# US 2019/0378312 A1 · Systems and methods for evaluating image quality

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

- Number: US 2019/0378312 A1
- Document ID: US20190378312A1
- Status: Published application
- Kind: A1
- Application number: 16/437,006
- Filed: 2019-06-11
- Published: 2019-12-12
- Earliest claimed: 2018-06-11
- Assignees: Shanghai United Imaging Healthcare Co., Ltd.
- Applicants: Shanghai United Imaging Healthcare Co., Ltd.
- Inventors: Yi WANG
- Web page: https://patentgrep.com/patent/US20190378312A1

## CPC

- G06T 12/30: Image post-processing, e.g. metal artefact correction
- A61B 5/489: {Blood vessels}
- A61B 6/032: {Transmission computed tomography [CT]}
- A61B 6/503: {for diagnosis of the heart}
- A61B 6/504: {for diagnosis of blood vessels, e.g. by angiography}
- A61B 6/5264: {due to motion}
- G06T 5/20: using local operators
- G06T 5/50: using two or more images, e.g. averaging or subtraction
- G06T 5/73: Deblurring; Sharpening
- G06T 7/0014: {using an image reference approach}
- G06T 7/11: Region-based segmentation
- G06T 7/136: involving thresholding
- G06T 7/90: Determination of colour characteristics
- G06T 12/10: Image preprocessing, e.g. calibration, positioning of sources or scatter correction
- A61B 6/037: {Emission tomography}
- A61B 6/481: {involving the use of contrast agents}
- A61B 6/5288: {involving retrospective matching to a physiological signal}
- A61B 6/541: {involving acquisition triggered by a physiological signal}
- G06T 2207/10072: Tomographic images
- G06T 2207/20201: Motion blur correction
- G06T 2207/30048: Heart; Cardiac
- G06T 2207/30101: Blood vessel; Artery; Vein; Vascular
- G06T 2207/30168: Image quality inspection
- G06T 2211/404: Angiography
- G06T 2211/412: Dynamic
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)

## Abstract

A method for evaluating image quality is provided. The method may include: obtaining an image, the image including a plurality of elements, each element of the plurality of elements being a pixel or voxel, each element having a gray level; determining, based on a maximum gray level of the plurality of elements, one or more thresholds for segmenting the image; determining one or more sub-images of a region of interest by segmenting, based on the one or more thresholds, the image; and determining, based on the one or more sub-images of the region of interest, a quality index for the image.

## Claims

### Claim 1

A method implemented on at least one machine each of which has at least one processor and at least one storage device for evaluating image quality, the method comprising:
obtaining an image, the image including a plurality of elements, each element of the plurality of elements being a pixel or voxel, each element having a gray level;
determining, based on a maximum gray level of the plurality of elements, one or more thresholds for segmenting the image;
determining one or more sub-images of a region of interest by segmenting, based on the one or more thresholds, the image; and
determining, based on the one or more sub-images of the region of interest, a quality index for the image.

### Claim 2 (depends on 1)

The method of claim 1, wherein the determining, based on the one or more sub-images of the region of interest, a quality index for the image comprises:
determining, based on the one or more sub-images of the region of interest, a regularity degree of the image;
determining, based on the one or more sub-images of the region of interest, a sharpness degree of the image; and
determining, based on the regularity degree and the sharpness degree, the quality index for the image.

### Claim 3 (depends on 2)

The method of claim 2, wherein the determining, based on the regularity degree and the sharpness degree, the quality index for the image comprises:
designating a weighted sum of the regularity degree and the sharpness degree as the quality index for the image.

### Claim 4 (depends on 2)

The method of claim 2, wherein the determining, based on the one or more sub-images of the region of interest, a quality index for the image further comprises:
identifying one or more connected domains in the one or more sub-images of the image;
determining a count of the identified connected domains in the image; and
in response to a determination that the count of the identified connected domains in the image is zero,
designating the regularity degree of the image as zero; and
designating the sharpness degree of the image as zero.

