CN109801277B

CN109801277B - Image processing method and device and storage medium

Info

Publication number: CN109801277B
Application number: CN201910047390.0A
Authority: CN
Inventors: 高琪
Original assignee: Zhejiang University ZJU
Current assignee: HANGZHOU SHENGSHI TECHNOLOGY Co.,Ltd.
Priority date: 2019-01-18
Filing date: 2019-01-18
Publication date: 2021-04-20
Anticipated expiration: 2039-01-18
Also published as: CN109801277A

Abstract

The embodiment of the invention discloses an image processing method, an image processing device and a storage medium, wherein the image processing method comprises the following steps: when the initial coronary artery three-dimensional image is obtained, carrying out aorta identification in the initial coronary artery three-dimensional image based on the aorta form to obtain aorta position information; determining an aorta connected domain three-dimensional image from the initial coronary artery three-dimensional image based on the aorta position information; based on the aorta position information and the aorta physiological structure, performing cardiac sinus identification in the aorta connected domain three-dimensional image to obtain the boundary position information of the aorta and the left ventricle; and (4) carrying out coronary artery regrowth based on the boundary position information of the aorta and the left ventricle to obtain a coronary artery three-dimensional image.

Description

Image processing method and device and storage medium

Technical Field

The present invention relates to image processing technologies in the field of computers, and in particular, to an image processing method and apparatus, and a storage medium.

Background

Coronary artery is a blood vessel branch for supplying blood to heart, and focus of coronary artery can generate functional influence on corresponding heart region, and is the reason of causing heart diseases such as coronary heart disease, angina pectoris, myocardial infarction, etc.; therefore, by performing CTA (Computed Tomography angiography) on coronary arteries, doctors can know exactly the position and degree of stenosis and occlusion of cardiac vessels of patients, and can provide great help for diagnosis of heart diseases, such as MSCT (multi-slice helical Computed Tomography). However, since the biomedical image itself has many inevitable defects, in order to improve the readability of the biomedical image, the biomedical image needs to be processed by a computer to obtain a processed biomedical image, so that the diagnosis of a disease is performed based on the processed biomedical image. Therefore, the CTA image of the coronary artery should be processed by a computer before being used as a basis for diagnosing heart diseases.

Currently, computer processing for CTA images of coronary arteries mainly extracts coronary arteries from CTA images of coronary arteries. In the prior art, the extraction of coronary arteries is usually realized by clustering a CTA image of the coronary arteries or manually selecting seed points for coronary artery growth to perform region growth, but both the clustering and region growth processes need manual intervention, so the intelligence for extracting the coronary arteries is low; in addition, the CTA image of the coronary artery may also adopt a Frangi algorithm to extract the coronary artery, however, the stenosis portion in the extracted result image is not obvious, and thus, the effect of extracting the coronary artery is poor.

Disclosure of Invention

In order to solve the above technical problems, embodiments of the present invention are to provide an image processing method, an image processing apparatus, and a storage medium, which can improve the intelligence of coronary artery acquisition and improve the effect of coronary artery acquisition.

The technical scheme of the invention is realized as follows:

in a first aspect, an embodiment of the present invention provides an image processing method, where the method includes:

when an initial coronary artery three-dimensional image is obtained, carrying out aorta identification in the initial coronary artery three-dimensional image based on the aorta form to obtain aorta position information;

determining an aorta connected domain three-dimensional image from the initial coronary artery three-dimensional image based on the aorta position information;

based on the aorta position information and the aorta physiological structure, performing cardiac sinus recognition in the aorta connected domain three-dimensional image to obtain boundary position information of an aorta and a left ventricle;

and carrying out coronary artery regrowth based on the boundary position information of the aorta and the left ventricle to obtain a coronary artery three-dimensional image.

In the above scheme, before the obtaining of the aorta position information by performing aorta identification in the initial coronary artery three-dimensional image based on the aorta morphology when the initial coronary artery three-dimensional image is obtained, the method further includes:

when at least two coronary artery angiography two-dimensional images are obtained, corresponding image gray scale correction information is respectively obtained from the at least two coronary artery angiography two-dimensional images, and the image gray scale correction information comprises initial gray scale values and format information corresponding to the at least two coronary artery angiography two-dimensional images;

obtaining density values corresponding to the at least two coronary angiography two-dimensional images according to the initial gray value and the format information;

and superposing the at least two coronary angiography two-dimensional images according to the density value and a preset image layer sequence to obtain the initial coronary three-dimensional image.

In the above scheme, the performing aorta identification in the initial coronary artery three-dimensional image based on the aorta morphology to obtain aorta position information includes:

determining a radius threshold from the aorta morphology;

and performing binarization processing on the hierarchical coronary artery three-dimensional image in the initial coronary artery three-dimensional image according to a preset gray value based on the preset image hierarchical sequence, and identifying the aorta in a result image corresponding to the hierarchical coronary artery three-dimensional image subjected to binarization processing according to a preset positioning algorithm and the radius threshold value until the aorta position information is obtained.

In the above solution, the determining a three-dimensional image of the connected domain of aorta from the initial three-dimensional image of coronary arteries based on the aorta position information includes:

obtaining an initial aorta gray value according to the aorta position information;

determining an aorta gray value according to a preset gray value and the initial aorta gray value;

according to the aorta gray value, carrying out binarization processing on the initial coronary artery three-dimensional image to obtain a binarized initial coronary artery three-dimensional image;

and determining an aorta communication region from the binarized initial coronary artery three-dimensional image according to the aorta position information to obtain the aorta communication region three-dimensional image.

In the above scheme, the performing cardiac sinus recognition in the three-dimensional image of the aorta connected domain based on the aorta position information and the aorta physiological structure to obtain the boundary position information between the aorta and the left ventricle includes:

determining a position judgment condition according to the aorta physiological structure, wherein the position judgment condition is used for identifying the cardiac sinus;

and determining a search plane from the aorta position information according to a preset search step length in the aorta connected domain three-dimensional image until the aorta section area corresponding to the search plane meets the position judgment condition, and taking the corresponding search plane as the aorta and left ventricle boundary position information.

In the above solution, the performing coronary artery regrowth based on the aorta and left ventricle boundary position information to obtain a three-dimensional image of a coronary artery includes:

performing regrowth of coronary arteries based on the boundary position information of the aorta and the left ventricle to obtain a coronary artery growth three-dimensional image;

identifying an aorta region on the coronary artery growth three-dimensional image by using a preset algorithm;

and deleting the aorta area from the coronary artery growth three-dimensional image to obtain the coronary artery three-dimensional image.

