Blood vessel three-dimensional model generation method and device, equipment and storage medium

Abstract

The invention belongs to the field of vascular interventional operations, and relates to a vascular three-dimensional model generation method, device and equipment and a storage medium, and the method comprises the steps: obtaining vascular three-dimensional data, angiography image data, a vascular tomography image and preset rendering effect information; performing registration on the blood vessel three-dimensional data and the angiography image data to obtain equipment position relation information; performing device position marking on the blood vessel tomography image based on the device position relation information to obtain an effective device marking image; performing three-dimensional reconstruction according to the effective device mark image and the blood vessel three-dimensional data to obtain an effective three-dimensional model; and rendering the effective three-dimensional model according to the preset rendering effect information to obtain a virtual blood vessel three-dimensional model. According to the method and the device, the virtual blood vessel three-dimensional model fused with the equipment position information can be constructed, so that the condition in the blood vessel can be conveniently, intuitively and accurately acquired.

Description

Technical Field

[0001] The present application relates to the technical field of vascular interventional surgery, and in particular to a method, device, computer equipment and storage medium for generating a three-dimensional vascular model. Background Art

[0002] Vascular interventional surgery is a treatment method that uses surgical instruments to treat the patient's intravascular diseases. During the treatment, the operator needs to remotely control the surgical instruments to enter the blood vessels to perform treatment on the diseased site.

[0003] Precise positioning and visualization of intravascular devices are key challenges in vascular interventional surgery. Traditional methods are difficult to accurately present the three-dimensional spatial position relationship of devices in complex vascular structures, which seriously affects the accuracy and safety of the surgery. Doctors lack intuitive and comprehensive information about the location of devices during the operation, which can easily cause the devices to be misplaced or damage the blood vessels. Especially in narrow and curved blood vessels, the precise positioning of devices is more difficult. At the same time, two-dimensional angiography images cannot fully reflect the three-dimensional vascular structure, making it difficult for doctors to accurately judge the relative position of the device and the vascular wall. In addition, there are technical barriers to information fusion between different imaging modalities, making it difficult to effectively combine vascular three-dimensional data with real-time angiography images. The existence of these problems makes it difficult for doctors to fully grasp the real-time position and movement trajectory of the equipment during the operation, increasing the risk of surgery. How to achieve accurate positioning and intuitive visualization of devices in complex three-dimensional vascular structures has become a key technical problem to improve the safety and effectiveness of vascular interventional surgery. Summary of the invention

[0004] The purpose of this application is to propose a method, device, computer equipment and storage medium for generating a three-dimensional model of a blood vessel, so as to solve the problem that it is difficult to accurately and effectively construct a three-dimensional model of a blood vessel at the position of a fusion device during surgery, so as to facilitate intuitive and accurate acquisition of the internal conditions of the blood vessel.

[0005] In order to solve the above technical problems, the present application provides a method for generating a three-dimensional blood vessel model, which adopts the following technical solution:

[0006] Acquire vascular three-dimensional data, angiography image data, vascular tomography images, and preset rendering effect information;

[0007] Registering the three-dimensional blood vessel data with the angiography image data to obtain equipment position relationship information;

[0008] Marking the equipment position on the blood vessel tomography image based on the equipment position relationship information to obtain a valid equipment marked image;

[0009] Performing three-dimensional reconstruction according to the effective equipment marking image and the three-dimensional data of the blood vessel to obtain an effective three-dimensional model;

[0010] The effective three-dimensional model is rendered according to the preset rendering effect information to obtain a virtual blood vessel three-dimensional model.

[0011] Furthermore, the step of obtaining the three-dimensional blood vessel data, the angiography image data, the blood vessel tomography image, and the preset rendering effect information specifically includes:

[0012] Obtain medical image information identification, patient tag information, and effect information identification;

[0013] extracting patient medical image data from a medical image database according to the medical image information identifier and the patient tag information;

[0014] Parsing the patient medical image data to obtain the blood vessel three-dimensional data, the angiography image data, and the blood vessel tomography image;

[0015] The preset rendering effect information is extracted from a visual database according to the effect information identifier.

[0016] Furthermore, the step of registering the three-dimensional blood vessel data and the angiography image data to obtain the equipment position relationship information specifically includes:

[0017] Acquire feature point information of the three-dimensional blood vessel data and the angiography image data to obtain three-dimensional blood vessel feature points and angiography image feature points;

[0018] Determine the correspondence between the three-dimensional blood vessel data and the angiography image data according to the three-dimensional blood vessel feature points and the angiography image feature points, and obtain feature point correspondence information;

[0019] Establishing a spatial position correspondence relationship between the blood vessel three-dimensional data and the angiography image data according to the feature point correspondence relationship information;

[0020] The three-dimensional blood vessel data and the angiography image data are registered based on the spatial position correspondence to obtain the equipment position relationship information.

[0021] Furthermore, the step of marking the equipment position of the vascular tomography image based on the equipment position relationship information to obtain a valid equipment marked image specifically includes:

[0022] Preprocessing the blood vessel tomography image to obtain an effective blood vessel tomography image;

[0023] Extracting features from the effective blood vessel tomographic scan image to obtain scan image features, and acquiring slice position information according to the scan image features;

[0024] The blood vessel tomography image is marked with equipment positions according to the slice position information and the equipment position relationship information to obtain the effective equipment marked image.

[0025] Furthermore, the step of marking the equipment position of the blood vessel tomography image according to the slice position information and the equipment position relationship information to obtain the effective equipment marked image specifically includes:

[0026] Determining a device position area in the blood vessel tomography image according to the slice position information and the device position relationship information;

[0027] Acquire a preset equipment template image, and calculate the image matching degree between the preset equipment template image and the equipment position area;

[0028] Obtaining a preset matching threshold, and determining whether the image matching degree is greater than or equal to the preset matching threshold;

[0029] If the image matching degree is greater than or equal to the preset matching threshold, the equipment position is marked according to the equipment position area, and the blood vessel tomography image after marking the equipment position is used as the effective equipment marked image.

