Method and readable storage medium for reconstructing coronary artery model based on CTA images

Abstract

The present application relates to a method and a readable storage medium for reconstructing a coronary artery vascular model based on CTA images. The method comprises: acquiring three-dimensional image data of coronary CTA; extracting a first center path point and radius information along the first center path point from the three-dimensional image data; correcting the first center path point to obtain a corrected second center path point and the radius information along the second center path point; identifying the left coronary system and the right coronary system, and removing interfering branches based on the identification results; generating curve data based on the second center path point, traversing the second center path point, and generating a vascular pipeline in combination with the radius information, and merging to obtain a reconstructed coronary artery vascular model. The method provided in the present application automatically reconstructs the coronary artery vascular model and automatically completes the identification of the left coronary system and the right coronary system by extracting and correcting the center line and the radius along the coronary artery.

Description

Technical Field

[0001] The present application relates to the field of medical image processing, and in particular to a method and a readable storage medium for reconstructing a coronary artery vascular model based on CTA images. Background Art

[0002] Coronary artery atherosclerosis (CHD) is one of the diseases with the highest morbidity and mortality rates worldwide, with over 20 million people dying from CHD each year. With the continuous improvement of living standards, the age of onset of heart disease is getting younger and younger.

[0003] CTA imaging technology (CT angiography) offers advantages such as requiring no hospitalization and being non-invasive. Coronary CTA is often used clinically for preliminary screening. It is highly clinically valuable for diagnosing and ruling out coronary heart disease, and accurate segmentation of blood vessels facilitates further diagnostic work.

[0004] However, in actual research applications, manual or semi-automatic methods are often used to segment blood vessels to obtain recognition results, which are not repeatable and are time-consuming and labor-intensive. Summary of the Invention

[0005] Based on this, it is necessary to provide a method for reconstructing a coronary artery vascular model based on CTA images to address the above technical issues.

[0006] The present invention provides a method for reconstructing a coronary artery model based on CTA images, including:

[0007] Acquire three-dimensional imaging data of coronary CTA;

[0008] Extracting a first central path point and radius information along the first central path point from the three-dimensional image data;

[0009] Correcting the first central path point to obtain a corrected second central path point and the radius information along the second central path point;

[0010] Identify the left coronary artery system and the right coronary artery system, and remove interfering branches based on the identification results;

[0011] Curve data is generated according to the second central path point, and the second central path point is traversed and combined with the radius information to generate a blood vessel pipeline, and a reconstructed coronary artery vascular model is obtained after merging.

[0012] Optionally, correcting the first central path point to obtain a corrected second central path point specifically includes:

[0013] Based on the three-dimensional image data, sequentially obtaining two-dimensional sections along the first central path point, the two-dimensional sections including a blood vessel cross section and an image of its surroundings;

[0014] For any two-dimensional plane, a search range is set according to the first central path point in the plane, and a blood vessel wall is located according to a blood vessel CT threshold;

[0015] If the pixel with the largest CT value within the search range is smaller than the vascular CT threshold, or the pixel with the smallest CT value within the search range is larger than the calcification CT threshold, the corresponding first center path point is corrected to the vascular wall and mapped to the three-dimensional image data to obtain a corrected second center path point.

[0016] Optionally, sequentially obtaining two-dimensional sections along the first central path point based on the three-dimensional image data specifically includes:

[0017] For any first central path point, obtain the tangent vector, normal vector, and binormal vector of the curve on which the first central path point is located;

[0018] According to the tangent vector, normal vector and binormal vector, as well as the three-dimensional coordinates of the first central path point, the cutting matrix of the first central path point is obtained, and then the two-dimensional section of the first central path point is obtained.

[0019] Optionally, the vascular CT threshold is obtained by multiplying the average CT value of the aorta by a first preset coefficient, and the calcification CT threshold is obtained by multiplying the average CT value of the aorta by a second preset coefficient;

[0020] Setting a search range according to the first central path point in the plane specifically includes:

[0021] The search range is set by a preset radius with the first central path point as the center of the circle.

[0022] Optionally, the right crown identification system includes performing the following operations according to the second center path point information:

[0023] Establishing an identification coordinate system based on the three-dimensional image data, the identification coordinate system including: an X-axis pointing from the right hand side to the left hand side, a Y-axis pointing from the front side to the back side, and a Z-axis pointing from the bottom side to the top side;

[0024] The coronary artery with the longest span along the Y axis is selected as the candidate right coronary artery.

