Method and device for determining blood flow parameters of brain blood vessels and computer equipment

Abstract

The invention relates to a brain blood vessel blood flow parameter determination method and device, computer equipment and a storage medium, and the method comprises the steps: constructing a corresponding brain blood vessel geometric model according to a brain medical image of a target object; constructing a grid model corresponding to the brain blood vessel geometric model, and inputting the brain blood vessel geometric model into a pre-trained model parting device to obtain a model parting corresponding to the brain blood vessel geometric model; according to the grid model and the model type, determining a corresponding calculation model and a boundary condition; and determining blood flow parameters of brain blood vessels of the target object through the calculation model and the boundary conditions. By adopting the method, comprehensive haemodynamics evaluation data can be provided.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a method, apparatus, computer equipment, storage medium and computer program product for determining cerebral vascular blood flow parameters. Background Art

[0002] Intracranial vascular lesions include aneurysms and arterial stenosis, which have a significant impact on the life and health of patients. Among them, the hemodynamic parameters of intracranial vessels are important functional indicators for analyzing intracranial vascular lesions. Therefore, how to obtain hemodynamic parameters has become the main research focus.

[0003] However, it is difficult to model intracranial blood vessels, which have complex structures and numerous pathways, and it is extremely difficult to simulate their hemodynamics. At present, the analysis methods for intracranial vascular lesions mainly include structural evaluation, functional evaluation, and graded evaluation schemes. However, these traditional technical means are greatly affected by image quality and are often limited to local lesion areas, and cannot provide comprehensive and accurate evaluations. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for determining brain vascular blood flow parameters in order to address the technical problem that the above-mentioned method cannot accurately evaluate intracranial blood vessels.

[0005] In a first aspect, the present application provides a method for determining cerebral vascular blood flow parameters. The method comprises:

[0006] According to the brain medical image of the target object, a corresponding brain blood vessel geometric model is constructed;

[0007] Constructing a mesh model corresponding to the cerebral vascular geometry model, and inputting the cerebral vascular geometry model into a pre-trained model classification device to obtain a model classification corresponding to the cerebral vascular geometry model;

[0008] Determine the corresponding calculation model and boundary conditions according to the grid model and the model classification;

[0009] The blood flow parameters of the brain blood vessels of the target object are determined by using the calculation model and the boundary conditions.

[0010] In one embodiment, the step of constructing a mesh model corresponding to the brain blood vessel geometric model includes:

[0011] Performing mesh division on the geometric model of brain blood vessels to obtain a divided model;

[0012] Determining the inlet and outlet areas and the wall area of ​​the divided model;

[0013] Based on the inlet and outlet areas and the wall area, the divided model is tetrahedronized to obtain a corresponding mesh model.

[0014] In one embodiment, determining the corresponding calculation model and boundary conditions according to the grid model and the model classification includes:

[0015] Determine a connected domain of the cerebral vascular geometric model according to the grid model and the model classification, and use the connected domain as a calculation model;

[0016] Determine the boundary parameters of the connected domain, and use the boundary parameters as boundary conditions of the calculation model.

[0017] In one embodiment, determining the boundary parameters of the connected domain includes:

[0018] Determining inlet parameters of the blood flow inlet and outlet parameters of the blood flow outlet of the connected domain, and determining a blood vessel wall model and a blood model;

[0019] The inlet parameters, the outlet parameters, the blood vessel wall model and the blood model are determined as the boundary parameters.

[0020] In one embodiment, determining the blood flow parameters of the brain blood vessels of the target object by using the calculation model and the boundary conditions includes:

[0021] Obtain the governing equations of fluid mechanics;

[0022] Determining a discrete set of equations based on the computational model, the boundary conditions, and the control equations;

[0023] The discrete equations are solved by numerical calculation method to determine the blood flow parameters of the brain blood vessels of the target object.

[0024] In one embodiment, after determining the blood flow parameters of the cerebral blood vessels of the target object by using the calculation model and the boundary conditions, the method further includes:

[0025] Based on the blood flow parameters, drawing a cloud map of the brain blood vessels of the target object;

[0026] Based on the cloud map, a blood flow parameter at any position of the cerebral blood vessel is determined.

