a grid having a plurality of grid points;
for each grid point of the plurality of grid points, estimate an offset between the central plane and the target imaging plane; and
estimate coordinates of the target imaging plane based on the offset for each grid point of the bounding box.

### Claim 13 (depends on 12)

A system as claimed in claim 12, wherein the processor is further adapted to apply a multi-resolution neural network to the central plane, wherein the processor is adapted to:
generate a first image patch from the central plane, wherein the first image patch has a first resolution;
generate a second image patch from the central plane, wherein the second image patch has a second resolution, lower than the first resolution;
extract a first feature map from the first image patch and a second feature map from the second image patch;
combine the first feature map with the second feature map; and
generate an output layer based on the combined maps.

### Claim 14 (depends on 11)

A system as claimed in claim 11, wherein the system comprises a display adapted to display the instruction to a user to acquire the another 3D ultrasound image at the second position, wherein the instruction comprises a visual instruction.

### Claim 15 (depends on 11)

A system as claimed in claim 11, wherein the system comprises an audio output device adapted to output the instruction to a user to acquire the another 3D ultrasound image at the second position, wherein the instruction comprises an audible instruction.