Intravascular stent anchoring degree evaluation method, device, equipment and storage medium

Abstract

The invention discloses an intravascular stent anchoring degree evaluation method, device and equipment and a storage medium, and the method comprises the steps: building a mapping relation between the radial supporting force of an intravascular stent and the radius of the intravascular stent, defining an anchoring force index used for evaluating the anchoring degree of the intravascular stent, processing the blood vessel image data, generating a three-dimensional blood vessel model, and obtaining the anchoring degree of the intravascular stent. The method comprises the following steps: establishing an anchoring force index, combining the anchoring force index, implementing an intravascular stent virtual implantation process on a computer, calculating and updating the anchoring force indexes of the intravascular stent at different positions in a blood vessel in real time according to the actual expansion degree of the intravascular stent, finally collecting clinical follow-up data after the intravascular stent is implanted, and combining the anchoring force index to extract key feature parameters. And training by using a machine learning model to obtain a trained intravascular stent anchoring degree evaluation model so as to evaluate the anchoring degree of the intravascular stent. According to the method, the anchoring force index is provided from the mechanical angle, and the anchoring degree of the intravascular stent can be evaluated more accurately.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and particularly to a method, device, equipment and storage medium for evaluating the anchoring degree of a vascular stent. Background Art

[0002] An intracranial aneurysm refers to an abnormal bulge in the wall of an intracranial artery, with an overall prevalence rate of approximately 3% - 5%. Once an intracranial aneurysm ruptures and causes subarachnoid hemorrhage, the fatality rate can reach 40%. Currently, the main interventional treatment method for medium and small aneurysms, especially ruptured aneurysms, is to embolize the aneurysm cavity with metal coils. For wide-neck aneurysms, large aneurysms or fusiform aneurysms, a vascular stent can achieve better treatment effects.

[0003] Existing technologies for vascular stent selection propose calculation methods for visualization parameters such as apposition, metal coverage, and pore density to assist doctors in evaluating the surgical effects of virtual stents. However, these parameters mainly start from a geometric perspective. Although they can reflect the adaptation between the vascular stent and the blood vessel wall to a certain extent, they cannot comprehensively reflect the anchoring degree of the vascular stent after implantation into the blood vessel. The anchoring degree of a vascular stent plays a crucial role in the success or failure of the surgery: if the selected vascular stent is too thin, the anchoring degree is low, the radial support force is insufficient, and it is prone to displacement under the impact of blood flow; if it is too thick, problems such as difficulty in opening may be encountered during implantation. Although apposition reflects the contact between the vascular stent and the blood vessel wall to a certain extent, it cannot completely replace the evaluation of mechanical properties. For example, two vascular stents with the same apposition may have significantly different radial support forces due to different design and material characteristics.

[0004] Therefore, although existing parameters such as apposition, metal coverage, and pore density can reflect the adaptation between the vascular stent and the blood vessel wall to a certain extent, these geometric parameters cannot comprehensively evaluate the anchoring degree of the stent after implantation. This leads to an increased risk of surgical failure due to overlooking key factors during the selection of a vascular stent, such as problems like vascular stent displacement or difficulty in opening. Therefore, there are obvious limitations in the existing technology for evaluating the anchoring degree of vascular stents. Summary of the Invention

[0005] Based on this, in view of the above technical problems, the present invention provides a method, device, equipment and storage medium for evaluating the anchoring degree of a vascular stent.

[0006] On the one hand, the present invention provides a method for evaluating the anchoring degree of a vascular stent, the method comprising: Establishing a mapping relationship between the radial support force of the vascular stent and the radius of the vascular stent; Define an anchoring force index for evaluating the anchoring degree of a vascular stent based on a mapping relationship; Process the vascular image data to generate a three-dimensional vascular model, and combine the anchoring force index to implement the virtual implantation process of the vascular stent on a computer. Calculate and update the anchoring force index of the vascular stent at different positions in the blood vessel in real time according to the actual deployment degree of the vascular stent; Collect the clinical follow-up data after the implantation of the vascular stent, combine the anchoring force index, extract key feature parameters, and train using a machine learning model to obtain a trained evaluation model for the anchoring degree of the vascular stent; Evaluate the anchoring degree of the vascular stent based on the trained evaluation model and the key feature parameters to be measured.