In the above solution, the performing coronary artery regrowth based on the aorta and left ventricle boundary position information to obtain a three-dimensional image of coronary artery growth includes:

determining a coronary artery growth gray value according to the aorta and left ventricle boundary position information and the aorta position information;

deleting the three-dimensional image of the aorta communication domain from the initial coronary artery three-dimensional image according to the boundary position information of the aorta and the left ventricle to obtain a deleted initial coronary artery three-dimensional image;

and performing coronary artery growth based on the coronary artery growth gray value and the deleted initial coronary artery three-dimensional image to obtain the coronary artery growth three-dimensional image.

In the above solution, the determining a coronary artery growth gray scale value according to the aorta and left ventricle boundary position information and the aorta position information includes:

obtaining a coronary artery communication domain according to the boundary position information of the aorta and the left ventricle;

when the volume corresponding to the coronary artery communication domain is larger than a preset volume, circularly increasing a preset adhesion removing step length on the basis of the aorta gray value corresponding to the aorta position information until the volume corresponding to the coronary artery communication domain is not larger than the preset volume, and taking the gray value after circular increase as the coronary artery growth gray value.

In the above scheme, the performing coronary artery growth based on the coronary artery growth gray value and the deleted initial coronary artery three-dimensional image to obtain the coronary artery growth three-dimensional image includes:

and according to the coronary artery growth gray value and a preset growth step length, performing coronary artery generation on the deleted initial coronary artery three-dimensional image until the coronary artery growth gray value is reduced to a preset minimum growth gray value, finishing coronary artery growth, and obtaining the coronary artery growth three-dimensional image.

In a second aspect, an embodiment of the present invention provides an image processing apparatus, including: a processor, a memory and a communication bus, the memory communicating with the processor through the communication bus, the memory storing a program executable by the processor, the program, when executed, executing the image processing method as described above through the processor.

In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a program is stored, which, when executed by a processor, implements the image processing method as described above.

The embodiment of the invention provides an image processing method and device and a storage medium. Firstly, when an initial coronary artery three-dimensional image is obtained, carrying out aorta identification in the initial coronary artery three-dimensional image based on the aorta morphology to obtain aorta position information; determining an aorta connected domain three-dimensional image from the initial coronary artery three-dimensional image based on the aorta position information; based on the aorta position information and the aorta physiological structure, performing cardiac sinus identification in the aorta connected domain three-dimensional image to obtain the boundary position information of the aorta and the left ventricle; and (4) carrying out coronary artery regrowth based on the boundary position information of the aorta and the left ventricle to obtain a coronary artery three-dimensional image. By adopting the technical scheme, the image processing device accurately identifies the aorta and the coronary artery in the initial coronary artery three-dimensional image according to the morphology structures of the aorta and the physiological structure of the aorta, and automatically grows the coronary artery based on the identified boundary position information of the aorta and the left ventricle, so that the coronary artery three-dimensional image is obtained, the automatic and accurate extraction of the coronary artery is realized, the intelligence of the coronary artery acquisition is improved, and the effect of the coronary artery acquisition is improved.

Drawings

Fig. 1 is a flowchart of an implementation of an image processing method according to an embodiment of the present invention;

FIG. 2 is an exemplary three-dimensional image of the connected domain of the aorta provided by embodiments of the present invention;

FIG. 3 is a diagram illustrating an exemplary search for aortic and left ventricular boundary location information according to an embodiment of the present invention;

FIG. 4 is a schematic diagram illustrating an exemplary determination of a gray-scale value for coronary artery growth provided by an embodiment of the present invention;

FIG. 5 is an exemplary aorta and coronary connectivity domain image provided by embodiments of the invention;

FIG. 6 is a plan view of an exemplary deleted three-dimensional image of an initial coronary artery provided by embodiments of the present invention;

FIG. 7 is an exemplary three-dimensional image of coronary artery growth provided by an embodiment of the present invention;

FIG. 8 is an exemplary three-dimensional image of a coronary artery provided by an embodiment of the present invention;

fig. 9 is a first schematic structural diagram of a speech signal processing apparatus according to an embodiment of the present invention;

fig. 10 is a schematic structural diagram of a speech signal processing apparatus according to an embodiment of the present invention.

Detailed Description

The technical solution 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.

Example one

An embodiment of the present invention provides an image processing method, and fig. 1 is a flowchart illustrating an implementation of the image processing method according to the embodiment of the present invention, where as shown in fig. 1, the image processing method includes:

s101, when the initial coronary artery three-dimensional image is obtained, carrying out aorta identification in the initial coronary artery three-dimensional image based on the aorta shape to obtain aorta position information.

In the embodiment of the invention, the angiography device performs angiography on the coronary artery after the contrast agent is injected, and at least two coronary artery angiography images obtained by angiography are input into the image processing device, and at the moment, the image processing device acquires the at least two coronary artery angiography images; when the image processing device superposes at least two acquired coronary artery contrast images, an initial coronary artery three-dimensional image is obtained. The aorta morphology can be determined based on a priori knowledge: the cross section is circular, and the image processing device determines the position information of the aorta in the initial coronary artery three-dimensional image based on the shape that the cross section of the aorta is circular.

Here, the contrast may be a CT contrast, an X-ray contrast, or another contrast technique, and the embodiment of the present invention is not particularly limited to this. Specifically, when the contrast is CT contrast, the coronary artery contrast image corresponds to a coronary artery CT contrast image.

It should be noted that the initial coronary artery three-dimensional image includes an image corresponding to a portion of a region where the coronary artery is located, for example, a stereo image of a human chest (a region including a heart); generally, the initial coronary artery three-dimensional image is a stereo image, for example, the initial coronary artery three-dimensional image can be represented by a three-dimensional matrix; the aorta position information characterizes the position information of the aorta in the initial coronary artery three-dimensional image.

And S102, determining an aorta connected domain three-dimensional image from the initial coronary artery three-dimensional image based on the aorta position information.

In the embodiment of the present invention, after the image processing apparatus acquires the aorta position information, since the aorta is connected to the coronary artery, after the image processing apparatus acquires the initial coronary artery three-dimensional image, the image processing apparatus determines the connected region where the aorta is located in the initial coronary artery three-dimensional image based on the aorta position information, thereby acquiring the aorta connected region three-dimensional image including the coronary artery.

That is, the three-dimensional image of the connected region of the aorta represents a stereoscopic image made up of the connected region where the aorta is located.

Specifically, after obtaining the aorta position information, the image processing device finds the connected region where the aorta is located according to the aorta position information, and thus obtains the three-dimensional image of the aorta connected region.

It is understood that since the aorta is connected to the coronary arteries, the coronary arteries are included in the three-dimensional image of the aorta connected region.

S103, performing cardiac sinus recognition in the three-dimensional image of the aorta connected domain based on the aorta position information and the aorta physiological structure to obtain the boundary position information of the aorta and the left ventricle.