[0027] In a second aspect, the present application also provides a device for determining cerebral vascular blood flow parameters. The device comprises:

[0028] A first processing module is used to construct a corresponding brain blood vessel geometric model according to the brain medical image of the target object;

[0029] A second processing module is used to construct a mesh model corresponding to the cerebral vascular geometry model, and input the cerebral vascular geometry model into a pre-trained model typer to obtain a model type corresponding to the cerebral vascular geometry model;

[0030] A boundary determination module, used to determine the corresponding calculation model and boundary conditions according to the grid model and the model classification;

[0031] The parameter determination module is used to determine the blood flow parameters of the brain blood vessels of the target object through the calculation model and the boundary conditions.

[0032] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0033] According to the brain medical image of the target object, a corresponding brain blood vessel geometric model is constructed;

[0034] Constructing a mesh model corresponding to the cerebral vascular geometry model, and inputting the cerebral vascular geometry model into a pre-trained model classification device to obtain a model classification corresponding to the cerebral vascular geometry model;

[0035] Determine the corresponding calculation model and boundary conditions according to the grid model and the model classification;

[0036] The blood flow parameters of the brain blood vessels of the target object are determined by using the calculation model and the boundary conditions.

[0037] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0038] According to the brain medical image of the target object, a corresponding brain blood vessel geometric model is constructed;

[0039] Constructing a mesh model corresponding to the cerebral vascular geometry model, and inputting the cerebral vascular geometry model into a pre-trained model classification device to obtain a model classification corresponding to the cerebral vascular geometry model;

[0040] Determine the corresponding calculation model and boundary conditions according to the grid model and the model classification;

[0041] The blood flow parameters of the brain blood vessels of the target object are determined by using the calculation model and the boundary conditions.

[0042] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0043] According to the brain medical image of the target object, a corresponding brain blood vessel geometric model is constructed;

[0044] Constructing a mesh model corresponding to the cerebral vascular geometry model, and inputting the cerebral vascular geometry model into a pre-trained model classification device to obtain a model classification corresponding to the cerebral vascular geometry model;

[0045] Determine the corresponding calculation model and boundary conditions according to the grid model and the model classification;

[0046] The blood flow parameters of the brain blood vessels of the target object are determined by using the calculation model and the boundary conditions.

[0047] The above-mentioned method, device, computer equipment, storage medium and computer program product for determining the blood flow parameters of the brain blood vessels construct the corresponding geometric model of the brain blood vessels through the brain medical image of the target object, and construct the grid model corresponding to the geometric model of the brain blood vessels, and at the same time input the geometric model of the brain blood vessels into the pre-trained model typer to obtain the model type corresponding to the geometric model of the brain blood vessels. According to the grid model and the model type, the corresponding calculation model and boundary conditions are determined; the blood flow parameters of the brain blood vessels of the target object are determined by the calculation model and the boundary conditions. The method realizes the simulation of the brain blood vessels by constructing the geometric model of the brain blood vessels corresponding to the brain medical image, and calculates the blood flow parameters by using the simulated geometric model, so that the calculation results can be unaffected by the quality of the brain medical image, thereby ensuring the accuracy of the determined blood flow parameters. At the same time, the calculation model and boundary conditions are determined according to the geometric model of the brain blood vessels, and the blood flow parameters are further determined, so that the whole brain area is taken into consideration, thereby providing comprehensive hemodynamic evaluation data, overcoming the defect that the traditional method is limited to the local lesion area. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 FIG. 1 is an application environment diagram of a method for determining cerebral vascular blood flow parameters in one embodiment;

[0049] Figure 2 is a flow chart of a method for determining cerebral vascular blood flow parameters in one embodiment;

[0050] Figure 3 is a schematic diagram of a cerebral artery circle in one embodiment;

[0051] Figure 4 is a flow chart of a method for determining cerebral blood vessel blood flow parameters in another embodiment;