[0007] In one embodiment, the establishment of the mapping relationship is achieved at least through one of the following methods: Simulation method: Use computer simulation technology to perform solid modeling on the vascular stent, simulate the radial compression process of the vascular stent, and output the relationship curve between the radial support force and the radius of the vascular stent; Experimental method: Radially compress the vascular stent through a radial loading device, and use a force sensor to obtain the relationship curve between the radial support force and the radius of the vascular stent; Theoretical calculation: Based on materials science and mechanics principles, regard each stent wire of the vascular stent as a spring, analyze its force condition, and derive the functional relationship of the radial support force with respect to the radius of the vascular stent.

[0008] In one embodiment, the anchoring force index is calculated based on the radial support force of the vascular stent or its derived parameters.

[0009] In one embodiment, the key feature parameters include: parameters related to the anchoring force, as well as parameters related to the individual differences of patients and parameters related to the vascular state in the clinical follow-up data.

[0010] In one embodiment, the parameters related to the anchoring force include one or a combination of the following: High-anchoring area: The surface area of the vascular stent where the anchoring force index is higher than a certain threshold; High-anchoring area ratio: The ratio of the high-anchoring area to the total surface area of the vascular stent; Low-anchoring area: The surface area of the vascular stent where the anchoring force index is lower than a certain threshold; Low-anchoring area ratio: The ratio of the low-anchoring area to the total surface area of the vascular stent; Anchoring ratio: The ratio of the high-anchoring area to the low-anchoring area.

[0011] In one embodiment, the key feature parameter further includes: a derivative feature parameter obtained by further analysis and calculation based on the parameter related to the anchoring force.

[0012] In one embodiment, the derivative feature parameter includes one or a combination of the following: Ratio of extreme anchoring forces: the ratio of the maximum anchoring force to the minimum anchoring force in the entire vascular stent; Spatial entropy of anchoring force: The region of the vascular stent is evenly divided into a distal end, a mid-distal end, a lesion area, a mid-proximal end, and a proximal end according to length. The following formula is used to calculate the spatial entropy of the anchoring force: ; where is the ratio of the maximum anchoring force to the minimum anchoring force in the i-th region.

[0013] where is the ratio of the maximum anchoring force to the minimum anchoring force in the i-th region.

[0014] On the other hand, the present invention provides a device for evaluating the anchoring degree of a vascular stent. The device includes: A mapping relationship establishing module, configured to establish a mapping relationship between the radial supporting force of the vascular stent and the radius of the vascular stent; An anchoring force index defining module, configured to define an anchoring force index for evaluating the anchoring degree of the vascular stent based on the mapping relationship; A virtual implantation and calculation module, configured to process vascular image data to generate a three-dimensional vascular model, and in combination with the anchoring force index, implement the virtual implantation process of the vascular stent on a computer, and calculate and update the anchoring force index of the vascular stent at different positions in the blood vessel in real time according to the actual deployment degree of the vascular stent; A training module, configured to collect clinical follow-up data after the vascular stent is implanted, extract key feature parameters in combination with the anchoring force index, and train using a machine learning model to obtain a trained evaluation model for the anchoring degree of the vascular stent; An evaluation module, configured to evaluate the anchoring degree of the vascular stent based on the trained evaluation model and the key feature parameters to be measured In yet another aspect, the present invention provides a computer device, including a memory and a processor. When the processor executes the computer program, the following steps are implemented: Establish a mapping relationship between the radial supporting force of the vascular stent and the radius of the vascular stent; Define an anchoring force index for evaluating the anchoring degree of the vascular stent based on the mapping relationship; Process vascular image data to generate a three-dimensional vascular model, and in combination with the anchoring force index, implement the virtual implantation process of the vascular stent on a computer, and calculate and update the anchoring force index of the vascular stent at different positions in the blood vessel in real time according to the actual deployment degree of the vascular stent; Collect the clinical follow-up data after the implantation of the vascular stent, combine with the anchoring force index, extract the key characteristic parameters, and use a machine learning model for training to obtain a trained evaluation model for the anchoring degree of the vascular stent; Based on the trained evaluation model and the key characteristic parameters to be measured, evaluate the anchoring degree of the vascular stent.