[0030] Furthermore, the step of performing three-dimensional reconstruction based on the effective equipment marker image and the blood vessel three-dimensional data to obtain an effective three-dimensional model specifically includes:

[0031] Performing image segmentation on the effective equipment marked image to obtain an effective equipment area, and extracting contour features of the effective equipment area;

[0032] Determine pixel coordinates of the effective equipment area in the blood vessel tomography image according to the contour features, and determine the pixel coordinates as effective equipment position information;

[0033] Determine a first center line corresponding to the blood vessel tomography image and a second center line corresponding to the blood vessel three-dimensional data, and determine the three-dimensional coordinates corresponding to the effective equipment position information in the blood vessel three-dimensional data based on matching and alignment of the first center line and the second center line;

[0034] Based on the three-dimensional coordinates, three-dimensional reconstruction is performed according to the effective equipment position information and the three-dimensional data of the blood vessel to generate the effective three-dimensional blood vessel model.

[0035] Furthermore, the step of rendering the effective three-dimensional model according to the preset rendering effect information to obtain a virtual blood vessel three-dimensional model specifically includes:

[0036] Determining the blood vessel state according to the blood vessel tomography image to obtain blood vessel state information;

[0037] Filtering a corresponding state rendering effect from the preset rendering effect information according to the blood vessel state information;

[0038] The state position area corresponding to the blood vessel state information in the effective three-dimensional model is determined, and the state position area is rendered according to the state rendering effect, and the rendered effective three-dimensional model is used as the virtual blood vessel three-dimensional model.

[0039] In order to solve the above technical problems, the present application also provides a device for generating a three-dimensional model of a blood vessel, including:

[0040] A data acquisition module, used to acquire vascular three-dimensional data, angiography image data, vascular tomography images, and preset rendering effect information;

[0041] A data registration module, used for registering the three-dimensional blood vessel data and the angiography image data to obtain equipment position relationship information;

[0042] A position marking module, used for marking the equipment position of the blood vessel tomography image based on the equipment position relationship information to obtain a valid equipment marked image;

[0043] A model reconstruction module, used for performing three-dimensional reconstruction according to the effective equipment marking image and the blood vessel three-dimensional data to obtain a valid three-dimensional model;

[0044] The model rendering module is used to render the effective three-dimensional model according to the preset rendering effect information to obtain a virtual blood vessel three-dimensional model.

[0045] In order to solve the above technical problems, the embodiment of the present application further provides a computer device, which adopts the following technical solution:

[0046] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above-mentioned method for generating a three-dimensional blood vessel model when executing the computer program.

[0047] In order to solve the above technical problems, the embodiment of the present application further provides a computer-readable storage medium, which adopts the following technical solution:

[0048] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method for generating a three-dimensional blood vessel model are implemented.

[0049] Compared with the prior art, the embodiments of the present application have the following beneficial effects:

[0050] The present application obtains vascular three-dimensional data, angiography image data, vascular tomography image, and preset rendering effect information, and registers the vascular three-dimensional data and the angiography image data to obtain equipment position relationship information; based on the equipment position relationship information, the vascular tomography image is marked with equipment positions to obtain an effective equipment marking image; three-dimensional reconstruction is performed based on the effective equipment marking image and the vascular three-dimensional data to obtain an effective three-dimensional model; the effective three-dimensional model is rendered based on the preset rendering effect information to obtain a virtual vascular three-dimensional model. Thus, the construction of a virtual vascular three-dimensional model integrating equipment position information is effectively realized, so as to facilitate intuitive and accurate acquisition of the internal conditions of the blood vessels. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the scheme in the present application, a brief introduction is given below to the drawings required for use in the description of the embodiments of the present application. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0052] Figure 1 A flow chart of an embodiment of a method for generating a three-dimensional blood vessel model according to the present application;

[0053] Figure 2 yes Figure 1 A flowchart of a specific implementation of step S10;

[0054] Figure 3 yes Figure 1 A flowchart of a specific implementation of step S20;

[0055] Figure 4 yes Figure 1 A flowchart of a specific implementation of step S30;

[0056] Figure 5 yes Figure 4 A flowchart of a specific implementation of step S303;

[0057] Figure 6 yes Figure 1 A flowchart of a specific implementation of step S40;

[0058] Figure 7 yes Figure 1 A flowchart of a specific implementation of step S50;

[0059] Figure 8 is a schematic structural diagram of an embodiment of a device for generating a three-dimensional model of a blood vessel according to the present application;

[0060] Fig. 9 It is a structural diagram of an embodiment of a computer device according to the present application. DETAILED DESCRIPTION

[0061] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present application; the terms used in the specification of the application herein are only for the purpose of describing specific embodiments and are not intended to limit the present application; the terms "including" and "having" and any variations thereof in the specification and claims of the present application and the above-mentioned drawings are intended to cover non-exclusive inclusions. The terms "first", "second", etc. in the specification and claims of the present application or the above-mentioned drawings are used to distinguish different objects, not to describe a specific order.

[0062] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0063] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the accompanying drawings.

[0064] refer to Figure 1 , shows a flow chart of an embodiment of a method for generating a three-dimensional model of a blood vessel according to the present application. The method for generating a three-dimensional model of a blood vessel comprises the following steps:

[0065] Step S10, acquiring blood vessel three-dimensional data, angiography image data, blood vessel tomography image, and preset rendering effect information;

[0066] In this embodiment, the three-dimensional blood vessel data is the three-dimensional model data or image data of the blood vessel system obtained by the three-dimensional imaging technology. The three-dimensional imaging technology can provide detailed information of the blood vessel in three-dimensional space, including the course, branching, morphology, diameter, wall thickness, etc. of the blood vessel, as well as whether there are lesions such as stenosis, aneurysm, thrombosis, etc. The three-dimensional blood vessel data can be obtained by using a CT scanner to perform a whole-body or partial scan of the patient. During the scanning process, the X-ray rotates around the patient, and the detector receives the X-ray that passes through the human body, thereby obtaining the data of the vascular structure in the patient's body, and generating a three-dimensional image based on the data to obtain the three-dimensional blood vessel data. The angiographic image data is the vascular image information obtained by angiographic technology (a technology of injecting contrast agent into the blood vessel and then taking a vascular image by X-ray), which is used to effectively display the anatomical structure, blood flow state and lesions of the blood vessel, such as stenosis, occlusion, aneurysm, vascular malformation, etc. The vascular tomography image is a two-dimensional image information obtained based on OCT (optical coherence tomography). OCT technology is a non-invasive, high-resolution imaging technology that uses the principle of low-coherence light interference to obtain two-dimensional images of biological tissues by measuring the reflection and scattering of light in biological tissues. The preset rendering effect information is a preset image rendering effect, which is used to render the effective three-dimensional model with real image effects. The real image effects include lighting effects, materials and textures, colors and contrast, rendering quality and performance, and specific effects (preset rendering effects corresponding to different health conditions, such as the display effects of plaques, thrombi, stenosis and other lesions).

