Method for reconstructing a coronary model based on coronary angiography

Abstract

The application relates to the technical field of model reconstruction, in particular to a method for reconstructing a coronary artery model based on coronary angiography. The method comprises the following steps: acquiring a coronary artery scanning image of a patient; performing three-dimensional coronary artery spatial structure construction on the coronary artery image of the patient to generate a three-dimensional coronary artery spatial model; performing blood vessel diameter analysis on the three-dimensional coronary artery spatial model to generate coronary artery blood vessel diameter data; acquiring an X-ray angiography image of the patient; performing coronary artery blood vessel network structure construction on the X-ray angiography image of the patient to generate a three-dimensional coronary artery network model; and performing blood vessel wall thickness analysis on the three-dimensional coronary artery network model to generate coronary artery blood vessel wall thickness data. The application combines the coronary artery scanning image and the X-ray angiography image of the patient to perform multi-modal modeling, and performs abnormal analysis on the coronary artery, thereby improving the accuracy and reliability of the coronary artery model reconstruction.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of model reconstruction, and in particular to a method for reconstructing a coronary artery model based on coronary angiography. BACKGROUND

[0002] With the development of computer vision and image processing algorithms, three-dimensional reconstruction technology based on coronary angiography has undergone revolutionary changes. Machine learning and deep learning techniques have been introduced, which can automatically extract the three-dimensional structure of coronary arteries from two-dimensional images, greatly reducing the need for manual operation. For example, using algorithms such as convolutional neural networks (CNN), the blood vessel boundaries can be automatically identified from the blood vessel images, and accurate three-dimensional models can be generated. In recent years, the field of medical image processing has also seen the emergence of deep learning-based generative adversarial networks (GAN) technology, which can generate high-quality three-dimensional coronary artery models from limited data. The GAN model can learn from a large number of coronary artery samples and then generate realistic new samples, filling the data gap and improving the accuracy and stability of the reconstruction. However, traditional modeling often only reconstructs the structure of the blood vessels without considering important parameters such as blood vessel diameter and blood vessel wall thickness, and relies solely on single modality data such as coronary angiography, resulting in low precision and reliability of the model reconstruction. SUMMARY

[0003] Therefore, it is necessary to provide a method for reconstructing a coronary artery model based on coronary angiography to solve at least one of the above technical problems.

[0004] To achieve the above-mentioned purpose, a method for reconstructing a coronary artery model based on coronary angiography, the method comprising the following steps:

[0005] Step S1: obtaining a patient coronary artery scan image; constructing a three-dimensional coronary artery spatial structure for the patient coronary artery image to generate a three-dimensional coronary artery spatial model; analyzing the blood vessel diameter of the three-dimensional coronary artery spatial model to generate coronary artery blood vessel diameter data;

[0006] Step S2: obtaining a patient X-ray angiogram image; constructing a coronary artery vascular structure for the patient X-ray angiogram image to generate a three-dimensional coronary artery vascular model; analyzing the blood vessel wall thickness of the three-dimensional coronary artery vascular model to generate coronary artery blood vessel wall thickness data;

[0007] Step S3: Constructing coronary artery flow structure according to coronary artery wall thickness data and coronary artery diameter data, generating three-dimensional coronary artery blood flow model; integrating three-dimensional coronary artery space model, three-dimensional coronary artery network model and three-dimensional coronary artery blood flow model to generate coronary artery integrated model; analyzing coronary artery integrated model to generate high abnormal site depth exploration data and low abnormal site shallow exploration data;

[0008] Step S4: Reconstructing coronary artery model through high abnormal site depth exploration data and low abnormal site shallow exploration data to generate coronary artery lesion model; predicting virtual surgery effect on coronary artery lesion model to construct corresponding implementation plan template.

[0009] The present application generates an accurate three-dimensional coronary artery space model by constructing a three-dimensional space structure from the patient's coronary artery scan image. This helps doctors have a more comprehensive understanding of the patient's arterial anatomy. Through analysis of vessel diameter and vessel wall thickness, detailed coronary artery vessel feature data can be provided, which helps to assess the health status and possible lesion condition of the vessel. According to the vessel wall thickness and vessel diameter data, a three-dimensional coronary artery blood flow model is constructed. This can help doctors understand the blood flow in the artery, which helps to assess the influence of blood flow dynamics on the health of the vessel. The three-dimensional coronary artery space model, three-dimensional coronary artery network model and three-dimensional coronary artery blood flow model are integrated into a coronary artery integrated model. This integration can provide more comprehensive and integrated information about the structure and function of the coronary artery, providing a basis for subsequent analysis and diagnosis. Through the generated high abnormal site depth exploration data and low abnormal site shallow exploration data, doctors can locate and analyze the abnormality of the coronary artery. Further use of these data to reconstruct the lesion of the coronary artery integrated model generates a coronary artery lesion model. This helps doctors to more accurately diagnose coronary artery lesions. Predicting the effect of virtual surgery on the coronary artery lesion model can help doctors develop corresponding implementation plan templates. This prediction can be simulated before surgery, which helps doctors evaluate the effects of different schemes and improve the success rate and safety of surgery. Therefore, the present application improves the accuracy and reliability of coronary artery model reconstruction by combining patient's coronary artery scan image and X-ray angiogram image for multi-modal modeling and analyzing the abnormality of the coronary artery.

[0010] The beneficial effects of the present application are that by processing the patient's coronary artery scan images, a three-dimensional coronary artery spatial model of the patient can be established, and the blood vessel diameter analysis can be performed. This helps doctors understand the morphology, structure and blood vessel diameter of the patient's coronary artery. By processing the patient's X-ray angiography images, a three-dimensional coronary artery network model of the patient can be established, and the blood vessel wall thickness analysis can be performed. This helps doctors understand the network structure and blood vessel wall thickness of the patient's coronary artery. According to the coronary artery blood vessel wall thickness data and the coronary artery blood vessel diameter data, a three-dimensional coronary artery blood flow model can be constructed. This helps to simulate and analyze the blood flow in the patient's coronary artery. By integrating the three-dimensional coronary artery spatial model, the coronary artery network model and the coronary artery blood flow model, a coronary artery integrated model is generated. By performing abnormal analysis on the coronary artery integrated model, high abnormality site depth exploration data and low abnormality site shallow exploration data can be determined, thereby providing more accurate coronary artery lesion information. By using the high abnormality site depth exploration data and the low abnormality site shallow exploration data, the coronary artery integrated model is reconstructed to generate a coronary artery lesion model. Then, the coronary artery lesion model can be used for virtual surgery effect prediction to evaluate the effect of different treatment schemes and possible coronary artery lesion correction surgery schemes. Therefore, the present application combines the patient's coronary artery scan images and X-ray angiography images for multi-modal modeling, and performs abnormal analysis on the coronary artery, thereby improving the accuracy and reliability of the coronary artery model reconstruction. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1 A step flowchart for a method of reconstructing a coronary artery model based on coronary angiography;

[0012] Figure 2 A detailed implementation step flowchart for step S3 in the method of reconstructing a coronary artery model based on coronary angiography; Figure 1 A detailed implementation step flowchart for step S31 in the method of reconstructing a coronary artery model based on coronary angiography;

[0013] Figure 3 A detailed implementation step flowchart for step S33 in the method of reconstructing a coronary artery model based on coronary angiography. Figure 2 A detailed implementation step flowchart for step S33 in the method of reconstructing a coronary artery model based on coronary angiography.

[0014] Figure 4 A detailed implementation step flowchart for step S33 in the method of reconstructing a coronary artery model based on coronary angiography. Figure 2 A detailed implementation step flowchart for step S33 in the method of reconstructing a coronary artery model based on coronary angiography.

[0015] The implementation of the present application, functional features and advantages will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0016] The technical solutions of the patent application will be described clearly and completely below with reference to the drawings. Obviously, the described embodiments are only part of, but not all of the embodiments of the patent application. Based on the embodiments of the patent application, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the patent application.

[0017] In addition, the drawings are only schematic illustrations of the patent application and are not necessarily drawn to scale. Identical reference numerals in the drawings represent identical or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities, which do not necessarily have to correspond to physically or logically independent entities. The functional entities can be implemented in the form of software, or in one or more hardware modules or integrated circuits, or in different network and / or processor methods and / or microcontroller methods.

[0018] It should be understood that although the terms "first", "second" and the like can be used herein to describe various elements, these elements should not be limited by these terms. These terms are only used to distinguish one element from another. For example, without departing from the scope of the exemplary embodiments, a first element can be referred to as a second element, and similarly a second element can be referred to as a first element. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0019] To achieve the above-mentioned purpose, please refer to Figures 1 to 4 A method for reconstructing a coronary artery model based on coronary angiography, the method comprising the following steps:

[0020] Step S1: acquiring a patient coronary artery scan image; constructing a three-dimensional coronary artery spatial structure for the patient coronary artery image to generate a three-dimensional coronary artery spatial model; analyzing the three-dimensional coronary artery spatial model for a blood vessel diameter to generate coronary artery blood vessel diameter data;

[0021] Step S2: acquiring a patient X-ray angiography image; constructing a coronary artery blood vessel structure for the patient X-ray angiography image to generate a three-dimensional coronary artery structure model; analyzing the three-dimensional coronary artery structure model for a blood vessel wall thickness to generate coronary artery blood vessel wall thickness data;

[0022] Step S3: Constructing coronary artery flow structure according to coronary artery wall thickness data and coronary artery diameter data, generating three-dimensional coronary artery blood flow model; integrating three-dimensional coronary artery space model, three-dimensional coronary artery network model and three-dimensional coronary artery blood flow model to generate coronary artery integrated model; analyzing coronary artery integrated model to generate high abnormal site depth exploration data and low abnormal site shallow exploration data;

[0023] Step S4: Reconstructing coronary artery model through high abnormal site depth exploration data and low abnormal site shallow exploration data to generate coronary artery lesion model; predicting virtual surgery effect on coronary artery lesion model to construct corresponding implementation plan template.