[0015] On the other hand, the present invention provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Establish a mapping relationship between the radial supporting force of the vascular stent and the radius of the vascular stent; Define an anchoring force index for evaluating the anchoring degree of the vascular stent based on the mapping relationship; Process the vascular image data to generate a three-dimensional vascular model, and combine with the anchoring force index to implement the virtual implantation process of the vascular stent on a computer, and calculate and update the anchoring force index of the vascular stent at different positions in the blood vessel in real time according to the actual deployment degree of the vascular stent; Collect the clinical follow-up data after the implantation of the vascular stent, combine with the anchoring force index, extract the key characteristic parameters, and use a machine learning model for training to obtain a trained evaluation model for the anchoring degree of the vascular stent; Based on the trained evaluation model and the key characteristic parameters to be measured, evaluate the anchoring degree of the vascular stent.

[0016] Compared with the prior art, by comprehensively considering the relationship between the radial supporting force of the vascular stent and the radius of the vascular stent, the present invention defines an anchoring force index that can quantify the fixation firmness of the vascular stent. This new parameter proposed from the mechanical perspective can more accurately evaluate the anchoring degree of the vascular stent. Compared with only relying on geometric parameters (such as wall apposition, metal coverage, and pore density), the present invention not only helps to optimize the selection of vascular stents, but also improves the success rate of the operation and the long-term prognosis of patients. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic flow chart of the method for evaluating the anchoring degree of the vascular stent in an embodiment.

[0018] Figure 2 It is a relationship curve between the radial supporting force of the vascular stent and the radius of the vascular stent in an embodiment.

[0019] Figure 3 It is a schematic diagram of the partition of the vascular stent in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0021] As Figure 1 shown, a method for evaluating the anchoring degree of a vascular stent according to this embodiment includes the following steps: Step S100, establishing a mapping relationship between the radial support force of the vascular stent and the radius of the vascular stent.

[0022] In step S100, first, a mapping relationship between the radial support force of the vascular stent and the radius of the vascular stent needs to be established. This mapping relationship is the basis of the entire evaluation method because it directly reflects the internal connection between the mechanical properties of the vascular stent and its geometric shape. Specifically, this mapping relationship can be obtained through experiments, simulations or theoretical calculations, and finally presented as a relationship curve between the radial support force of the vascular stent and the radius of the vascular stent as Figure 2 shown.

[0023] Using the simulation method: In one embodiment, the present invention uses computer simulation technology to perform solid modeling on the vascular stent and numerically simulate its radial compression process, thereby outputting a relationship curve between the radial support force and the radius of the vascular stent. The advantage of this method is that it can quickly generate a large amount of data, which is convenient for subsequent analysis and verification, and at the same time avoids the high costs and complex operations that may be brought about by actual experiments.

[0024] Using the experimental method: In another embodiment, the present invention physically compresses the vascular stent through a radial loading device and uses a force sensor to record the change relationship between the radial support force and the radius of the vascular stent in real time. The advantage of this method is that the data is real and reliable, but due to the limitations of experimental conditions, problems such as insufficient sample size or poor experimental repeatability may be faced.

[0025] Using the theoretical calculation method: In the third embodiment, based on material science and mechanical principles, the present invention regards each stent wire of the vascular stent as a spring and analyzes its force condition. By deriving the functional relationship of the radial support force with respect to the radius of the vascular stent, it can provide theoretical support for subsequent evaluations. Specifically, each vascular stent wire can be regarded as a spring with equal pitch and equal diameter. By performing a detailed force analysis on each spring, a functional expression of the radial support force with respect to the radius of the spring is obtained. Subsequently, by superimposing the radial support forces of all stent wires, the functional relationship between the radial support force and the radius of the overall vascular stent can be obtained.

