# US 2024/0202943 A1 · Cbct simulation for ct-to-cbct registration and cbct segmentation

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

- Number: US 2024/0202943 A1
- Document ID: US20240202943A1
- Status: Published application
- Kind: A1
- Application number: 18/539,976
- Filed: 2023-12-14
- Published: 2024-06-20
- Earliest claimed: 2022-12-16
- Assignees: Koninklijke Philips N.V.
- Applicants: Koninklijke Philips N.V.
- Inventors: ALEXANDER SCHMIDT-RICHBERG; SVEN PETER PREVRHAL; RAFAEL WIEMKER; TOBIAS KLINDER; HEIKE CAROLUS; DIRK SCHAEFER
- Web page: https://patentgrep.com/patent/US20240202943A1

## CPC

- G06T 7/30: Determination of transform parameters for the alignment of images, i.e. image registration
- G06T 12/30: Image post-processing, e.g. metal artefact correction
- G06T 7/11: Region-based segmentation
- G06T 12/20: Inverse problem, i.e. transformations from projection space into object space
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/20081: Training; Learning
- G06T 2210/41: Medical
- G06T 2211/441: AI-based methods, deep learning or artificial neural networks
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

The present invention relates to a computer-implemented method for generating a simulated CBCT image based on a computed tomography image. A computed tomography image is converted into attenuation coefficients of the represented tissue, and the computed tomography image is forward-projected to a projection image based on scanner parameters of a simulated CBCT scanner. After the addition of artificial noise to the projection image representing noise detected by the simulated CBCT scanner, the projection image is back-projected with a reconstruction algorithm for the generation of a simulated CBCT image of the subject. The present invention relates further to a method for generating training data for training an artificial intelligence module based on the simulated images, and to methods for registering a computed tomography image to a CBCT image and for segmenting a CBCT image with an artificial intelligence module trained with training data comprising the simulated CBCT images.

## Claims

### Claim 1

A computer-implemented method for generating a simulated cone-beam computed tomography (CBCT) image based on a computed tomography image, the method comprising the steps of:
receiving data representing a CT image comprising a volume of a subject, wherein the volume is divided into voxels, wherein the voxels comprise a representation of a tissue property of a tissue of the subject in a Hounsfield Unit;
converting the Hounsfield Unit of the CT image into attenuation coefficients:
receiving scanner parameters of a simulated CBCT scanner,
forward-projecting the CT image to a projection image based on the scanner parameters of the simulated CBCT scanner;
adding artificial noise to the projection image, the artificial noise is a representation of noise detected by the simulated CBCT scanner;
back-projecting the projection image with a reconstruction algorithm, thereby generating a simulated CBCT image of the subject; and
providing the simulated CBCT image of the subject.

### Claim 2 (depends on 1)

The method of claim 1, wherein the method further comprises the step of modifying the tissue property of the tissue of the subject.

### Claim 3 (depends on 1)

The method of claim 1, wherein the scanner parameters comprise at least two tube peak voltages of the simulated CBCT scanner.

### Claim 4 (depends on 1)

The method of claim 1, wherein the computed tomography image is a fan-beam computed tomography image or a CBCT image.

### Claim 5 (depends on 1)

A computer-implemented method for generating training data for training of an artificial intelligence module to register a CBCT image to a computed tomography image, the method comprising the steps of:
receiving data representing a first computed tomography image of a subject;
generating data representing a second computed tomography image of the subject, wherein the second computed tomography image differs from the first computed tomography image in that a transformation is applied to the second computed tomography image, the transformation comprising a deformation, and/or distortion, and/or rotation, and/or translation of the subject, and/or a cropped field of view;
generating data representing the transformation;
generating a simulated CBCT image based on one of the first computed tomography image and the second computed tomography image according to the method of claim 1, wherein the data representing the computed tomography image comprises the first and/or the second computed tomography image;
generating a set of training data, the set of training data comprising the simulated CBCT image based on one of the first computed tomography image and the second computed tomography image, the other one of the first computed tomography image and the second computed tomography image, and data representing the transformation; and
providing the set of training data.

### Claim 6 (depends on 5)

The method of claim 5, wherein the generating data representing a second computed tomography image of the subject comprises receiving data representing the second computed tomography image of the subject acquired by a computed tomography scanner.

### Claim 7 (depends on 6)

The method of claim 6, wherein the generating data representing the transformation comprises registering the first computed tomography image to the second computed tomography image.

### Claim 8 (depends on 7)

The method of claim 7, wherein the registering of the first computed tomography image to the second computed tomography image is performed with a registering algorithm or an AI-based registering algorithm.

### Claim 9 (depends on 5)

The method of claim 5, wherein the generating data representing a second computed tomography image of the subject comprises applying an artificial transformation to the data representing the first computed tomography image of the subject thereby generating data representing the second computed tomography image of the subject.

### Claim 10 (depends on 9)

The method of claim 9, wherein the step of generating data representing the transformation comprises receiving data representing the artificial transformation.

### Claim 11 (depends on 5)

A computer-implemented method for registering a computed tomography image to a CBCT image, the method comprising:
receiving data representing a computed tomography image of a subject;
receiving data representing a CBCT image of the subject;
determining a transformation necessary for registering the computed tomography image to the CBCT image using an artificial intelligence module,
wherein the artificial intelligence module is trained with training data generated with the method of claim 5;
registering the computed tomography image to the CBCT image according to the determined transformation; and
providing the computed tomography image registered to the CBCT.

### Claim 12 (depends on 1)

A computer-implemented method for segmenting a CBCT image, the method comprising the steps of:
receiving data representing a CBCT image of a subject acquired by a CBCT scanner;
segmenting the CBCT image using an artificial intelligence module,
wherein the artificial intelligence module is trained with training data comprising a plurality of simulated CBCT images generated with the method according to claim 1; and
providing the segmented CBCT image.

### Claim 13 (depends on 12)

The method of claim 12, wherein the training data comprises a plurality of CT images acquired with a computed tomography scanner and/or a plurality of CBCT images acquired with a CBCT scanner.

### Claim 14 (depends on 11)

The method of claim 11, wherein the artificial intelligence module is trained with the training data using a supervised or a semi-supervised training algorithm.

### Claim 15 (depends on 1)

A non-transient computer readable medium comprising instructions which, when the program is executed by a computer, cause the computer to carry out the steps of the method of claim 1.

### Claim 16 (depends on 1)

The method of claim 1, wherein the forward projecting is based on the attenuation coefficients.

### Claim 17 (depends on 1)

The method of claim 1, wherein the forward projecting includes creating raw data based on the attenuation coefficients.