In the embodiment of the invention, after obtaining the three-dimensional image of the aorta position information and the aorta communication domain, the image processing device searches the boundary position information of the aorta and the left ventricle from the far end to the near end along the aorta position information in the three-dimensional image of the aorta communication domain, in the process, the aorta has a section of thick physiological structure and then thin physiological structure, and after the position of the physiological structure is determined, the boundary position information of the aorta and the left ventricle is determined.

It should be noted that the thick-first and thin-second physiological structure is characterized by a cardiac sinus, which is a convex position on the aorta corresponding to the coronary artery.

It will be appreciated that since the three-dimensional image of the aorta connectivity domain characterizes the connectivity domain in which the aorta lies in the initial coronary image, the aorta is typically in communication with the coronary arteries, left ventricle, etc.; therefore, after the image processing device obtains the boundary position information of the aorta and the left ventricle, the communication domain where the left ventricle communicated with the aorta is located can be removed according to the boundary position information of the aorta and the left ventricle, and convenience is further provided for extracting the coronary artery.

And S104, carrying out coronary artery regrowth based on the boundary position information of the aorta and the left ventricle to obtain a coronary artery three-dimensional image.

In the embodiment of the present invention, since the three-dimensional image of the connected region of the aorta includes not only the communication between the aorta and the coronary artery, but also the communication between the aorta and another part (e.g., the left ventricle), and the communication between the coronary artery and another part (e.g., the auricle), after the image processing apparatus acquires the boundary position information between the aorta and the left ventricle, the coronary artery regrowth processing is performed on the three-dimensional image of the connected region of the aorta according to the boundary position information between the aorta and the left ventricle, the unnecessary connected region (the communication between the aorta and another part, and the communication between the coronary artery and another part) is removed, the extraction of the coronary artery is completed, and the three-dimensional image of the coronary artery is obtained.

Here, the three-dimensional coronary artery image is processed by computer technology and can be used as a basis for medical diagnosis of heart diseases, for example, a three-dimensional coronary artery mesh model.

It can be understood that the image processing device accurately positions the aorta and the coronary artery in the obtained initial coronary artery three-dimensional image through the morphological structure of the aorta, so that the efficient and complete segmentation and reconstruction processing is realized, and the automatic and accurate extraction of the coronary artery in the CT (computed tomography) coronary angiography two-dimensional image is completed.

Further, in the embodiment of the present invention, when at least two coronary angiography two-dimensional images are acquired, the image processing apparatus superimposes the at least two coronary angiography two-dimensional images based on a preset image level sequence to obtain an initial coronary artery three-dimensional image. The method specifically comprises S105-S107, wherein:

and S105, when the at least two coronary artery angiography two-dimensional images are obtained, respectively obtaining corresponding image gray scale correction information from the at least two coronary artery angiography two-dimensional images, wherein the image gray scale correction information comprises initial gray scale values and format information corresponding to the at least two coronary artery angiography two-dimensional images.

In the embodiment of the present invention, when performing a tomographic scan of a coronary artery, at least two coronary artery two-dimensional images can be obtained by injecting a contrast medium intravenously, and when the at least two coronary artery two-dimensional images are introduced into the image processing apparatus, the image processing apparatus acquires the at least two coronary artery two-dimensional images. And the at least two coronary angiography two-dimensional images obtained by the image processing device comprise image gray-scale correction information, and the image gray-scale correction information is used for performing image conversion on the coronary angiography two-dimensional images: converting the coronary angiography two-dimensional image from the first space to a second space so that the image processing device performs extraction processing of the coronary artery in the second space; here, the first space represents an image space corresponding to at least two coronary artery angiography two-dimensional images obtained when the first space representation angiography device performs coronary artery angiography, and the second space representation image processing device represents an image space corresponding to at least two coronary artery angiography two-dimensional images when the second space representation image processing device performs coronary artery extraction on the at least two coronary artery angiography two-dimensional images.

Here, the image gradation correction information includes initial gradation values and format information corresponding to at least two coronary artery contrast two-dimensional images.

It should be noted that the at least two coronary artery contrast two-dimensional images acquired by the image processing device are images in the first space, and the image format corresponding to each coronary artery contrast two-dimensional image at this time is the first image format, for example, a DICOM image, so that the format information corresponding to the at least two coronary artery contrast two-dimensional images represents information corresponding to the first image format, for example, header information of the DICOM image.

In addition, the initial gray values corresponding to the at least two coronary artery angiography two-dimensional images represent the corresponding gray values of the at least two coronary artery angiography two-dimensional images in the first space.

That is, the image processing apparatus reads information corresponding to the first image format and a gradation value corresponding to the first space from the at least two coronary artery contrast two-dimensional images obtained, that is, acquires image gradation correction information.

And S106, obtaining density values corresponding to the at least two coronary artery angiography two-dimensional images according to the initial gray value and the format information.

In the embodiment of the present invention, after obtaining the image gray scale correction information, the image processing apparatus can perform a conversion process from the first space to the second space on at least two coronary angiography two-dimensional images, specifically: and the image processing device obtains the corresponding density values of the at least two coronary angiography two-dimensional images according to the initial gray value and the format information.

It should be noted that the density values represent information, such as CT values, of the at least two coronary angiography two-dimensional images in the second image format corresponding to the second space.

Illustratively, the image processing device obtains a set of CTA images (at least two coronary angiography two-dimensional images) of a human chest containing a heart region, the set of CTA images being DICOM images; firstly, the image processing device acquires a "cache Slope" and a "cache interrupt" (format information) from header file information of each DICOM image, and determines a gray value (initial gray value) of each of at least two coronary angiography two-dimensional images; next, the image processing apparatus determines CT values (density values) corresponding to the at least two coronary angiography two-dimensional images in the second space according to formula (1), where formula (1) is:

HU＝Rescale Slope×I+Rescale Intercept (1)

HU represents a CT value corresponding to each pixel point in at least two coronary angiography two-dimensional images, and I represents an initial gray value.

And S107, superposing at least two coronary artery angiography two-dimensional images according to the density value and the preset image hierarchical sequence to obtain an initial coronary artery three-dimensional image.

In the embodiment of the present invention, after the image processing device obtains the density values corresponding to the at least two coronary angiography two-dimensional images, the CT value corresponding to each part in the region where the coronary artery is located is determined, and the computed tomography apparatus sequentially photographs the parts where the coronary artery is located, so that a fixed image level exists between the obtained at least two coronary angiography two-dimensional images, and therefore, the image processing device performs the overlay processing on the at least two coronary angiography two-dimensional images based on the density values and the preset image level order, and can obtain the initial coronary artery three-dimensional image for extracting the coronary artery.

Here, each pixel point in the initial coronary artery three-dimensional image corresponds to its own CT value, and the subsequent coronary artery extraction is performed based on the CT value.

It should be noted that the pixel points representing the same portion correspondingly exist in at least one coronary angiography two-dimensional image, but in the second space, the density values corresponding to the pixel points of the same portion are the same.

