CN109949243B - Calcification artifact eliminating method and device and computer storage medium - Google Patents
Calcification artifact eliminating method and device and computer storage medium Download PDFInfo
- Publication number
- CN109949243B CN109949243B CN201910214918.9A CN201910214918A CN109949243B CN 109949243 B CN109949243 B CN 109949243B CN 201910214918 A CN201910214918 A CN 201910214918A CN 109949243 B CN109949243 B CN 109949243B
- Authority
- CN
- China
- Prior art keywords
- calcification
- original
- image data
- image
- artifact
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Abstract
The invention discloses a calcification artifact eliminating method, a device and a computer storage medium, wherein the method comprises the following steps: acquiring and processing original blood vessel image data to obtain original calcification image data; fitting the original calcification image data to obtain a gray-scale change curved surface; extracting the original calcification image data according to the gray scale change curve to obtain a calcification center region image; and adjusting according to the calcification center region image to obtain an artifact corrected calcification image. According to the embodiment of the invention, after the primary calcification area of the original image is extracted, the gray scale fitting is carried out on the image data of the primary calcification area to obtain the gray scale change curved surface, the influence of the artifact is eliminated again by using the gray scale change curved surface, and the method for correcting the calcification image by the artifact is obtained, so that the influence effect of the calcification artifact is eliminated better, and the more accurate calcification calculation result is obtained.
Description
Technical Field
The present invention relates to the field of blood vessel image technology, and in particular, to a calcification artifact removing method, device, and computer storage medium.
Background
In the field of modern medical technology, the coronary artery automatic stenosis result calculation technology can rapidly produce the condition result of a patient, which is very helpful for a clinician, and an important problem in automatic stenosis calculation is how to obtain an accurate stenosis degree, namely, how to obtain an accurate vascular calcification degree.
Since the calcified part of the blood vessel is excited by the X-ray to be very bright during the enhancement scan, the surrounding blood vessel tissue is also illuminated very brightly by the bright light, thereby causing calcification artifacts and greatly influencing the judgment of the calcification degree. Generally, a clinician calculates the actual calcification degree by a method such as reducing the judgment result of naked eyes, but the method has large error and is not suitable for automatic judgment by a computer. Therefore, how to better eliminate the influence effect of calcification artifacts and obtain a more accurate calcification calculation result becomes an urgent problem to be solved.
Disclosure of Invention
In order to effectively overcome the above-mentioned defects in the prior art, embodiments of the present invention creatively provide a calcification artifact removing method, a calcification artifact removing apparatus, and a computer storage medium.
One aspect of the present invention provides a calcification artifact removing method, including: acquiring and processing original blood vessel image data to obtain original calcification image data; fitting the original calcification image data to obtain a gray-scale change curved surface; extracting the original calcification image data according to the gray scale change curve to obtain a calcification center region image; and adjusting according to the calcification center region image to obtain an artifact corrected calcification image.
In an embodiment, the processing the raw blood vessel image data to obtain raw calcification image data includes: performing primary segmentation on the original blood vessel image data to obtain an original calcified area; performing dot multiplication on the original calcification region and the corresponding original blood vessel image data to obtain original calcification image data, wherein the original blood vessel image data at least comprises one of the following data: a vessel straightened image or a vessel short axis CT image.
In an embodiment, the fitting the raw calcification image data to obtain a gray-scale variation curve includes: and performing two-dimensional Gaussian surface fitting on the original calcification image data by taking the gray level as the marking variance to obtain a two-dimensional gray level change curved surface.
In an embodiment, the extracting the original calcification image data according to the gray scale variation curve to obtain a calcification center region image includes: determining the number of gray pixels according to the two-dimensional gray change curved surface; determining a gray threshold corresponding to the original calcification image data according to the number of gray pixels; and extracting the original calcification image data according to the gray threshold value to obtain a calcification center region image.
In an embodiment, the determining the number of gray pixels according to the two-dimensional gray-scale variation surface includes: searching a maximum change rate point and a central point of the two-dimensional gray scale change curved surface; calculating the area of a circle by taking the distance from the maximum change rate point to the central point as a radius; determining the circle area as a number of gray scale pixels.
In an embodiment, the determining the gray level threshold corresponding to the raw calcification image data according to the gray level pixel number includes: acquiring the gray level sequence of the original calcification image data; and determining the gray level sequence value of the gray level pixel quantity in the corresponding original calcification image data as a gray level threshold value.