[0024] The present application generates an accurate three-dimensional coronary artery space model by constructing a three-dimensional space structure from the patient's coronary artery scan image. This helps doctors have a more comprehensive understanding of the patient's arterial anatomy. Through analysis of vessel diameter and vessel wall thickness, detailed coronary artery vessel feature data can be provided, which helps to assess the health status and possible lesion condition of the vessel. According to the vessel wall thickness and vessel diameter data, a three-dimensional coronary artery blood flow model is constructed. This can help doctors understand the blood flow in the artery, which helps to assess the influence of blood flow dynamics on the health of the vessel. The three-dimensional coronary artery space model, three-dimensional coronary artery network model and three-dimensional coronary artery blood flow model are integrated into a coronary artery integrated model. This integration can provide more comprehensive and integrated information on the structure and function of the coronary artery, providing a basis for subsequent analysis and diagnosis. Through the generated high abnormal site depth exploration data and low abnormal site shallow exploration data, doctors can locate and analyze the abnormality of the coronary artery. Further use of these data to reconstruct the lesion of the coronary artery integrated model generates a coronary artery lesion model. This helps doctors to more accurately diagnose coronary artery lesions. Predicting the effect of virtual surgery on the coronary artery lesion model can help doctors develop corresponding implementation plan templates. This prediction can be simulated before surgery, which helps doctors evaluate the effectiveness of different schemes and improve the success rate and safety of surgery. Therefore, the present application improves the accuracy and reliability of coronary artery model reconstruction by combining patient coronary artery scan images and X-ray angiography images for multi-modal modeling and analyzing coronary artery abnormalities.

[0025] In the embodiment of the present application, reference is made to Figure 1 The present application is a step flowchart of a method for reconstructing a coronary artery model based on coronary angiography. In this example, the method includes the following steps:

[0026] Step S1: Obtain patient coronary artery scan images; construct three-dimensional coronary artery spatial structure for patient coronary artery images, generate three-dimensional coronary artery spatial model; analyze vessel diameter of three-dimensional coronary artery spatial model, generate coronary artery vessel diameter data;

[0027] In the embodiments of the present application, a medical imaging device such as computed tomography (CT) or magnetic resonance imaging (MRI) is used to scan the patient's coronary arteries to obtain coronary artery image data. Through image processing and segmentation techniques on the coronary artery images, the vascular structure information of the coronary artery is extracted. This can include edge detection, threshold segmentation, region growing and other operations using image processing algorithms to obtain the three-dimensional spatial structure of the coronary artery. The extracted coronary artery vascular structure information is converted into a three-dimensional model representation. Computer graphics and three-dimensional reconstruction techniques can be used to convert two-dimensional image data into a three-dimensional coronary artery spatial model. This can include methods such as surface reconstruction, voxelization, etc. to construct a three-dimensional model with spatial position and morphological characteristics. Vessel diameter analysis is performed on the three-dimensional coronary artery spatial model to obtain coronary artery vessel diameter data. This can be achieved by extracting vessel branches and measuring diameters on the coronary artery spatial model. Common methods include curvature and width-based vessel branch tracking algorithms, morphological operations, etc.

[0028] Step S2: Obtain patient X-ray angiography images; construct coronary artery vascular structure for patient X-ray angiography images, generate three-dimensional coronary artery vascular model; analyze vessel wall thickness of three-dimensional coronary artery vascular model, generate coronary artery vessel wall thickness data;

[0029] In the embodiments of the present application, X-ray angiography technology is used to perform coronary angiography on the patient to obtain angiography image data of the coronary artery. Image processing and segmentation techniques are used on the obtained angiography images to construct the coronary artery vascular structure. This can involve preprocessing steps such as noise removal, image enhancement, etc. Then, vessel segmentation algorithms such as threshold segmentation, edge detection, etc. are applied to extract the coronary artery vascular structure. The extracted coronary artery vascular structure is converted into a three-dimensional model representation. Volume rendering algorithms such as voxelization or surface reconstruction-based methods can be used to convert two-dimensional vascular structure into a model with three-dimensional spatial information. The generated three-dimensional coronary artery vascular model is analyzed for vessel wall thickness to obtain coronary artery vessel wall thickness data. This can be achieved by measuring the distance between the inner and outer surfaces of the vessel. Common methods include curvature or gray scale gradient change-based vessel wall segmentation algorithms, morphological operations, etc.

[0030] Step S3: according to the coronary artery wall thickness data and the coronary artery vessel diameter data, the coronary artery blood flow structure is constructed, and a three-dimensional coronary artery blood flow model is generated; the three-dimensional coronary artery space model, the three-dimensional coronary artery network model and the three-dimensional coronary artery blood flow model are integrated to generate a coronary artery integrated model; the coronary artery integrated model is analyzed to generate high abnormal site deep exploration data and low abnormal site shallow exploration data;

[0031] In the embodiment of the present application, the coronary artery blood flow model can be constructed according to the coronary artery wall thickness data and the coronary artery vessel diameter data. This involves combining the blood vessel network model with the blood flow physical model. By modeling the blood flow in the blood vessel as a fluid dynamics model, the flow behavior of the blood in the coronary artery can be simulated. The specific fluid dynamics model construction process includes using the Navier-Stokes equation set as the basic equation. This equation set includes the continuity equation and the momentum equation, which are used to describe the motion and flow of the fluid. Considering the non-Newtonian nature of blood, the commonly used model is the compressible Navier-Stokes equation and the non-Newtonian model of blood, such as the Carreau-Yasuda model, the geometry of the blood vessel is determined, including the diameter, length, curvature of the blood vessel, the inlet boundary condition is set, such as the flow rate or velocity of the inlet, the outlet boundary condition is set, which is the pressure value or resistance, and the boundary condition of the blood vessel wall is usually the no-slip wall condition, that is, the blood flow moves along the blood vessel wall, and the density and viscosity of the blood are considered. The density of blood is usually 1060 kg / m 3, viscosity is usually described using models such as Carreau-Yasuda model, numerical solution is carried out using computational fluid dynamics (CFD) software such as ANSYS Fluent, COMSOL Multiphysics, etc. Set the geometry, boundary conditions and fluid properties of the model in the software, select appropriate meshing and solver parameters for simulation, get the blood flow velocity, pressure distribution, etc. Compare the simulation results with the experimental data to verify the accuracy of the model. Integrate the coronary artery blood flow model with the previously generated coronary artery spatial model and coronary artery network model to generate a coronary artery integrated model. This can be achieved by spatial coordinate alignment and fusion of data from the three models. The specific spatial alignment process is to extract some feature points or feature structures from each model, such as key vessel bifurcation points, vessel wall features, etc. Match at these feature points to establish the correspondence between different models. According to the results of feature matching, perform spatial transformation to align the coordinate systems of different models, involving rotation, translation and scaling transformations, such as using point-by-point matching algorithm, least squares registration and nonlinear registration for spatial transformation. By combining the aligned coronary artery blood flow model, coronary artery spatial model and coronary artery network model, including mapping blood flow data to the geometry of the spatial model, mapping velocity, pressure, etc. Information in the blood flow model to the inside of the coronary artery spatial model, by interpolating the results of the flow model to the grid of the spatial model, ensure that the integrated model is consistent in geometry and flow characteristics. Verify the integrated model, such as comparing with experimental data or clinical observation. The integrated model will include the geometry of the coronary artery, the structure of the vessel network and the blood flow information. Based on the coronary artery integrated model, perform coronary artery anomaly analysis. Computer-aided diagnosis algorithms, machine learning models, etc. Methods can be used for anomaly detection and quantitative analysis of coronary arteries. This can identify high abnormality sites and low abnormality sites and generate corresponding deep exploration data and shallow exploration data. These data can provide quantitative indicators about coronary artery abnormalities, such as blood flow velocity abnormalities, stenosis degree, etc.

[0032] Step S4: coronary artery model reconstruction of the coronary artery integrated model through high abnormality site deep exploration data and low abnormality site shallow exploration data, generate coronary artery lesion model; virtual surgery effect prediction is carried out on the coronary artery lesion model to construct the corresponding implementation plan template.

[0033] In the embodiments of the present application, the high abnormal site deep exploration data and the low abnormal site shallow exploration data generated in step S3 are used to reconstruct the coronary artery model of the integrated model. This can be achieved by registering and fusing the morphological information of the abnormal site with the integrated model. The registration and fusion process can use image registration algorithms, three-dimensional reconstruction techniques and other methods to add specific lesion details of the abnormal site to the integrated model to generate a coronary artery lesion model. Based on the coronary artery lesion model, virtual surgery effect prediction is performed. This can use computer-aided surgery planning software, simulation platforms and other tools to simulate and predict the effect of different surgical operations on the coronary artery lesion. By adjusting the surgical plan and simulating the surgical operation, the blood flow, vessel patency and possible side effects after surgery can be predicted. This helps to develop a corresponding implementation plan template to provide guidance and reference for real surgery.

[0034] Preferably, step S1 comprises the following steps:

[0035] Step S11: Obtain the coronary artery scan image of the patient;

[0036] Step S12: Perform image denoising on the patient's coronary artery image to generate a coronary artery denoised image; perform image contrast enhancement on the coronary artery denoised image to generate a coronary artery enhanced image;

[0037] Step S13: Perform image blood vessel region segmentation on the coronary artery enhanced image to generate a coronary artery blood vessel region segmentation image; perform image binarization on the coronary artery blood vessel region segmentation image to generate a coronary artery blood vessel region binarization image;

[0038] Step S14: Perform three-dimensional coronary artery spatial structure construction based on the coronary artery blood vessel region binarization image to generate a three-dimensional coronary artery spatial model; perform vessel diameter analysis on the three-dimensional coronary artery spatial model to generate coronary artery vessel diameter data.