### Claim 5 (depends on 4)

The method of claim 4, wherein the determining, based on the one or more sub-images of the region of interest, a regularity degree of the image comprises:
determining a perimeter and an area of each connected domain of the identified connected domains in the image; and
determining, based on the one or more perimeters and the one or more areas, a regularity degree for the image.

### Claim 6 (depends on 4)

The method of claim 4, wherein the determining, based on the one or more sub-images of the region of interest, a sharpness degree of the image comprises:
for each connected domain of the identified connected domains in the image,
determining an edge of the each connected domain; and
determining a gradient map of the each connected domain; and
determining, based on the one or more edges and the gradient maps, the sharpness degree of the image.

### Claim 7 (depends on 1)

The method of claim 1, wherein the determining, based on a maximum gray level of the plurality of elements, one or more thresholds for segmenting the image comprises:
designating the maximum gray level multiplied by one or more predetermined multiples as the one or more thresholds for segmenting the image.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
obtaining a second images, the second image including a plurality of second elements, each element of the plurality of second elements being a pixel or voxel, each second element having a gray level;
determining, based on a maximum gray level of the plurality of second elements, one or more second thresholds for segmenting the second image;
determining one or more second sub-images of a second region of interest by segmenting, based on the one or more second thresholds, the second image; and
determining, based on the one or more second sub-images of the region of interest, a second quality index for the second image.
comparing the quality index and the second quality index; and
designating one of the image or the second image that has a larger quality index as a target image.

### Claim 9

(canceled)

### Claim 10 (depends on 1)

The method of claim 1, wherein the obtaining the image comprising:
obtaining projection data;
reconstructing a plurality of initial images based on the projection data;
determining a mean phase based on the plurality of initial images;
selecting one or more candidate cardiac motion phases in a preset phase range, the preset phase range including the mean phase;
obtaining an image of a region of interest by extracting the region of interest in each initial image of the preset phase range;
identifying a blood vessel centerline associated with the plurality of images of the region of interest; and
obtaining the image by segmenting, based on a preset region including the blood vessel centerline, one of the plurality of images of the region of interest.

### Claim 11

A method implemented on at least one machine each of which has at least one processor and at least one storage device for reconstructing a target cardiac image, the target cardiac image including a plurality of elements, each element of the plurality of elements being a pixel or voxel, the method comprising:
obtaining projection data generated by an imaging device, the projection data including a plurality of sub-sets of projection data, each sub-set of projection data corresponding to a cardiac motion phase;
obtaining a plurality of cardiac images corresponding to one or more cardiac motion phases based on the plurality of sub-sets of projection data corresponding to the one or more cardiac motion phases;
determining a quality index for each cardiac image of the plurality of cardiac images;
determining a phase of interest base on the plurality of quality indexes; and
obtaining the target cardiac image of the phase of interest.

### Claim 12 (depends on 11)

The method of claim 11, wherein the obtaining a plurality of cardiac images corresponding to one or more cardiac motion phases comprises:
reconstructing a plurality of initial cardiac images based on the projection data, the plurality of initial cardiac images corresponding to a plurality of cardiac motion phases;
determining a mean phase based on the plurality of initial cardiac images;
selecting one or more candidate cardiac motion phases in a preset phase range, the preset phase range including the mean phase;
obtaining an image of a region of interest by extracting the region of interest in each initial cardiac image of one or more initial cardiac images of the one or more candidate cardiac motion phases;
identifying a blood vessel centerline associated with the one or more images of the region of interest; and
obtaining the each cardiac image of the plurality of cardiac images by segmenting, based on a preset region including the blood vessel centerline, each image of the region of interest.

### Claim 13

(canceled)

### Claim 14 (depends on 12)

The method of claim 12, wherein the determining a mean phase based on the plurality of initial cardiac images comprises:
obtaining a plurality of mean absolute differences (MADs) by determining an MAD between two initial cardiac images of each two adjacent cardiac motion phases of the plurality of cardiac motion phases;
determining a plurality of cardiac motion parameters corresponding to the plurality of cardiac motion phases based on the plurality of mean absolute differences; and
determining the mean phase based on the plurality of cardiac motion parameters corresponding to the plurality of cardiac motion phases.