[0067] Step S20, registering the three-dimensional blood vessel data and the angiography image data to obtain equipment position relationship information;

[0068] In this embodiment, registration refers to matching the corresponding points of the same vascular anatomical structure in the three-dimensional blood vessel data and the angiography image data in spatial position to obtain the equipment position relationship information that effectively displays the relative position relationship between the equipment and the blood vessel. The equipment position relationship information includes spatial coordinate information: coordinate data of the equipment and the blood vessel in the image; direction information: the direction of the equipment relative to the blood vessel, such as the orientation and tilt angle of the equipment; distance information: the straight-line distance between the equipment and the blood vessel or the distance along a specific path; angle information: the relative angle relationship between the equipment and the blood vessel, such as the angle of blood vessel formation, the rotation angle of the equipment, etc. In this embodiment, registration is achieved by performing operations such as feature point extraction, feature point correspondence, spatial position correspondence, and image registration on the three-dimensional blood vessel data and the angiography image data.

[0069] Step S30, marking the equipment position of the blood vessel tomography image based on the equipment position relationship information to obtain a valid equipment marked image;

[0070] In this embodiment, the effective equipment marking image is a blood vessel tomography image marked with equipment position, and the equipment position marking is achieved by obtaining the slice position information from the blood vessel tomography image and then identifying the equipment position based on the slice position information and equipment relative position information.

[0071] In this embodiment, the equipment position can also be marked on the vascular ultrasound two-dimensional image based on the equipment position relationship information to obtain an effective equipment marking image. The vascular ultrasound two-dimensional image is image information obtained based on IVUS (intravascular ultrasound), wherein IVUS uses high-frequency ultrasonic imaging technology to transmit and receive ultrasonic signals to the blood vessel wall to obtain a fine image of the inside of the blood vessel to obtain a vascular ultrasound two-dimensional image.

[0072] Step S40, performing three-dimensional reconstruction according to the effective equipment marking image and the blood vessel three-dimensional data to obtain a valid three-dimensional model;

[0073] In this embodiment, three-dimensional reconstruction refers to the process of generating a three-dimensional model through computer technology using data sources such as images and three-dimensional data, wherein the three-dimensional reconstruction is implemented based on a three-dimensional reconstruction algorithm. In this embodiment, the three-dimensional reconstruction algorithm can use VRT (volume rendering technology). VRT creates a three-dimensional model image that is close to the real object by considering the density, color and light transmission properties of each voxel, so as to effectively realize three-dimensional reconstruction based on effective equipment marker images and vascular three-dimensional data.

[0074] Step S50, rendering the effective three-dimensional model according to the preset rendering effect information to obtain a virtual blood vessel three-dimensional model.

[0075] In this embodiment, a rendering operation is performed on the effective three-dimensional model by preset rendering effect information to obtain a virtual blood vessel three-dimensional model.

[0076] The present application obtains vascular three-dimensional data, angiography image data, vascular tomography image, and preset rendering effect information, and registers the vascular three-dimensional data and the angiography image data to obtain equipment position relationship information; based on the equipment position relationship information, the vascular tomography image is marked with equipment positions to obtain an effective equipment marking image; three-dimensional reconstruction is performed based on the effective equipment marking image and the vascular three-dimensional data to obtain an effective three-dimensional model; the effective three-dimensional model is rendered based on the preset rendering effect information to obtain a virtual vascular three-dimensional model. Thus, the construction of a virtual vascular three-dimensional model integrating equipment position information is effectively realized, so as to facilitate intuitive and accurate acquisition of the internal conditions of the blood vessels.

[0077] Continue to refer Figure 2 , shows a flowchart of a specific embodiment of step S10, comprising the following steps:

[0078] Step S101, obtaining medical image information identification, patient tag information, and effect information identification;

[0079] In this embodiment, the medical image information identifier is a unique identifier used to distinguish different medical imaging examinations or sequences, wherein the medical image information identifier may include information such as the examination type (such as CT, MRI, X-ray, etc.), examination date, time, and sequence number. The patient tag information is used to identify the patient, and in particular, may be patient coding information, including, for example, the patient's medical record number (MRN), ID number, or other unique identifier used within the hospital. The effect information identifier is a tag pointing to preset rendering effect information that describes a specific rendering effect, and the tag may be a string, a numeric code, or any information that can identify a preset rendering effect.

[0080] Step S102, extracting patient medical image data from a medical image database according to the medical image information identifier and the patient tag information;

[0081] In this embodiment, the medical image information identifier and the patient tag information are used as query conditions to perform a matching query in the medical image database, so as to effectively realize the extraction of the patient's medical image data. The database query can be realized by constructing an SQL query statement or other database query language, and then retrieving the image data according to the provided medical image information identifier and the patient tag information.

[0082] Step S103, parsing the patient medical image data to obtain the blood vessel three-dimensional data, the angiography image data, and the blood vessel tomography image;

[0083] In this embodiment, the vascular three-dimensional data and the angiography image data are information pre-stored in the medical image database and integrated into the patient medical image data, wherein each patient corresponds to a patient medical image data, and the patient medical image data is parsed to effectively extract the vascular three-dimensional data, the angiography image data, and the vascular tomography image from the patient medical image data.

[0084] Step S104: extracting the preset rendering effect information from a visual database according to the effect information identifier.

[0085] In this embodiment, the visual database is a database that stores a large amount of visual-related data such as visual images, graphics, rendering effects, etc., and the corresponding preset rendering effect information is extracted by performing a matching search in the visual database using the effect information identifier as a query condition.

[0086] This embodiment obtains medical image information identification, patient marking information, and effect information identification, extracts patient medical image data from a medical image database according to the medical image information identification and the patient marking information, and parses the patient medical image data, thereby effectively obtaining vascular three-dimensional data, angiography image data, and vascular tomography images corresponding to the patient marking information, and extracts the preset rendering effect information from a visual database according to the effect information identification to obtain the pre-set preset rendering effect information, thereby effectively realizing the accurate construction of a virtual vascular three-dimensional model.