[0052] Figure 5 is a structural block diagram of a device for determining cerebral vascular blood flow parameters in one embodiment;

[0053] Figure 6 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0055] The method for determining cerebral vascular blood flow parameters provided in the embodiments of the present application can be applied to Figure 1 In the application environment shown. Among them, the server 102 communicates with the medical scanning device 104 through the network. The data storage system can store the data that the server 102 needs to process. The data storage system can be integrated on the server 102, or it can be placed on the cloud or other network servers. In the application scenario of the present application, the medical image of the brain of the target object is collected by the medical scanning device 104, and the server 102 can obtain the medical image of the brain of the target object from the medical scanning device 104 through the network, construct a corresponding brain vascular geometry model, and construct a grid model corresponding to the brain vascular geometry model, and input the brain vascular geometry model into a pre-trained model typer to obtain the model type corresponding to the brain vascular geometry model; further determine the corresponding calculation model and boundary conditions based on the grid model and model type; finally, determine the blood flow parameters of the brain blood vessels of the target object through the boundary conditions.

[0056] The medical scanning device 104 may be a medical device such as a computed tomography (CT) device, a magnetic resonance (MR) device, a digital subtraction angiography (DSA) device, etc. The server 104 may be implemented as an independent server or a server cluster consisting of multiple servers.

[0057] In one embodiment, Figure 2 As shown, a method for determining blood flow parameters of cerebral blood vessels is provided, and the method is applied to Figure 1 Taking the server 102 in the example as an example, the following steps are included:

[0058] Step S210: constructing a corresponding brain blood vessel geometric model according to the brain medical image of the target object.

[0059] The target object may be an object including the brain of a biological object.

[0060] The brain medical image is an image acquired by a medical scanning device, for example, the brain medical image may be a CT image, an MR image, a DSA image, and the like.

[0061] Among them, the brain vascular geometry model is a model used to describe and analyze the morphological structure and geometric characteristics of the brain vascular system.

[0062] In a specific implementation, the target object's brain medical image can be segmented by blood vessel segmentation, and the corresponding brain blood vessel geometric model can be constructed based on the segmentation results. Blood vessel segmentation refers to the process of accurately extracting blood vessels from medical images. Blood vessel segmentation can be achieved by using techniques such as threshold, edge detection, region growing, horizontal line transformation, and active contour model. A convolutional neural network based on deep learning can be used to automatically segment brain blood vessels. After the segmentation is completed, surface reconstruction, geometric modeling, etc. can be performed based on the segmentation results to obtain a brain blood vessel geometric model.

[0063] Step S220, constructing a mesh model corresponding to the brain blood vessel geometry model, and inputting the brain blood vessel geometry model into a pre-trained model classifier to obtain a model classification corresponding to the brain blood vessel geometry model.

[0064] In a specific implementation, the mesh model corresponding to the brain vascular geometry model can be constructed by the finite element method, and the model typing corresponding to the brain vascular geometry model can be obtained by pre-training a model typing device and inputting the brain vascular geometry model into the pre-trained model typing device. More specifically, the training of the model typing device may include: obtaining a sample brain vascular geometry model, annotating the sample brain vascular geometry model, and training the model typing device based on the sample brain vascular geometry model and the corresponding annotation. For example, the sample brain vascular geometry model can be input into the model typing device to obtain the output predicted model typing, and the predicted model typing can be compared with the annotated real model typing, and the model typing device can be trained based on the difference between the two, until the obtained difference value converges or is less than a threshold value, and a trained model typing device is obtained.