[0039] The application can reduce noise and interference in the image and improve the clarity and contrast of the image by denoising and contrast enhancement of the coronary artery image. This helps doctors more accurately observe and analyze the morphology and structure of the coronary artery. By segmenting the coronary artery enhanced image, the blood vessel region in the image can be distinguished from other tissue regions. This helps to extract the shape and contour information of the coronary artery, providing an accurate basis for subsequent analysis and measurement. Based on the coronary artery blood vessel region binary image, a three-dimensional coronary artery spatial structure can be constructed. By constructing a three-dimensional model, the three-dimensional structure, morphology and path of the coronary artery can be more comprehensively understood. This provides more information for subsequent blood vessel analysis and diagnosis. By analyzing the diameter of the three-dimensional coronary artery spatial model, the diameter information of the coronary artery blood vessel can be measured. The diameter of the blood vessel is one of the key indicators for evaluating the degree of coronary artery disease, which can provide important information such as blood vessel stenosis and lesion degree, helping doctors to diagnose and plan treatment.

[0040] In the embodiment of the application, the coronary artery image is denoised by using appropriate image denoising algorithms, such as filter-based methods, wavelet transform or non-local averaging, etc. The denoised image is subjected to contrast enhancement, which can use histogram equalization, adaptive histogram equalization or other enhancement algorithms. Using appropriate segmentation algorithms, such as threshold segmentation, watershed algorithm, region growing, etc., the blood vessel region of the coronary artery is segmented from the image. The blood vessel segmentation image is subjected to binaryzation operation, which divides the blood vessel region into foreground (blood vessel) and background (other tissues), generating a coronary artery blood vessel region binary image. Based on the coronary artery blood vessel region binary image, a three-dimensional coronary artery spatial model can be constructed using surface reconstruction, voxelization, etc. The three-dimensional coronary artery spatial model is subjected to blood vessel diameter analysis, which can obtain coronary artery blood vessel diameter data by measuring the cross-sectional diameter, length and curvature of the blood vessel, etc. The specific measurement method uses medical image software OsiriX, opens the medical image file of the coronary artery, which is usually in DICOM format, selects appropriate measurement tools in the software, such as line segment measurement tool or circular measurement tool, marks the two endpoints of the blood vessel or the edge of the blood vessel on the cross section of the coronary artery blood vessel, for diameter, usually uses the circular measurement tool, places the two points of the tool on the inner wall or edge of the blood vessel, the software will automatically calculate the diameter, for length, uses the line segment measurement tool to measure the length of the blood vessel, records the measured diameter, length, etc. Data can be saved as a report or exported as a data file.

[0041] Preferably, step S14 comprises the following steps:

[0042] Step S141: Vessel centerline extraction is performed on the coronary artery vessel region binary image to obtain a coronary artery vessel region centerline; and vessel region skeletonization processing is performed on the coronary artery vessel region binary image according to the coronary artery vessel region centerline to generate a coronary artery vessel skeleton image;

[0043] Step S142: Skeleton image pixel value change analysis is performed on the coronary artery vessel skeleton image to generate a vessel centerline direction pixel change value; and radial projection is performed on the coronary artery vessel skeleton image based on the vessel centerline direction pixel change value to generate coronary artery main vessel radial projection data;

[0044] Step S143: Vessel position confirmation is performed based on the coronary artery vessel skeleton image to obtain coronary artery vessel position data; and vessel tortuosity analysis is performed according to the coronary artery vessel position data and the coronary artery main vessel radial projection data to generate coronary artery vessel curvature data;

[0045] Step S144: Vessel stent detection is performed on the coronary artery vessel skeleton image using the coronary artery vessel curvature data to generate coronary artery vessel branch point position data; three-dimensional coronary artery spatial structure construction is performed based on the coronary artery vessel branch point position data and the coronary artery main vessel radial projection data to generate a three-dimensional coronary artery spatial model; and vessel diameter analysis is performed on the three-dimensional coronary artery spatial model to generate coronary artery vessel diameter data.

[0046] The present application can obtain the centerline and vessel skeleton image of the coronary artery vessel region by performing vessel centerline extraction and skeletonization processing on the coronary artery vessel region binary image. This helps to further analyze the morphology and structure of the vessel. By performing pixel value analysis and radial projection on the vessel skeleton image, the vessel centerline direction pixel change value and main vessel radial projection data can be obtained. These data help to measure the changes and morphological characteristics of the vessel and provide radial distribution information of the vessel. Based on the vessel skeleton image, the position of the coronary artery vessel can be confirmed, and vessel curvature analysis can be performed. Vessel curvature data can reveal the bending degree and morphological characteristics of the vessel, and plays an important role in evaluating the health status and lesions of the vessel. Using vessel curvature data to detect the vessel stent on the vessel skeleton image can locate the branch point position of the vessel. Based on the branch point position data and the main vessel radial projection data, a three-dimensional coronary artery spatial model can be constructed to further analyze the structure and connection mode of the coronary artery vessel. By performing vessel diameter analysis on the three-dimensional coronary artery spatial model, the diameter data of the coronary artery vessel can be obtained. These data are very important for evaluating the degree of vessel stenosis, calculating hemodynamic parameters, and developing treatment strategies.

[0047] In the embodiment of the present application, by extracting the center line of the coronary artery blood vessel region from the binary image of the coronary artery blood vessel region, the center line of the coronary artery blood vessel region can be extracted using image processing techniques such as edge detection, morphological operation, etc. Subsequently, the binary image is skeletonized according to the center line of the coronary artery blood vessel region to obtain a coronary artery blood vessel skeleton image. The pixel value change analysis of the coronary artery blood vessel skeleton image can be mainly achieved by calculating the change value of the pixel point along the direction of the blood vessel center line to obtain the pixel change value in the direction of the blood vessel center line, wherein the change value refers to the change of the diameter of the blood vessel along the direction of the blood vessel center line. The specific steps are as follows: extracting the center line of the coronary artery from the medical image data, for each point on the center line, calculating the blood vessel radius in the direction perpendicular to the center line, and by comparing the blood vessel radii of adjacent points, the diameter change of the blood vessel along the direction of the center line can be calculated. The calculation process can be expressed by mathematical method as follows: Wherein, ri+1 is the radius of the next point on the center line, and ri-1 is the radius of the previous point on the center line. In this way, the diameter change value of each point in the direction of the blood vessel center line can be obtained. Subsequently, the radial projection of the coronary artery blood vessel skeleton image can be performed using these change values to generate the radial projection data of the main coronary artery. Based on the coronary artery blood vessel skeleton image, the blood vessel position can be confirmed, and the coronary artery blood vessel position data can be obtained by using morphological operation and geometric shape analysis. According to the coronary artery blood vessel position data and the radial projection data of the main coronary artery, the curvature analysis of the blood vessel can be performed to calculate the curvature data of the coronary artery blood vessel. The specific curvature analysis of the blood vessel involves measuring and calculating the curvature of the blood vessel path, which can be achieved by using the coronary artery blood vessel position data and the radial projection data of the main blood vessel. For the radial projection data of the main blood vessel, the curvature can be calculated using mathematical method. A commonly used method is to use three-point method to calculate the curvature by using the positions of three adjacent points. From the curvature calculation, the curvature change of the blood vessel along the direction of the main blood vessel can be obtained. The bending degree can be defined as the curvature change per unit length. The following formula can be used to calculate the bending degree: Wherein, Δκ is the curvature change, ΔS is the unit length, and the tortuosity can tell us the degree of bending of the blood vessel near a certain point. Using the coronary artery vessel curvature data to detect the coronary artery vessel skeleton image, the image segmentation algorithm and morphological operation technology can be used to detect the stent of the blood vessel, and the coronary artery vessel branch point position data is obtained. Based on the coronary artery vessel branch point position data and the coronary artery main vessel radial projection data, the three-dimensional coronary artery spatial structure can be constructed, and the three-dimensional coronary artery spatial model is generated. The three-dimensional coronary artery spatial model is analyzed, and the diameter data of the coronary artery vessel can be calculated by using the measurement tool and algorithm. Specifically, in the medical image software, the diameter of the blood vessel can be measured directly on the image by using the straight line or circular measurement tool. By selecting the appropriate measurement tool in the medical image software, such as the straight line or circular measurement tool, a known length is selected as the size calibration on the image, and then the diameter of the blood vessel is measured by using the measurement tool. Or by using the automatic measurement algorithm, the image is preprocessed, such as edge detection, and then the diameter of the blood vessel is identified and measured by using the algorithm. The measured diameter data is recorded and analyzed as needed, such as calculating the average diameter, the maximum diameter, etc.

[0048] Preferably, step S2 comprises the following steps:

[0049] Step S21: acquiring the X-ray angiography image of the patient;

[0050] Step S22: image preprocessing is performed on the X-ray angiography image of the patient to generate a standard X-ray angiography image of the patient, wherein the image preprocessing includes image denoising, image brightness enhancement and image edge sharpening;

[0051] Step S23: according to the coronary artery vessel diameter data, the coronary artery vessel structure of the standard X-ray angiography image of the patient is constructed to generate a three-dimensional coronary artery vessel model;

[0052] Step S24: the three-dimensional coronary artery vessel model is analyzed to generate the coronary artery vessel wall thickness data.

[0053] The present application obtains the patient's X-ray angiogram image, which is the basis for obtaining the patient's coronary artery vascular structure information. Through the X-ray angiogram image, the position and shape of the blood vessels can be clearly displayed. The patient's X-ray angiogram image is preprocessed, including denoising, brightness enhancement and edge sharpening and other processing. These preprocessing operations can improve the quality and clarity of the image, making the subsequent analysis and processing steps more accurate and reliable. According to the coronary artery vascular diameter data, the coronary artery vascular structure is constructed, and a three-dimensional coronary artery vascular model is generated. Through this step, the two-dimensional blood vessel image can be converted into a three-dimensional blood vessel model, and the structure and morphology of the coronary artery can be more detailed and comprehensive. The three-dimensional coronary artery vascular model is analyzed for vascular wall thickness, and coronary artery vascular wall thickness data is generated. This step can provide detailed information about the coronary artery vascular wall, which helps to assess the health of the blood vessels and diagnose and monitor related diseases.