In the embodiment of the present invention, when the initial coronary artery three-dimensional image is a stereo image, for example, the initial coronary artery three-dimensional image can be represented by a three-dimensional matrix, the coronary angiography two-dimensional image is correspondingly a two-dimensional matrix, so that the image processing device sequentially superimposes the coronary angiography two-dimensional images represented by the plurality of two-dimensional matrices into the initial coronary artery three-dimensional image in the form of a three-dimensional matrix according to the preset image levels.

Here, when the image processing apparatus converts the at least two coronary angiography images into the initial coronary artery three-dimensional image according to the density value and the preset image gradation order, the image processing apparatus may construct a three-dimensional image model according to the density value and the preset image gradation order and input the at least two coronary angiography images into the three-dimensional image model, thereby obtaining the initial coronary artery three-dimensional image; or the image processing device stretches and combines the plane structures in the at least two coronary artery angiography images according to the density value and the preset image level sequence to obtain an initial coronary artery three-dimensional image; the embodiment of the present invention is not particularly limited thereto.

Illustratively, a CT apparatus (angiography apparatus) performs tomography on a chest (region including a heart) of a patient after injection of a contrast medium to obtain a set of coronary CTA images (at least two coronary angiography two-dimensional images), wherein each image in the set of coronary CTA images is a two-dimensional matrix, and the image processing device arranges the set of coronary CTA images in a preset image level sequence to form a three-dimensional matrix, i.e., an initial coronary artery three-dimensional image.

It can be understood that the image processing device obtains the initial coronary artery three-dimensional image by processing and overlapping a plurality of coronary artery angiography two-dimensional images, and provides original information for the extraction of subsequent coronary arteries.

Further, in the embodiment of the present invention, in S101, the image processing apparatus performs aorta identification in the initial coronary artery three-dimensional image based on the aorta morphology to obtain aorta position information, which specifically includes: the image processing device determines a radius threshold according to the aorta morphology; and performing binarization processing on the hierarchical coronary artery two-dimensional image in the initial coronary artery three-dimensional image according to a preset gray value based on a preset image hierarchical sequence, and identifying the aorta in a result image corresponding to the binary processing of the hierarchical coronary artery two-dimensional image according to a preset positioning algorithm and a radius threshold value until the aorta position information is obtained.

It should be noted that, in the initial coronary artery three-dimensional image, the cross section of two structures is circular, one of the two structures is the aorta, the other is the inferior artery, and the radius of the inferior artery is significantly smaller than that of the aorta, so that the image processing device determines the minimum threshold value of the radius, i.e. the radius threshold value, for example, 40 pixels, according to the size of the radius of the aorta; based on the radius threshold, the disturbance of the lower artery is thus excluded.

Specifically, the image processing apparatus performs positioning of the aorta based on a preset image hierarchy order: firstly, carrying out binarization processing on a first layer image by using a preset gray value from the first layer image to obtain a binarized first layer image; and determining the cross section of the aorta by using a preset positioning algorithm for positioning the circular structure and the set radius threshold, namely obtaining the position information of the aorta. If the aorta position information is not determined in the first layer image, the image processing device continues the positioning of the aorta in the second layer image, and the specific positioning process is the same as the positioning process of the aorta positioning in the first layer image. Similarly, if no aorta position information is determined in the second image, the image processing device will continue the positioning of the aorta in the third layer image, thus traversing the initial coronary artery three-dimensional image until the position of the aorta is determined; at this time, the aorta position information represents the position information of the aorta on the hierarchical coronary artery two-dimensional image in the initial coronary artery three-dimensional image; for example, the aorta position information is expressed by equation (2):

position_Aorta＝(x₀,y₀,i) (2)

wherein the position_AortaRepresenting aortic position information, (x)₀,y₀And i) represents the aorta center (x)₀,y₀) Position on the ith layer image.

It should be noted that the preset gray-scale value is a gray-scale value preset by the image processing apparatus, and the preset gray-scale value is obtained based on a combination of a large number of theories and experiments, such as: 226. the preset positioning algorithm is used for positioning the circular structure, such as Hough transformation: the Hough transform may determine the likelihood that a geometric shape in the image is a standard figure (e.g., circle, ellipse, line). The first layer image, the second layer image, and the third layer image … are two-dimensional images of the aorta in the initial coronary artery three-dimensional image.

Further, in the embodiment of the present invention, the image processing apparatus in S102 determines the three-dimensional image of the connected domain of the aorta from the initial three-dimensional image of the coronary artery based on the aorta position information, and specifically includes: the image processing device obtains an initial aorta gray value according to the aorta position information; determining an aorta gray value according to a preset gray value and the initial aorta gray value; performing binarization processing on the initial coronary artery three-dimensional image according to the aorta gray value to obtain a binarized initial coronary artery three-dimensional image; and determining an aorta communication region from the initial coronary artery three-dimensional image after binarization according to the aorta position information to obtain an aorta communication region three-dimensional image.

In the embodiment of the invention, after the image processing device obtains the aorta position information, the aorta position information represents the position of the aorta in the two-dimensional image of the coronary artery of a certain level, so that the initial aorta gray value corresponding to the two-dimensional image of the coronary artery of the level can be obtained according to the aorta position information. That is, the initial aorta gray value characterizes the gray value of the aorta in a certain level of the two-dimensional image of the coronary arteries. In addition, the image processing device determines an aorta connected domain three-dimensional image from the initial coronary artery three-dimensional image according to the aorta position information and the initial aorta gray value. That is, after obtaining the aorta position information and the initial aorta gray scale value, the image processing device can search the connected domain where the aorta is located at the aorta position information determined in the initial coronary artery three-dimensional image according to the initial aorta gray scale value, thereby obtaining the aorta connected domain three-dimensional image.

Specifically, after the image processing device obtains the initial aorta gray value, the image processing device performs binarization processing on the initial coronary artery three-dimensional image by using the aorta gray value. Therefore, when the aorta connected domain three-dimensional image is determined, the aorta gray value is required to be obtained according to the initial aorta gray value, the aorta gray value represents the gray value of the aorta in the initial coronary image, at the moment, the image processing device updates the initial aorta gray value by using the preset gray value, and the obtained updated gray value is the aorta gray value.

Exemplarily, the image processing apparatus uses formula (3) to determine the aorta gray scale value according to the preset gray scale value and the initial aorta gray scale value, where formula (3) is:

wherein, gray_newRepresenting the aortic grey value, gray_AortaRepresenting the initial aortic grey value, gray_expRepresenting a preset gray value.

After obtaining the aorta gray value, the image processing device carries out binarization processing on the initial coronary artery by using the aorta gray value, and searches a connected domain of the aorta by using the known aorta position information on the obtained binarized initial coronary artery three-dimensional image. For example, the image processing device traverses all pixel points with a value of 1, which are communicated with the aorta position information, on the initial coronary artery three-dimensional image after binarization by using a region growing method, and marks the pixel points with the communicated value of 1, so that all the marked pixel points with the communicated value of 1 are determined as a communicated domain where the aorta is located.