[0065] The principle of the model classifier to determine the model classification corresponding to the brain vascular geometric model is to determine the corresponding model classification by analyzing the situation of the Willis circle (cerebral artery circle) in the brain vascular geometric model, specifically, the model classification is determined according to the patency of the anterior communicating artery and the posterior communicating artery in the Willis circle. Figure 3, is a schematic diagram of a cerebral artery circle shown in an embodiment. The Willis circle is the most important collateral circulation pathway in the brain, connecting the two hemispheres with the anterior and posterior circulations. The Willis circle, also known as the cerebral artery circle, is located below the base of the brain, above the sella turcica, around the optic chiasm, greater tubercle, and mammillary body, and is formed by the anastomosis of the anterior communicating artery, the initial segments of the anterior cerebral arteries on both sides, the terminal segments of the internal carotid arteries on both sides, the posterior communicating arteries on both sides, and the initial segments of the posterior cerebral arteries on both sides.

[0066] When it is determined according to the brain vascular geometry model that both the anterior communicating artery and the posterior communicating artery of the cerebral arterial circle are open, the model type is determined to be the first type; when it is determined according to the brain vascular geometry model that the anterior communicating artery of the cerebral arterial circle is open and the posterior communicating artery is not open, the model type is determined to be the second type; when it is determined according to the brain vascular geometry model that the anterior communicating artery of the cerebral arterial circle is not open and the posterior communicating artery is unilaterally open, the model type is determined to be the third type; when it is determined according to the brain vascular geometry model that the anterior communicating artery of the cerebral arterial circle is not open and the posterior communicating artery is bilaterally open, the model type is determined to be the fourth type; when it is determined according to the brain vascular geometry model that both the anterior communicating artery and the posterior communicating artery of the cerebral arterial circle are closed, the model type is determined to be the fifth type.

[0067] In this step, by pre-training a model classifier, when determining the model classification corresponding to the brain vascular geometry model, the brain vascular geometry model is input into the pre-trained model classifier to obtain the model classification corresponding to the brain vascular geometry model, which can improve the efficiency and accuracy of determining the model classification.

[0068] Step S230, determining the corresponding calculation model and boundary conditions according to the grid model and model classification.

[0069] The computational model represents any connected domain included in the cerebral vascular geometric model, and the boundary condition represents the boundary parameters of the connected domain.

[0070] In a specific implementation, after obtaining the mesh model and model classification corresponding to the brain blood vessel geometric model, the connected domain of the brain blood vessel geometric model can be determined according to the mesh model and model classification, and the connected domain can be used as a calculation model. At the same time, the boundary parameters of the connected domain are determined, and the boundary parameters are used as boundary conditions of the calculation model, so as to further calculate the blood flow parameters of the brain blood vessels according to the boundary conditions.

[0071] Step S240, determining the blood flow parameters of the target object's brain blood vessels by calculating the model and boundary conditions.

[0072] In a specific implementation, the blood flow parameters of the target object's brain blood vessels can be calculated based on fluid mechanics algorithms, computational models, and boundary conditions.

[0073] The blood flow parameters of the cerebral blood vessels may include blood pressure, vascular wall shear stress, blood flow velocity, etc. In one embodiment, the blood flow reserve can also be calculated based on the blood pressure, and the blood flow reserve can also be used as a blood flow parameter. Specifically, the calculation of the blood flow reserve at any point in the cerebral blood vessels can be determined based on the blood pressure at that point and the pressure of the blood flow inlet of the selected calculation model, which can be expressed by the formula:

[0074]

[0075] in, Indicates the location of brain blood vessels Blood flow reserve at Indicates the location of brain blood vessels Blood pressure at Represents the pressure at the blood flow inlet of the computational model corresponding to the cerebral blood vessels.

[0076] In the above-mentioned method for determining the blood flow parameters of brain blood vessels, a corresponding geometric model of brain blood vessels is constructed through the brain medical image of the target object, and a grid model corresponding to the geometric model of brain blood vessels is constructed, and the geometric model of brain blood vessels is input into a pre-trained model typer to obtain the model type corresponding to the geometric model of brain blood vessels. According to the grid model and the model type, the corresponding calculation model and boundary conditions are determined; and the blood flow parameters of the brain blood vessels of the target object are determined through the calculation model and the boundary conditions. This method realizes the simulation of brain blood vessels by constructing a geometric model of brain blood vessels corresponding to the brain medical image, and calculates the blood flow parameters using the simulated geometric model, so that the calculation results can be unaffected by the quality of the brain medical image, thereby ensuring the accuracy of the determined blood flow parameters. At the same time, the calculation model and boundary conditions are determined according to the geometric model of brain blood vessels, and the blood flow parameters are further determined, so that the whole brain area is taken into consideration, thereby providing comprehensive hemodynamic evaluation data, overcoming the defect that the traditional method is limited to the local lesion area.