[0026] The mapping relationship curves obtained through the above three methods can not only intuitively reflect the mechanical behavior of the vascular stent, but also provide an important basis for further defining the anchoring force index.

[0027] Step S200: Define an anchoring force index for evaluating the anchoring degree of the vascular stent based on the mapping relationship.

[0028] In step S200, the definition of the anchoring force index is one of the core links of the entire evaluation method. The anchoring force index is calculated based on the radial support force of the vascular stent or its derived parameters, aiming to quantify the anchoring ability of the vascular stent at different positions. To ensure the comprehensiveness and accuracy of the evaluation, there are multiple possibilities for determining the anchoring force index. It can either directly select the magnitude of the radial support force as the anchoring force index, or select a dimensionless parameter (such as the normalized radial support force) derived from the radial support force as the anchoring force index, or select the radius of the vascular stent corresponding to the radial support force as the anchoring force index. Any parameter related to the radial support force or the radius of the vascular stent for evaluating the anchoring degree of the vascular stent or evaluating whether the diameter of the vascular stent is appropriate is within the protection scope of the present invention.

[0029] In practical applications, the definition of the anchoring force index needs to be flexibly adjusted according to specific clinical needs and research objectives. For example, in some cases, doctors may be more concerned about the overall anchoring ability of the vascular stent, so they will choose to use the average value of the radial support force as the anchoring force index; in other cases, if it is necessary to evaluate the performance of the vascular stent in a specific area, the local maximum or minimum radial support force can be selected as the anchoring force index. In addition, the anchoring force index can be combined with the deployment radius of the vascular stent for comprehensive evaluation to better reflect the actual anchoring effect of the vascular stent at different positions.

[0030] Generally speaking, the definition of the anchoring force index not only reflects the mechanical characteristics of the vascular stent, but also provides a key reference basis for subsequent virtual implantation and evaluation. By reasonably selecting and defining the anchoring force index, the accuracy and reliability of the evaluation results can be effectively improved.

[0031] Step S300: Process the vascular image data to generate a three-dimensional vascular model, and in combination with the anchoring force index, implement the virtual implantation process of the vascular stent on a computer, and calculate and update the anchoring force index of the vascular stent at different positions in the blood vessel in real time according to the actual deployment degree of the vascular stent.

[0032] In step S300, first read the vascular image data and reconstruct a three-dimensional vascular model based on this, then implement the virtual implantation of the vascular stent, and finally calculate and visualize the anchoring force index. Specifically, it includes the following sub-steps: S310, Image Reading and Vascular Reconstruction. First, it is necessary to obtain the vascular image data of the patient, which usually comes from DSA, CTA or MRA. These image data not only contain the geometric structure information of the blood vessels, but also reflect the state of the vessel wall and the location of the lesion area, so they are an important basis for subsequent analysis.

[0033] To extract the geometric information of the blood vessels from the image data, thresholding method, level set method or artificial intelligence segmentation model is usually used to segment the image sequence. These methods have their own advantages and disadvantages: the thresholding method is simple and easy to use, but is sensitive to noise; the level set method can handle complex boundary problems well, but has a high computational complexity; while the artificial intelligence segmentation model, with its powerful learning ability, can significantly improve the efficiency while ensuring the accuracy. After the segmentation is completed, the marching cubes algorithm is also needed to perform surface reconstruction on the segmentation result to generate a three-dimensional vascular model. This model can not only intuitively display the morphological characteristics of the blood vessels, but also provide a necessary geometric framework for subsequent virtual implantation.

[0034] S320, Virtual Implantation of Vascular Stent. First, it is necessary to calculate the coordinate sequence of the centerline points from the proximal opening to the distal opening of the blood vessel and the sequence of their radii along the line (i.e., the radius of the largest inscribed sphere). These information not only reflect the overall geometric shape of the blood vessels, but also provide an important reference basis for subsequent virtual implantation.