It should be noted that although the aorta position information is the position of the aorta on the hierarchical coronary artery two-dimensional image, since the hierarchical coronary artery two-dimensional image is the image information in the initial coronary artery three-dimensional image, the aorta position information also corresponds to the position information of the aorta in the initial coronary artery three-dimensional image.

Fig. 2 is an exemplary three-dimensional image of an aorta connected domain according to an embodiment of the present invention, as shown in fig. 2, a circular structural portion is an aorta 10, and in addition, in the three-dimensional image of the aorta connected domain, coronary arteries, left ventricular cavity, left atrial cavity, atrial appendage, pulmonary veins connected to the left atrium, and the like are also included; in addition, according to the difference of the CTA image capturing time, the aorta connected domain three-dimensional image may further include the right ventricle inner cavity, the right atrium inner cavity, and the pulmonary artery connected to the right ventricle.

It can be understood that the three-dimensional image of the aorta connected domain is obtained by determining the connected domain where the aorta is located in the initial three-dimensional image of the coronary arteries. Therefore, when the image processing device extracts the coronary artery from the three-dimensional image of the aorta connected domain, the extraction range of the coronary artery is reduced, and the feasibility of extracting the coronary artery is improved to a certain extent.

Further, in the embodiment of the present invention, in S103, the image processing device performs cardiac sinus identification in the three-dimensional image of the connected domain of the aorta based on the aorta position information and the aorta physiological structure, so as to obtain the boundary position information between the aorta and the left ventricle, which specifically includes: the image processing device determines a position judgment condition according to the physiological structure of the aorta, and the position judgment condition is used for identifying the cardiac sinus; and determining a search plane from the aorta position information according to a preset search step length in the aorta connected domain three-dimensional image until the section area of the aorta corresponding to the search plane meets the position judgment condition, and taking the corresponding search plane as the boundary position information of the aorta and the left ventricle.

Here, the image processing apparatus determines a search plane according to a preset search step at the aorta position information, and specifically includes: taking the aorta position information as a first position, and constructing a first search plane corresponding to the first position; determining a second position according to the first position and a preset search step length; constructing a second search plane corresponding to the second position; determining a third position according to the first position and the second position; and constructing a third search plane corresponding to the third position. And finally, obtaining a cross-sectional image of the aorta according to the first search plane, the second search plane and the third search plane. Here, the first search plane, the second search plane, and the third search plane are the search planes described above.

That is, first, the image processing apparatus constructs a first search plane using the aorta position information as a first position; when the aorta position information is expressed by equation (2), the first search plane is expressed by equation (4):

(y-y₀)+(z-i)＝0 (4)

the three-dimensional image of the connected region of the aorta is a stereo image, when the three-dimensional coordinate (x, y, z) is used for representing, z represents the direction from the far end to the near end, and (x, y) represents the cross section shot by the CT device.

In the first search plane, the image processing apparatus removes the first position_Aorta1Comprises the following steps: position_AortaThe non-connected region, obtaining an image IM only containing the aorta section_Aorta1。

Next, the image processing apparatus determines the second position of the aorta based on a preset search step (e.g., 10 pixels)_Aorta2Comprises the following steps: position_Aorta+ (0,0, step), resulting in a second search plane, as shown in equation (5):

(y-y₀)+[z-(i+step)]＝0 (5)

in the second search plane, the image processing device removes the second position_Aorta2The non-connected region, obtaining an image IM only containing the aorta section_Aorta2。

Then, the image processing device predicts a third position according to the first position and the second position, and specifically determines a direction vector of the aorta according to the first position and the second position

As shown in formula (6):

thus, the image processing apparatus determines the third position_Aorta3Is composed of

Further obtaining a third search plane, as shown in equation (7):

wherein the content of the first and second substances,

is position_Aorta3The corresponding value of y is set to,

is position_Aorta3The corresponding z value.

In the third search plane, the image processing device removes the third position_Aorta3The non-connected region, obtaining an image IM only containing the aorta section_Aorta3。

Finally, by repeating the above search procedure, a series of images { IM ] containing only the aortic cross-section is obtained_Aorta1，IM_Aorta2，IM_Aorta3，…，IM_AortajWhere j denotes the jth aortic cross-section. When the image processing device judges that the cross section area of the series of images only containing the aorta section is increased and then decreased, the image processing device finishes the search of the aorta section and performs IM_AortajThe corresponding position information is used as the aorta and left ventricle boundary position information.

In the embodiment of the present invention, the position determination condition under which the image processing apparatus determines the boundary position information of the aorta and the left ventricle is: area of most recent aortic cross-section S (IM)_Aortaj+1) First greater than the area S (IM) of the aorta section of the previous time_Aortaj) Characterizing the search location as reaching above the cardiac sinus; then, the area S (IM) of the most recent aortic cross section_Aortak+1) Smaller than the area S (IM) of the aorta section from the previous time_Aortak) The search location is characterized as reaching below the cardiac sinus.

Preferably, the position determination condition is: s (IM)_Aortaj+1)>α×S(IM_Aortaj) And S (IM)_Aortak+1)<β×S(IM_Aortak) Wherein α is greater than 1, e.g., 1.01; beta is less than 1, e.g., 0.99. Therefore, the influence of image noise is reduced, and the judgment precision is improved.

In addition, in the embodiment of the present invention, when the obtained aortic cross section satisfies the above determination condition, two more searches are performed, and the corresponding position at this time is used as the boundary position information between the aorta and the left ventricle.

Fig. 3 is a schematic diagram of an exemplary method for searching information of a boundary between an aorta and a left ventricle according to an embodiment of the present invention. As shown in fig. 3, 1 to i represent a first search plane to an ith search plane, where the position corresponding to the ith search plane is the aorta and left ventricle boundary position information.

It will be appreciated that since the aorta is connected to the left ventricle, the removal of the left ventricle from the aorta-connected image is conditioned by determining the aorta-left ventricle boundary location information.

Further, in the embodiment of the present invention, in S104, the image processing apparatus performs coronary artery regrowth based on the information of the boundary position between the aorta and the left ventricle, so as to obtain a three-dimensional image of a coronary artery, which specifically includes S104a-S104c, where:

s104a, performing coronary artery regrowth based on the boundary position information of the aorta and the left ventricle to obtain a coronary artery growth three-dimensional image.

In the embodiment of the invention, after the image processing device obtains the boundary position information of the aorta and the left ventricle, the image processing device performs the regrowth of the coronary artery based on the boundary position information of the aorta and the left ventricle, and then obtains the three-dimensional image of the coronary artery growth.