[0077] In an exemplary embodiment, constructing a mesh model corresponding to the brain blood vessel geometry model in the above step S220 includes: meshing the brain blood vessel geometry model to obtain a meshed model; determining the inlet and outlet areas and wall areas of the meshed model; and tetrahedroning the meshed model based on the inlet and outlet areas and wall areas to obtain a corresponding mesh model.

[0078] In a specific implementation, the geometric model of brain blood vessels is meshed to obtain a divided model. For example, a triangulation algorithm is used to triangulate the geometric model of brain blood vessels to obtain a triangulated model as the divided model. The inlet and outlet areas and wall areas of the divided model are determined, and based on the inlet and outlet areas and the wall areas, the divided model is tetrahedroned to obtain a corresponding mesh model.

[0079] Before tetrahedroning the divided model, the divided model may be preprocessed, for example, by mesh optimization, local smoothing, and local refinement to obtain a preprocessed model, and then tetrahedroning the preprocessed model to obtain a corresponding mesh model.

[0080] In this embodiment, by converting the geometric model of brain blood vessels into a grid model, it is easier to perform subsequent hemodynamic simulation and analysis, and it is easier to understand the flow of blood in the cerebral vascular system, such as blood flow velocity, pressure distribution and other information, by performing numerical calculations on the grid model.

[0081] In an exemplary embodiment, the above step S230 determines the corresponding calculation model and boundary conditions based on the grid model and model classification, including: determining the connected domain of the brain vascular geometric model based on the grid model and model classification, and using the connected domain as the calculation model; determining the boundary parameters of the connected domain, and using the boundary parameters as the boundary conditions of the calculation model.

[0082] It should be noted that the cerebral vascular geometric model of any object includes connected domains, but the number of connected domains may vary, and the number of connected domains is associated with the model type corresponding to the cerebral vascular geometric model. Specifically, except for the first type of model type in which both the anterior and posterior communicating arteries are open, which has only one connected domain, the other second to fourth types of model types all have two or more connected domains.

[0083] In a specific implementation, if the model classification corresponding to the brain vascular geometry model determined in step S220 is the first type, the only connected domain contained therein can be determined as the calculation model based on the mesh model and model classification corresponding to the brain vascular geometry model, and then the boundary parameters of the connected domain can be determined as the boundary conditions of the calculation model.

[0084] If the model classification corresponding to the determined brain vascular geometric model is other than the first type, since there are multiple connected domains corresponding to the other types, one connected domain can be selected as the calculation model each time, and after the boundary conditions of the calculation model are determined, another connected domain is selected as the calculation model again, and so on, until the corresponding boundary conditions are determined for each connected domain as the calculation model. Similarly, when calculating the blood flow parameters later, the blood flow parameters are calculated based on the boundary conditions of the calculation model corresponding to each connected domain, thereby obtaining the blood flow parameters of the entire brain blood vessels.

[0085] In this embodiment, for different model classifications, the determined connected domains will be different. Determining boundary parameters for different connected domains respectively can ensure the comprehensiveness of the blood flow parameters of the brain blood vessels of the target object determined subsequently.

[0086] In an exemplary embodiment, determining the boundary parameters of a connected domain further includes: determining inlet parameters of a blood flow inlet, outlet parameters of a blood flow outlet, and a blood vessel wall model and a blood model of the connected domain; and determining the inlet parameters, outlet parameters, and the blood vessel wall model and the blood model as boundary parameters.