[0087] Continue to refer Figure 3 , shows a flowchart of a specific embodiment of step S20, comprising the following steps:

[0088] S201, acquiring feature point information of the blood vessel three-dimensional data and the blood vessel angiography image data, and obtaining blood vessel three-dimensional feature points and angiography image feature points;

[0089] In this embodiment, the three-dimensional feature points of blood vessels include blood vessel bifurcation points, blood vessel bends, blood vessel diameter change points, and blood vessel wall features; the feature points of angiography images include blood vessel contours, stenosis or occlusion areas, plaques or calcification foci, and blood vessel branch points. Before obtaining feature point information, the three-dimensional blood vessel data and the angiography image data need to be preprocessed. The preprocessing includes image denoising, image smoothing, image enhancement, etc. The three-dimensional blood vessel data and the angiography image data can be feature extracted by a pre-trained feature extraction model to obtain the three-dimensional blood vessel feature points and the angiography image feature points. The pre-trained feature extraction model can adopt a three-dimensional convolutional neural network and a convolutional neural network fusion model. The three-dimensional convolutional neural network and the convolutional neural network fusion model are trained by sample medical images to generate a feature extraction model that accurately extracts feature point information.

[0090] S202, determining a correspondence between the three-dimensional blood vessel data and the angiography image data according to the three-dimensional blood vessel feature points and the angiography image feature points, and obtaining feature point correspondence information;

[0091] In this embodiment, feature point correspondence information is determined based on the feature matching algorithm according to the 3D feature points of the blood vessel and the feature points of the angiography image. The processing steps based on the feature matching algorithm include feature descriptor calculation: for each extracted feature point of the angiography image, the corresponding feature descriptor is calculated, wherein the feature descriptor is a vector used to describe the local image characteristics around the feature point. Commonly used feature descriptor algorithms include SIFT (Scale Invariant Feature Transform), SURF (Speeded Robust Features), ORB (Oriented FAST and Rotated BRIEF), etc. In this embodiment, the feature descriptor algorithm uses SIFT (Scale Invariant Feature Transform). Since the 3D feature points of the blood vessel are the feature points of the 3D image, the corresponding feature descriptors can be extracted by projecting the 3D feature points of the blood vessel onto a 2D plane and then using SIFT (Scale Invariant Feature Transform). Feature matching: Use a feature matching algorithm to match two sets of feature descriptors to find corresponding feature point pairs. Commonly used feature matching algorithms include Brute-Force Matcher, Fast Nearest Neighbor Search (FLANN Matcher), etc. In this embodiment, Fast Nearest Neighbor Search (FLANN Matcher) can be used for feature matching. During the feature matching process, a matching threshold can be set or a ratio test method can be used to screen high-quality matching point pairs and eliminate incorrect matches.

[0092] S203, establishing a spatial position correspondence relationship between the three-dimensional blood vessel data and the angiography image data according to the feature point correspondence relationship information;

[0093] In this embodiment, based on the feature point correspondence information, the spatial position correspondence between the vascular three-dimensional data and the angiography image is established by calculating the transformation matrix (such as affine transformation, rigid body transformation or more complex nonlinear transformation). The transformation matrix describes how to map points in the vascular three-dimensional data to corresponding positions in the angiography image data. In this embodiment, affine transformation and nonlinear transformation are used to calculate the transformation matrix. The transformation matrix is ​​used to find the method that minimizes the distance (or other metrics) between corresponding feature points between two data sources, which can be achieved through an iterative algorithm (such as gradient descent, Levenberg-Marquardt algorithm, etc.).

[0094] S204, performing image registration on the three-dimensional blood vessel data and the angiography image data based on the spatial position correspondence to obtain the equipment position relationship information.

[0095] In this embodiment, the three-dimensional blood vessel data and the angiographic image are registered by using a transformation matrix of the spatial position correspondence relationship, and the error (such as mean square error, mutual information, etc.) between the three-dimensional blood vessel data and the angiographic image data can be minimized by iteratively optimizing the parameters of the transformation matrix, thereby achieving image registration. When the registration is completed, the three-dimensional blood vessel data and the angiographic image will be optimally aligned in space, so that the positions of the blood vessel structure and the intracavitary device are consistent in the two, thereby obtaining device position relationship information that characterizes the relative position relationship between the device and the blood vessel.

[0096] This embodiment obtains the feature point information of the blood vessel three-dimensional data and the angiography image data to obtain the blood vessel three-dimensional feature points and the angiography image feature points; determines the correspondence between the blood vessel three-dimensional data and the angiography image data according to the blood vessel three-dimensional feature points and the angiography image feature points to obtain feature point correspondence information; establishes the spatial position correspondence between the blood vessel three-dimensional data and the angiography image data according to the feature point correspondence information; and performs image registration on the blood vessel three-dimensional data and the angiography image data based on the spatial position correspondence, thereby obtaining equipment position relationship information that effectively displays the position of the equipment in the three-dimensional blood vessel, so as to facilitate the subsequent accurate equipment position marking according to the equipment position relationship information.

[0097] Continue to refer Figure 4 , shows a flowchart of a specific embodiment of step S30, comprising the following steps:

[0098] Step S301, preprocessing the blood vessel tomography image to obtain a valid blood vessel tomography image;

[0099] In this embodiment, the preprocessing of the vascular tomography image is image segmentation, and the vascular tomography image is segmented by an image segmentation algorithm to segment the blood vessels from the background and other tissues to obtain an effective vascular tomography image. The image segmentation algorithm can adopt a model-based segmentation to segment the image by a mathematical model of the blood vessel (such as a cylinder, an ellipsoid, etc.) to accurately extract the vascular structure.

[0100] Step S302, extracting features from the effective blood vessel tomography image to obtain scan image features, and acquiring slice position information according to the scan image features;

[0101] In this embodiment, a pre-trained convolutional neural network (CNN) model can be used to perform feature extraction operations on the vascular tomography image. In this embodiment, the pre-trained convolutional neural network model can use a VGG model. The VGG model is trained by a sample vascular tomography image to obtain a pre-trained convolutional neural network model. The tomography position information is the image area corresponding to the intravascular device in the determined vascular tomography image. The spatial position coordinates of the device in the vascular cavity are determined by analyzing the shape features of the intravascular device in the scanned image features. Then, according to the intravascular region image and the spatial position coordinates of the device, it is determined whether the device is located in the intravascular region. If the device is located in the intravascular region, the region is marked as a valid device region, and then the valid device region is subjected to morphological processing such as corrosion and expansion operations to eliminate noise and interference in the image, and obtain an accurate image region corresponding to the intravascular device.

