# US 9,437,017 B2 · Method and apparatus for metal artifact elimination in a medical image

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

- Number: US 9,437,017 B2
- Document ID: US9437017B2
- Status: Granted
- Kind: B2
- Application number: 14/522,783
- Filed: 2014-10-24
- Published: 2015-04-30
- Granted: 2016-09-06
- Earliest claimed: 2013-10-31
- Assignees: General Electric Company
- Applicants: General Electric Company
- Inventors: Shuqin Dong; Jiaqin Dong; Shuo Li; Jiang Hsieh
- Web page: https://patentgrep.com/patent/US9437017B2

## CPC

- G06T 12/30: Image post-processing, e.g. metal artefact correction
- A61B 6/5258: {involving detection or reduction of artifacts or noise}
- G06T 5/77: Retouching; Inpainting; Scratch removal
- G06T 2207/10081: Computed x-ray tomography [CT]
- G06T 2207/30004: Biomedical image processing
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)

## Abstract

A method and apparatus for metal artifact elimination in a medical image. The method includes: obtaining a medical image to be processed; determining whether or not a metal region is contained in the medial image; and performing artifact elimination processing to the medical image when metal regions are contained in the medical image and a metal density value of one of the metal regions is greater than or equal to a preset density value.

## Claims

### Claim 1

A method for metal artifact elimination in a medical image, operable in a medical imaging device, the method comprising:
obtaining a medical image;
determining a metal region in the medial image;
determining a metal density value of the metal region; and
performing an artifact elimination processing to the medical image when the metal density value of the metal region is greater than or equal to a preset density value, said artifact elimination processing comprising:
determining a boundary region of the metal region as:
forming a circular detecting area for determining a boundary region with each of the pixel points in the metal region being as a center of a circle, and
presetting an initial radius;
determining the circular detection area is the boundary region when a ratio between the metal region and the non-metal region within the circular detecting area is greater than or equal to a preset value, and
reducing the initial radius gradually when the ratio between the metal region and the non-metal region within the circular detecting area is smaller than the preset value until the ratio between the metal region and non-metal region within the formed circular detecting area is greater than the preset value; and
performing boundary smoothing processing to the boundary region.

### Claim 2 (depends on 1)

The method according to claim 1 further comprising: when the metal density value of the metal region is smaller than a preset density value:
determining whether the artifact elimination processing needs to be performed to the metal region based on the size of the metal region.

### Claim 3 (depends on 2)

The method according to claim 2, wherein determining whether the artifact elimination processing needs to be performed comprises:
performing the artifact elimination processing when the size of the metal region is greater than a preset size; and
not performing the artifact elimination processing when the size of the metal region is smaller than a preset size.

### Claim 4 (depends on 1)

The method according to claim 1, wherein performing artifact elimination processing to the medical image comprises:
determining a projection region in the medical image;
performing interpolation correction processing to an interpolation value in the projection region; and
performing restoration and reconstruction processing to the medical image.

### Claim 5

An apparatus for metal artifact elimination in a medical image, the apparatus comprising:
a computer comprising:
an obtaining module configured to obtain the medical image;
a metal region determining module configured to determine a metal region in the medical image and a metal density value of the metal region; and
a first artifact eliminating module configured to perform an artifact elimination processing on the medical image when the metal density value of the metal region is greater than or equal to a preset density value, said first artifact eliminating module comprising:
a boundary determining module configured to determine a boundary region of the metal region, said boundary determining module comprising:
a circular detecting area forming sub-module configured to form a circular detecting area determining a boundary region with each of the pixel points in the metal region being as a center of circle, and presetting an initial radius; and
a boundary determining sub-module configured to determine the circular detecting area is the boundary region when a ratio between the metal region and non-metal region within the circular detecting area is greater than or equal to a preset value, and when the ratio between the metal region and non-metal region within the circular detecting area is smaller than the preset value, reducing the initial radius gradually until the ratio between the metal region and non-metal region within the formed circular detecting area is greater than the preset value;
a boundary processing module configured to perform a boundary smoothing processing to the boundary region.

### Claim 6 (depends on 5)

The apparatus according to claim 5 further comprising:
a second artifact eliminating module configured to determine, when the metal density value of the metal region is smaller than a preset density value;
determining whether the artifact elimination processing needs to be performed to the metal region based on the size of the metal region.

### Claim 7 (depends on 5)

The apparatus according to claim 5, wherein the first artifact eliminating module comprises:
a metal region determining module configured to determine a metal region in a projection region of the medical image;
an interpolation module configured to perform an interpolation correction processing to pixels within the projection region; and
an image reconstructing module for performing restoration and reconstruction to the medical image.

### Claim 8

An apparatus for metal artifact elimination in a medical image, the apparatus comprising:
a computer comprising:
an obtaining module configured to obtain the medical image;
a metal region determining module configured to:
determine at least one metal region in the medical image; and
a corresponding metal density value of for each of the at least one metal region; and
for each of the at least one metal region:
determining whether the metal density value of the metal region is greater than a preset density value;
for each of the at least one metal region having a metal density greater than the preset density value:
perform an artifact eliminating module comprising;
a boundary determining module configured to:
determine a boundary region of the metal region, said boundary determining module comprising:
a circular detecting area forming sub-module configured to:
form a circular detecting area determining a boundary region with each of the pixel points in the metal region being a center of a circle, and
preset an initial radius; and
a boundary determining sub-module configured to:
determine the circular detecting area as the boundary region when a ratio between the metal region and non-metal region within the circular detecting area is greater than or equal to a second preset value, and
when the ratio between the metal region and non-metal region within the circular detecting area is smaller than the second preset value:
reducing the initial radius gradually until the ratio between the metal region and non-metal region within the formed circular detecting area is greater than the second preset value; and
a boundary processing module configured to:
perform a boundary smoothing processing to the boundary region.