# US 2023/0419565 A1 · System and Method for Artifact Reducation In An Image

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

- Number: US 2023/0419565 A1
- Document ID: US20230419565A1
- Status: Published application
- Kind: A1
- Application number: 18/464,537
- Filed: 2023-09-11
- Published: 2023-12-28
- Earliest claimed: 2018-04-06
- Assignees: Medtronic Navigation, Inc.; The Johns Hopkins University
- Applicants: Medtronic Navigation, Inc.; The Johns Hopkins University
- Inventors: Patrick A. HELM; Jeffrey Harold SIEWERDSEN; Ali UNERI; Wojciech ZBIJEWSKI; Xiaoxuan ZHANG; Joseph STAYMAN
- Web page: https://patentgrep.com/patent/US20230419565A1

## CPC

- G06T 12/10: Image preprocessing, e.g. calibration, positioning of sources or scatter correction
- G06T 12/20: Inverse problem, i.e. transformations from projection space into object space
- A61B 6/032: {Transmission computed tomography [CT]}
- A61B 6/5282: {due to scatter}
- A61B 34/10: Computer-aided planning, simulation or modelling of surgical operations
- A61B 90/37: {Surgical systems with images on a monitor during operation}
- G06T 5/70: Denoising; Smoothing
- G06T 5/77: Retouching; Inpainting; Scratch removal
- G06T 7/60: Analysis of geometric attributes
- A61B 2034/102: {Modelling of surgical devices, implants or prosthesis}
- A61B 2090/376: {using X-rays, e.g. fluoroscopy}
- A61B 2090/3764: {with a rotating C-arm having a cone beam emitting source}
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/10124: Digitally reconstructed radiograph [DRR]
- G06T 2207/20081: Training; Learning
- G06T 2207/20182: Noise reduction or smoothing in the temporal domain; Spatio-temporal filtering
- G06T 2207/20221: Image fusion; Image merging
- G06T 2207/30052: Implant; Prosthesis
- G06T 2211/448: involving metal artefacts, streaking artefacts, beam hardening or photon starvation
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)

## Abstract

Selected artifacts, which may be based on distortions or selected attenuation features, may be reduced or removed from a reconstructed image. Various artifacts may occur due to the presence of a metal object in a field of view. The metal object may be identified and removed from a data that is used to generate a reconstruction.

## Claims

### Claim 1

A method of reducing artifacts in an image due to an object, comprising:
accessing parameters of the object;
creating at least one forward projection of the object based on the accessed parameters;
registering the object in the forward projection to at least one acquired projection having the object therein;
modifying the at least one acquired projection to a representation of the registered object; and
generating a reconstruction based on the modified at least one acquired projection.

### Claim 2 (depends on 1)

The method of claim 1, wherein modifying the at least one acquired projection includes inpainting the representation of the object in the at least one acquired projection.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
acquiring a plurality of the projections;
modifying at least a first sub-plurality of acquired projections of the acquired plurality of projections to the representation of the registered object;
wherein generating the reconstruction includes generating the reconstruction based on all of at least the first sub-plurality of acquired projections of the acquired plurality of projections.

### Claim 4 (depends on 3)

The method of claim 3, wherein generating the reconstruction based on at least all of the modified first sub-plurality of acquired projections of the acquired plurality of projections includes generating a three dimensional image.

### Claim 5 (depends on 4)

The method of claim 4, further comprising:
generating a visualization of the reconstruction for display with a display device.

### Claim 6 (depends on 5)

The method of claim 5, wherein generating the visualization comprises at least one of:
generating a direct reconstruction of modified projection values of the modified first sub-plurality of acquired projections;
replacing voxels or pixels that coincide with the registered object in the modified first sub-plurality of acquired projections;
orienting the visualization such that a 2D slice coincides with at least one feature of the object;
superimposing a graphical representation of the object on a display of the at least one of the projections of the acquired plurality of projections; or
combinations thereof.

### Claim 7 (depends on 4)

The method of claim 4, wherein the generated reconstruction is based on at least one of a filtered back projection, a model-based iterative reconstruction process, or combinations thereof.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
determining the parameters of the object to include at least one of a geometry, number of portions, dimensions, materials, interaction of X-rays with the materials, degrees of freedom in motion of the object, or combinations thereof.

### Claim 9 (depends on 8)

The method of claim 8, wherein creating the forward projection of the object based on the accessed parameters includes creating a digitally reconstructed radiograph of the object.

### Claim 10 (depends on 8)

The method of claim 8, wherein the determined parameters are comprised of at least one of exact values based on specifications of the object, parametrically defined, or combinations thereof.

### Claim 11 (depends on 10)

The method of claim 10, wherein the parametrically defined parameters of the object are determined during the registering the object in the forward projection to at least one acquired projection having the object therein.

### Claim 12 (depends on 1)

The method of claim 1, further comprising:
placing the object in a subject; and
acquiring the at least one projection of the subject and the placed object.

### Claim 13 (depends on 1)

The method of claim 1, wherein modifying the acquired projections according to the representation comprises at least one of:
an interpolation-based inpainting of the acquired projections;
machine-learning based inpainting using prior training; or
determining estimated pixel or voxel values using polyenergetic modeling of x-rays in a x-ray beam.

### Claim 14 (depends on 1)

The method of claim 1, further comprising:
generating a visualization based on the generated reconstruction with reduced artifacts in the generated visualization due to the objects in the at least one acquired projection based on the modified at least one acquired projection.

### Claim 15

A system for reducing artifacts in an image due to an object, comprising:
a processor system configured to execute instructions for:
accessing parameters of the object;
creating at least one forward projection of the object based on the accessed parameters;
registering the object in the forward projection to at least one acquired projection having the object therein;
modifying the at least one acquired projection to a representation of the registered object; and
generating a reconstruction based on the modified at least one acquired projection; and
a display device to display a visualization based on the generated reconstruction.

### Claim 16 (depends on 15)

The system of claim 15, wherein the processor system is further configured for:
accessing a plurality of the projections; and
modifying at least a first sub-plurality of acquired projections of the acquired plurality of projections to the representation of the registered object;
wherein generating the reconstruction includes generating the reconstruction based on all of at least the first sub-plurality of acquired projections of the acquired plurality of projections.

### Claim 17 (depends on 16)

The system of claim 16, wherein generating the reconstruction based on at least all of the modified first sub-plurality of acquired projections of the acquired plurality of projections includes generating a three dimensional image.

### Claim 18 (depends on 17)

The system of claim 17, wherein the processor system is further configured for:
generating the visualization for display with the display device comprising at least one of:
generating a direct reconstruction of modified projection values of the modified first sub-plurality of acquired projections;
replacing voxels that coincide with the registered object in the modified first sub-plurality of acquired projections; or
orienting the visualization such that a 2D slice coincides with at least one feature of the object;
superimposing a graphical representation of the object on a display of the at least one of the projections of the acquired plurality of projections; or
combinations thereof.

### Claim 19 (depends on 15)

The system of claim 15, wherein the processor system is further configured for:
determining the parameters of the object to include at least one of a geometry, number of portions, dimensions, materials, interaction of X-rays with the materials, degrees of freedom in motion of the object, or combinations thereof.

### Claim 20

A method of reducing artifacts in an image due to an object, comprising:
operating a processor system for:
accessing parameters of the object;
creating at least one forward projection of the object based on the accessed parameters;
registering the object in the forward projection to at least one acquired projection having the object therein;
modifying the at least one acquired projection to a representation of the registered object; and
generating a reconstruction based on the modified at least one acquired projection;
displaying a visualization of the generated reconstruction.