[0054] In the embodiment of the present application, the patient is examined by using X-ray angiography technology to obtain the vascular structure information of the coronary artery. This technology can clearly show the position and shape of the blood vessels by injecting contrast agent and using X-ray imaging. The obtained images are preprocessed to improve the image quality and clarity, facilitating subsequent analysis and processing. The image preprocessing includes the following operations: using a denoising algorithm to remove noise in the image to improve the clarity of the image. Adjust the brightness and contrast of the image to make the features of the blood vessels more obvious. Enhance the edge features of the image to make the blood vessel profile clearer. According to the coronary artery vessel diameter data, the standardized patient X-ray angiogram is converted into a three-dimensional coronary artery network model using computer image processing technology. This process involves steps such as blood vessel segmentation, blood vessel connection and establishment of network structure to reconstruct the entire coronary artery vascular network. Specifically, the patient X-ray angiogram is first segmented, and according to the gray difference between the blood vessels and the surrounding tissues, the blood vessels are separated from the background by setting a threshold, and the two-dimensional image is converted into three-dimensional voxel data, so that each voxel represents a small cube region in the image. According to the voxel data, the three-dimensional blood vessel model is reconstructed using the connection relationship of the voxels, and the commonly used algorithm includes the Marching Cubes algorithm, thereby converting the three-dimensional coronary artery network model. The generated three-dimensional coronary artery network model is analyzed for vessel wall thickness. By measuring the wall thickness of the blood vessels, the health status of the coronary arteries can be evaluated and relevant data can be obtained. These data can be used for the diagnosis and monitoring of coronary artery disease. The specific measurement process includes separating the blood vessels from the background using appropriate segmentation methods according to the blood vessels to be measured, using edge detection algorithms such as Canny edge detection to find the edges of the blood vessel walls, and calculating the distance from the centerline of the blood vessel for each point on the blood vessel wall. This distance is the wall thickness of the blood vessel. For the entire blood vessel segment, the average wall thickness of each point is calculated to obtain the average wall thickness of the blood vessel. The blood vessel can be divided into several segments, and the average wall thickness of each segment is calculated.

[0055] Preferably, step S23 comprises the following steps:

[0056] Step S231: divide the standard patient X-ray angiogram into surface and deep angiogram images, and divide the surface and deep angiogram images into overlapping and non-overlapping regions to generate angiogram overlapping region images and angiogram non-overlapping region images;

[0057] Step S232: perform initial blood vessel network connection on the angiogram non-overlapping region images according to the coronary artery vessel diameter data to obtain an initial blood vessel network image;

[0058] Step S233: using the initial blood vessel graph image to perform overlap region connection path prediction on the angiography overlap region image, to generate blood vessel overlap region connection path prediction data;

[0059] Step S234: based on the blood vessel overlap region connection path prediction data and the coronary artery blood vessel curvature data, performing blood vessel connection verification on the angiography overlap region image, to generate blood vessel connection verification result data; using the blood vessel connection verification result data to perform coronary artery blood vessel graph structure construction on the angiography overlap region image and the angiography non-overlap region image, to generate a three-dimensional coronary artery graph model.

[0060] The present application divides the standard patient X-ray angiography image into layers to obtain surface angiography images and deep angiography images. Then, these images are divided into overlap regions to generate angiography overlap region images and angiography non-overlap region images. This helps to decompose the angiography image into smaller regions, facilitating subsequent blood vessel connection analysis and path prediction. Using coronary artery blood vessel diameter data, the angiography non-overlap region image is connected to an initial blood vessel graph. The purpose of this step is to establish an initial blood vessel graph image, providing a basis for subsequent connection path prediction and verification. Using the initial blood vessel graph image, the angiography overlap region image is connected to a path prediction. By analyzing the morphology and structure of the blood vessels, the connection path of the blood vessels in the overlap region is predicted. This can infer the direction and connection method of the blood vessels in the overlap region, providing a basis for subsequent verification. Based on the blood vessel overlap region connection path prediction data and the coronary artery blood vessel curvature data, the angiography overlap region image is connected to a blood vessel connection verification. By verifying the predicted connection path, its accuracy and reasonableness are judged, to generate blood vessel connection verification result data. According to these verification result data, the angiography overlap region image and the angiography non-overlap region image are connected to a coronary artery blood vessel graph structure construction, to generate a three-dimensional coronary artery graph model. Such a model can provide a detailed description of the coronary artery graph structure, which is helpful for further analysis.

[0061] In the embodiment of the present application, the X-ray angiography image of the standard patient is preprocessed, including denoising, enhancement, etc. The preprocessed image is divided into a surface angiography image and a deep angiography image. The specific hierarchical division method uses the region growing method, that is, starting from a seed point (a feature point of the surface or deep blood vessel), the region growing method is used to divide adjacent pixels into the same category for image hierarchical division. The surface angiography image and the deep angiography image are divided into overlapping regions. According to the pixel value, edge detection and other methods, an angiography overlapping region image and an angiography non-overlapping region image are generated. According to the coronary artery vessel diameter data, the angiography non-overlapping region image is connected with the initial blood vessel network. Specifically, the coronary artery vessel diameter data is converted into corresponding spatial coordinates. For the non-overlapping blood vessel region, the blood vessels are connected according to the blood vessel diameter data to form a blood vessel network. The connectivity of the blood vessels is determined according to the diameter size, that is, the connection between the blood vessels with a diameter greater than a certain threshold is connected. Using image processing and analysis techniques such as binarization, morphological operations, etc., the initial blood vessel network is connected into an initial blood vessel network image. The initial blood vessel network image is used to predict the connection path of the overlapping region of the angiography overlapping region image. Using image segmentation, path planning and other algorithms, the angiography overlapping region image is analyzed to predict the blood vessel connection path and generate blood vessel overlapping region connection path prediction data. Specifically, the image of the blood vessel overlapping region is segmented to distinguish different blood vessels. For the connected blood vessel region, the region growing algorithm is used to segment different blood vessels. If the boundary between the blood vessels is clear, the Canny edge detection method is used to find the blood vessel boundary. The segmented blood vessel region is path planned to predict the connection path of the blood vessel. The shortest path algorithm such as Dijkstra algorithm, A* algorithm, etc. is used to search for the shortest path in the segmented blood vessel region. Based on the blood vessel overlapping region connection path prediction data and the coronary artery vessel curvature data, the blood vessel connection of the angiography overlapping region image is verified. Using blood vessel morphology analysis, curvature calculation and other methods, the accuracy of the predicted blood vessel connection path is verified, and blood vessel connection verification result data is generated. According to the blood vessel connection verification result data, the coronary artery blood vessel network structure is constructed based on the angiography overlapping region image and the angiography non-overlapping region image. Using three-dimensional modeling technology, the segmented two-dimensional image data is converted into three-dimensional voxel data. According to the voxel data, the three-dimensional reconstruction algorithm such as Marching Cubes algorithm is used to convert the voxel data into a three-dimensional blood vessel model. The generated three-dimensional blood vessel model is optimized and smoothed to make it more realistic and continuous. The verified blood vessel connection path and blood vessel network structure are reconstructed to generate a three-dimensional coronary artery network model.

[0062] Preferably, step S233 comprises the following steps:

[0063] Step S2331: the initial blood vessel graph image is used for blood vessel connection port segmentation of the angiography overlapping area image, to obtain overlapping area blood vessel connection port data; the overlapping area blood vessel connection port data is subjected to data set division, to generate a model training set and a model test set;

[0064] Step S2332: a support vector machine algorithm is used for model training of the model training set, to generate a blood vessel overlapping area connection path training model; the model test set is used for model testing of the blood vessel overlapping area connection path training model, to generate a blood vessel overlapping area connection path prediction model;

[0065] Step S2333: the overlapping area blood vessel connection port data is imported into the blood vessel overlapping area connection path prediction model for overlapping area blood vessel connection path prediction, to generate blood vessel overlapping area connection path prediction data.

[0066] The present application can accurately extract the blood vessel connection port data in the overlapping area by performing blood vessel connection port segmentation on the angiography overlapping area image. This provides an important input for subsequent path prediction. The overlapping area blood vessel connection port data is divided into a model training set and a model test set. A prediction model of the blood vessel overlapping area connection path can be constructed by performing model training on the training set based on a support vector machine algorithm. The overlapping area blood vessel connection port data can be imported into the trained blood vessel overlapping area connection path prediction model for prediction of the blood vessel overlapping area connection path. This prediction process can help determine the connection relationship of the blood vessel graph and generate corresponding blood vessel overlapping area connection path prediction data.