In an embodiment, the adjusting according to the calcification center region image to obtain an artifact-corrected calcification image includes: searching a continuous region and a discontinuous region in the calcification center region image; judging whether the ratio of the area of the discontinuous region to the area of the continuous region exceeds a set threshold value or not; if not, determining the calcification center region image without the discontinuous region as an artifact correction calcification image; and if so, determining the image obtained by expanding the set pixels in the direction of the discontinuous region from the continuous region as an artifact-corrected calcification image.
Another aspect of the present invention provides a calcification artifact eliminating apparatus, including: the original image processing module is used for acquiring and processing original blood vessel image data to obtain original calcification image data; the image fitting module is used for fitting the original calcification image data to obtain a gray level change curved surface; and the calcification center extraction module is used for extracting the original calcification image data according to the gray scale change curve to obtain a calcification center region image. And the calcification adjusting module is used for adjusting according to the calcification center region image to obtain an artifact correction calcification image.
In one embodiment, the raw image processing module comprises: the image segmentation unit is used for carrying out primary segmentation on the original blood vessel image data to obtain an original calcified area; an image dot multiplication unit, configured to perform dot multiplication on the original calcified region and the corresponding original blood vessel image data to obtain original calcified image data, where the original blood vessel image data at least includes one of the following data: a vessel straightened image or a vessel short axis CT image.
In one embodiment, the image fitting module comprises: and the Gaussian fitting unit is used for performing two-dimensional Gaussian surface fitting on the original calcification image data by taking the gray level as the marking variance to obtain a two-dimensional gray level change curved surface.
Another aspect of the invention provides a computer-readable storage medium comprising a set of computer-executable instructions which, when executed, perform the calcification artifact removal method of any of the above.
The invention provides a calcification artifact eliminating method for solving the problem that the error is larger when the actual calcification degree is calculated because the influence of calcification artifacts is eliminated by reduction in the traditional method. Firstly, obtaining original calcification image data by obtaining and processing original blood vessel image data, thus preliminarily extracting rough region image data of a calcification image, then performing fitting processing on the extracted original calcification image data to obtain a gray scale change curved surface, wherein the gray scale change curved surface can intuitively display gray scale change gradient between each pixel point in the original calcification image, and is convenient to extract the original calcification image data according to the gray scale change curved surface so as to obtain a calcification center region image, wherein the calcification center region image is extracted according to a set range on the gray scale change curved surface, therefore, an artifact part in the original calcification image data can be separated according to gray scale characteristics of calcification and the artifact part, so that a more accurate calcification region is obtained, and finally, adjustment is performed according to the calcification center region image, and analyzing and optimizing the obtained data again to obtain an artifact correction calcification image. According to the embodiment of the invention, after the primary calcification area of the original image is extracted, the gray scale fitting is carried out on the image data of the primary calcification area to obtain the gray scale change curved surface, the influence of the artifact is eliminated again by using the gray scale change curved surface, and the method for correcting the calcification image by the artifact is obtained, so that the influence effect of the calcification artifact is eliminated better, and the more accurate calcification calculation result is obtained.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
in the drawings, the same or corresponding reference numerals indicate the same or corresponding parts.
Fig. 1 is a schematic flow chart illustrating an implementation of a calcification artifact removing method according to an embodiment of the present invention;
fig. 2 is a schematic flowchart of a calcification artifact eliminating method according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a calcification artifact removing apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic flow chart illustrating an implementation of a calcification artifact removing method according to an embodiment of the present invention; fig. 2 is a schematic flowchart of a calcification artifact eliminating method according to an embodiment of the present invention; please refer to fig. 1 and fig. 2.
One aspect of the present invention provides a calcification artifact removing method, including:
102, fitting the original calcification image data to obtain a gray-scale change curved surface;
103, extracting original calcification image data according to the gray scale change curve to obtain a calcification center region image;
and 104, adjusting according to the calcification center area image to obtain an artifact corrected calcification image.