### Claim 15 (depends on 14)

The method of claim 14, wherein the determining a plurality of cardiac motion parameters corresponding to the plurality of cardiac motion phases comprises:
determining a first mean absolute difference (MAD) between a first initial cardiac image of a first cardiac motion phase that occurs before the each cardiac motion phase and an initial cardiac image of the each cardiac motion phase;
determining a second mean absolute difference (MAD) between a second initial cardiac image of a second cardiac motion phase that occurs after the each cardiac motion phase and an initial cardiac images of the each cardiac motion phase; and
designating a sum of the first mean absolute difference (MAD) and the second mean absolute difference (MAD) as the cardiac motion parameter corresponding to the each cardiac motion phase.

### Claim at position 16

16-18. (canceled)

### Claim 19 (depends on 12)

The method of claim 12, wherein the obtaining an image of a region of interest by extracting the region of interest in each initial cardiac image of one or more initial cardiac images of the one or more candidate cardiac motion phases comprises:
extracting a ventricular image from the each initial cardiac image of the one or more initial cardiac images;
obtaining, based on the ventricular image, a first threshold associated with gray levels of a contrast agent in the one or more initial cardiac images;
obtaining a contrast agent image by segmenting the ventricular image based on the first threshold; and
extracting the image of the region of interest from the contrast agent image.

### Claim 20 (depends on 19)

The method of claim 19, wherein the obtaining an image of a region of interest by extracting the region of interest in each initial cardiac image of one or more initial cardiac images of the one or more candidate cardiac motion phases further comprises:
smoothing the each initial cardiac image of the one or more initial cardiac images using a low pass filter.

### Claim 21 (depends on 12)

The method of claim 12, wherein the identifying a blood vessel centerline associated with the one or more images of the region of interest comprises:
generating one or more images in a coronal plane and one or more images in a sagittal plane based on the one or more images of the region of interest;
determining a blood vessel main body based on the one or more images in the coronal plane and the one or more images in the sagittal plane;
filtering out one or more false positive vessels from the blood vessel main body; and
identifying, based on the filtered blood vessel main body, a blood vessel center in each transverse layer associated with the one or more image of the region of interest.

### Claim 22 (depends on 12)

The method of claim 12, wherein the obtaining the each cardiac image of the plurality of cardiac images by segmenting, based on a preset region including the blood vessel centerline, each image of the region of interest comprises:
generating a transformed image of the region of interest by performing a top-hat transformation on the each image of the region of interest;
generating an image including an intraventricular region by segmenting, based on a second threshold associated with gray levels of a soft tissue, the transformed image of the region of interest; and
obtaining the each cardiac image of the plurality of cardiac images by segmenting, based on the preset region including the blood vessel centerline, the image including the intraventricular region.

### Claim 23 (depends on 11)

The method of claim 11, wherein the determining a phase of interest base on the plurality of quality indexes comprises:
determining a maximum quality index in the plurality of quality indexes; and
designating a phase of an image that has the maximum quality index as the phase of interest.

### Claim 24

(canceled)

### Claim 25 (depends on 11)

The method of claim 11, wherein the determining a quality index for each cardiac image of the plurality of cardiac images comprises:
determining, based on a maximum gray level of the plurality of elements of the each cardiac image, one or more thresholds for segmenting the each cardiac image;
determining one or more sub-images of a region of interest by segmenting, based on the one or more thresholds, the each cardiac image; and
determining, based on the one or more sub-images of the region of interest, a quality index for the each cardiac image.

### Claim 26

A system for evaluating image quality, comprising:
at least one 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 an image, the image including a plurality of elements, each element of the plurality of elements being a pixel or voxel, each element having a gray level;
determining, based on a maximum gray level of the plurality of elements, one or more thresholds for segmenting the image;
determining one or more sub-images of a region of interest by segmenting, based on the one or more thresholds, the image; and
determining, based on the one or more sub-images of the region of interest, a quality index for the image.

### Claim at position 25

27-31. (canceled)