[0087] In a specific implementation, the boundary parameters of the connected domain are determined, specifically, the inlet parameters of the blood flow inlet and the outlet parameters of the blood flow outlet of the connected domain are determined, and the vascular wall model and the blood model are determined. The inlet parameters can be the velocity or flow rate of the blood flow inlet, and the outlet parameters can be the pressure of the blood flow outlet.

[0088] More specifically, the outlet parameters of the blood flow outlet may be determined according to the blood pressure data of the target subject or according to a reference pressure boundary.

[0089] For the blood vessel wall model, it can be set as a rigid no-slip wall model.

[0090] For the blood model, it can be set as an incompressible Newtonian fluid with a density of 1056 kg / m 3 , the viscosity can be .

[0091] Regarding the inlet parameters of the blood flow inlet, since there is more than one blood flow inlet in the connected domain, the determined inlet parameters include the inlet parameters of each blood flow inlet. Specifically, the total flow rate of all blood flow inlets included in the connected domain can be determined first, and the total flow rate can be distributed to each blood flow inlet, thereby obtaining the inlet parameters of each blood flow inlet.

[0092] Determining the total flow of all blood flow inlets includes: determining the inlet type of each blood flow inlet in the connected domain; obtaining the preset reference flow corresponding to each inlet type; and determining the total flow of the blood flow inlet based on each preset reference flow, such as adding each preset reference flow to obtain the total flow of the blood flow inlet. The preset reference flow corresponding to each inlet type includes the left internal carotid artery flow , right internal carotid artery flow , left vertebral artery flow , right vertebral artery flow It can be understood that different connected domains include different inlet types, and the corresponding total flow is also different. For example, a connected domain only includes the flow of the left internal carotid artery. , right internal carotid artery flow , left vertebral artery flow , then the total flow is: Q = + + , if a connected domain includes all inlet types, the total flow of the corresponding calculation model is: .

[0093] The total flow is distributed to each blood flow inlet, including: determining the area of ​​each blood flow inlet included in the connected domain; and distributing the total flow to each blood flow inlet based on the area of ​​each blood flow inlet. Specifically, the inlet flow of each blood flow inlet can be determined according to a power law. The flow of each blood flow inlet is positively correlated with the area, which can be expressed as follows: , where k can be selected from empirical values, and d is a parameter associated with the blood flow entrance area. Indicates blood flow entrance of traffic.

[0094] In this embodiment, by determining the inlet parameters of the blood flow inlet and the outlet parameters of the blood flow outlet of the connected domain, and determining the blood vessel wall model and the blood model as boundary parameters, the blood flow parameter information of the calculation model corresponding to the connected domain is determined. This comprehensively considers information from multiple dimensions and can ensure the accuracy of the determined blood flow parameters.

[0095] In an exemplary embodiment, the blood flow parameters of the target object's brain blood vessels are determined in the above step S240 through the calculation model and boundary conditions, including: obtaining the control equations of fluid mechanics; determining a discrete equation group based on the calculation model, boundary conditions and control equations; solving the discrete equation group by a numerical calculation method to determine the blood flow parameters of the target object's brain blood vessels.

[0096] In the specific implementation, the boundary conditions of the computational model are composed of the boundary parameters of the connected domain corresponding to the computational model. Therefore, when determining the blood flow parameters, the control equations of fluid mechanics can be obtained, and the boundary conditions can be substituted into the control equations to obtain a discrete set of equations. The discrete set of equations is solved by the computational fluid algorithm to obtain the blood flow parameters of the brain blood vessels of the target object.

[0097] The governing equations of fluid mechanics are as follows:

[0098]

[0099]

[0100] Among them, u represents blood velocity, ρ represents blood density, p represents blood pressure, μ represents blood viscosity, and f represents external force.

[0101] The fluid mechanics parameters obtained by solving the above control equations include blood pressure, vascular wall shear stress, blood flow velocity, etc. Therefore, it is necessary to further solve the blood flow reserve based on the blood pressure and the pressure of the blood flow inlet of the calculation model, and use the blood pressure, vascular wall shear stress, blood flow velocity and blood flow reserve as the blood flow parameters of the target object's brain blood vessels.