[0035] Next, based on the coordinate sequence of the centerline points, calculate the tangent unit vector, principal normal vector and binormal vector at each point of the centerline. These vectors together constitute the local coordinate system of the blood vessels, which can help us better understand the bending and torsion of the blood vessels. In addition, it is also necessary to calculate the radius of curvature, cross-sectional area and cross-sectional perimeter at each point of the centerline. These parameters are crucial for evaluating the deployment state and anchoring ability of the vascular stent.

[0036] After the above preparations are completed, the virtual implantation of the vascular stent can be started. Currently, the commonly used virtual implantation technologies include finite element simulation technology, virtual implantation technology based on active contour algorithm and virtual implantation technology based on geometric algorithm. These technologies have their own characteristics: the finite element simulation technology can accurately simulate the mechanical behavior of the vascular stent, but the computational cost is high; the virtual implantation technology based on active contour algorithm is known for its flexibility and can adapt to complex vascular morphologies; while the virtual implantation technology based on geometric algorithm, with its high efficiency, becomes an ideal choice for rapid evaluation.

[0037] S330. Calculation and visualization of the anchoring force index. First, it is necessary to calculate the anchoring force index at any position on the surface of the vascular stent according to the deployed radius of the vascular stent and in combination with the anchoring force index defined in step S200. This process not only involves a large amount of mathematical operations but also needs to consider the actual deployed state of the vascular stent and the influence of the surrounding environment.

[0038] For the convenience of users' understanding and analysis, the visualization of the anchoring force index usually adopts two methods: one is to directly represent it with a continuous gradient color bar according to the magnitude of the anchoring force index, and this method can intuitively display the spatial distribution of the anchoring force index; the other is to divide the anchoring force index into different intervals (such as "insufficient anchoring", "appropriate anchoring", "excessive anchoring") and use different colors to represent different intervals. The advantage of the latter is that it can help doctors quickly judge the anchoring effect of the vascular stent, but it depends on the experimental data provided by the vascular stent manufacturer to divide the critical values of the intervals.

[0039] In addition, considering the influence of the virtual compaction or dragging of the vascular stent on the anchoring force index, this step also realizes the dynamic update function of the anchoring force index. When the deployed radius of the vascular stent increases after virtual compaction, its anchoring force index will also change accordingly; similarly, when the deployed radius of the vascular stent decreases after virtual dragging, the anchoring force index will also be adjusted accordingly. This real-time update mechanism not only improves the accuracy of the evaluation but also provides a more flexible operation experience for doctors.

[0040] Finally, this step also includes the post-processing function of the anchoring force index distribution. For example, the high-anchoring area (i.e., the surface area of the vascular stent where the anchoring force index is higher than the established threshold), the high-anchoring area ratio (the ratio of the high-anchoring area to the total area of the vascular stent), the low-anchoring area (the surface area of the vascular stent where the anchoring force index is lower than the established threshold), the low-anchoring area ratio (the ratio of the low-anchoring area to the total area of the vascular stent), and the anchoring ratio (the ratio of the high-anchoring area to the low-anchoring area) can be calculated according to a certain threshold. These indicators can not only quantify the anchoring effect of the vascular stent but also provide important references for subsequent risk assessment.

[0041] Step S400. Collect the clinical follow-up data after the implantation of the vascular stent, extract key characteristic parameters in combination with the anchoring force index, and use a machine learning model for training to obtain a trained evaluation model for the anchoring degree of the vascular stent.

[0042] In step S400, in order to further improve the accuracy of the evaluation, it is necessary to collect the clinical follow-up data after the implantation of the vascular stent, extract key characteristic parameters in combination with the anchoring force index, and then use a machine learning model for training, and finally obtain a trained evaluation model for the anchoring degree of the vascular stent.

[0043] Among them, the extraction of key characteristic parameters is a crucial step in constructing an evaluation model, mainly including the following two categories: Parameters related to the anchoring force: These parameters directly reflect the anchoring ability of the vascular stent, including the area of the high-anchoring region, the proportion of the high-anchoring region, the area of the low-anchoring region, the proportion of the low-anchoring region, and the anchoring ratio. These indicators can not only quantify the overall anchoring effect of the vascular stent but also reveal its specific performance in different regions.