Here, the three-dimensional image of coronary artery growth represents a three-dimensional image including an aorta and a coronary artery.

Further, in the embodiment of the present invention, the image processing apparatus in S104a performs coronary artery regrowth based on the boundary position information of the aorta and the left ventricle to obtain a three-dimensional image of coronary artery growth, which specifically includes S104a1-S104a3, where:

and S104a1, determining a coronary artery growth gray value according to the aorta and left ventricle boundary position information and the aorta position information.

In the embodiment of the invention, after the boundary position information of the aorta and the left ventricle is determined, the image processing device divides the three-dimensional image of the aorta communication domain into two parts: a connected domain where coronary arteries are located and a connected domain where ventricles are located; and the image processing device judges whether the coronary artery is adhered to the auricle in the communication domain where the coronary artery is located, and when the coronary artery is determined to be adhered to the auricle, the image processing device performs increasing processing on the aorta gray value corresponding to the aorta position information according to a preset adhesion removing step length until the coronary artery is not adhered to the auricle, and the corresponding gray value at the moment is used as the coronary artery growth gray value.

In addition, the image processing apparatus determines that the coronary artery is in the connected region and the coronary artery is not adhered to the atrial appendage, and then sets the aorta gray level value as the coronary artery growth gray level value.

Furthermore, the image processing device determines the coronary artery growth gray value according to the aorta and left ventricle boundary position information and the aorta position information, and specifically includes: the image processing device obtains a coronary artery communication domain according to the boundary position information of the aorta and the left ventricle; and when the volume corresponding to the coronary artery communication domain is larger than the preset volume, circularly increasing the preset adhesion removing step length on the basis of the aorta gray value corresponding to the aorta position information until the volume corresponding to the coronary artery communication domain is not larger than the preset volume, and taking the gray value after circular increase as the coronary artery growth gray value. Here, the coronary artery communication domain refers to a communication domain in which a coronary artery is located.

It should be noted that the aorta gray value corresponding to the aorta position information means that the image processing device determines the aorta gray value according to the aorta position information, specifically, the image processing device determines the initial aorta gray value according to the aorta position information, and determines the aorta gray value according to the initial aorta gray value and the preset gray value.

That is to say, once the coronary artery and the auricle are adhered, the volume corresponding to the connected domain where the coronary artery is located is larger than the preset volume, and therefore, the image processing device judges whether the coronary artery and the auricle are adhered according to the preset number of connected pixels, for example, the preset number of connected pixels is 1300000, and then, when the number of pixels of the connected domain of the aorta and the coronary artery is larger than 1300000, it is determined that the coronary artery and the auricle are adhered; and when the number of the pixel points of the connected domain of the aorta and the coronary artery is not more than 1300000, determining that the coronary artery is not adhered to the auricle.

Meanwhile, the image processing device continuously increases the preset adhesion removing step length on the basis of the aorta gray value, and judges whether the coronary artery and the auricle are adhered on the increased gray value; if the adhesion exists, continuously increasing a preset adhesion removing step length on the basis of the gray value of the time, and judging whether the coronary artery and the auricle are adhered on the gray value which is increased again; the process is repeated until the coronary artery and the auricle are not adhered any more, and the corresponding improved gray value at the moment is the coronary artery growth gray value.

FIG. 4 is a schematic diagram of an exemplary determination of a coronary artery growth gray scale value according to an embodiment of the present invention, as shown in FIG. 4, a preset adhesion-removing step size_gray120, see the top left diagram in fig. 4: the aorta gray value is 373.5, and the image processing device determines that the coronary artery is adhered to the auricle at this time, so that the gray value is raised by 20, and the upper right-hand graph in fig. 4 is obtained; in the upper right-hand diagram in fig. 4: the corresponding gray value is 393.5, and the image processing device determines that the coronary artery is adhered to the auricle at this time, so that the gray value is raised by 20, and the lower left corner image in fig. 4 is obtained; in the lower left diagram in fig. 4: the corresponding gray value is 413.5, and the image processing device determines that the coronary artery is adhered to the auricle at the moment, so that the gray value is increased by 20, and a lower right corner image in fig. 4 is obtained; in the lower right hand diagram in fig. 4: the corresponding gray value is 433.5 and the image processing means determines that the coronary artery is not stuck to the atrial appendage at this time, thereby determining that the coronary artery growth gray value is 433.5.

In the embodiment of the invention, after obtaining the boundary position information of the aorta and the left ventricle, the image processing device removes the communication domain where the left ventricle is located in the three-dimensional image of the aorta communication domain to obtain the communication domain of the aorta and the coronary artery, and carries out adhesion removal processing on the coronary artery and the auricle in the communication domain of the aorta and the coronary artery to obtain the image of the aorta and the coronary artery communication domain for growing the coronary artery. Fig. 5 is an exemplary aorta and coronary connectivity domain image, as shown in fig. 5, showing the aorta 10 and the coronary arteries 20 in communication, according to an embodiment of the invention.

And S104a2, deleting the three-dimensional image of the aorta connected domain from the initial coronary artery three-dimensional image according to the boundary position information of the aorta and the left ventricle to obtain the deleted initial coronary artery three-dimensional image.

In the embodiment of the present invention, after the image processing apparatus obtains the images of the connected domain of the aorta and the coronary artery, because the gray value corresponding to the images of the connected domain of the aorta and the coronary artery, that is, the gray value of the growth of the coronary artery, is higher, the information amount of the coronary artery included in the images of the connected domain of the aorta and the coronary artery is less; therefore, the image processing device needs to remove the three-dimensional image of the aorta connected domain in the initial coronary artery three-dimensional image according to the boundary position information of the aorta and the left ventricle so as to regrow the coronary artery; here, the three-dimensional image of the connected region of the aorta is removed from the three-dimensional image of the initial coronary artery, and the three-dimensional image of the initial coronary artery after the removal is obtained.

Specifically, the image processing device divides the three-dimensional image of the aorta connected domain into two parts according to the boundary position information of the aorta and the left ventricle: the communication domain where the coronary artery is located and the communication domain where the ventricle is located, so that the image processing device respectively deletes the communication domain where the coronary artery is located and the communication domain where the ventricle is located from the initial coronary artery three-dimensional image; the image processing device expands the connected domain where the ventricle is located according to a preset degree, and then deletes the connected domain where the ventricle is located from the initial coronary artery three-dimensional image; and the image processing device directly deletes the connected domain where the coronary artery is located from the initial coronary artery three-dimensional image.

Here, the deletion processing means that the CT value information in the corresponding region is set to zero in the initial coronary artery three-dimensional image.

Fig. 6 is a plan view of an exemplary deleted three-dimensional initial coronary artery image according to an embodiment of the present invention, as shown in fig. 6, where the left drawing is a plan view of a 101 th layer of the three-dimensional initial coronary artery image; the right image is a 101 st layer plane view of the initial coronary artery three-dimensional image after the aorta connected region is emptied, namely a 101 st layer plane view of the initial coronary artery three-dimensional image after deletion.