[0067] In the embodiment of the present application, the angiography overlapping area image is preprocessed by using an image processing algorithm to remove interference and noise. For the preprocessed image, a blood vessel connection port segmentation algorithm is applied to identify and extract the blood vessel connection port of the overlapping area. The extracted blood vessel connection port data is divided into a model training set and a model test set. This can be used for model training and evaluation. The data of the model training set is used as input, and a support vector machine algorithm is used for model training. The algorithm will learn the relationship between the blood vessel connection port data and the corresponding connection path. The performance and accuracy of the trained model are evaluated by predicting the model test set data. This can select the best model parameters and optimize the performance of the model. The blood vessel connection port data of the overlapping area is imported into the trained support vector machine model. The model will predict the blood vessel connection path of the overlapping area according to the input blood vessel connection port data, and generate blood vessel overlapping area connection path prediction data. The specific model construction includes preparing training set data and test set data, wherein the training set data includes feature data of the blood vessel overlapping area and corresponding connection path labels, and the test set data also includes feature data of the blood vessel overlapping area and corresponding connection path labels. The training set and the test set are divided into 70% model training set and 30% model test set. The kernel function of the SVM model is selected, such as linear kernel function, polynomial kernel function, Gaussian kernel function, etc. The selection of the kernel function should be considered according to the characteristics and nonlinearity of the data. In many machine learning libraries, a ready-made SVM model can be directly called. Specifically, in Python, the SVC (Support Vector Classifier) class in the sklearn.svm library can be used to build the model. The training set is used to train the model to learn the relationship between the blood vessel connection port data and the connection path. The fit method of the model is called and the training data is input for training. After training, the performance of the model needs to be evaluated and necessary tuning is performed. The test set is used to evaluate the prediction accuracy of the model. If the data volume allows, cross-validation can be performed to better evaluate the generalization ability of the model. According to the evaluation result, the parameters of the model are adjusted, such as the regularization parameter, the kernel function parameter, etc., to obtain better performance. The trained support vector machine model can be used to predict the connection path corresponding to new blood vessel connection port data. For new blood vessel connection port data, the predict method of the trained model is used for prediction, and the corresponding connection path data is generated according to the prediction result.

[0068] Preferably, step S3 comprises the following steps:

[0069] Step S31: blood dynamics flow simulation is performed according to the coronary artery wall thickness data and the coronary artery vessel diameter data, coronary artery blood dynamics flow simulation data is generated, and coronary artery vessel flow structure construction is performed based on the coronary artery blood dynamics flow simulation data, so as to generate a three-dimensional coronary artery blood flow model;

[0070] Step S32: three-dimensional model integration is performed on the three-dimensional coronary artery space model, the three-dimensional coronary artery network model and the three-dimensional coronary artery blood flow model, a coronary artery integrated model is generated, dynamic coronary angiography simulation is performed on the coronary artery integrated model, and a dynamic coronary angiography simulation video is generated;

[0071] Step S33: arterial blood flow condition analysis is performed on the dynamic coronary angiography simulation video, arterial blood flow feature data is generated, and coronary artery integrated model is subjected to coronary artery abnormality analysis based on the arterial blood flow feature data, so as to obtain coronary artery abnormality analysis data;

[0072] Step S34: the coronary artery abnormality analysis data is compared with a preset standard abnormality threshold value, when the coronary artery abnormality analysis data is greater than or equal to the preset standard abnormality threshold value, coronary artery site depth exploration is performed on the patient based on the coronary artery abnormality analysis data, so as to obtain high abnormality site depth exploration data, and when the coronary artery abnormality analysis data is less than the preset standard abnormality threshold value, low abnormality site shallow layer exploration data is generated.

[0073] The present application can generate coronary blood dynamics flow simulation data by simulating the flow of blood in the coronary artery and combining the arm thickness and diameter data of the coronary artery. This helps to understand the flow characteristics and patterns of blood in the coronary artery and provides basic data for subsequent steps. By integrating the three-dimensional coronary artery space model, the coronary artery network model and the blood flow model, a coronary artery integrated model can be generated. The specific integration process requires the data of the three-dimensional coronary artery space model, the coronary artery network model and the blood flow model. By aligning the coordinate systems of the three models, they are ensured to be in the same space. The data of the three models are fused, which usually involves combining the position, shape, size of the blood vessels with the dynamic information of the blood flow. The fused data is integrated into a complete coronary artery integrated model. According to the integrated data, a mathematical model or a calculation model is established to describe the overall structure and hemodynamic characteristics of the coronary artery. Using this integrated model, simulation and analysis can be performed, such as simulating the flow of blood in the coronary artery, analyzing blood flow velocity, blood pressure distribution and other information. Furthermore, using the model to perform dynamic coronary angiography simulation can generate simulation videos to provide doctors and researchers with intuitive observation and analysis of the flow of the coronary artery. By analyzing the simulation video, characteristic data about blood flow can be obtained. Further, using these characteristic data, coronary artery integrated model is analyzed for coronary artery abnormalities to obtain coronary artery abnormality analysis data. This helps to discover potential coronary artery abnormalities and provides a basis for subsequent processing and diagnosis. The coronary artery abnormality analysis data is compared with the set standard abnormal threshold value. If it is greater than or equal to the preset standard abnormal threshold value, further exploration of the coronary artery site can be performed to obtain high abnormal site depth exploration data. On the contrary, if the coronary artery abnormality analysis data is lower than the preset standard abnormal threshold value, low abnormal site shallow exploration data is generated. These data help to locate the coronary artery abnormalities and provide visual results to promote the decision-making process of clinical diagnosis and coronary artery processing.

[0074] As an example of the present application, reference is made to Figure 2 In this example, the step S3 includes:

[0075] Step S31: performing blood dynamics flow simulation according to the coronary artery wall thickness data and the coronary artery diameter data to generate coronary blood dynamics flow simulation data; and performing coronary artery blood vessel flow structure construction based on the coronary blood dynamics flow simulation data to generate a three-dimensional coronary blood flow model.

[0076] In the embodiments of the present application, the data of the coronary artery wall thickness and vessel diameter are collected. This can be obtained through non-invasive imaging techniques such as computed tomography (CT) or magnetic resonance imaging (MRI). The blood flow in the coronary artery is simulated using computational fluid dynamics (CFD) method. CFD simulation uses numerical methods and physical equations to simulate the flow behavior of blood in the blood vessels. Based on the arm thickness and diameter data of the coronary artery vessels, a geometric model can be established, and the flow behavior of blood is simulated as a mathematical equation. Using computer algorithms and numerical solution methods, the simulation data of blood flow in the coronary artery can be calculated. Using the data obtained by blood flow simulation, the structure of coronary artery blood flow is constructed. According to the simulation data, the velocity distribution, pressure distribution and other blood flow parameters of blood in the coronary artery can be determined. These parameters can be presented through visualization technology, and the blood flow structure of the coronary artery is visualized as a three-dimensional model. Based on the results of the structure construction of the coronary artery blood flow, a three-dimensional coronary artery blood flow model can be generated. This model can be used for subsequent steps such as model integration and coronary artery anomaly analysis.

[0077] Step S32: integrating the three-dimensional coronary artery space model, the three-dimensional coronary artery network model and the three-dimensional coronary artery blood flow model to generate a coronary artery integrated model; simulating dynamic coronary angiography on the coronary artery integrated model to generate a dynamic coronary angiography simulation video;

[0078] In the embodiments of the present application, the three-dimensional coronary artery space model, the three-dimensional coronary artery network model and the three-dimensional coronary artery blood flow model are integrated. This can be done through computer-aided design (CAD) software or three-dimensional model modeling software. The data of the three models are combined and aligned to ensure that they are in the same spatial coordinate system. The integrated coronary artery model is used to simulate dynamic coronary angiography. Coronary angiography is an interventional examination used to assess the degree of stenosis and blood flow in the coronary artery. In the simulation, the introduction of contrast agent and the observation of its flow in the coronary artery can be simulated. This can be simulated using computational fluid dynamics (CFD) method, considering the geometric shape of the blood vessels, the blood flow parameters and the transport behavior of the contrast agent. Based on the results of the coronary angiography simulation, a dynamic coronary angiography simulation video can be generated, which requires the use of professional visualization software and technology to present the dynamic changes in the simulation process in the form of a video. The video can show the blood flow in the coronary artery and the transmission path of the contrast agent, simulating the real coronary angiography process.

[0079] Step S33: analyzing the arterial blood flow condition based on the arterial blood flow characteristic data to generate coronary artery anomaly analysis data;

[0080] In the embodiments of the present application, the blood flow characteristic data is obtained by analyzing the simulated video of dynamic coronary angiography. This can involve calculating parameters such as blood flow velocity, blood flow pressure gradient, and vascular wall shear stress. Computational fluid dynamics (CFD) methods can be used to post-process and analyze the simulated video to obtain these data. CFD analysis is usually based on the equations of fluid mechanics and the boundary conditions of the coronary artery model. Based on the analysis of the simulated video of coronary angiography, the blood flow characteristic data is extracted and calculated, which requires the use of professional analysis software and algorithms to process the simulation results, so as to obtain parameters such as blood flow velocity, vascular resistance, and blood flow distribution. The coronary artery integration model is analyzed for coronary artery abnormalities using the arterial blood flow characteristic data. By combining blood flow data and coronary artery model, possible coronary artery abnormalities such as stenosis, obstruction or thrombosis can be detected and analyzed. This can be achieved by quantitatively analyzing the model and comparing the differences between the flow characteristic data and the normal reference range. According to the results of the coronary artery abnormality analysis, coronary artery abnormality analysis data is generated. These data can include information such as the degree of coronary artery stenosis, the combined hemodynamic impact, and the blood flow distribution in the abnormal area. According to the needs, the analysis results can be visually presented in the form of charts, reports or other forms.

[0081] Step S34: Compare the coronary artery abnormality analysis data with the preset standard abnormal threshold value. When the coronary artery abnormality analysis data is greater than or equal to the preset standard abnormal threshold value, the patient is subjected to a deep exploration of the coronary artery site based on the coronary artery abnormality analysis data, and high abnormal site depth exploration data is obtained. When the coronary artery abnormality analysis data is less than the preset standard abnormal threshold value, low abnormal site shallow exploration data is generated.

[0082] In the embodiments of the present application, the coronary artery abnormality analysis data is compared with the preset standard abnormal threshold value. These standard abnormal threshold values can be established according to clinical experience, research data or guidelines, and are used to judge the abnormality of the coronary artery. If the coronary artery abnormality analysis data is greater than or equal to the preset standard abnormal threshold value, it indicates that the patient has a high abnormality of the coronary artery. In this case, a deep exploration of the coronary artery site is needed. This can include using coronary angiography, computed tomography (CT), nuclear medicine imaging or other related technologies to further evaluate the abnormality of the coronary artery. The results can include detailed information such as the degree of coronary artery stenosis, the location and extent of branch vessel lesions, etc. If the coronary artery abnormality analysis data is less than the preset standard abnormal threshold value, it indicates that the patient has a low degree of coronary artery abnormality. In this case, a deep exploration of the coronary artery is usually not needed. Low abnormal site shallow exploration data can be generated, including basic coronary artery structure, blood flow distribution and normal range of coronary artery state.

