# US 2025/0095107 A1 · System and method for improved panoramic ultrasound images

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

- Number: US 2025/0095107 A1
- Document ID: US20250095107A1
- Status: Published application
- Kind: A1
- Application number: 18/368,265
- Filed: 2023-09-14
- Published: 2025-03-20
- Earliest claimed: 2023-09-14
- Assignees: GE Precision Healthcare LLC
- Applicants: GE Precision Healthcare LLC
- Inventors: Gwang Hee Park
- Web page: https://patentgrep.com/patent/US20250095107A1

## CPC

- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 5/60: using machine learning, e.g. neural networks
- A61B 6/5241: {combining overlapping images of the same imaging modality, e.g. by stitching}
- A61B 8/5215: {involving processing of medical diagnostic data}
- A61B 8/5269: {involving detection or reduction of artifacts}
- G06T 5/77: Retouching; Inpainting; Scratch removal
- G06T 2207/10132: Ultrasound image
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)

## Abstract

Systems and methods for acquiring by an ultrasound probe of an ultrasound system, ultrasound image data of an anatomical structure, generating, by at least one processor of the ultrasound system, an acquired panoramic ultrasound image of the anatomical structure based on the ultrasound image data, the acquired panoramic ultrasound image including a loss area, processing, by the at least one processor of the ultrasound system, the acquired panoramic ultrasound image based on one or more reference panoramic ultrasound images without the loss area, and outputting, by the at least one processor of the ultrasound system, an enhanced panoramic ultrasound image without the loss area for presentation on a display system.

## Claims

### Claim 1

A method for enhancing a panoramic ultrasound image comprising:
acquiring by an ultrasound probe of an ultrasound system, ultrasound image data of an anatomical structure;
generating, by at least one processor of the ultrasound system, an acquired panoramic ultrasound image of the anatomical structure based on the ultrasound image data, the acquired panoramic ultrasound image including a loss area;
processing, by the at least one processor of the ultrasound system, the acquired panoramic ultrasound image using one or more reference panoramic ultrasound images without the loss area; and
outputting, by the at least one processor of the ultrasound system, an enhanced panoramic ultrasound image without the loss area for presentation on a display system.

### Claim 2 (depends on 1)

The method of claim 1, wherein the ultrasound image data is 2D or 3D.

### Claim 3 (depends on 1)

The method of claim 1, wherein processing the acquired panoramic ultrasound image is performed using a generative adversarial network (GAN) model.

### Claim 4 (depends on 3)

The method of claim 3, wherein the GAN model comprises:
generating, by at least one processor of the ultrasound system, one or more sample panoramic ultrasound images;
obtaining the one or more reference panoramic ultrasound images without the loss area;
classifying, by the at least one processor of the ultrasound system, the one or more sample panoramic ultrasound images and the one or more reference panoramic ultrasound images; and
providing feedback based on the classifying of the one or more sample panoramic ultrasound images and the one or more reference panoramic ultrasound images.

### Claim 5 (depends on 4)

The method of claim 4, the feedback comprising an error rate.

### Claim 6 (depends on 5)

The method of claim 5, wherein the feedback comprising an error rate is a cost function, a loss function, or a probability distribution.

### Claim 7 (depends on 1)

The method of claim 1, further comprising learning the loss area of the one or more reference panoramic ultrasound images using deep learning, wherein the learning the loss area is repeated with the one or more reference panoramic ultrasound images until an objective function is reached.

### Claim 8

An ultrasound system comprising:
an ultrasound probe configured to:
acquire ultrasound image data of an anatomical structure; and
at least one processor configured to:
generate an acquired panoramic ultrasound image of the anatomical structure based on the ultrasound image data, the acquired panoramic ultrasound image including a loss area;
process the acquired panoramic ultrasound image using one or more reference panoramic ultrasound images without the loss area; and
output an enhanced panoramic ultrasound image without the loss area for presentation on a display system.

### Claim 9 (depends on 8)

The ultrasound system of claim 8, wherein the ultrasound image data is 2D or 3D.

### Claim 10 (depends on 8)

The ultrasound system of claim 8, wherein the at least one processor is further configured to process the acquired panoramic ultrasound image using a generative adversarial network (GAN) model.

### Claim 11 (depends on 8)

The ultrasound system of claim 8, wherein the at least one processor is further configured to: generate one or more sample panoramic ultrasound images;
obtain the one or more reference panoramic ultrasound images without the loss area;
classify the one or more sample panoramic ultrasound images and the one or more reference panoramic ultrasound images; and
provide feedback based on the classification of the one or more sample panoramic ultrasound images and the one or more reference panoramic ultrasound images.

### Claim 12 (depends on 11)

The ultrasound system of claim 11, wherein the feedback is a cost function, a loss function, or a probability distribution.

### Claim 13 (depends on 11)

The ultrasound system of claim 11, wherein the feedback is used to generate additional sample panoramic images.

### Claim 14 (depends on 8)

The ultrasound system of claim 8, wherein the at least one processor is further configured to learn the loss area of the one or more reference panoramic ultrasound images using deep learning, wherein the learning the loss area is repeated by processing the one or more reference panoramic ultrasound images until an objective function is reached.

### Claim 15

An ultrasound system for enhancing panoramic ultrasound images comprising:
an ultrasound probe configured to:
acquire ultrasound image data of an anatomical structure; and
at least one processor configured to:
generate an acquired panoramic ultrasound image of the anatomical structure based on the ultrasound image data, the acquired panoramic ultrasound image including a loss area;
learn the loss area of using deep learning by processing one or more reference panoramic ultrasound images without the loss area;
process the acquired panoramic ultrasound image using the learned loss area; and
output an enhanced panoramic ultrasound image without the loss area for presentation on a display system.

### Claim 16 (depends on 15)

The ultrasound system of claim 15, wherein the ultrasound image data is 2D or 3D.

### Claim 17 (depends on 15)

The ultrasound system of claim 15, wherein the deep learning is performed using a generative adversarial network (GAN) model.

### Claim 18 (depends on 15)

The ultrasound system of claim 15, wherein the at least one processor is further configured to learn the loss area by:
generating one or more sample panoramic ultrasound images;
obtaining the one or more reference panoramic ultrasound images without the loss area;
classifying the one or more sample panoramic ultrasound images and the one or more reference panoramic ultrasound images; and
provide feedback based on the classification of the one or more sample panoramic ultrasound images and the one or more reference panoramic ultrasound images.

### Claim 19 (depends on 18)

The ultrasound system of claim 18, wherein the feedback is a cost function, a loss function, or a probability distribution.

### Claim 20 (depends on 18)

The ultrasound system of claim 18, wherein the feedback is used to generate additional sample panoramic images.