It can be understood that the image processing apparatus deletes the connected domain where the left ventricle is located in the initial coronary artery three-dimensional image, so that the auricle, the left atrium, and the left ventricle in the initial coronary artery three-dimensional image are cleared, and the tissues of the auricle, the left atrium, and the left ventricle, which have been cleared when the subsequent coronary artery is regenerated, will not grow out, and will not be affected by the parts, such as the auricle, which are easily adhered to the coronary artery. The image processing device deletes the connected domain where the coronary artery is located in the initial coronary artery three-dimensional image, so that when the connected domain is constructed by reducing the gray value in the subsequent process of coronary artery regrowth, the connected domain connected with the coronary artery and the aorta is not a whole large connected domain any more, but a plurality of small connected domains, and the small connected domains are not connected with each other. Once a small connected domain is attached to other tissues, one can choose to discard this small connected domain, while the other small connected domains can grow normally.

S104a3, performing coronary artery growth based on the coronary artery growth gray value and the deleted initial coronary artery three-dimensional image to obtain a coronary artery growth three-dimensional image.

In the embodiment of the invention, after the image processing device obtains the coronary artery growth gray value and the deleted initial coronary artery three-dimensional image, the cyclic operation enables the coronary artery growth gray value to be reduced by the preset growth step length each time, and the connected domains grown after the gray value is reduced each time are marked until the coronary artery growth gray value is reduced to the preset minimum growth gray value, and all the marked connected domains are counted, so that the coronary artery growth three-dimensional image is obtained.

Further, in the embodiment of the present invention, in S103d, the image processing apparatus performs coronary artery growth based on the coronary artery growth gray-scale value and the deleted initial coronary artery three-dimensional image, so as to obtain a coronary artery growth three-dimensional image, which specifically includes: and the image processing device generates the coronary artery of the deleted initial coronary artery three-dimensional image according to the coronary artery growth gray value and the preset growth step length until the coronary artery growth gray value is reduced to a preset minimum growth gray value, so as to obtain a coronary artery growth three-dimensional image and finish the coronary artery growth.

It should be noted that, when the image processing apparatus performs coronary artery growth, the image processing apparatus determines the number of pixels in the labeled connected domain each time, and discards the labeled connected domain when the number of pixels in the labeled connected domain is greater than a preset number threshold (for example, 100000); and when the number of the pixel points in the marked connected domain is not more than the preset number threshold, adding the marked connected domain into the coronary artery growth three-dimensional image, and deleting the marked connected domain from the deleted initial coronary artery three-dimensional image. The image processing device repeats this operation until the coronary artery growth gray value is reduced to a preset minimum growth gray value, and the coronary artery growth is completed, so as to obtain a three-dimensional image of the coronary artery growth, as shown in fig. 7.

S104b, the aorta area is identified on the coronary artery growth three-dimensional image by using a preset algorithm.

In the embodiment of the invention, since the coronary artery three-dimensional image comprises the coronary artery region and the aorta region, the image processing device can obtain the target image only comprising the coronary artery region, namely the coronary artery three-dimensional image, by removing the aorta region in the coronary artery growth three-dimensional image. Here, the image processing means performs the identification of the aorta region on the three-dimensional image of the coronary artery growth according to a preset algorithm.

Preferably, the preset algorithm is an erosion-before-expansion algorithm, and the image processing device can remove the coronary artery region in the three-dimensional image of the coronary artery growth by eroding and expanding the three-dimensional image of the coronary artery growth.

It should be noted that, the erosion algorithm is to reduce the shape in the three-dimensional binary matrix uniformly according to a specified rule, which is equivalent to removing several layers of points on the outer layer of the shape, and the expansion algorithm is opposite to the erosion algorithm.

And S104c, deleting the aorta area from the coronary artery growth three-dimensional image to obtain a coronary artery three-dimensional image.

In the embodiment of the present invention, after the image processing device identifies the aorta region in the three-dimensional image of the coronary artery growth, the aorta region is deleted from the three-dimensional image of the coronary artery growth, for example, the three-dimensional image of the coronary artery growth and the aorta region are differentiated, so that the three-dimensional image of the coronary artery with only two maximum connected regions left after the aorta is removed is obtained, wherein the two maximum connected regions represent the left coronary artery and the right coronary artery.

Preferably, after obtaining the three-dimensional image of the coronary artery, the image processing device extracts the isosurface data from the three-dimensional image of the coronary artery, performs surface reconstruction on the isosurface data by using a predetermined mesh algorithm (such as a poisson surface reconstruction algorithm), and performs smoothing on the surface reconstruction result, so as to obtain a three-dimensional mesh model of the coronary artery, as shown in fig. 8. That is, the coronary artery three-dimensional image is a solid stereo image, and the image processing apparatus processes the solid stereo image into an empty stereo image and then uses the image as a medical diagnosis basis.

It can be understood that, because the image processing device is constructed according to the morphology of the aorta and the physiological structure of the aorta, the aorta and the coronary artery are accurately identified in the initial coronary artery three-dimensional image, and the coronary artery is automatically grown based on the identified boundary position information of the aorta and the left ventricle, so that the coronary artery three-dimensional image is obtained, the automatic and accurate extraction of the coronary artery is realized, the intelligence of the coronary artery acquisition is improved, and the effect of the coronary artery acquisition is improved.

Example two

Based on the same inventive concept as the embodiment, an embodiment of the present invention provides an image processing apparatus 30, and fig. 9 is a schematic structural diagram of the image processing apparatus according to the embodiment of the present invention, as shown in fig. 9, the image processing apparatus 30 includes:

a first identification unit 300, configured to, when obtaining an initial coronary artery three-dimensional image, perform aorta identification in the initial coronary artery three-dimensional image based on an aorta morphology to obtain aorta position information;

a determining unit 301, configured to determine an aorta connected domain three-dimensional image from the initial coronary artery three-dimensional image based on the aorta position information;

a second identifying unit 302, configured to perform cardiac sinus identification in the three-dimensional image of the aorta connected domain based on the aorta position information and the aorta physiological structure, so as to obtain boundary position information between an aorta and a left ventricle;

and a regrowth unit 303, configured to perform coronary artery regrowth based on the aorta and left ventricle boundary position information, so as to obtain a three-dimensional coronary artery image.

Further, the image processing apparatus 30 further includes an overlaying unit 304, where the overlaying unit 304 is configured to, when at least two coronary angiography two-dimensional images are acquired, acquire corresponding image grayscale correction information from the at least two coronary angiography two-dimensional images, respectively, where the image grayscale correction information includes initial grayscale values and format information corresponding to the at least two coronary angiography two-dimensional images; obtaining density values corresponding to the at least two coronary angiography two-dimensional images according to the initial gray value and the format information; and superposing the at least two coronary artery angiography two-dimensional images according to the density value and a preset image level sequence to obtain the initial coronary artery three-dimensional image.

