# US 2021/0343054 A1 · Systems and methods for image reconstruction

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

- Number: US 2021/0343054 A1
- Document ID: US20210343054A1
- Status: Published application
- Kind: A1
- Application number: 17/305,333
- Filed: 2021-07-05
- Published: 2021-11-04
- Earliest claimed: 2018-06-29
- Assignees: Shanghai United Imaging Healthcare Co., Ltd.
- Applicants: Shanghai United Imaging Healthcare Co., Ltd.
- Inventors: Jingbo WANG; Yuchen WANG
- Web page: https://patentgrep.com/patent/US20210343054A1

## CPC

- 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
- G06T 12/10: Image preprocessing, e.g. calibration, positioning of sources or scatter correction
- G06T 2211/412: Dynamic
- G06T 2211/421: Filtered back projection [FBP]
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A system includes a storage device storing a set instructions and a processor in communication with the storage device, wherein when executing the set of instructions, the processor is configured to cause the system to obtain raw data. The processor may also be configured to cause the system to determine one or more reconstruction-related algorithms and determine one or more containers for the one or more reconstruction-related algorithms. Each of the one or more containers may correspond to at least one of the one or more reconstruction-related algorithms. The system may also be configured determine a reconstruction flow based on the one or more containers and process the raw data according to the reconstruction flow to generate a target image.

## Claims

### Claim at position 1

1-24. (canceled)

### Claim 25

A system, comprising:
a storage device storing a set of instructions; and
at least one processor in communication with the storage device, wherein when executing the set of instructions, the at least one processor is configured to cause the system to perform operations including:
obtaining raw data generated by scanning an object;
determining multiple reconstruction-related algorithms;
determining multiple containers for executing the multiple reconstruction-related algorithms, each of the multiple containers containing at least one of the multiple reconstruction-related algorithms;
determining a reconstruction flow by arranging the multiple containers in an order based on the multiple reconstruction-related algorithms contained in the multiple containers; and
processing the raw data according to the reconstruction flow to generate a target image by executing the multiple containers arranged in the order, wherein for each of the multiple containers,
the container is configured with a capacity of dynamically determining, from a plurality of hardware resources, a hardware resource that is idle; and
the container is configured with a capacity of compiling the reconstructed-related algorithm contained in the container to a format understandable by the hardware resource.

### Claim 26 (depends on 25)

The system of claim 25, wherein the determining multiple containers for executing the multiple reconstruction-related algorithms includes:
for each of at least one of the multiple reconstruction-related algorithms, determining a container for the reconstruction-related algorithm; and
configurating the container for implementing the reconstruction algorithm according to specifications of the reconstruction-related algorithm.

### Claim 27 (depends on 26)

The system of claim 26, wherein the specifications of the reconstruction-related algorithm include at least one of a content of the reconstructed-related algorithm, an amount of resource that the reconstruction-related algorithm needs to utilize corresponding to different hardware resources, or a next reconstruction-related algorithm needs to be used after the reconstruction-related algorithm.

### Claim 28 (depends on 26)

The system of claim 26, wherein the specifications of the reconstruction-related algorithm are a portion of the reconstruction-related algorithm.

### Claim 29 (depends on 25)

The system of claim 25, wherein the determining multiple containers for executing the multiple reconstruction-related algorithms includes:
for one of the multiple reconstruction-related algorithms,
determining whether there is an existing container containing the reconstruction-related algorithm;
in response to determining there is no existing container containing the reconstruction-related algorithm, determining whether there is a container containing a second reconstruction-related algorithm; and
in response to determining that there is the container containing the second reconstruction-related algorithm, replacing the second reconstruction-related algorithm in the container with the first reconstruction-related algorithm.

### Claim 30 (depends on 25)

The system of claim 25, wherein for at least some of the multiple containers arranged in the order, an output of a container is an input of a subsequent container according to the order.

### Claim 31 (depends on 25)

The system of claim 25, wherein the processing the raw data according to the reconstruction flow to generate a target image includes:
determining a first container group from the multiple containers, the first container group including at least one container;
processing the raw data using the first container group to generate image data;
determining a second container group from the multiple containers, the second container group including at least one container; and
processing the image data using the second container group to generate the target image.