The invention provides a calcification artifact eliminating method for solving the problem that the error is larger when the actual calcification degree is calculated because the influence of calcification artifacts is eliminated by reduction in the traditional method. Firstly, obtaining and processing original blood vessel image data through step 101 to obtain original calcification image data, thus rough region image data of a calcification image is preliminarily extracted, then performing fitting processing on the extracted original calcification image data through step 102 to obtain a gray scale change curved surface, wherein the gray scale change curved surface can intuitively display gray scale change gradient between each pixel point in the original calcification image, and is convenient for extracting the original calcification image data according to the gray scale change curved surface through step 103 to obtain a calcification center region image, wherein the calcification center region image is extracted according to a set range on the gray scale change curved surface, therefore, an artifact part in the original calcification image data can be separated according to the gray scale characteristics of calcification and the artifact part, so that a more accurate calcification region is obtained, and finally, adjusting is performed according to the calcification center region image through step 104, and analyzing and optimizing the obtained data again to obtain an artifact correction calcification image. According to the embodiment of the invention, after the primary calcification area of the original image is extracted, the gray scale fitting is carried out on the image data of the primary calcification area to obtain the gray scale change curved surface, the influence of the artifact is eliminated again by using the gray scale change curved surface, and the method for correcting the calcification image by the artifact is obtained, so that the influence effect of the calcification artifact is eliminated better, and the more accurate calcification calculation result is obtained.
In one embodiment, processing the raw blood vessel image data to obtain raw calcification image data includes:
performing primary segmentation on original blood vessel image data to obtain an original calcified area;
performing dot multiplication on the original calcification area and the corresponding original blood vessel image data to obtain original calcification image data, wherein the original blood vessel image data at least comprises one of the following data: a vessel straightened image or a vessel short axis CT image.
According to the embodiment of the invention, the original calcification region with the partial calcification artifact region is obtained by performing primary segmentation on the original blood vessel image data, and then the original calcification region and the corresponding original blood vessel image data are subjected to dot multiplication to obtain the original calcification image data capable of displaying the calcification artifact image data in the original calcification region. Therefore, the method is favorable for carrying out deep processing on the original calcification image data with the calcification artifact part, and obtaining a more accurate calcification calculation result for eliminating the influence effect of the calcification artifact.
In an embodiment, the fitting the raw calcification image data to obtain the gray-scale variation curve includes:
and (4) performing two-dimensional Gaussian surface fitting on the original calcification image data by taking the gray level as the marking variance to obtain a two-dimensional gray level change curved surface.
As shown in fig. 2, in the embodiment of the present invention, a two-dimensional gaussian function surface fitting is performed on original calcification image data by setting a gray level as an annotation variance, wherein a minimum difference of the original calcification image data is a height of a gaussian function, and an obtained two-dimensional gray level change surface can display a gray level change gradient between pixel points in the original calcification image, so that a calcification artifact can be found according to the two-dimensional gray level change surface, the influence of the calcification artifact is further eliminated, and the accuracy of a calcification calculation result is improved. Before the fitting process, the embodiment of the invention can perform an image morphology operation on the original calcification image data: and expanding, and then performing two-dimensional Gaussian function fitting on the expanded original calcification image data, so that the fitted two-dimensional gray scale change curved surface can express more obvious gray scale gradient change difference, and the extraction precision of actual calcification region data is improved.
In an embodiment, extracting the raw calcification image data according to the gray scale variation curve, and obtaining the calcification center region image includes:
determining the number of gray pixels according to the two-dimensional gray change curved surface;
determining a gray threshold corresponding to the original calcification image data according to the number of gray pixels;
and extracting the original calcification image data according to the gray threshold value to obtain a calcification center region image.
The number of gray-scale pixels is determined according to the two-dimensional gray-scale change curved surface, wherein the number of gray-scale pixels is used for determining the number of actual calcified pixels needing to be reserved in the original calcified image data, specifically, a gray-scale threshold corresponding to the number of actual calcified pixels in the original calcified image data can be determined according to the number of gray-scale pixels, and then the original calcified image data is extracted according to the gray-scale threshold to obtain a calcified central region image corresponding to the number of actual calcified pixels. Therefore, the number of gray pixels and the gray threshold value are determined through the two-dimensional gray change curved surface, so that the actual calcified pixels are accurately extracted, the image of the calcified central area is obtained, and the extraction precision of the actual calcified area and the accuracy of a calcified settlement result can be improved.
In one embodiment, determining the number of gray pixels from the two-dimensional gray-scale variation surface includes:
searching a maximum change rate point and a central point of the two-dimensional gray scale change curved surface;
calculating the area of the circle by taking the distance from the maximum change rate point to the central point as a radius;
the circle area is determined as the number of gray pixels.