Further, the first identification unit 300 is specifically configured to determine a radius threshold according to the aorta morphology; and performing binarization processing on the hierarchical coronary artery three-dimensional image in the initial coronary artery three-dimensional image according to a preset gray value based on the preset image hierarchical sequence, and identifying the aorta in a result image corresponding to the hierarchical coronary artery three-dimensional image subjected to binarization processing according to a preset positioning algorithm and the radius threshold value until the aorta position information is obtained.

Further, the determining unit 301 is specifically configured to obtain an initial aorta grayscale value according to the aorta position information; determining an aorta gray value according to a preset gray value and the initial aorta gray value; performing binarization processing on the initial coronary artery three-dimensional image according to the aorta gray value to obtain a binarized initial coronary artery three-dimensional image; and determining an aorta communication region from the binarized initial coronary artery three-dimensional image according to the aorta position information to obtain the aorta communication region three-dimensional image.

Further, the second identifying unit 302 is specifically configured to determine a position determination condition according to the physiological structure of the aorta, where the position determination condition is used for identifying the cardiac sinus; and determining a search plane from the aorta position information according to a preset search step length in the aorta connected domain three-dimensional image until the aorta section area corresponding to the search plane meets the position judgment condition, and taking the corresponding search plane as the aorta and left ventricle boundary position information.

Further, the regrowth unit 303 is specifically configured to perform coronary artery regrowth based on the boundary position information of the aorta and the left ventricle, so as to obtain a three-dimensional image of coronary artery growth; identifying an aorta region on the coronary artery growth three-dimensional image by using a preset algorithm; and deleting the aorta area from the coronary artery growth three-dimensional image to obtain the coronary artery three-dimensional image.

Further, the regrowth unit 303 is further specifically configured to determine a coronary artery growth gray value according to the aorta and left ventricle boundary position information and the aorta position information; deleting the three-dimensional image of the aorta communication domain from the initial coronary artery three-dimensional image according to the boundary position information of the aorta and the left ventricle to obtain a deleted initial coronary artery three-dimensional image; and performing coronary artery growth based on the coronary artery growth gray value and the deleted initial coronary artery three-dimensional image to obtain the coronary artery growth three-dimensional image.

Further, the regrowth unit 303 is further specifically configured to obtain a coronary artery connected domain according to the information of the boundary position between the aorta and the left ventricle; and when the volume corresponding to the coronary artery communication domain is larger than a preset volume, circularly increasing a preset adhesion removing step length on the basis of the aorta gray value corresponding to the aorta position information until the volume corresponding to the coronary artery communication domain is not larger than the preset volume, and taking the gray value after circular increase as the coronary artery growth gray value.

Further, the regrowth unit 303 is further specifically configured to perform coronary artery generation on the deleted initial coronary artery three-dimensional image according to the coronary artery growth gray value and a preset growth step length until the coronary artery growth gray value is reduced to a preset minimum growth gray value, so as to complete coronary artery growth, and obtain the coronary artery growth three-dimensional image.

In practical applications, the first identifying Unit 300, the determining Unit 301, the second identifying Unit 302, and the regenerating Unit 303 may be implemented by a processor 304 located on the image Processing apparatus 30, specifically, a CPU (Central Processing Unit), an MPU (micro processor Unit), a DSP (Digital Signal processor), a Field Programmable Gate Array (FPGA), or the like.

An embodiment of the present invention further provides an image processing apparatus 30, as shown in fig. 10, where the image processing apparatus 30 includes: a processor 304, a memory 305 and a communication bus 306, wherein the memory 305 communicates with the processor 304 via the communication bus 306, and the memory 305 stores a program executable by the processor 304, and when the program is executed, the image processing method according to the first embodiment is executed by the processor 305.

In practical applications, the Memory 305 may be a volatile Memory (volatile Memory), such as a Random-Access Memory (RAM); or a non-volatile Memory (non-volatile Memory), such as a Read-Only Memory (ROM), a flash Memory (flash Memory), a Hard Disk (Hard Disk Drive, HDD) or a Solid-State Drive (SSD); or a combination of the above types of memories and provides instructions and data to the processor 304.

An embodiment of the present invention provides a computer-readable storage medium, on which a program is stored, which when executed by the processor 304 implements the image processing method according to the first embodiment.

As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention.

Claims

1. An image processing method, characterized in that the method comprises:

performing coronary artery regrowth based on the boundary position information of the aorta and the left ventricle to obtain a coronary artery three-dimensional image;

wherein, the regrowth of the coronary artery based on the boundary position information of the aorta and the left ventricle to obtain a three-dimensional image of the coronary artery comprises the following steps:

2. The method of claim 1, wherein before performing aorta identification in the initial coronary artery three-dimensional image based on aorta morphology when the initial coronary artery three-dimensional image is acquired to obtain aorta position information, the method further comprises:

3. The method according to claim 1, wherein the aorta recognition is performed in the initial coronary artery three-dimensional image based on the aorta morphology to obtain aorta position information, comprising:

determining a radius threshold from the aorta morphology;

and performing binarization processing on the hierarchical coronary artery three-dimensional image in the initial coronary artery three-dimensional image according to a preset gray value based on a preset image hierarchical sequence, and identifying the aorta in a result image corresponding to the hierarchical coronary artery three-dimensional image subjected to binarization processing according to a preset positioning algorithm and the radius threshold value until the aorta position information is obtained.

4. The method of claim 1, wherein determining an aorta connected domain three-dimensional image from the initial coronary artery three-dimensional image based on the aorta position information comprises:

5. The method according to claim 1, wherein the performing cardiac sinus recognition in the three-dimensional image of the connected domain of aorta based on the aortic position information and aortic physiological structures to obtain aortic and left ventricular boundary position information comprises:

6. The method of claim 5, wherein the re-growing of coronary arteries based on the aortic and left ventricular boundary location information, resulting in a three-dimensional image of coronary artery growth, comprises:

7. The method of claim 6, wherein determining a coronary artery growth gray scale value from the aorta and left ventricle boundary position information and the aorta position information comprises:

8. The method of claim 6, wherein the performing coronary artery growth based on the coronary artery growth gray scale value and the deleted initial coronary artery three-dimensional image to obtain the coronary artery growth three-dimensional image comprises:

9. An image processing apparatus, characterized in that the apparatus comprises: a processor, a memory and a communication bus, the memory in communication with the processor through the communication bus, the memory storing a program executable by the processor, the program, when executed, causing the processor to perform the method of any of claims 1-8.

10. A computer-readable storage medium, on which a program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1 to 8.