[0044] Parameters related to patient individual differences and vascular status in clinical follow-up data: To ensure the universality of the evaluation model, it is also necessary to collect at least more than 1000 cases of imaging follow-up data 6 - 24 months after vascular stent treatment. These data should cover various aspects of information such as the patient's age, vascular calcification degree (such as Agatston score), vascular stent type (such as cobalt-chromium alloy wire, nitinol alloy wire, etc.), the deployed length of the vascular stent, and vascular curvature. These parameters can not only reflect the impact of patient individual differences on the anchoring effect but also help identify potential risk factors that may lead to the migration of the vascular stent.

[0045] On the basis of extracting the above key characteristic parameters, in order to further improve the performance of the evaluation model, it is also necessary to introduce derivative characteristic parameters obtained by further analysis and calculation based on the parameters related to the anchoring force. These derivative parameters can reveal the anchoring ability of the vascular stent from different perspectives, thus providing richer input information for the evaluation model. For example: Ratio of extreme values of anchoring force: By calculating the ratio of the maximum anchoring force to the minimum anchoring force in the entire vascular stent, the uniformity of the anchoring ability of the vascular stent can be quantified. If the ratio of extreme values is large, it indicates that there are significant differences in the anchoring ability of the vascular stent in different regions, and there may be a risk of local insufficient anchoring.

[0046] Spatial entropy of anchoring force: By evenly dividing the regions of the vascular stent into distal, mid-distal, lesion area, mid-proximal, and proximal (as Figure 3 shown), and calculating the spatial entropy of the anchoring force using the following formula: ; Here, is the ratio of the maximum anchoring force to the minimum anchoring force in the i-th region. The spatial entropy of the anchoring force can reflect the spatial distribution characteristics of the anchoring ability of the vascular stent. The higher the entropy value, the more uneven the distribution of the anchoring ability. By introducing these derivative characteristic parameters, the anchoring ability of the vascular stent can be more comprehensively described, thus providing richer data support for subsequent model training.

[0047] After extracting the key feature parameters, the next step is to select a suitable machine learning model for training. Commonly used models include random forest, support vector machine, etc. These models have their own advantages and can be flexibly selected according to specific requirements. In addition, in order to optimize the performance of the model, an appropriate loss function (such as Focal Loss) also needs to be selected, and the model is tuned through methods such as cross-validation.

[0048] During the training process, the dataset is usually divided into a training set and a validation set in a ratio of 4:1. The training set is used to fit the model parameters, while the validation set is used to evaluate the generalization ability of the model. In this way, it can be ensured that the trained model not only performs well on the training data but also maintains a high prediction accuracy on new data.

[0049] Step S500: Evaluate the anchoring degree of the vascular stent based on the trained evaluation model and the key feature parameters to be measured.

[0050] In step S500, based on the trained evaluation model and the key feature parameters to be measured, the anchoring degree of the vascular stent can be evaluated. Specifically, using the trained evaluation model, with the feature parameters to be extracted as the input, the anchoring degree of the vascular stent is evaluated, and the probability of the vascular stent migrating is predicted. According to the prediction results, the migration risk can be divided into three levels: High risk: The migration probability is greater than 30%, indicating that the anchoring ability of the vascular stent is insufficient, there is a high migration risk, and corresponding intervention measures need to be taken.

[0051] Medium risk: The migration probability is between 10% and 30%, indicating that the anchoring ability of the vascular stent is acceptable, but still needs to be closely monitored.

[0052] Low risk: The migration probability is less than 10%, indicating that the anchoring ability of the vascular stent is strong and the migration risk is low.

[0053] In this way, not only can intuitive risk assessment results be provided for doctors, but also important references can be provided for formulating personalized treatment plans for patients.

[0054] It should be understood that although Figure 1 the steps in the flowchart in Figure 1At least a part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed and completed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0055] In one embodiment, the present invention provides a device for evaluating the anchoring degree of a vascular stent, including: a mapping relationship establishment module, an anchoring force index definition module, a virtual implantation and calculation module, a training module, and an evaluation module, where: The mapping relationship establishment module is used to establish the mapping relationship between the radial supporting force of the vascular stent and the radius of the vascular stent.