[0102] Step S303: marking the equipment position of the blood vessel tomography image according to the slice position information and the equipment position relationship information to obtain the effective equipment marking image.

[0103] In this embodiment, the effective equipment marking image refers to a vascular tomography image marked with the equipment position. The equipment position area corresponding to the equipment in the vascular tomography image is determined by using the tomography position information and the equipment position relationship information. Then, the equipment position area is matched with the preset equipment template image corresponding to the equipment to determine whether it is necessary to mark the equipment position area. When the equipment position area matches the preset equipment template image, the equipment position area is marked in the vascular tomography image to obtain a effective equipment marking image.

[0104] This embodiment obtains an effective vascular tomography image by preprocessing the vascular tomography image; extracts features from the effective vascular tomography image to obtain scan image features, and acquires slice position information based on the scan image features; and marks the equipment position on the vascular tomography image based on the slice position information and the equipment position relationship information, thereby obtaining an effective equipment marking image that effectively displays the equipment position in the vascular tomography image, so as to provide effective data support for the reconstruction of an effective three-dimensional model.

[0105] Continue to refer Figure 5 , shows a flowchart of a specific embodiment of step S303, including the following steps:

[0106] Step S3031, determining a device position area in the blood vessel tomography image according to the slice position information and the device position relationship information;

[0107] In this embodiment, the device position region is an image region of a physical device object in the vascular tomography image. The device position region is determined in the vascular tomography image by matching the tomography position information with the device position relationship information.

[0108] Step S3032, obtaining a preset equipment template image, and calculating the image matching degree between the preset equipment template image and the equipment position area;

[0109] In this embodiment, the preset equipment template image is a known and representative equipment image that is stored in advance. The template image covers various forms and angles that the equipment may appear in, so that it can be accurately matched. The matching degree between the preset equipment template image and the image of the equipment position area is calculated by an image matching algorithm. The image matching algorithm can calculate the similarity between the two images based on multiple features, such as color, texture, shape, etc. In this embodiment, the image matching algorithm adopts a template matching algorithm. The steps of calculating the matching degree by the image matching algorithm include: defining a similarity metric: selecting a suitable similarity metric standard, such as square difference matching, correlation matching, coefficient matching, etc.; sliding the template: sliding the preset equipment template image on the equipment position area according to a preset step length, and in each step, the preset equipment template image will cover a part of the equipment position area; calculating the similarity score: for each area covered by the preset equipment template image, using the selected similarity metric standard to calculate the similarity score between the template image and the area; calculating the average of the overall similarity scores of the equipment position area to obtain the average similarity score of the area, and the average similarity score of the area is the image matching degree.

[0110] Step S3033, obtaining a preset matching threshold, and determining whether the image matching degree is greater than or equal to the preset matching threshold;

[0111] In this embodiment, the preset matching threshold is a preset threshold used to determine whether the matching degree between the image of the equipment location area and the template image is high enough. The preset matching threshold and the image matching degree take corresponding measurement units to facilitate data comparison. The image matching degree can take a percentage value or a percentage value, and the preset matching threshold takes a percentage value or a percentage value accordingly. In this embodiment, the preset matching threshold is 90% or 90.

[0112] Step S3034: if the image matching degree is greater than or equal to the preset matching threshold, the equipment position is marked according to the equipment position area, and the blood vessel tomography image after marking the equipment position is used as the effective equipment marked image.

[0113] In this embodiment, the position of the equipment can be effectively marked by highlighting or other forms of visual prompts on the vascular tomography image.

[0114] Step S3035: if the image matching degree is less than the preset matching threshold, the equipment position area is divided into a non-equipment position.

[0115] In this embodiment, the equipment position area division may be performed in a marking form different from the above-mentioned equipment position marking, such as grayscale processing, so as to effectively distinguish the non-equipment position from the equipment position.

[0116] This embodiment determines the equipment position area in the vascular tomography image according to the slice position information and the equipment position relationship information; obtains a preset equipment template image, calculates the image matching degree between the preset equipment template image and the equipment position area; obtains a preset matching threshold, determines whether the image matching degree is greater than or equal to the preset matching threshold; if the image matching degree is greater than or equal to the preset matching threshold, marks the equipment position according to the equipment position area, and uses the vascular tomography image after marking the equipment position as the effective equipment marking image; if the image matching degree is less than the preset matching threshold, the equipment position area is divided into a non-equipment position. This effectively realizes accurate marking of the equipment position in the vascular tomography image to reduce the influence of image noise on the marking result.

[0117] Continue to refer Figure 6 , shows a flowchart of a specific embodiment of step S40, comprising the following steps:

[0118] Step S401, performing image segmentation on the effective equipment mark image to obtain an effective equipment area, and extracting contour features of the effective equipment area;

[0119] In this embodiment, the effective equipment mark image is segmented by an image segmentation algorithm. In this embodiment, the image segmentation algorithm can adopt a region-based segmentation algorithm, which starts from a known equipment position mark and adds adjacent pixels to the equipment region according to the similarity between pixels (such as color, texture, etc.) until no pixels that meet the conditions can be found, thereby effectively extracting the effective equipment region and its overall contour features.

[0120] Step S402, determining pixel coordinates of the effective equipment area in the blood vessel tomography image according to the contour features, and determining the pixel coordinates as effective equipment position information;

[0121] In this embodiment, the boundary points constituting the contour are extracted from the contour features by an edge detection algorithm, and the pixel coordinates corresponding to the contour features are determined according to the boundary points. In this embodiment, the contour boundary points can be extracted by a Sobel operator, which is a gradient-based edge detection algorithm that detects edges by calculating the horizontal and vertical gradients of each pixel in the image and finding the local maximum of the gradient.