As shown in fig. 2, in the embodiment of the present invention, by searching for the point with the maximum gradient change rate on the two-dimensional gaussian surface, since the gray gradient change between the calcification pixel point and the artifact pixel point is theoretically the maximum point, the point with the maximum change rate is the boundary point between the actual calcification region and the artifact region. And then, the distance from the point to the center of the Gaussian curve is used as a radius to calculate, and the obtained circle area comprises all pixel points representing the actual calcified area, so that the circle area is determined as the number of gray pixels, all the pixel numbers corresponding to the actual calcified area can be extracted, and the accuracy and the reliability of calculating the actual calcified area are greatly improved.
In one embodiment, determining the threshold gray level corresponding to the raw calcification image data based on the number of gray level pixels includes:
obtaining gray level sequencing of original calcification image data;
and determining the gray level sorting value of the gray level pixel quantity in the corresponding original calcification image data as a gray level threshold value.
As shown in fig. 2, after the number of gray pixels is obtained, the gray ranking value of the number of gray pixels in the corresponding original calcification image data is obtained and queried, where the gray ranking value is the boundary gray ranking value between the actual calcification pixel and the artifact pixel in the original calcification image data, and the gray ranking value is determined as the gray threshold, that is, the gray threshold can perform relatively accurate extraction on the original calcification image data to obtain a relatively accurate calcification center region image.
In an embodiment, the adjusting according to the calcification center region image to obtain the artifact-corrected calcification image includes:
searching a continuous area and a discontinuous area in the calcification center area image;
judging whether the ratio of the area of the discontinuous area to the area of the continuous area exceeds a set threshold value or not;
if not, determining the calcification center region image without the discontinuous region as an artifact correction calcification image;
if the difference exceeds the threshold value, the image obtained by expanding the continuous region by the set pixels in the direction of the discontinuous region is determined as the artifact-corrected calcification image.
In the embodiment of the present invention, since the calcified region center image is extracted from the original blood vessel image data according to the gray threshold, and the gray threshold is likely to have some discontinuous regions with relatively small areas in the original blood vessel image data, and the actual calcified region is theoretically a continuous region with relatively large area, the calcified region center image obtained by extraction may need to be adjusted again. As shown in fig. 2, it can be specifically determined by first searching the continuous region and the discontinuous region in the calcification center region image, and determining whether the ratio of the area of the discontinuous region to the area of the continuous region exceeds a set threshold, and if not, it indicates that the influence of ignoring the discontinuous region is small, so that the calcification center region image without the discontinuous region can be determined as the artifact-corrected calcification image. If the number of the set pixels exceeds the set threshold, the influence of the discontinuous region needs to be considered, and then the image after expanding the set pixels towards the discontinuous region is determined as an artifact-corrected calcified image on the basis of the continuous region with a larger area, wherein the number of the set pixels can be the number of the pixels of the discontinuous region. Partial pixels are expanded or abandoned through the step of carrying out secondary adjustment on the center image of the calcified area, and the extraction precision of actual calcified pixels is favorably further improved, so that the influence effect of calcified artifacts is better eliminated, and a more accurate calcified calculation result is obtained.
Fig. 3 is a schematic structural diagram of a calcification artifact removing apparatus according to an embodiment of the present invention, please refer to fig. 3.
Another aspect of the present invention provides a calcification artifact eliminating apparatus, including:
an original image processing module 201, configured to acquire and process original blood vessel image data to obtain original calcification image data;
the image fitting module 202 is configured to perform fitting processing on the original calcification image data to obtain a gray level change curved surface;
and the calcification center extracting module 203 is configured to extract the original calcification image data according to the gray scale change curve to obtain a calcification center region image.
And the calcification adjusting module 204 is configured to adjust according to the calcification center region image to obtain an artifact-corrected calcification image.