[0056] The anchoring force index definition module is used to define an anchoring force index for evaluating the anchoring degree of the vascular stent based on the mapping relationship.

[0057] The virtual implantation and calculation module is used to process the vascular image data to generate a three-dimensional vascular model, and in combination with the anchoring force index, implement the virtual implantation process of the vascular stent on a computer, and calculate and update the anchoring force index of the vascular stent at different positions in the blood vessel in real time according to the actual deployment degree of the vascular stent.

[0058] The training module is used to collect the clinical follow-up data after the vascular stent is implanted, extract key characteristic parameters in combination with the anchoring force index, and train using a machine learning model to obtain a trained evaluation model for the anchoring degree of the vascular stent.

[0059] The evaluation module is used to evaluate the anchoring degree of the vascular stent based on the trained evaluation model and the key characteristic parameters to be measured.

[0060] For the specific limitations on the device for evaluating the anchoring degree of the vascular stent, reference can be made to the limitations on the method for evaluating the anchoring degree of the vascular stent in the above text, which will not be elaborated here. Each module in the above device for evaluating the anchoring degree of the vascular stent can be implemented in whole or in part through software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the computer device in the form of hardware or be independent of it, or can be stored in the memory of the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to the above-mentioned modules.

[0061] In one embodiment, a computer device is provided. The computer device may be a terminal, which includes a processor, a memory, a network interface, a display screen, and an input device connected via a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, it implements a method for evaluating the anchoring degree of a vascular stent. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device may be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0062] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented: Step S100, establish a mapping relationship between the radial supporting force of the vascular stent and the radius of the vascular stent.

[0063] Step S200, define an anchoring force index for evaluating the anchoring degree of the vascular stent based on the mapping relationship.

[0064] Step S300, process the vascular image data to generate a three-dimensional vascular model, and in combination with the anchoring force index, implement the virtual implantation process of the vascular stent on a computer, and calculate and update the anchoring force index of the vascular stent at different positions in the blood vessel in real time according to the actual deployment degree of the vascular stent.

[0065] Step S400, collect the clinical follow-up data after the implantation of the vascular stent, extract key characteristic parameters in combination with the anchoring force index, and train using a machine learning model to obtain a trained evaluation model for the anchoring degree of the vascular stent.

[0066] Step S500, evaluate the anchoring degree of the vascular stent based on the trained evaluation model and the key characteristic parameters to be measured.

[0067] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the following steps are implemented: Step S100, establish a mapping relationship between the radial supporting force of the vascular stent and the radius of the vascular stent.

[0068] Step S200, define an anchoring force index for evaluating the anchoring degree of the vascular stent based on the mapping relationship.

[0069] Step S300: Process the vascular image data to generate a three-dimensional vascular model, and in combination with the anchoring force index, implement the virtual implantation process of the vascular stent on a computer, and calculate and update the anchoring force index of the vascular stent at different positions in the blood vessel in real time according to the actual deployment degree of the vascular stent.

[0070] Step S400: Collect the clinical follow-up data after the implantation of the vascular stent, extract key characteristic parameters in combination with the anchoring force index, and train using a machine learning model to obtain a trained evaluation model for the anchoring degree of the vascular stent.

[0071] Step S500: Evaluate the anchoring degree of the vascular stent based on the trained evaluation model and the key characteristic parameters to be measured.

[0072] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided by the present invention can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0073] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0074] The above-described embodiments merely represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the present invention patent shall be subject to the appended claims.