[0025] If the Y-axis coordinate of the end of the alternative right coronary artery trunk is greater than the opening of the right coronary artery trunk, the alternative right coronary artery trunk is confirmed as the right coronary artery trunk; otherwise, the coronary artery with the longest span along the X-axis is determined as the right coronary artery trunk.

[0026] Optionally, identifying the left coronary artery system includes identifying the left anterior descending artery and the left circumflex artery, specifically including:

[0027] Obtaining a first portion and a second portion of the left main branch, wherein the first portion includes the left anterior descending branch and its side branches, and the second portion includes the left circumflex branch and its side branches;

[0028] Selecting the coronary artery with the largest span or the longest span on the Y axis from the first part as the left anterior descending artery;

[0029] The coronary artery with the largest span or the longest span on the Z-axis is selected from the second part as the left circumflex artery.

[0030] Optionally, the identification of the left coronary artery system includes identifying the left main branch, specifically including:

[0031] The remaining coronary arteries except the identified right coronary system are obtained, and the remaining coronary arteries include the left main branch, the left anterior descending branch, the left circumflex branch, and the side branches. The left main branch is identified based on the overlap of the left anterior descending branch and the left circumflex branch before identification.

[0032] Optionally, removing the interfering branch specifically includes:

[0033] Based on the identified right coronary artery, left main branch, left anterior descending artery, and left circumflex artery, the remaining side branches and their corresponding side branch trunks are obtained. For one of the remaining side branches:

[0034] If the remaining side branch is parallel to the main branch to which it belongs, remove the remaining side branch;

[0035] If the angle between the extension direction of the remaining side branch and the extension direction of the side branch trunk to which it belongs is greater than a preset angle, the remaining side branch is removed.

[0036] Optionally, a reconstructed coronary artery model is obtained after merging, specifically including:

[0037] After merging, the initial vascular model was obtained;

[0038] Converting the initial blood vessel model along the second central path point after deleting the interference branch into image data as input of the first level set;

[0039] According to the initial blood vessel model, denoising and gradient calculation are sequentially performed on the three-dimensional image data to obtain image edge features, and the image edge features are used as input of the second level set;

[0040] Combining the first level set and the second level set, using an active contour model based on a partial differential equation to find a segmentation edge, and obtaining an image sequence along a second central path point;

[0041] Surface reconstruction is performed on the image sequence to obtain a reconstructed coronary artery model.

[0042] The present application also provides a readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method for reconstructing a coronary artery model based on CTA images described in the present application.

[0043] The method for reconstructing a coronary artery model based on CTA images in this application has at least the following effects:

[0044] The present application discloses a method for reconstructing a coronary artery model based on CTA images. By extracting and correcting the centerline and the radius along the coronary artery, i.e., the second center path point and radius information, the coronary artery model can be automatically reconstructed. The corrected centerline ensures the accuracy of the coronary artery model reconstruction.

[0045] This application can automatically complete the identification of the left coronary system and the right coronary system of the coronary artery without the need for manual identification and labeling, thereby improving work efficiency.

[0046] This application uses the radius information before correction to generate the vascular pipeline, which is closer to the actual morphology of the coronary artery compared to the reconstructed coronary artery model obtained by customizing the input radius information. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 Schematic diagram of a flow chart of a method for reconstructing a coronary artery model based on CTA images in one embodiment of the present application;

[0048] Figure 2 FIG. 1 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0049] In order to make the purpose, technical solutions and advantages of this application more clear, the following further describes this application in detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain this application and are not intended to limit this application.

[0050] In one embodiment of the present application, a method for reconstructing a coronary artery model based on CTA images is provided, comprising steps S100 to S500:

[0051] Step S100 , obtaining three-dimensional image data of coronary CTA (coronary CT angiography).

[0052] In step S200, a first central path point and radius information along the first central path point are extracted from the three-dimensional image data. The extraction method may utilize a trained convolutional neural network, for example.

[0053] Step S300: Correct the first central path point to obtain the corrected second central path point and radius information along the second central path point.