[0083] Preferably, step S31 comprises the following steps:

[0084] Step S311: Based on the coronary artery wall thickness data and coronary artery diameter data, perform global external vessel feature screening on the three-dimensional coronary artery network model and the three-dimensional coronary artery spatial model to obtain global external vessel feature data;

[0085] Step S312: Perform virtual endoscopy based on global external vessel length data, global external vessel diameter data, and global external vessel tortuosity data to obtain global internal vessel feature data; set blood flow boundary conditions using global external vessel feature data and global internal vessel feature data to obtain vessel blood flow boundary condition data;

[0086] Step S313: Calculate the vascular velocity field using vascular blood flow boundary condition data to generate blood flow velocity field data; perform vascular pressure distribution analysis based on blood flow velocity field data and vascular blood flow boundary condition data to generate coronary artery hemodynamic flow simulation data, which includes blood flow rate simulation data and blood flow shear stress simulation data.

[0087] Step S314: Construct the coronary artery flow structure using blood flow simulation data and blood flow shear stress simulation data to generate a three-dimensional coronary artery blood flow model.

[0088] This invention obtains overall external structural information about the coronary artery system by filtering and extracting global external vascular feature data based on coronary artery wall thickness and diameter data. This feature data can be used for subsequent internal structural analysis and simulation. Virtual endoscopy is performed based on global external vascular length, diameter, and tortuosity data to obtain global internal vascular feature data. This step provides more detailed information about the internal structure of the coronary arteries, including lumen size and tortuosity. Using the global external and internal vascular feature data, vascular blood flow boundary conditions can be set. These boundary conditions are key parameters for blood flow simulation, enabling the simulation and analysis of blood flow within the coronary arteries. Blood flow velocity field calculations are performed using the vascular blood flow boundary condition data to generate blood flow velocity field data. Pressure distribution analysis is then performed using the blood flow velocity field data and vascular blood flow boundary condition data to generate coronary artery hemodynamic flow simulation data. This data provides quantitative and qualitative information about blood flow within the coronary arteries. Using the blood flow rate simulation data and blood flow shear stress simulation data, a three-dimensional coronary artery blood flow model can be constructed. This model can be used to further analyze coronary artery abnormalities, assess vascular lesions, and predict hemodynamic effects.

[0089] As an example of the present invention, reference is made to Figure 3 As shown, in this example, step S31 includes:

[0090] Step S311: Global extravascular feature screening is performed on the three-dimensional coronary vessel network model and the three-dimensional coronary vessel space model according to the coronary vessel wall thickness data and the coronary vessel diameter data, and global extravascular feature data is obtained;

[0091] In the embodiments of the present application, the vessel wall thickness data and the vessel diameter data of the coronary artery are collected. These data can be obtained by measurement means, such as medical imaging technology (e.g., CT or MRI). The collected vessel data is used to establish a three-dimensional coronary vessel network model and a three-dimensional coronary vessel space model. This can be done by computer-aided design and modeling software. A suitable feature screening algorithm is selected, and the vessel wall thickness data and the vessel diameter data are used as input to screen the vessels in the three-dimensional coronary vessel network model and the three-dimensional coronary vessel space model. The specific feature screening algorithm needs to consider the following criteria: relevance: select the features most relevant to the structure and characteristics of the vessels, for example, the vessel wall thickness and the diameter are related to the type, size, shape, etc. of the vessels; interpretability: consider the interpretability and explainability of the final application, and select features with biological significance; predictability: select features that can well predict the target (here, the structure, shape, etc. of the vessels). Common feature screening algorithms include threshold segmentation, morphological operation, domain analysis, etc. The feature data of the vessels, such as the vessel length, the vessel curvature, the vessel branching condition, etc. are extracted and recorded according to the feature screening algorithm. At the same time, the extracted feature data is processed and normalized for subsequent use. The extracted and processed global extravascular feature data is saved and output. These data can be used for subsequent internal structure analysis, blood flow simulation, etc.

[0092] Step S312: Virtual endoscopy is performed based on the global extravascular length data, the global extravascular diameter data, and the global extravascular curvature data, and global intravascular feature data is obtained; blood flow boundary condition data is obtained by setting the blood flow boundary conditions based on the global extravascular feature data and the global intravascular feature data;

[0093] In the embodiments of the present application, the process of virtual endoscopy is simulated based on the global extravascular length data, the global extravascular diameter data, and the global extravascular tortuosity data. This can be achieved through computer simulation and image processing techniques. The specific steps include: establishing a virtual endoscope model based on the global extravascular data, and aligning it with the global extravascular data. Based on the characteristics of the virtual endoscope and the geometry of the global extravascular, the endoscope path is planned to ensure that the endoscope can smoothly pass through the blood vessels. Along the endoscope path, endoscopic images are simulated. Realistic endoscopic images can be generated using ray tracing or other image synthesis techniques. Based on the endoscopic images generated by the virtual endoscopy, the feature data of the global intravascular is extracted. These feature data can include the change of the vessel diameter, the thickness of the vessel wall, the vessel texture, etc. The blood flow boundary conditions are set using the global extravascular feature data and the global intravascular feature data. This includes setting the blood flow velocity, the friction coefficient of the vessel wall, and other parameters during the simulation of blood flow movement, to simulate the real blood flow conditions. The determined blood flow boundary condition data is saved and output. These data can be used for subsequent blood flow simulation, blood flow analysis, etc.

[0094] Step S313: blood vessel flow velocity field calculation is performed through the blood vessel blood flow boundary condition data to generate blood flow velocity field data; based on the blood flow velocity field data and the blood vessel blood flow boundary condition data, blood vessel pressure distribution analysis is performed to generate coronary artery hemodynamic flow simulation data, wherein the coronary artery hemodynamic flow simulation data includes blood flow volume simulation data and blood flow shear stress simulation data;

[0095] In the embodiments of the present application, by using the blood flow boundary condition data, the flow velocity field of the blood vessel can be calculated using numerical simulation methods (such as computational fluid dynamics simulation). The specific steps include: establishing a mathematical model of blood flow motion, considering the geometric shape of the blood vessel, fluid flow equation, boundary conditions of the fluid, etc. The geometric shape of the blood vessel is discretized into a grid so that calculations can be performed at each grid point. The fluid flow equation is discretized and solved using numerical methods (such as finite element method, finite volume method, etc.), thereby obtaining the flow velocity field data of the blood vessel. The blood flow velocity field data and the blood flow boundary condition data are used to analyze the pressure distribution of the blood vessel. This can be done by substituting the blood flow velocity field data and the blood flow boundary condition data into the fluid mechanics equation and solving to obtain the pressure distribution within the blood vessel. The specific steps include: according to the theory of fluid mechanics, the motion equation of blood flow in the blood vessel is established. The blood flow boundary condition data is applied to the fluid mechanics equation to set the inlet boundary and outlet boundary conditions. The fluid mechanics equation is discretized and solved using numerical methods to obtain the pressure distribution data within the blood vessel. Based on the blood flow velocity field data and the blood vessel pressure distribution data, the blood flow simulation data of the coronary artery can be generated, including blood flow simulation data and blood flow shear stress simulation data. By integrating the velocity distribution on the cross section of the blood vessel, the flow distribution data of the blood flow at different positions can be obtained. Based on the blood flow velocity gradient and the blood viscosity, the shear stress distribution data of the blood flow in the blood vessel is calculated.

[0096] Step S314: coronary artery blood vessel flow structure construction is performed using the blood flow simulation data and the blood flow shear stress simulation data to generate a three-dimensional coronary artery blood flow model.

[0097] In the embodiments of the present application, the blood vessel geometry information of the coronary artery is obtained by using blood vessel imaging techniques such as CT scanning, MRI, etc. According to the blood flow distribution data and the blood flow shear stress data, the blood vessel geometry is reconstructed using computer-aided design and three-dimensional modeling software. This can be achieved by converting the geometric information inside and outside the blood vessel into a three-dimensional geometric model representation. According to the blood vessel geometry model, a blood vessel grid for numerical simulation is generated. The blood vessel model is discretized into small geometric units, such as finite element grids or finite difference grids. This can be achieved by using grid generation software and algorithms. Based on the blood flow rate simulation data and the blood flow shear stress simulation data, the blood vessel flow is simulated using numerical simulation methods. This can be achieved by using computational fluid dynamics methods such as finite element method, finite difference method, etc. to solve the fluid dynamics equations, simulating the blood flow in the coronary artery. According to the blood flow rate simulation data and the blood flow shear stress simulation data, the corresponding boundary conditions and initial conditions are set. Then, the numerical method for solving the fluid dynamics equations is used to simulate the flow in the blood vessel. This can be achieved by using numerical simulation software and algorithms. According to the numerical simulation results, the visualization results of the three-dimensional coronary artery blood flow model are generated. This can be achieved by using three-dimensional visualization software and tools to process and present the simulation data. The visualization results can provide an intuitive understanding and analysis of the blood flow in the coronary artery.

[0098] Preferably, step S33 comprises the following steps:

[0099] Step S331: Abnormal frame analysis is performed on the dynamic coronary angiography simulation video to obtain abnormal initial frame images and abnormal end frame images of the lesion; based on the abnormal initial frame images and the abnormal end frame images of the lesion, the lesion area is confirmed to obtain lesion area position data;

[0100] Step S332: According to the lesion area position data, the lesion type of the abnormal initial frame images and the abnormal end frame images of the lesion is divided to obtain lesion area type division data; based on the lesion area type division data, the lesion area position data is subjected to lesion area quantitative feature extraction to obtain lesion area blood vessel feature data;

[0101] Step S333: The lesion area position data is subjected to lesion area blood flow analysis by the coronary artery integration model to obtain arterial blood flow feature data; the severity analysis is performed by the lesion area blood vessel feature data and the arterial blood flow feature data to obtain coronary artery abnormality analysis data.