[0122] Step S403, determining a first center line corresponding to the blood vessel tomography image and a second center line corresponding to the blood vessel three-dimensional data, and performing matching and alignment based on the first center line and the second center line to determine the three-dimensional coordinates corresponding to the effective equipment position information in the blood vessel three-dimensional data;

[0123] In this embodiment, the first center line is a center line corresponding to the blood vessel in the blood vessel tomography image, and the center line can be regarded as a curve connecting the two ends of the blood vessel and passing through the center of the blood vessel, and the second center line is a center line corresponding to the blood vessel in the three-dimensional model of the blood vessel three-dimensional data. The first center line can be extracted according to the effective blood vessel tomography image separated from the blood vessel tomography image, using a center line extraction algorithm (such as a minimum path technology), and the second center line can be calculated by an algorithm (such as a point cloud-based method) to calculate the center line of the blood vessel in the three-dimensional model of the blood vessel three-dimensional data. The step of matching and aligning the first center line and the second center line includes: extracting feature points (such as inflection points, branch points, etc.) on the first center line and the second center line respectively, and matching them using an algorithm (such as an ICP algorithm, a graph matching technology, etc.); based on the matching results of the feature points, calculating a transformation matrix (such as a rotation matrix, a translation vector, etc.), and transforming the first center line to a position aligned with the second center line. In this embodiment, the three-dimensional coordinates are determined by slicing the three-dimensional model reconstructed from the three-dimensional data of the blood vessel. The three-dimensional slice image corresponds to the blood vessel tomography image corresponding to the effective equipment position information. The three-dimensional coordinates corresponding to the effective equipment position information in the three-dimensional data of the blood vessel are obtained by mapping the pixel coordinates of the effective equipment position information to the three-dimensional slice image.

[0124] Step S404 , based on the three-dimensional coordinates, three-dimensional reconstruction is performed according to the effective equipment position information and the three-dimensional blood vessel data to generate the effective three-dimensional blood vessel model.

[0125] In this embodiment, three-dimensional reconstruction is performed using three-dimensional reconstruction software (such as mimics, 3D Slicer, etc.) using the three-dimensional slice image and three-dimensional blood vessel data mapped with pixel coordinates of the effective device position information. The reconstruction process includes image segmentation (separating the blood vessel from the background), surface reconstruction (generating a three-dimensional surface model of the blood vessel), and other steps. The effective three-dimensional blood vessel model is generated through the above three-dimensional reconstruction steps.

[0126] This embodiment obtains an effective equipment area by performing image segmentation on the effective equipment marking image, and extracts contour features of the effective equipment area; determines pixel coordinates of the effective equipment area in the blood vessel tomography image based on the contour features, and determines the pixel coordinates as effective equipment position information; determines a first center line corresponding to the blood vessel tomography image and a second center line corresponding to the blood vessel three-dimensional data, and determines the three-dimensional coordinates corresponding to the effective equipment position information in the blood vessel three-dimensional data by matching and aligning the first center line and the second center line; performs three-dimensional reconstruction based on the effective equipment position information and the blood vessel three-dimensional data based on the three-dimensional coordinates, thereby effectively generating an effective three-dimensional blood vessel model reconstructed based on the pixel coordinates of the effective equipment marking image and the three-dimensional coordinates of the blood vessel three-dimensional data, so as to ensure the accuracy of the three-dimensional blood vessel model.

[0127] Continue to refer Figure 7 , shows a flowchart of a specific embodiment of step S50, comprising the following steps:

[0128] Step S501, determining the blood vessel state according to the blood vessel tomography image to obtain blood vessel state information;

[0129] In this embodiment, the vascular state may include the morphology of the blood vessel and the lesions of the blood vessel. The morphological analysis of the above segmented blood vessel images including parameters such as the diameter, length, curvature, and branching of the blood vessel is performed to obtain the morphological information of the blood vessel; plaque detection is performed on the blood vessel images to observe whether there are plaques on the blood vessel wall, and the size, location, stability, etc. of the plaques are evaluated, and whether there is stenosis or occlusion in the blood vessel is evaluated, and the degree and location of the stenosis or occlusion are determined to obtain the lesion information of the blood vessel. The morphological information and lesion information of the blood vessel are used as the vascular state information to evaluate the health state of the blood vessel. Furthermore, in this embodiment, the vascular state may also include the function of the blood vessel, and the hemodynamic performance of the blood vessel is evaluated according to the measurement of parameters such as blood flow velocity, blood flow, and blood flow resistance, and the functional state of the vascular endothelium is evaluated using a specific inspection method (such as a vascular endothelial function detector), and the hemodynamic performance and the functional state of the vascular endothelium are integrated as the functional information of the blood vessel, and the morphological information, lesion information, and functional information of the blood vessel are used as more comprehensive vascular state information to perform a more effective vascular health state evaluation.

[0130] Step S502, selecting a corresponding state rendering effect from the preset rendering effect information according to the blood vessel state information;

[0131] In this embodiment, the blood vessel status information is used as a query condition, and condition matching is performed in the preset rendering effect information to filter out the corresponding status rendering effect.

[0132] Step S503, determining a state position area corresponding to the blood vessel state information in the effective three-dimensional model, rendering the state position area according to the state rendering effect, and using the rendered effective three-dimensional model as the virtual blood vessel three-dimensional model.

[0133] In this embodiment, the state position area is determined by mapping the vascular tomography image corresponding to the vascular state information to the effective three-dimensional model. The state rendering effect (such as plaque, stenosis, occlusion, etc.) is mapped to the state position area and the effect rendering is performed to obtain a virtual vascular three-dimensional model. In this embodiment, the area can be divided according to the category of the state position area, such as volume area (such as plaque volume), surface area (such as vascular wall of the stenosis section) or path area (such as vascular pathway of the occlusion section), and then the corresponding rendering is performed according to the divided category area to achieve fast rendering of the state position area.

[0134] This embodiment determines the state of the blood vessel according to the blood vessel tomography image to obtain blood vessel state information; extracts the preset rendering effect information from the database according to the blood vessel state information; determines the state position area corresponding to the blood vessel state information in the effective three-dimensional model, and renders the state position area according to the preset rendering effect information, and uses the rendered effective three-dimensional model as the virtual blood vessel three-dimensional model. This effectively realizes the construction of a virtual blood vessel three-dimensional model that displays the internal conditions of the real blood vessel, so as to intuitively and accurately display the internal conditions of the blood vessel.

[0135] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a non-volatile storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0136] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0137] Further references Figure 8 , as a response to the above Figure 1 The present application provides an embodiment of a device for generating a three-dimensional model of a blood vessel. Figure 1 Corresponding to the method embodiment shown, the device can be specifically applied to various electronic devices.