Claims

1. A method for evaluating the anchoring degree of a vascular stent, characterized in that, The method includes: Establishing a mapping relationship between the radial support force of the vascular stent and the radius of the vascular stent; Defining an anchoring force index for evaluating the anchoring degree of the vascular stent based on the mapping relationship; Processing the vascular image data to generate a three-dimensional vascular model, and combining with the anchoring force index, implementing the virtual implantation process of the vascular stent on a computer, and calculating and updating the anchoring force index of the vascular stent at different positions in the blood vessel in real time according to the actual deployment degree of the vascular stent; Collecting the clinical follow-up data after the implantation of the vascular stent, combining with the anchoring force index, extracting key characteristic parameters, and training using a machine learning model to obtain a trained evaluation model for the anchoring degree of the vascular stent; Evaluating the anchoring degree of the vascular stent based on the trained evaluation model and the key characteristic parameters to be measured.

2. The method for evaluating the anchoring degree of a vascular stent according to claim 1, wherein The establishment of the mapping relationship is achieved at least by one of the following methods: Simulation method: Using computer simulation technology, performing solid modeling on the vascular stent, simulating the radial compression process of the vascular stent, and outputting the relationship curve between the radial support force and the radius of the vascular stent; Experimental method: Radially compressing the vascular stent through a radial loading device, and obtaining the relationship curve between the radial support force and the radius of the vascular stent using a force sensor; Theoretical calculation: Based on material science and mechanics principles, regarding each stent wire of the vascular stent as a spring, and analyzing its force situation, deriving the functional relationship of the radial support force with respect to the radius of the vascular stent.

3. The method for evaluating the anchoring degree of a vascular stent according to claim 1, characterized in that, The anchoring force index is calculated based on the radial support force of the vascular stent or its derived parameters.

4. The method for evaluating the anchoring degree of a vascular stent according to claim 1, characterized in that, The key characteristic parameters include: parameters related to the anchoring force, as well as parameters related to the individual differences of patients and parameters related to the vascular state in the clinical follow-up data.

5. The method for evaluating the anchoring degree of a vascular stent according to claim 4, wherein The parameters related to the anchoring force include one or a combination of the following: High-anchoring area: The surface area of the vascular stent where the anchoring force index is higher than a certain threshold; High-anchoring area ratio: The ratio of the high-anchoring area to the total surface area of the vascular stent; Low-anchoring area: The surface area of the vascular stent where the anchoring force index is lower than a certain threshold; Low-anchoring area ratio: The ratio of the low-anchoring area to the total surface area of the vascular stent; Anchoring ratio: The ratio of the high-anchoring area to the low-anchoring area.

6. The method for evaluating the anchoring degree of a vascular stent according to claim 4, wherein The key characteristic parameters also include: Derived characteristic parameters obtained through further analysis and calculation based on the parameters related to the anchoring force.

7. The method for evaluating the anchoring degree of a vascular stent according to claim 6, characterized in that, The derived characteristic parameters include one or a combination of the following: Anchoring force extreme ratio: The ratio of the maximum anchoring force to the minimum anchoring force in the entire vascular stent; Anchoring force spatial entropy: Dividing the area of the vascular stent into the distal end, mid-distal end, lesion area, mid-proximal end, and proximal end on average by length, and calculating the anchoring force spatial entropy using the following formula: ； Among them, is the ratio of the maximum anchoring force to the minimum anchoring force in the i-th region.

8. An apparatus for evaluating the anchoring degree of a vascular stent, characterized in that, The device includes: A mapping relationship establishment module for establishing a mapping relationship between the radial support force of the vascular stent and the radius of the vascular stent; An anchoring force index definition module for defining an anchoring force index for evaluating the anchoring degree of the vascular stent based on the mapping relationship; A virtual implantation and calculation module, which is used to process vascular image data, generate a three-dimensional vascular model, and combine with the anchoring force index to implement the virtual implantation process of a vascular stent on a computer, and calculate and update the anchoring force index of the vascular stent at different positions in the blood vessel in real time according to the actual deployment degree of the vascular stent; A training module, which is used to collect clinical follow-up data after the implantation of the vascular stent, combine with the anchoring force index, extract key feature parameters, and train using a machine learning model to obtain a trained evaluation model for the anchoring degree of the vascular stent; An evaluation module, which is used to evaluate the anchoring degree of the vascular stent based on the trained evaluation model and the key feature parameters to be measured.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method described in any one of claims 1 to 7 are implemented.

Images