[0054] Step S300 can correct the initial center path point data. If some of the first center path points in step S200 are not located within the coronary artery lumen (due to the deviation extracted in step S200), after correction, the first path points that deviate from the lumen are corrected to be within the coronary artery lumen.

[0055] Step S300 specifically includes steps S310 to S330, wherein:

[0056] Step S310, based on the three-dimensional image data, sequentially obtaining two-dimensional sections along the first central path point, the two-dimensional sections including the blood vessel cross section and its surrounding image;

[0057] Step S310 specifically includes steps S311 to S330, wherein:

[0058] Step S311: for any first central path point, obtain the tangent vector, normal vector, and binormal vector of the curve on which the first central path point is located;

[0059] Before performing step S310, the first central path points may be sequentially connected into a curve and smoothed multiple times, and the smoothed first central path points are used to perform step S310.

[0060] Step S312, obtaining the cutting matrix of the first central path point according to the tangent vector, the normal vector and the binormal vector, as well as the three-dimensional coordinates of the first central path point, and then obtaining the two-dimensional section of the first central path point.

[0061] That is, a cutting matrix at each first central path point is calculated according to the tangent vector, normal vector, binormal vector, and three-dimensional coordinates of the point, and a two-dimensional section of the image is cut out at the point using the cutting matrix.

[0062] Step S320: For any two-dimensional plane, set a search range according to the first central path point in the plane and locate the blood vessel wall according to the blood vessel CT threshold;

[0063] Furthermore, setting the search range according to the first central path point in the plane specifically includes: taking the first central path point as the center of a circle and setting the search range by a preset radius. The preset radius may be, for example, 1.5 mm.

[0064] In step S330, if the pixel with the largest CT value within the search range is smaller than the vascular CT threshold, or the pixel with the smallest CT value within the search range is larger than the calcification CT threshold, the corresponding first center path point is corrected to the inside of the vascular wall and mapped to the three-dimensional image data to obtain a corrected second center path point.

[0065] In step S330 , the vessel CT threshold is obtained by multiplying the average CT value of the aorta by a first preset coefficient, and the calcification CT threshold is obtained by multiplying the average CT value of the aorta by a second preset coefficient.

[0066] The first preset coefficient can be, for example, 1.0 to 1.1. The second preset coefficient can be, for example, 1.2. The pixel with the largest HU value is searched within the search range. If the HU value of the pixel is less than a set threshold (vascular CT threshold), the two-dimensional coordinates of the pixel on the two-dimensional section are corrected to be within the blood vessel. The pixel with the smallest HU value is searched within the search range. If the HU value of the pixel is greater than a set threshold (vascular CT threshold), the two-dimensional coordinates of the pixel on the two-dimensional section are corrected to be within the blood vessel.

[0067] After the correction is complete, the correction result is transformed into the 3D coordinate system of the corresponding original 3D image, and the original center path point coordinates are updated accordingly (updating the coordinates of the first center path point). If the above conditions are not triggered, the coordinates of the original first center path point do not need to be corrected. This step iterates through all first center path points, completes the correction, and obtains the corrected second center path point.

[0068] Step S400 includes identifying the left coronary system (step S420), identifying the right coronary system (step S410), and removing interfering branches based on the identification results (step S430). This step utilizes the second central path point information combined with anatomical features to perform vascular segmentation.

[0069] Step S400 also includes dividing all second central path points into two parts, and determining whether each part belongs to the left or right coronary artery system based on the coordinates of the second central path point at the coronary artery ostium. After the determination is completed, the following steps S410 to S430 are executed. It will be understood that before executing S410 to S420, this method can only distinguish between the left and right coronary artery systems, but cannot identify the sub-parts of the left or right coronary artery system. In other words, the right coronary artery trunk, left main branch, left anterior descending artery, and left circumflex artery are not yet identified and named.

[0070] In step S410, identifying the right crown system includes performing the following operations based on the second center path point information:

[0071] Step S411: establishing a recognition coordinate system based on the three-dimensional image data, where the recognition coordinate system includes: an X-axis pointing from the right hand side to the left hand side, a Y-axis pointing from the front side to the back side, and a Z-axis pointing from the bottom side to the top side;

[0072] Step S412: select the coronary artery with the longest span along the Y-axis as the candidate right coronary artery trunk;

[0073] Step S413: If the Y-axis coordinate of the end of the candidate right coronary artery trunk is greater than the opening of the right coronary artery trunk, the candidate right coronary artery trunk is confirmed as the right coronary artery trunk; otherwise, the coronary artery with the longest span along the X-axis is determined as the right coronary artery trunk.

