# US 10,765,890 B2 · System and method for diagnostic and treatment

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

- Number: US 10,765,890 B2
- Document ID: US10765890B2
- Status: Granted
- Kind: B2
- Application number: 16/222,151
- Filed: 2018-12-17
- Published: 2019-07-11
- Granted: 2020-09-08
- Earliest claimed: 2017-11-08
- Assignees: Shanghai United Imaging Healthcare Co., Ltd.
- Applicants: Shanghai United Imaging Healthcare Co., Ltd.
- Inventors: Haining Sun; Guotao Quan; Yuan Bao; Wenjing Cao
- Web page: https://patentgrep.com/patent/US10765890B2

## CPC

- G06T 5/70: Denoising; Smoothing
- A61N 5/1039: {using functional images, e.g. PET or MRI}
- A61N 5/1067: {in real time, i.e. during treatment}
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 5/60: using machine learning, e.g. neural networks
- G06T 7/0014: {using an image reference approach}
- G06T 11/00: Two-dimensional [2D] image generation
- G06T 12/20: Inverse problem, i.e. transformations from projection space into object space
- G06T 12/30: Image post-processing, e.g. metal artefact correction
- G06V 10/24: Aligning, centring, orientation detection or correction of the image
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS
- G16H 30/40: for processing medical images, e.g. editing
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30196: Human being; Person
- G06T 2211/424: Iterative
- G06V 2201/031: of internal organs
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- A61N: ELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY (measurement of bioelectric currents A61B; surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body A61B18/00; anaesthetic apparatus in general A61M; incandescent lamps H01K; infrared radiators for heating H05B)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA

## Abstract

A method may include obtaining first image data relating to a region of interest (ROI) of a first subject. The first image data corresponding to a first equivalent dose level may be acquired by a first device. The method may also include obtaining a model for denoising relating to the first image data and determining second image data corresponding to an equivalent dose level higher than the first equivalent dose level based on the first image data and the model for denoising. In some embodiments, the method may further include determining information relating to the ROI of the first subject based on the second image data and ecording the information relating to the ROI of the first subject.

## Claims

### Claim 1

A method implemented on a computing device having at least one processor and at least one computer-readable storage medium, the method comprising:
obtaining first image data relating to a region of interest (ROI) of a first subject, the first image data corresponding to a first equivalent dose level;
obtaining a model for denoising relating to the first image data;
determining, based on the first image data and the model for denoising, second image data corresponding to a second equivalent dose level higher than the first equivalent dose level;
determining, based on the second image data, information relating to the ROI of the first subject;
obtaining information relating to the ROI of the first subject from a treatment plan of the first subject; and
performing a delivery of a treatment radiation beam based on the determined information relating to the ROI of the first subject and the information relating to the ROI obtained from the treatment plan of the first subject.

### Claim 2 (depends on 1)

The method of claim 1, wherein the model for denoising includes a first neural network model for denoising, and the obtaining a model for denoising, further includes:
obtaining multiple groups of training data relating to multiple second subjects, each group of the multiple groups of training data relating to a second subject, each of the multiple groups of training data including third image data corresponding to a third equivalent dose level and fourth image data corresponding to a fourth equivalent dose level lower than the third equivalent dose level; and
training, based on the multiple groups of training data, a neural network model to obtain the first neural network model for denoising.

### Claim 3 (depends on 1)

The method of claim 1, wherein the model for denoising includes a first neural network model for denoising, and the obtaining a model for denoising, further includes:
obtaining multiple groups of training data relating to multiple second subjects, each group of the multiple groups of training data relating to a second subject, each of the multiple groups of training data including third image data corresponding to a third equivalent dose level and fourth image data corresponding to a fourth equivalent dose level lower than the third equivalent dose level;
training, based on the multiple groups of training data, a neural network model to obtain a second neural network model for denoising;
obtaining fifth image data relating to the first subject, the fifth image data corresponding to a fifth equivalent dose level higher than the first equivalent dose level; and
training, based on the fifth image data relating to the first subject, the second neural network model for denoising to obtain the first neural network model for denoising.

### Claim 4 (depends on 3)

The method of claim 3, wherein the first image data is acquired by a first device, and the fourth image data is acquired by the first device or by a second device different from the first device.

### Claim 5 (depends on 3)

The method of claim 3, further comprising preprocessing at least one of the first image data or the fourth image data.

### Claim 6 (depends on 1)

The method of claim 1, wherein the determining, based on the first image data and the model for denoising, second image data corresponding to a second equivalent dose level higher than the first equivalent dose level, further includes:
determining, based on the model for demising and the first image data, noise data included in the first image data; and
determining, based on the noise data and the first image data, the second image data.

### Claim 7 (depends on 1)

The method of claim 1, wherein the model for denoising includes an image reconstruction model using an iterative reconstruction algorithm, the image reconstruction model includes a first statistical model of noises in a projection domain, the first image data includes first projection data, and the determining, based on the first image data and the model for denoising, second image data corresponding to a second equivalent dose level higher than the first equivalent dose level, further includes:
processing, based on the first statistical model of noises in the projection domain, the first projection data to obtain second projection data;
generating, based on the second projection data, a first image;
generating, based on the first statistical model of noises, a second statistical model of noises in an image domain; and
determining, based on the first image and the second statistical model of noises, the second image data including a second image relating to the ROI of the subject.