The invention provides calcification artifact eliminating equipment for overcoming the problem that the error is larger when the actual calcification degree is calculated because the influence of calcification artifacts is eliminated by reduction in the traditional method. Firstly, the original blood vessel image data is obtained and processed by the original image processing module 201 to obtain the original calcification image data, so that the rough area image data of the calcification image is preliminarily extracted, then the extracted original calcification image data is fitted by the image fitting module 202 to obtain the gray scale change curved surface, wherein the gray scale change curved surface can visually display the gray scale change gradient between each pixel point in the original calcification image, the original calcification image data is extracted by the calcification center extracting module 203 according to the gray scale change curved surface to obtain the calcification center area image, wherein the calcification center area image is extracted according to the set range on the gray scale change curved surface, so that the artifact parts in the original calcification image data can be separated according to the gray scale characteristics of the calcification and artifact parts, therefore, a relatively accurate calcified area is obtained, adjustment is finally performed through the calcified adjustment module 204 according to the calcified central area image, analysis and optimization are performed on obtained data again, and an artifact corrected calcified image is obtained. According to the embodiment of the invention, after the primary calcification area of the original image is extracted, the gray scale fitting is carried out on the image data of the primary calcification area to obtain the gray scale change curved surface, the influence of the artifact is eliminated again by using the gray scale change curved surface, and the method for correcting the calcification image by the artifact is obtained, so that the influence effect of the calcification artifact is eliminated better, and the more accurate calcification calculation result is obtained.
In one embodiment, the raw image processing module 201 includes:
the image segmentation unit is used for carrying out primary segmentation on the original blood vessel image data to obtain an original calcified area;
the image dot multiplication unit is used for performing dot multiplication on the original calcification area and the corresponding original blood vessel image data to obtain original calcification image data, wherein the original blood vessel image data at least comprises one of the following data: a vessel straightened image or a vessel short axis CT image.
According to the embodiment of the invention, the original blood vessel image data is subjected to primary segmentation through the image segmentation unit to obtain the original calcification area with a partial calcification artifact area, and then the original calcification area and the corresponding original blood vessel image data are subjected to dot multiplication through the image dot multiplication unit to obtain the original calcification image data capable of displaying the calcification artifact image data in the original calcification area. Therefore, the method is favorable for carrying out deep processing on the original calcification image data with the calcification artifact part, and obtaining a more accurate calcification calculation result for eliminating the influence effect of the calcification artifact.
In one possible embodiment, the image fitting module 202 includes:
and the Gaussian fitting unit is used for performing two-dimensional Gaussian surface fitting on the original calcification image data by taking the gray level as the marking variance to obtain a two-dimensional gray level change surface.
According to the embodiment of the invention, the gray scale is set as the marking variance through the Gaussian fitting unit to perform two-dimensional Gaussian function surface fitting on the original calcification image data, wherein the minimum difference of the original calcification image data is the height of the Gaussian function, and the obtained two-dimensional gray scale change surface can display the gray scale change gradient between pixel points in the original calcification image, so that calcification artifacts can be found according to the two-dimensional gray scale change surface, the influence of the calcification artifacts is further eliminated, and the accuracy of calcification calculation results is improved. Before the fitting process, the embodiment of the invention can perform an image morphology operation on the original calcification image data: and expanding, and then performing two-dimensional Gaussian function fitting on the expanded original calcification image data, so that the fitted two-dimensional gray scale change curved surface can express more obvious gray scale gradient change difference, and the extraction precision of actual calcification region data is improved.
In another aspect, the present invention provides a computer-readable storage medium comprising a set of computer-executable instructions which, when executed, perform the calcification artifact removal method of any one of the above.
The invention aims to overcome the problem that the influence of calcification artifacts is eliminated by reduction in the traditional method, so that the error is large when the actual calcification degree is calculated, and particularly provides a computer-readable storage medium which comprises a set of computer executable instructions and is used for executing the following calcification artifact elimination method when the instructions are executed: firstly, obtaining original calcification image data by obtaining and processing original blood vessel image data, thus preliminarily extracting rough region image data of a calcification image, then performing fitting processing on the extracted original calcification image data to obtain a gray scale change curved surface, wherein the gray scale change curved surface can intuitively display gray scale change gradient between each pixel point in the original calcification image, and is convenient to extract the original calcification image data according to the gray scale change curved surface so as to obtain a calcification center region image, wherein the calcification center region image is extracted according to a set range on the gray