[0074] Specifically, with the sagittal plane as the X-axis, the coronal plane as the Y-axis, and the transverse plane as the Z-axis, calculate the range of each branch of the right coronary artery in the Y-axis and Z-axis, and the projection of each branch of the right coronary artery on the plane perpendicular to the X-axis. Find the one with the largest span along the Y-axis as the candidate right coronary artery trunk. Compare the Y-axis coordinates of the end of the candidate right coronary artery trunk with the Y-axis coordinates of the right coronary artery opening point. If the coordinates of the end of the candidate trunk are greater than the coordinates of the right coronary artery opening point, it is determined to be the right coronary artery trunk. Otherwise, search for the branch with the largest span in the X-direction as the right coronary artery trunk.

[0075] Step S420 , identifying the left coronary system, including identifying the left main branch (step S421 ), and identifying the left anterior descending branch and the left circumflex branch (step S422 ).

[0076] Step S421, identifying the left main branch, specifically includes: obtaining the remaining coronary arteries excluding the identified right coronary system, the remaining coronary arteries including the left main branch, left anterior descending branch, left circumflex branch, and side branches, and identifying and obtaining the left main branch based on the overlap of the left anterior descending branch and the left circumflex branch before identification.

[0077] Step S422, identifying the left anterior descending artery and the left circumflex artery, specifically includes: (1) obtaining the first part and the second part after removing the left main artery, the first part including the left anterior descending artery and its side branches, and the second part including the left circumflex artery and its side branches; (2) selecting the coronary artery with the largest span or the longest span on the Y axis from the first part as the left anterior descending artery; (3) selecting the coronary artery with the largest span or the longest span on the Z axis from the second part as the left circumflex artery.

[0078] Specifically, all branches of the left coronary artery were removed from the left main branch, and the remaining branches were divided into two parts. The first part contained the left anterior descending artery LAD and its side branches (part A), and the second part contained the left circumflex artery LCX and its side branches (part B). From the first part, the left anterior descending artery was determined based on the length of each branch (longest length) or the span on the Y axis (largest span). From the second part, the branch with the largest span on the Z axis was selected as the left circumflex artery.

[0079] Step S430, removing interfering branches, specifically includes: obtaining the remaining side branches and their corresponding side branch trunks (the side branch trunks refer to the right coronary artery trunk, left main branch, left anterior descending branch and left circumflex branch) based on the identified right coronary artery trunk, left main branch, left anterior descending branch and left circumflex branch; for one of the remaining side branches: if the remaining side branch is parallel to the corresponding side branch trunk, removing the remaining side branch; if the angle between the extension direction of the remaining side branch and the extension direction of the corresponding side branch trunk is greater than a preset angle, removing the remaining side branch.

[0080] The preset angle can be, for example, one hundred and twenty degrees. In the process of removing interfering branches, it also includes re-sorting the order in which each side branch (remaining side branches) appears relative to the side branch trunk. In this step, the angle between each side branch and the trunk to which it belongs is determined. If the side branch direction vector and the trunk direction vector are almost parallel, the side branch is deleted. If the angle between the side branch direction vector and the trunk direction vector is greater than the preset value, the side branch is deleted. After completing step S430, the venous branch interference is removed.

[0081] Step S500, curve data is generated according to the second central path point, the second central path point is traversed, and a blood vessel pipeline is generated in combination with radius information (step S510), and a reconstructed coronary artery vascular model is obtained after merging (step S520).

[0082] Step S510 specifically includes: generating curve data according to the second central path point, sweeping along each curve (traversing the central path point one by one), and generating a pipeline with a set radius. The set radius is the radius information above.

[0083] Step S520, after merging, obtains a reconstructed coronary artery model, specifically including:

[0084] Step S521, obtaining an initial blood vessel model after merging;

[0085] Step S522 , converting the initial blood vessel model along the second central path point after deleting the interference branch into image data as input of the first level set;

[0086] Step S523: Denoising and gradient calculation are performed on the three-dimensional image data in sequence according to the initial blood vessel model to obtain image edge features, which are used as input for the second level set method.