### Claim 8 (depends on 1)

The method of claim 1, wherein the model for denoising includes an image reconstruction model using an iterative reconstruction algorithm, the first image data includes first projection data, the second image data includes a target image relating to the ROI of the first subject, and the determining, based on the first image data and the model for denoising, second image data corresponding to a second equivalent dose level higher than the first equivalent dose level, further includes:
determining third projection data indicating a difference between the first projection data and second projection data corresponding to an image estimation;
determining, based on the third projection data and the first statistical model of noises, fourth projection data;
generating, based on the fourth projection data, an error image relating to the ROI of the first subject; and
determining, based on the error image and a second statistical model of noises, the target image relating to the ROI of the first subject.

### Claim 9 (depends on 8)

The method of claim 8, wherein the determining, based on the error image and the second statistical model of noises, the target image relating to the ROI of the first subject, further includes:
iteratively determining, based on the error image and the second statistical model of noises, a value of an objective function in each iteration, including updating the image estimation after each iteration based on the value of the objective function obtained in a most recent iteration; and
determining the target image until a condition is satisfied.

### Claim 10 (depends on 1)

The method of claim 1, wherein the objective function further includes at least one of a first regularization item for suppressing noise and a second regularization item associated with sparsity of the first projection data for suppressing artifact.

### Claim 11 (depends on 1)

The method of claim 1, wherein the first equivalent dose level is no less than 15% of the second equivalent dose level, or no less than 50% of the second equivalent dose level, or no less than 85% of the second equivalent dose level.

### Claim 12 (depends on 1)

The method of claim 1, wherein the first image data is acquired by a computed tomography (CT), and a ratio of the first equivalent dose level to the second equivalent dose level is equal to 1:7.

### Claim 13 (depends on 12)

The method of claim 12, wherein the first device further includes a radiotherapy treatment (RT) device.

### Claim 14 (depends on 1)

The method of claim 1, wherein the first image data is acquired by a cone beam computed tomography (CBCT), and a ratio of the first equivalent dose level to the second equivalent dose level is equal to 1:3.

### Claim 15 (depends on 1)

The method of claim 1, further comprising:
adjusting, based on a comparison between the determined information relating to the ROI and the information relating to the ROI obtained from the treatment plan, a position of the first subject in space.

### Claim 16 (depends on 1)

The method of claim 1, further comprising:
modifying, based on a comparison between the determined information relating to the ROI and the information relating to the ROI obtained from the treatment plan of the first subject, the treatment plan of the first subject.

### Claim 17 (depends on 1)

The method of claim 1, wherein the performing a delivery of a treatment radiation beam based on the determined information relating to the ROI of the first subject and the information relating to the ROI obtained from the treatment plan of the first subject includes:
comparing the determined information relating to the ROI of the first subject and the information relating to the ROI obtained from the treatment plan of the first subject; and
performing the delivery of the treatment radiation beam based on the comparison, including at least one of:
deactivating a delivery of the treatment radiation beam in response to a determination that the comparison is outside a range; or
reactivating a delivery of the treatment radiation beam in response to a determination that the comparison is within the range.

### Claim 18 (depends on 1)

The method of claim 1, further comprising:
determining, based on the determined information relating to the ROI, the treatment plan of the first subject.

### Claim 19

A system, comprising:
a non-transitory computer-readable storage medium storing executable instructions, and
at least one processor in communication with the non-transitory computer-readable storage medium, when executing the executable instructions, causing the system to implement a method, comprising:
obtaining first image data relating to a region of interest (ROI) of a first subject, the first image data acquired by a first device, the first image data corresponding to a first equivalent dose level;
obtaining a model for denoising relating to the first image data;
determining, based on the first image data and the model for denoising, second image data corresponding to an equivalent dose level higher than the first equivalent dose level;
determining, based on the second image data, information relating to the ROI of the first subject;
obtaining information relating to the ROI of the first subject from a treatment plan of the first subject; and
performing a delivery of a treatment radiation beam based on the determined information relating to the ROI of the first subject and the information relating to the ROI obtained from the treatment plan of the first subject.

### Claim 20

A non-transitory computer readable medium, comprising:
instructions being executed by at least one processor, causing the at least one processor to implement a method, comprising:
obtaining first image data relating to a region of interest (ROI) of a first subject, the first image data acquired by a first device, the first image data corresponding to a first equivalent dose level;
obtaining a model for denoising relating to the first image data;
determining, based on the first image data and the model for denoising, second image data corresponding to an equivalent dose level higher than the first equivalent dose level;
determining, based on the second image data, information relating to the ROI of the first subject;
obtaining information relating to the ROI of the first subject from a treatment plan of the first subject; and
performing a delivery of a treatment radiation beam based on the determined information relating to the ROI of the first subject and the information relating to the ROI obtained from the treatment plan of the first subject.