scale change curved surface, therefore, an artifact part in the original calcification image data can be separated according to gray scale characteristics of calcification and the artifact part, so that a more accurate calcification region is obtained, and finally, adjustment is performed according to the calcification center region image, and analyzing and optimizing the obtained data again to obtain an artifact correction calcification image. According to the embodiment of the invention, after the primary calcification area of the original image is extracted, the gray scale fitting is carried out on the image data of the primary calcification area to obtain the gray scale change curved surface, the influence of the artifact is eliminated again by using the gray scale change curved surface, and the method for correcting the calcification image by the artifact is obtained, so that the influence effect of the calcification artifact is eliminated better, and the more accurate calcification calculation result is obtained.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means two or more unless specifically defined otherwise.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (6)
1. A calcification artifact removal method, comprising:
acquiring and processing original blood vessel image data to obtain original calcification image data;
fitting the original calcification image data to obtain a gray-scale change curved surface;
extracting the original calcification image data according to the gray scale change curve to obtain a calcification center region image;
adjusting according to the calcification center region image to obtain an artifact corrected calcification image;
wherein, the fitting processing of the original calcification image data to obtain a gray scale change curved surface comprises:
performing two-dimensional Gaussian surface fitting on the original calcification image data by taking the gray level as an annotation variance to obtain a two-dimensional gray level change curved surface;
correspondingly, the extracting the original calcification image data according to the gray scale change curve to obtain a calcification center region image includes:
searching a maximum change rate point and a central point of the two-dimensional gray scale change curved surface;
calculating the area of a circle by taking the distance from the maximum change rate point to the central point as a radius;
determining the circle area as the number of gray pixels;
acquiring the gray level sequence of the original calcification image data;
determining the gray level sequence value of the gray level pixel quantity in the corresponding original calcification image data as a gray level threshold value;
and extracting the original calcification image data according to the gray threshold value to obtain a calcification center region image.
2. The method of claim 1, wherein processing the raw blood vessel image data to obtain raw calcification image data comprises:
performing primary segmentation on the original blood vessel image data to obtain an original calcified area;
performing dot multiplication on the original calcification region and the corresponding original blood vessel image data to obtain original calcification image data, wherein the original blood vessel image data at least comprises one of the following data: a vessel straightened image or a vessel short axis CT image.
3. The method of claim 1, wherein said adjusting from said calcification center region image resulting in an artifact-corrected calcification image comprises:
searching a continuous region and a discontinuous region in the calcification center region image;
judging whether the ratio of the area of the discontinuous region to the area of the continuous region exceeds a set threshold value or not;
if not, determining the calcification center region image without the discontinuous region as an artifact correction calcification image;
and if so, determining the image obtained by expanding the set pixels in the direction of the discontinuous region from the continuous region as an artifact-corrected calcification image.
4. A calcification artifact removal apparatus, comprising:
the original image processing module is used for acquiring and processing original blood vessel image data to obtain original calcification image data;
the image fitting module is used for fitting the original calcification image data to obtain a gray level change curved surface;
the calcification center extracting module is used for extracting the original calcification image data according to the gray scale change curve to obtain a calcification center region image;
the calcification adjusting module is used for adjusting according to the calcification center region image to obtain an artifact correction calcification image;
wherein the image fitting module comprises:
the Gaussian fitting unit is used for performing two-dimensional Gaussian surface fitting on the original calcification image data by taking the gray level as the marking variance to obtain a two-dimensional gray level change surface;
correspondingly, the calcification center extracting module extracts the original calcification image data according to the gray scale change curve, and obtaining a calcification center region image includes:
searching a maximum change rate point and a central point of the two-dimensional gray scale change curved surface;
calculating the area of a circle by taking the distance from the maximum change rate point to the central point as a radius;
determining the circle area as the number of gray pixels;
acquiring the gray level sequence of the original calcification image data;
determining the gray level sequence value of the gray level pixel quantity in the corresponding original calcification image data as a gray level threshold value;
and extracting the original calcification image data according to the gray threshold value to obtain a calcification center region image.
5. The apparatus of claim 4, wherein the raw image processing module comprises:
the image segmentation unit is used for carrying out primary segmentation on the original blood vessel image data to obtain an original calcified area;
an image dot multiplication unit, configured to perform dot multiplication on the original calcified region and the corresponding original blood vessel image data to obtain original calcified image data, where the original blood vessel image data at least includes one of the following data: a vessel straightened image or a vessel short axis CT image.