[0138] like Figure 8 As shown, the blood vessel three-dimensional model generating device 600 described in this embodiment includes: a data acquisition module 601, a data registration module 602, a position marking module 603, a model reconstruction module 604, and a model rendering module 605. Among them:

[0139] The data acquisition module 601 is used to acquire blood vessel three-dimensional data, angiography image data, blood vessel tomography images, and preset rendering effect information;

[0140] A data registration module 602 is used to register the three-dimensional blood vessel data and the angiography image data to obtain equipment position relationship information;

[0141] A position marking module 603 is used to mark the equipment position of the blood vessel tomography image based on the equipment position relationship information to obtain a valid equipment marked image;

[0142] A model reconstruction module 604, configured to perform three-dimensional reconstruction according to the effective equipment marking image and the blood vessel three-dimensional data to obtain a valid three-dimensional model;

[0143] The model rendering module 605 is used to render the effective three-dimensional model according to the preset rendering effect information to obtain a virtual blood vessel three-dimensional model.

[0144] This embodiment, by setting a device module corresponding to the method for generating a three-dimensional model of a blood vessel, can obtain three-dimensional blood vessel data, angiography image data, blood vessel tomography image, and preset rendering effect information through a data acquisition module 601 to obtain effective support data; the three-dimensional blood vessel data and the angiography image data are registered through a data registration module 602 to obtain equipment position relationship information representing the position relationship between the equipment and the blood vessel; the position marking module 603 marks the equipment position of the blood vessel tomography image based on the equipment position relationship information to obtain an effective equipment marking image that effectively displays the equipment position in the blood vessel tomography image; the model reconstruction module 604 performs three-dimensional reconstruction based on the effective equipment marking image and the three-dimensional blood vessel data to obtain an effective three-dimensional model that accurately displays the position of the equipment in the three-dimensional space; the model rendering module 605 renders the effective three-dimensional model according to the preset rendering effect information to obtain a virtual blood vessel three-dimensional model that displays the internal conditions of the real blood vessel. This embodiment effectively realizes the construction of a virtual blood vessel three-dimensional model that integrates the equipment position information through the above-mentioned device, so as to facilitate intuitive and accurate acquisition of the internal conditions of the blood vessel.

[0145] To solve the above technical problems, the present application also provides a computer device. Fig. 9 , Fig. 9 This is a basic structural block diagram of the computer device in this embodiment.

[0146] The computer device 7 includes a memory 71, a processor 72, and a network interface 73 that are interconnected through a system bus. It should be noted that the figure only shows a computer device 7 with components 71-73, but it should be understood that it is not required to implement all the components shown, and more or fewer components can be implemented instead. Among them, those skilled in the art can understand that the computer device here is a device that can automatically perform numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (Application Specific Integrated Circuit, ASIC), programmable gate arrays (Field-Programmable Gate Array, FPGA), digital processors (Digital Signal Processor, DSP), embedded devices, etc.

[0147] The computer device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The computer device may interact with a user through a keyboard, a mouse, a remote controller, a touch pad, or a voice control device.

[0148] The memory 71 includes at least one type of readable storage medium, and the readable storage medium includes flash memory, hard disk, multimedia card, card-type memory (for example, SD or DX memory, etc.), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, disk, optical disk, etc. In some embodiments, the memory 71 can be an internal storage unit of the computer device 7, such as a hard disk or memory of the computer device 7. In other embodiments, the memory 71 can also be an external storage device of the computer device 7, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), etc. equipped on the computer device 7. Of course, the memory 71 can also include both the internal storage unit of the computer device 7 and its external storage device. In this embodiment, the memory 71 is generally used to store the operating system and various application software installed on the computer device 7, such as the program code of the blood vessel three-dimensional model generation method, etc. In addition, the memory 71 can also be used to temporarily store various types of data that have been output or are to be output.

[0149] The processor 72 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chips in some embodiments. The processor 72 is generally used to control the overall operation of the computer device 7. In this embodiment, the processor 72 is used to run the program code stored in the memory 71 or process data, such as running the program code of the blood vessel three-dimensional model generation method.

[0150] The network interface 73 may include a wireless network interface or a wired network interface. The network interface 73 is generally used to establish a communication connection between the computer device 7 and other electronic devices.

[0151] This embodiment can obtain blood vessel three-dimensional data, angiography image data, blood vessel tomography image, and preset rendering effect information by setting up a computer device corresponding to the blood vessel three-dimensional model generation method; align the blood vessel three-dimensional data and the angiography image data to obtain equipment position relationship information; mark the equipment position of the blood vessel tomography image based on the equipment position relationship information to obtain an effective equipment marking image; perform three-dimensional reconstruction based on the effective equipment marking image and the blood vessel three-dimensional data to obtain an effective three-dimensional model; render the effective three-dimensional model based on the preset rendering effect information to obtain a virtual blood vessel three-dimensional model. In this way, the construction of a virtual blood vessel three-dimensional model integrating equipment position information is effectively realized, so as to facilitate intuitive and accurate acquisition of the internal conditions of the blood vessel.

[0152] The present application also provides another embodiment, namely, providing a computer-readable storage medium, wherein the computer-readable storage medium stores a vascular three-dimensional model generation program, and the vascular three-dimensional model generation program can be executed by at least one processor so that the at least one processor performs the steps of the vascular three-dimensional model generation method as described above.

[0153] This embodiment can obtain blood vessel three-dimensional data, angiography image data, blood vessel tomography image, and preset rendering effect information by setting a computer-readable storage medium corresponding to the blood vessel three-dimensional model generation method; align the blood vessel three-dimensional data and the angiography image data to obtain equipment position relationship information; mark the equipment position of the blood vessel tomography image based on the equipment position relationship information to obtain an effective equipment marking image; perform three-dimensional reconstruction based on the effective equipment marking image and the blood vessel three-dimensional data to obtain an effective three-dimensional model; render the effective three-dimensional model based on the preset rendering effect information to obtain a virtual blood vessel three-dimensional model. In this way, the construction of a virtual blood vessel three-dimensional model integrating equipment position information is effectively realized, so as to facilitate intuitive and accurate acquisition of the internal conditions of the blood vessel.

[0154] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in each embodiment of the present application.