### Claim 32 (depends on 31)

The system of claim 31, wherein the processing the image data using the second container group to generate the target image includes:
determining a third container group from the second container group, the third container group including at least one container;
processing the image data using the third container group to generate a preliminary image;
determining a fourth container group from the second container group, the fourth container group including at least one container; and
processing the preliminary image using the fourth container group to generate the target image.

### Claim 33 (depends on 25)

The system of claim 25, wherein some of the multiple containers are operated in parallel.

### Claim 34 (depends on 25)

The system of claim 25, wherein each of at least one of the multiple containers receive an input from at least one container.

### Claim 35

A method, comprising:
obtaining raw data generated by scanning an object;
determining multiple reconstruction-related algorithms;
determining multiple containers for executing the multiple reconstruction-related algorithms, each of the multiple containers containing at least one of the multiple reconstruction-related algorithms;
determining a reconstruction flow by arranging the multiple containers in an order based on the multiple reconstruction-related algorithms contained in the multiple containers; and
processing the raw data according to the reconstruction flow to generate a target image by executing the multiple containers arranged in the order, wherein for each of the multiple containers,
the container is configured with a capacity of dynamically determining, from a plurality of hardware resources, a hardware resource that is idle; and
the container is configured with a capacity of compiling the reconstructed-related algorithm contained in the container to a format understandable by the hardware resource.

### Claim 36 (depends on 35)

The system of claim 35, wherein the determining multiple containers for executing the multiple reconstruction-related algorithms includes:
for each of at least one of the multiple reconstruction-related algorithms,
determining a container for the reconstruction-related algorithm; and
configurating the container for implementing the reconstruction algorithm according to specifications of the reconstruction-related algorithm.

### Claim 37 (depends on 36)

The system of claim 36, wherein the specifications of the reconstruction-related algorithm include at least one of a content of the reconstructed-related algorithm, an amount of resource that the reconstruction-related algorithm needs to utilize corresponding to different hardware resources, or a next reconstruction-related algorithm needs to be used after the reconstruction-related algorithm.

### Claim 38 (depends on 36)

The system of claim 36, wherein the specifications of the reconstruction-related algorithm are a portion of the reconstruction-related algorithm.

### Claim 39 (depends on 35)

The system of claim 35, wherein the determining multiple containers for executing the multiple reconstruction-related algorithms includes:
for one of the multiple reconstruction-related algorithms,
determining whether there is an existing container containing the reconstruction-related algorithm;
in response to determining there is no existing container containing the reconstruction-related algorithm, determining whether there is a container containing a second reconstruction-related algorithm; and
in response to determining that there is the container containing the second reconstruction-related algorithm, replacing the second reconstruction-related algorithm in the container with the first reconstruction-related algorithm.

### Claim 40 (depends on 35)

The system of claim 35, wherein for at least some of the multiple containers arranged in the order, an output of a container is an input of a subsequent container according to the order.

### Claim 41 (depends on 35)

The system of claim 35, wherein the processing the raw data according to the reconstruction flow to generate a target image includes:
determining a first container group from the multiple containers, the first container group including at least one container;
processing the raw data using the first container group to generate image data;
determining a second container group from the multiple containers, the second container group including at least one container; and
processing the image data using the second container group to generate the target image.

### Claim 42 (depends on 35)

The system of claim 35, wherein some of the multiple containers are operated in parallel.

### Claim 43 (depends on 35)

The system of claim 35, wherein each of at least one of the multiple containers receive an input from at least one container.

### Claim 44

A non-transitory computer-readable medium storing a set of instructions, the set of instructions, when executed by a computing device, causing the computing device to implement a method, the method comprising:
obtaining raw data generated by scanning an object;
determining multiple reconstruction-related algorithms;
determining multiple containers for executing the multiple reconstruction-related algorithms, each of the multiple containers containing at least one of the multiple reconstruction-related algorithms;
determining a reconstruction flow by arranging the multiple containers in an order based on the multiple reconstruction-related algorithms contained in the multiple containers; and
processing the raw data according to the reconstruction flow to generate a target image by executing the multiple containers arranged in the order, wherein for each of the multiple containers,
the container is configured with a capacity of dynamically determining, from a plurality of hardware resources, a hardware resource that is idle; and
the container is configured with a capacity of compiling the reconstructed-related algorithm contained in the container to a format understandable by the hardware resource.