[0087] In step S524, the first level set and the second level set are combined to find the segmentation edge using the active contour model based on partial differential equations to obtain an image sequence along the second center path point; for each image in the image sequence, the image inside the target contour is positive, the target contour is zero bounded, and the image outside the target contour is negative.

[0088] Step S525 , performing surface reconstruction on the image sequence to obtain a reconstructed coronary artery model.

[0089] Specifically, the multiple channels generated by the multiple curves are merged to form an initial channel model (initial vascular model) of the entire coronary artery tree. The channel model data is converted into image data, which serves as the input for the first initial level set. Based on the existing initial channel contours, potential image edge features are obtained by denoising the original 3D image data and calculating gradients, which serve as another input for the second level set. By extending inward and outward to find segmentation edges, an image sequence corresponding to the vessel's centerline path is obtained. The surface of this image sequence is reconstructed using the marching cubes algorithm to obtain a coronary artery model consisting of the vessels of interest.

[0090] The embodiments of the present application are based on a method for reconstructing a coronary artery model based on CTA images. By extracting and correcting the centerline and along-line radius of the coronary artery, i.e., the second center path point and radius information, the coronary artery model can be automatically reconstructed. The left and right coronary artery systems can also be automatically identified without manual identification and labeling, thereby improving work efficiency.

[0091] The coronary artery models reconstructed in the various embodiments of this application have smooth surfaces and eliminate interfering venous branches, replacing the traditionally complex manual pre-processing steps and significantly improving the reproducibility of the results. The fully automated reconstruction of the vascular model reduces time and labor costs, facilitating further diagnosis by doctors.

[0092] It should be understood that Figure 1 At least part of the steps in the flowchart may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0093] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 2As shown. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for reconstructing a coronary artery vascular model based on CTA images is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the computer device housing, or an external keyboard, touchpad or mouse.

[0094] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0095] Step S100, acquiring three-dimensional image data of coronary CTA;

[0096] Step S200, extracting a first central path point and radius information along the first central path point from the three-dimensional image data;

[0097] Step S300, correcting the first central path point to obtain a corrected second central path point and radius information along the second central path point;

[0098] Step S400: Identify the left coronary artery system and the right coronary artery system, and remove interference branches based on the identification results;

[0099] Step S500 , generating curve data according to the second central path point, traversing the second central path point, and generating a blood vessel pipeline in combination with radius information, and obtaining a reconstructed coronary artery vascular model after merging.

[0100] In one embodiment, a readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0101] Step S100, acquiring three-dimensional image data of coronary CTA;

[0102] Step S200, extracting a first central path point and radius information along the first central path point from the three-dimensional image data;

[0103] Step S300, correcting the first central path point to obtain a corrected second central path point and radius information along the second central path point;

[0104] Step S400: Identify the left coronary artery system and the right coronary artery system, and remove interference branches based on the identification results;

[0105] Step S500 , generating curve data according to the second central path point, traversing the second central path point, and generating a blood vessel pipeline in combination with radius information, and obtaining a reconstructed coronary artery vascular model after merging.

[0106] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0107] The technical features of the above embodiments may be combined in any manner. To simplify the description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there are no conflicts in the combination of these technical features, they should be considered to be within the scope of this specification. When technical features in different embodiments are reflected in the same figure, it can be regarded as that figure also discloses the combination examples of the various embodiments involved.

[0108] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A method for reconstructing a coronary artery model based on CTA images, characterized in that: include: Acquire three-dimensional imaging data of coronary CTA; Extracting a first central path point and radius information along the first central path point from the three-dimensional image data; Correcting the first central path point to obtain a corrected second central path point and the radius information along the second central path point, wherein obtaining the corrected second central path point specifically includes: sequentially obtaining two-dimensional sections along the first central path point based on the three-dimensional image data, the two-dimensional sections including a blood vessel cross-section and an image of its surroundings; for any two-dimensional plane, setting a search range based on the first central path point within the plane and locating the blood vessel wall based on a blood vessel CT threshold; if the pixel with the largest CT value within the search range is less than the blood vessel CT threshold, or the pixel with the smallest CT value within the search range is greater than the calcification CT threshold, correcting the corresponding first central path point to within the blood vessel wall and mapping it to the three-dimensional image data to obtain the corrected second central path point; Identify the left coronary artery system and the right coronary artery system, and remove interfering branches based on the identification results; Curve data is generated according to the second central path point, and the second central path point is traversed and combined with the radius information to generate a blood vessel pipeline, and a reconstructed coronary artery vascular model is obtained after merging.