[0102] The present application can obtain abnormal initial frame images and abnormal end frame images of lesions by analyzing abnormal frames of dynamic coronary angiography simulation videos. These images can provide information about the temporal and spatial changes of coronary lesions. Based on the abnormal initial frame images and the abnormal end frame images of lesions, the location data of the lesion area can be determined. This can accurately locate the specific position of the coronary lesion. According to the location data of the lesion area, the lesion type classification of the abnormal initial frame images and the abnormal end frame images of lesions can be performed. This helps to classify different types of coronary lesions, such as plaques, stenosis, etc. By feature extraction of the lesion area type classification data, the blood vessel feature data of the lesion area can be obtained. These features can be used to describe the morphology, size, shape, etc. of the lesion. By blood flow analysis of the coronary artery integration model on the lesion area location data, the arterial blood flow feature data can be obtained. This helps to evaluate the influence of coronary lesions on hemodynamics. By comprehensively considering the blood vessel feature data of the lesion area and the arterial blood flow feature data, the severity analysis of coronary abnormalities can be performed. This can help doctors evaluate the degree of coronary lesions and the possible impact on patient health.

[0103] As an example of the present application, reference is made to Figure 4 In this example, the step S33 includes:

[0104] Step S331: Abnormal frame analysis is performed on the dynamic coronary angiography simulation video to obtain abnormal initial frame images and abnormal end frame images of lesions; based on the abnormal initial frame images and the abnormal end frame images of lesions, lesion area confirmation is performed to obtain lesion area location data;

[0105] In the embodiment of the present application, by obtaining the relevant video of the patient during coronary angiography, it can be a video recorded by medical equipment or a computer-generated video simulating dynamic coronary angiography. Abnormal frame detection is performed on the dynamic coronary angiography simulation video. This can include using computer vision and image processing techniques such as motion detection, edge detection, background modeling, etc. to detect abnormal frames in the video. According to the abnormal frame detection result, the initial frame image and the end frame image of the lesion abnormality are extracted from the dynamic coronary angiography simulation video. These frame images may show the characteristics of coronary lesions, such as blood flow obstruction, plaque formation, etc. Based on the abnormal frame images of lesions, image processing and analysis methods are used for lesion area confirmation. This can include using image segmentation algorithms, edge detection algorithms, etc. to determine the location of the lesion area. The location data of the lesion area is extracted from the lesion area confirmation result. This can include coordinate information, size information, shape information, etc. of the lesion area.

[0106] Step S332: According to the lesion area position data, the lesion abnormal initial frame image and the lesion abnormal end frame image are classified by lesion type to obtain lesion area type classification data; based on the lesion area type classification data, the lesion area position data is extracted for quantitative feature extraction of the lesion area to obtain blood vessel feature data of the lesion area;

[0107] In the embodiment of the present application, the lesion area position data is used to classify the lesion type of the lesion abnormal initial frame image and the lesion abnormal end frame image. This can be based on expert knowledge or available lesion recognition algorithms. For example, different lesion types such as stenosis, plaque, thrombus, etc. can be classified by judging the morphological features, density changes, hemodynamic features, etc. of the lesion area. Based on the lesion area type classification data, quantitative feature extraction is performed on the lesion area position data. This can include the following aspects: extracting the shape features of the lesion area, such as area, perimeter, aspect ratio, etc. By analyzing the pixel gray value of the lesion area, the intensity features of the lesion are extracted, such as average intensity, standard deviation, etc. Texture analysis methods are used to extract the texture features of the lesion area, such as gray level co-occurrence matrix, local binary pattern, etc. By analyzing the blood flow velocity, blood flow pressure, etc. of the lesion area, the flow features of the blood vessels are extracted. From the quantitative features of the lesion area, the blood vessel feature data of the lesion area is extracted. This can include various feature data of the lesion area, such as shape features, intensity features, texture features, hemodynamic features, etc.

[0108] Step S333: The lesion area position data is analyzed by the coronary artery integrated model to obtain arterial blood flow feature data; the severity analysis is performed by the lesion area blood vessel feature data and the arterial blood flow feature data to obtain coronary artery abnormality analysis data.

[0109] In the embodiment of the present application, a coronary artery integrated model is established, which simulates the hemodynamic characteristics of the coronary artery. The model can be realized based on computational fluid dynamics (CFD) method or other suitable numerical simulation techniques. The model needs to consider the following factors: the blood vessel geometry data obtained from the lesion area position data is used to construct the model of the blood vessel. The flow characteristics of the blood, such as flow velocity, pressure, etc. are simulated. Based on the established coronary artery integrated model, the lesion area position data is input into the model for simulation to obtain the blood flow situation of the lesion area. Through the simulation results, the arterial blood flow feature data can be obtained, including blood flow velocity, pressure gradient, resistance, etc. The lesion area blood vessel feature data and the arterial blood flow feature data are combined to analyze the severity of the coronary artery abnormality, which involves evaluating the degree of lesion, the degree of vascular stenosis and the size of blood flow resistance according to the features of the lesion area and the blood flow characteristics. The evaluation can be based on existing coronary artery disease diagnosis standards or empirical rules.

[0110] Preferably, step S4 comprises the following steps:

[0111] Step S41: coronary artery model reconstruction is performed on the coronary artery integrated model by using the high abnormal site deep exploration data and the low abnormal site shallow exploration data, to generate a coronary artery lesion model;

[0112] Step S42: virtual surgery simulation is performed on the coronary artery lesion model to obtain a virtual surgery scheme; the virtual surgery scheme is used to predict the effect of the coronary artery lesion model, thereby generating coronary artery effect prediction data; and based on the coronary artery effect prediction data, the coronary artery lesion model is used to construct a corresponding implementation plan template.

[0113] The present application reconstructs the coronary artery integrated model by using high abnormal site deep exploration data and low abnormal site shallow exploration data to generate a coronary artery lesion model. Deep exploration data is used to obtain deeper coronary artery structure information, and shallow exploration data is used to obtain more superficial coronary artery structure information. By integrating the data of both, the model of the coronary artery can be more accurately reconstructed. Virtual surgery simulation is performed on the coronary artery lesion model. By setting different surgery schemes, the effect of processing the coronary artery under different conditions is simulated. This can help doctors and researchers predict the treatment effect of different treatment methods on coronary artery lesions. Based on the virtual surgery scheme and the coronary artery lesion model, coronary artery effect prediction can be performed, and coronary artery effect prediction data can be obtained. These data can provide information about the possible treatment effect under different treatment schemes. Based on the coronary artery effect prediction data, a corresponding implementation plan template can be constructed. These templates can help doctors develop treatment schemes in actual surgery and provide guidance and reference to achieve better treatment effect.

[0114] In the embodiments of the present application, high abnormality site deep exploration data and low abnormality site shallow exploration data are collected, which can come from medical imaging such as computed tomography (CT) or magnetic resonance imaging (MRI). The collected data is preprocessed, including image denoising, contrast enhancement and other operations, to improve data quality and clarity. Using computer-aided reconstruction (Computer-Aided Reconstruction) and other technologies, high abnormality site deep exploration data and low abnormality site shallow exploration data are integrated to construct a coronary artery integrated model. Based on the coronary artery integrated model, coronary artery model reconstruction is performed to generate a coronary artery lesion model. This will provide an accurate three-dimensional model to reflect the patient's coronary artery lesion situation. The coronary artery lesion model is used for virtual surgery simulation. According to the specific case and treatment target, different surgical plans are set, such as angioplasty or stenting, etc. In the virtual surgery simulation, the operation process of different surgical plans is simulated, and the model is processed to simulate the effect and effect of the operation on the coronary artery lesion. The effect of the virtual surgery plan is evaluated, and the treatment effect under different surgical plans is predicted. This can be achieved by calculating the hemodynamic parameters in the model, the improvement of the lesion degree, etc. Based on the virtual surgery plan and the coronary artery effect prediction data, a corresponding implementation plan template is constructed. The template will include information such as the specific steps of the surgical plan, the required equipment and materials, the treatment target, etc. to help doctors formulate and execute the treatment plan in the actual operation process.

[0115] The beneficial effects of the present application are that by processing the patient's coronary artery scan images, a three-dimensional coronary artery spatial model of the patient can be established, and the blood vessel diameter analysis can be performed. This helps doctors understand the morphology, structure and blood vessel diameter of the patient's coronary artery. By processing the patient's X-ray angiography images, a three-dimensional coronary artery network model of the patient can be established, and the blood vessel wall thickness analysis can be performed. This helps doctors understand the network structure and blood vessel wall thickness of the patient's coronary artery. According to the coronary artery blood vessel wall thickness data and the coronary artery blood vessel diameter data, a three-dimensional coronary artery blood flow model can be constructed. This helps to simulate and analyze the blood flow in the patient's coronary artery. By integrating the three-dimensional coronary artery spatial model, the coronary artery network model and the coronary artery blood flow model, a coronary artery integrated model is generated. By performing abnormal analysis on the coronary artery integrated model, high abnormality site deep exploration data and low abnormality site shallow exploration data can be determined, thereby providing more accurate coronary artery lesion information. By using the high abnormality site deep exploration data and the low abnormality site shallow exploration data, the coronary artery integrated model is reconstructed to generate a coronary artery lesion model. Then, the coronary artery lesion model can be used for virtual surgery effect prediction to evaluate the effect of different treatment schemes and possible coronary artery lesion correction surgery schemes. Therefore, the present application combines the patient's coronary artery scan images and X-ray angiography images for multi-modal modeling, and performs abnormal analysis on the coronary artery, thereby improving the accuracy and reliability of the coronary artery model reconstruction.