[0155] Obviously, the embodiments described above are only some embodiments of the present application, rather than all embodiments. The preferred embodiments of the present application are given in the accompanying drawings, but they do not limit the patent scope of the present application. The present application can be implemented in many different forms. On the contrary, the purpose of providing these embodiments is to make the understanding of the disclosure of the present application more thorough and comprehensive. Although the present application is described in detail with reference to the aforementioned embodiments, for those skilled in the art, it is still possible to modify the technical solutions recorded in the aforementioned specific implementation methods, or to perform equivalent replacement of some of the technical features therein. Any equivalent structure made using the contents of the specification and drawings of this application, directly or indirectly used in other related technical fields, is similarly within the scope of patent protection of this application.

Claims

1. A method for generating a three-dimensional blood vessel model, characterized in that: The steps include: Acquire vascular three-dimensional data, angiography image data, vascular tomography images, and preset rendering effect information; Registering the three-dimensional blood vessel data with the angiography image data to obtain equipment position relationship information; Marking the equipment position on the blood vessel tomography image based on the equipment position relationship information to obtain a valid equipment marked image; Performing three-dimensional reconstruction according to the effective equipment marking image and the three-dimensional data of the blood vessel to obtain an effective three-dimensional model; The effective three-dimensional model is rendered according to the preset rendering effect information to obtain a virtual blood vessel three-dimensional model.

2. The method for generating a three-dimensional blood vessel model according to claim 1, characterized in that: The step of obtaining the three-dimensional blood vessel data, the angiography image data, the blood vessel tomography image, and the preset rendering effect information specifically includes: Obtain medical image information identification, patient tag information, and effect information identification; extracting patient medical image data from a medical image database according to the medical image information identifier and the patient tag information; Parsing the patient medical image data to obtain the blood vessel three-dimensional data, the angiography image data, and the blood vessel tomography image; The preset rendering effect information is extracted from a visual database according to the effect information identifier.

3. The method for generating a three-dimensional blood vessel model according to claim 1, characterized in that: The step of registering the three-dimensional blood vessel data and the angiography image data to obtain the equipment position relationship information specifically includes: Acquire feature point information of the three-dimensional blood vessel data and the angiography image data to obtain three-dimensional blood vessel feature points and angiography image feature points; Determine the correspondence between the three-dimensional blood vessel data and the angiography image data according to the three-dimensional blood vessel feature points and the angiography image feature points, and obtain feature point correspondence information; Establishing a spatial position correspondence relationship between the three-dimensional blood vessel data and the angiography image data according to the feature point correspondence relationship information; The three-dimensional blood vessel data and the angiography image data are registered based on the spatial position correspondence to obtain the equipment position relationship information.

4. The method for generating a three-dimensional blood vessel model according to claim 1, characterized in that: The step of marking the equipment position of the blood vessel tomography image based on the equipment position relationship information to obtain a valid equipment marked image specifically includes: Preprocessing the blood vessel tomography image to obtain an effective blood vessel tomography image; Extracting features from the effective blood vessel tomographic scan image to obtain scan image features, and acquiring slice position information according to the scan image features; The blood vessel tomography image is marked with equipment positions according to the slice position information and the equipment position relationship information to obtain the effective equipment marked image.

5. The method for generating a three-dimensional blood vessel model according to claim 4, characterized in that: The step of marking the equipment position of the blood vessel tomography image according to the slice position information and the equipment position relationship information to obtain the effective equipment marked image specifically includes: Determining a device position area in the blood vessel tomography image according to the slice position information and the device position relationship information; Acquire a preset equipment template image, and calculate the image matching degree between the preset equipment template image and the equipment position area; Obtaining a preset matching threshold, and determining whether the image matching degree is greater than or equal to the preset matching threshold; If the image matching degree is greater than or equal to the preset matching threshold, the equipment position is marked according to the equipment position area, and the blood vessel tomography image after marking the equipment position is used as the effective equipment marked image.

6. The method for generating a three-dimensional blood vessel model according to claim 1, characterized in that: The step of performing three-dimensional reconstruction according to the effective equipment marker image and the blood vessel three-dimensional data to obtain an effective three-dimensional model specifically includes: Performing image segmentation on the effective equipment marked image to obtain an effective equipment area, and extracting contour features of the effective equipment area; Determine pixel coordinates of the effective equipment area in the blood vessel tomography image according to the contour features, and determine the pixel coordinates as effective equipment position information; Determine a first center line corresponding to the blood vessel tomography image and a second center line corresponding to the blood vessel three-dimensional data, and determine the three-dimensional coordinates corresponding to the effective equipment position information in the blood vessel three-dimensional data based on matching and alignment of the first center line and the second center line; Based on the three-dimensional coordinates, three-dimensional reconstruction is performed according to the effective equipment position information and the three-dimensional data of the blood vessel to generate the effective three-dimensional blood vessel model.

7. The method for generating a three-dimensional blood vessel model according to claim 1, characterized in that: The step of rendering the effective three-dimensional model according to the preset rendering effect information to obtain a virtual blood vessel three-dimensional model specifically includes: Determining the blood vessel state according to the blood vessel tomography image to obtain blood vessel state information; Filtering a corresponding state rendering effect from the preset rendering effect information according to the blood vessel state information; The state position area corresponding to the blood vessel state information in the effective three-dimensional model is determined, and the state position area is rendered according to the state rendering effect, and the rendered effective three-dimensional model is used as the virtual blood vessel three-dimensional model.

8. A device for generating a three-dimensional model of a blood vessel, characterized in that: include: A data acquisition module, used to acquire vascular three-dimensional data, angiography image data, vascular tomography images, and preset rendering effect information; A data registration module, used for registering the three-dimensional blood vessel data and the angiography image data to obtain equipment position relationship information; A position marking module, used for marking the equipment position of the blood vessel tomography image based on the equipment position relationship information to obtain a valid equipment marked image; A model reconstruction module, used for performing three-dimensional reconstruction according to the effective equipment marking image and the three-dimensional data of the blood vessel to obtain a valid three-dimensional model; The model rendering module is used to render the effective three-dimensional model according to the preset rendering effect information to obtain a virtual blood vessel three-dimensional model.

9. A computer device, characterized in that: The method comprises a memory and a processor, wherein the memory stores computer-readable instructions, and the processor implements the steps of the method for generating a three-dimensional blood vessel model according to any one of claims 1 to 7 when executing the computer-readable instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-readable instructions, and when the computer-readable instructions are executed by a processor, the steps of the method for generating a three-dimensional blood vessel model according to any one of claims 1 to 7 are implemented.

Images