6. A computer-readable storage medium comprising a set of computer-executable instructions which, when executed, perform the calcification artifact removal method of any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910214918.9A CN109949243B (en) | 2019-03-20 | 2019-03-20 | Calcification artifact eliminating method and device and computer storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910214918.9A CN109949243B (en) | 2019-03-20 | 2019-03-20 | Calcification artifact eliminating method and device and computer storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109949243A CN109949243A (en) | 2019-06-28 |
| CN109949243B true CN109949243B (en) | 2021-05-11 |
Family
ID=67010410
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910214918.9A Active CN109949243B (en) | 2019-03-20 | 2019-03-20 | Calcification artifact eliminating method and device and computer storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109949243B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113034491B (en) * | 2021-04-16 | 2021-10-08 | 北京安德医智科技有限公司 | Coronary calcified plaque detection method and device |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105118030A (en) * | 2015-08-11 | 2015-12-02 | 上海联影医疗科技有限公司 | Medical image metal artifact correction method and device |
-
2019
- 2019-03-20 CN CN201910214918.9A patent/CN109949243B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105118030A (en) * | 2015-08-11 | 2015-12-02 | 上海联影医疗科技有限公司 | Medical image metal artifact correction method and device |
Non-Patent Citations (2)
| Title |
|---|
| CT影像中主动脉血管钙化的分割与重建;国凯;《中国优秀硕士学位论文全文数据库信息科技辑》;20131215;正文第5页第1段-第35页第4段，附图2.1-3.14 * |
| 采用高斯拟合的全局阈值算法阈值优化框架;陈海鹏;《计算机研究与发展》;20160430;第895页左栏第1段-第900页右栏第1段，图1-10 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109949243A (en) | 2019-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109829942B (en) | Automatic quantification method for retinal vessel diameter of fundus image | |
| CN107180421B (en) | Fundus image lesion detection method and device | |
| US9679375B2 (en) | Ovarian follicle segmentation in ultrasound images | |
| CN108186051B (en) | Image processing method and system for automatically measuring double-apical-diameter length of fetus from ultrasonic image | |
| US10176614B2 (en) | Image processing device, image processing method, and program | |
| US20240074658A1 (en) | Method and system for measuring lesion features of hypertensive retinopathy | |
| US9974442B2 (en) | Method of, and apparatus for, processing volumetric image data | |
| CN108378869B (en) | Image processing method and processing system for automatically measuring head circumference length of fetus from ultrasonic image | |
| US11810293B2 (en) | Information processing device, information processing method, and computer program | |
| CN109273074B (en) | Network model adjusting method and equipment for medical image | |
| CN111105427B (en) | Lung image segmentation method and system based on connected region analysis | |
| CN109949243B (en) | Calcification artifact eliminating method and device and computer storage medium | |
| CN109948622B (en) | Method and device for detecting head and neck body aneurysm and computer readable storage medium | |
| CN113012127A (en) | Cardiothoracic ratio measuring method based on chest medical image | |
| CN106204548B (en) | Image distinguishing method and device | |
| CN106875410B (en) | Automatic image contour extraction method and system | |
| CN105225234A (en) | Based on the lung tumor identification method of support vector machine MRI Iamge Segmentation | |
| CN114387219A (en) | Method, device, medium and equipment for detecting arteriovenous cross compression characteristics of eyeground | |
| CN111462067B (en) | Image segmentation method and device | |
| CN110349203B (en) | Ultrasonic equipment and method for measuring blood vessel diameter in ultrasonic image thereof | |
| US20220245806A1 (en) | Method for learning threshold value | |
| CN108090900B (en) | Automatic bifurcated blood vessel identification method based on IVOCT image | |
| CN109447956B (en) | Method and system for calculating relative width of blood vessel | |
| KR102000615B1 (en) | A method for automatically extracting a starting point of coronary arteries, and an apparatus thereof | |
| CN112365489A (en) | Ultrasonic image blood vessel bifurcation detection method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100102 No. 501 No. 12, 5th floor, No. 6, Wangjing Dongyuan District 4, Chaoyang District, Beijing Patentee after: Shukun (Beijing) Network Technology Co.,Ltd. Address before: 100102 No. 501 No. 12, 5th floor, No. 6, Wangjing Dongyuan District 4, Chaoyang District, Beijing Patentee before: SHUKUN (BEIJING) NETWORK TECHNOLOGY Co.,Ltd. |
|
| CP01 | Change in the name or title of a patent holder | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230113 Address after: Room 307, Zone A, Floor 2, No. 420, Fenglin Road, Xuhui District, Shanghai, 200000 Patentee after: Shukun (Shanghai) Medical Technology Co.,Ltd. Address before: 100102 No. 501 No. 12, 5th floor, No. 6, Wangjing Dongyuan District 4, Chaoyang District, Beijing Patentee before: Shukun (Beijing) Network Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right |