[0116] The above description is only a specific embodiment of the present application, which enables those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to these embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for reconstructing a coronary artery model based on coronary angiography, characterized in that, Includes the following steps: Step S1: Acquire coronary artery scan images of the patient; construct a three-dimensional coronary artery spatial structure from the patient's coronary artery images to generate a three-dimensional coronary artery spatial model; perform vessel diameter analysis on the three-dimensional coronary artery spatial model to generate coronary artery vessel diameter data; Step S2: Acquire X-ray angiography images of the patient; construct the coronary artery network structure from the patient's X-ray angiography images to generate a three-dimensional coronary artery network model; perform vessel wall thickness analysis on the three-dimensional coronary artery network model to generate coronary artery vessel wall thickness data; Step S3: Construct the coronary artery flow structure based on coronary artery wall thickness and diameter data to generate a three-dimensional coronary artery blood flow model; integrate the three-dimensional coronary artery spatial model, the three-dimensional coronary artery vascular network model, and the three-dimensional coronary artery blood flow model to generate an integrated coronary artery model; perform coronary artery anomaly analysis on the integrated coronary artery model to generate in-depth exploration data for high-abnormality areas and superficial exploration data for low-abnormality areas; Step S3 includes the following steps: Step S31: Perform hemodynamic flow simulation based on coronary artery wall thickness data and coronary artery diameter data to generate coronary artery hemodynamic flow simulation data; construct the coronary artery flow structure based on the coronary artery hemodynamic flow simulation data to generate a three-dimensional coronary artery blood flow model; Step S32: Integrate the three-dimensional coronary artery spatial model, the three-dimensional coronary artery vascular model, and the three-dimensional coronary artery blood flow model into a three-dimensional model to generate an integrated coronary artery model; perform dynamic coronary angiography simulation on the integrated coronary artery model to generate a dynamic coronary angiography simulation video; Step S33: Analyze arterial blood flow in the dynamic coronary angiography simulation video to generate arterial blood flow characteristic data; perform coronary artery anomaly analysis on the integrated coronary artery model based on the arterial blood flow characteristic data to obtain coronary artery anomaly analysis data; Step S34: Compare the coronary artery abnormality analysis data with the preset standard abnormality threshold. When the coronary artery abnormality analysis data is greater than or equal to the preset standard abnormality threshold, the patient's coronary artery site is explored in depth based on the coronary artery abnormality analysis data to obtain the in-depth exploration data of the high abnormality site. When the coronary artery abnormality analysis data is less than the preset standard abnormality threshold, the shallow exploration data of the low abnormality site is generated. Step S4: Reconstruct the coronary artery model using in-depth exploration data of high-abnormality areas and superficial exploration data of low-abnormality areas to generate a coronary artery lesion model; predict the effect of virtual surgery on the coronary artery lesion model to construct a corresponding implementation plan template.

2. The method for reconstructing a coronary artery model based on coronary angiography according to claim 1, characterized in that, Step S1 includes the following steps: Step S11: Acquire coronary artery scan images of the patient; Step S12: Denoise the patient's coronary artery image to generate a denoised coronary artery image; enhance the contrast of the denoised coronary artery image to generate an enhanced coronary artery image; Step S13: Perform image vessel region segmentation on the enhanced coronary artery image to generate a segmented coronary artery vessel region image; perform image binarization on the segmented coronary artery vessel region image to generate a binarized coronary artery vessel region image; Step S14: Construct a three-dimensional coronary artery spatial structure based on the binarized image of the coronary artery region to generate a three-dimensional coronary artery spatial model; perform vessel diameter analysis on the three-dimensional coronary artery spatial model to generate coronary artery vessel diameter data.

3. The method for reconstructing a coronary artery model based on coronary angiography according to claim 2, characterized in that, Step S14 includes the following steps: Step S141: Extract the center line of the coronary artery region from the binarized image of the coronary artery region to obtain the center line of the coronary artery region; perform vascular skeletonization processing on the binarized image of the coronary artery region based on the center line of the coronary artery region to generate a coronary artery skeleton image. Step S142: Analyze the pixel value changes of the coronary artery skeleton image to generate pixel change values ​​in the direction of the vessel centerline; perform radial projection on the coronary artery skeleton image based on the pixel change values ​​in the direction of the vessel centerline to generate radial projection data of the main coronary artery. Step S143: Confirm the location of the coronary artery based on the image of the coronary artery skeleton to obtain the location data of the coronary artery; perform vascular curvature analysis based on the location data of the coronary artery and the radial projection data of the main coronary artery to generate the curvature data of the coronary artery. Step S144: Detect vascular stents in the coronary artery skeleton image using coronary artery curvature data to generate coronary artery branch point location data; construct a three-dimensional coronary artery spatial structure based on the coronary artery branch point location data and the radial projection data of the main coronary artery to generate a three-dimensional coronary artery spatial model; analyze the vessel diameter of the three-dimensional coronary artery spatial model to generate coronary artery diameter data.

4. The method for reconstructing a coronary artery model based on coronary angiography according to claim 1, characterized in that, Step S2 includes the following steps: Step S21: Acquire X-ray angiography images of the patient; Step S22: Perform image preprocessing on the patient's X-ray angiography image to generate a standard patient X-ray angiography image, wherein the image preprocessing includes image denoising, image brightness enhancement and image edge sharpening; Step S23: Construct the coronary artery vascular network structure based on the coronary artery diameter data of standard patient X-ray angiography images to generate a three-dimensional coronary artery network model; Step S24: Perform vessel wall thickness analysis on the three-dimensional coronary artery network model to generate coronary artery vessel wall thickness data.

5. The method for reconstructing a coronary artery model based on coronary angiography according to claim 4, characterized in that, Step S23 includes the following steps: Step S231: Divide the standard patient X-ray angiography image into layers to obtain surface angiography image and deep angiography image; divide the surface angiography image and deep angiography image into overlapping areas to generate angiography overlapping area image and angiography non-overlapping area image. Step S232: Based on the coronary artery diameter data, perform initial vascular vesicle connection on the non-overlapping area image of the angiography to obtain an initial vascular vesicle image; Step S233: Use the initial vascular network image to predict the connection path of the overlapping area of ​​the angiography image, and generate vascular overlapping area connection path prediction data. Step S234: Based on the predicted connection path data of the overlapping region of blood vessels and the curvature data of coronary arteries, perform blood vessel connection verification on the overlapping region image of angiography to generate blood vessel connection verification result data; construct the coronary artery network structure on the overlapping region image and the non-overlapping region image of angiography using the blood vessel connection verification result data to generate a three-dimensional coronary artery network model.

6. The method for reconstructing a coronary artery model based on coronary angiography according to claim 5, characterized in that, Step S233 includes the following steps: Step S2331: Use the initial vascular network image to segment the overlapping area image of the angiography to obtain the overlapping area vascular connection data; divide the overlapping area vascular connection data into datasets to generate the model training set and the model test set. Step S2332: Train the model on the training set based on the support vector machine algorithm to generate a training model for the connection path of the overlapping blood vessel region; test the training model for the connection path of the overlapping blood vessel region using the test set to generate a prediction model for the connection path of the overlapping blood vessel region. Step S2333: Import the overlapping region vascular connection data into the vascular overlapping region connection path prediction model to predict the overlapping region vascular connection path and generate vascular overlapping region connection path prediction data.

7. The method for reconstructing a coronary artery model based on coronary angiography according to claim 1, characterized in that, Step S31 Includes the following steps: Step S311: Based on the coronary artery wall thickness data and coronary artery diameter data, perform global external vessel feature screening on the three-dimensional coronary artery network model and the three-dimensional coronary artery spatial model to obtain global external vessel feature data; Step S312: Perform virtual endoscopy based on global external vessel length data, global external vessel diameter data, and global external vessel tortuosity data to obtain global internal vessel feature data; set blood flow boundary conditions using global external vessel feature data and global internal vessel feature data to obtain vessel blood flow boundary condition data; Step S313: Calculate the vascular velocity field using vascular blood flow boundary condition data to generate blood flow velocity field data; perform vascular pressure distribution analysis based on blood flow velocity field data and vascular blood flow boundary condition data to generate coronary artery hemodynamic flow simulation data, which includes blood flow rate simulation data and blood flow shear stress simulation data. Step S314: Construct the coronary artery flow structure using blood flow simulation data and blood flow shear stress simulation data to generate a three-dimensional coronary artery blood flow model.

8. The method for reconstructing a coronary artery model based on coronary angiography according to claim 1, characterized in that, Step S33 includes the following steps: Step S331: Perform abnormal frame analysis on the dynamic coronary angiography simulation video to obtain the initial frame image and the end frame image of the abnormal lesion; confirm the lesion area based on the initial frame image and the end frame image of the abnormal lesion to obtain the lesion area location data. Step S332: Based on the lesion area location data, classify the lesion type into the initial frame image and the end frame image of the lesion abnormality to obtain lesion area type classification data; based on the lesion area type classification data, extract quantitative features of the lesion area from the lesion area location data to obtain vascular feature data of the lesion area. Step S333: Analyze the blood flow in the lesion area using the coronary artery integrated model to obtain arterial blood flow characteristic data; perform severity analysis using the vascular characteristic data and arterial blood flow characteristic data to obtain coronary artery abnormality analysis data.

9. The method for reconstructing a coronary artery model based on coronary angiography according to claim 1, characterized in that, Step S4 includes the following steps: Step S41: Reconstruct the coronary artery model using in-depth exploration data of high-abnormality areas and superficial exploration data of low-abnormality areas to generate a coronary artery lesion model; Step S42: Perform virtual surgery simulation on the coronary artery lesion model to obtain a virtual surgical plan; use the virtual surgical plan to predict the effect of the coronary artery lesion model, thereby generating coronary artery effect prediction data; based on the coronary artery effect prediction data, construct a corresponding implementation plan template for the coronary artery lesion model.

Images