2. The method for reconstructing a coronary artery model based on CTA images according to claim 1, characterized in that: Sequentially obtaining two-dimensional sections along the first central path point based on the three-dimensional image data specifically includes: For any first central path point, obtain the tangent vector, normal vector, and binormal vector of the curve on which the first central path point is located; According to the tangent vector, normal vector and binormal vector, as well as the three-dimensional coordinates of the first central path point, the cutting matrix of the first central path point is obtained, and then the two-dimensional section of the first central path point is obtained.

3. The method for reconstructing a coronary artery model based on CTA images according to claim 1, characterized in that: The vascular CT threshold is obtained by multiplying the average CT value of the aorta by a first preset coefficient, and the calcification CT threshold is obtained by multiplying the average CT value of the aorta by a second preset coefficient; Setting a search range according to the first central path point in the plane specifically includes: The search range is set by a preset radius with the first central path point as the center of the circle.

4. The method for reconstructing a coronary artery model based on CTA images according to claim 1, characterized in that: The right crown identification system includes performing the following operations according to the second center path point information: Establishing an identification coordinate system based on the three-dimensional image data, the identification coordinate system including: an X-axis pointing from the right hand side to the left hand side, a Y-axis pointing from the front side to the back side, and a Z-axis pointing from the bottom side to the top side; The coronary artery with the longest span along the Y axis is selected as the candidate right coronary artery. If the Y-axis coordinate of the end of the alternative right coronary artery trunk is greater than the opening of the right coronary artery trunk, the alternative right coronary artery trunk is confirmed as the right coronary artery trunk; otherwise, the coronary artery with the longest span along the X-axis is determined as the right coronary artery trunk.

5. The method for reconstructing a coronary artery model based on CTA images according to claim 4, characterized in that: The identification of the left coronary artery system includes identification of the left main branch, specifically including: The remaining coronary arteries except the identified right coronary system are obtained, and the remaining coronary arteries include the left main branch, the left anterior descending branch, the left circumflex branch, and the side branches. The left main branch is identified based on the overlap of the left anterior descending branch and the left circumflex branch before identification.

6. The method for reconstructing a coronary artery model based on CTA images according to claim 5, characterized in that: The identification of the left coronary artery includes identifying the left anterior descending artery and the left circumflex artery, specifically including: Obtaining a first portion and a second portion of the left main branch, wherein the first portion includes the left anterior descending branch and its side branches, and the second portion includes the left circumflex branch and its side branches; Selecting the coronary artery with the largest span or the longest span on the Y axis from the first part as the left anterior descending artery; The coronary artery with the largest span or the longest span on the Z-axis is selected from the second part as the left circumflex artery.

7. The method for reconstructing a coronary artery model based on CTA images according to claim 6, characterized in that: The removing of the interference branch specifically includes: Based on the identified right coronary artery, left main branch, left anterior descending artery, and left circumflex artery, the remaining side branches and their corresponding side branch trunks are obtained. For one of the remaining side branches: If the remaining side branch is parallel to the main branch to which it belongs, remove the remaining side branch; If the angle between the extension direction of the remaining side branch and the extension direction of the side branch trunk to which it belongs is greater than a preset angle, the remaining side branch is removed.

8. The method for reconstructing a coronary artery model based on CTA images according to claim 1, characterized in that: After merging, the reconstructed coronary artery model is obtained, which specifically includes: After merging, the initial vascular model was obtained; Converting the initial blood vessel model along the second central path point after deleting the interference branch into image data as input of the first level set; According to the initial blood vessel model, denoising and gradient calculation are sequentially performed on the three-dimensional image data to obtain image edge features, and the image edge features are used as input of the second level set; Combining the first level set and the second level set, using an active contour model based on a partial differential equation to find a segmentation edge, and obtaining an image sequence along a second central path point; Surface reconstruction is performed on the image sequence to obtain a reconstructed coronary artery model.

9. A readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for reconstructing a coronary artery model based on CTA images according to any one of claims 1 to 8 are implemented.

Images