[0102] Computational Fluid Dynamics (CFD) is applied to the study of hemodynamics in the biomedical field, providing a unique perspective and role for clinical diagnosis and treatment practice. It obtains the flow field distribution and pressure distribution of the target area by modeling and calculating, and then obtains or calculates the corresponding hemodynamic indicators or clinically valuable parameters. In this embodiment, the blood flow parameters are solved by applying computational fluid technology, which can realize the non-invasive calculation of blood flow parameters.

[0103] In an exemplary embodiment, after the above step S240 determines the blood flow parameters of the target object's brain blood vessels through the calculation model and boundary conditions, it also includes: drawing a cloud map of the target object's brain blood vessels based on the blood flow parameters; and determining the blood flow parameters at any position of the brain blood vessels based on the cloud map.

[0104] In a specific implementation, after obtaining the blood flow parameters of various locations of the target object's brain blood vessels, the blood flow parameters at various locations can be mapped back to the calculation model, and a cloud map of the brain blood vessels can be drawn. For example, a cloud map of the brain blood vessels can be drawn using data visualization software or tools. This allows the blood flow parameters at any location of the brain blood vessels to be quickly determined based on the cloud map.

[0105] In one embodiment, different colors, sizes and shapes may be used to represent different blood parameters so as to intuitively display the state of the cerebral blood vessels. Furthermore, the cloud map of the cerebral blood vessels may be continuously updated and adjusted according to new blood flow parameters to reflect the latest state of the cerebral blood vessels.

[0106] In this embodiment, a cloud map of the target object's brain blood vessels is drawn based on the blood flow parameters, so that the blood flow parameters of various parts of the brain blood vessels can be intuitively displayed through the cloud map, allowing medical staff to intuitively and quickly understand the status of the target object's brain blood vessels, thereby facilitating a more accurate assessment of cerebrovascular function.

[0107] In an exemplary embodiment, if Figure 4 FIG. 2 is another flow chart of a method for determining cerebral vascular blood flow parameters. In this embodiment, the method includes the following steps:

[0108] Step S410, constructing a corresponding brain blood vessel geometric model according to the brain medical image of the target object;

[0109] Step S420, constructing a mesh model corresponding to the cerebral vascular geometry model, and inputting the cerebral vascular geometry model into a pre-trained model classification device to obtain a model classification corresponding to the cerebral vascular geometry model;

[0110] Step S430, determining the connected domain of the cerebral blood vessel geometric model according to the grid model and the model classification, and using the connected domain as a calculation model;

[0111] Step S440, determining inlet parameters of the blood flow inlet and outlet parameters of the blood flow outlet of the connected domain, and determining a blood vessel wall model and a blood model;

[0112] Step S450, determining the inlet parameters, outlet parameters, and the blood vessel wall model and the blood model as boundary conditions of the calculation model;

[0113] Step S460, obtaining the control equation of fluid mechanics; determining a discrete equation group based on the calculation model, boundary conditions and the control equation; solving the discrete equation group by a numerical calculation method to determine the blood flow parameters of the brain blood vessels of the target object;

[0114] Step S470, drawing a cloud map of the brain blood vessels of the target object based on the blood flow parameters;

[0115] Step S480, determining the blood flow parameters at any position of the cerebral blood vessels based on the cloud map.

[0116] In this embodiment, a geometric model of brain blood vessels corresponding to the brain medical image is constructed to simulate the blood vessels of the entire brain. The simulated geometric model is used to calculate the blood flow parameters so that the calculation results are not affected by the quality of the brain medical image, thereby ensuring the accuracy of the determined blood flow parameters. At the same time, the calculation model and boundary conditions are determined based on the geometric model of the brain blood vessels, and the blood flow parameters are further determined, thereby taking the entire brain area into consideration, thereby providing comprehensive hemodynamic evaluation data and overcoming the defect that traditional methods are limited to local lesion areas.

[0117] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0118] Based on the same inventive concept, the embodiment of the present application also provides a device for determining cerebral vascular blood flow parameters for implementing the above-mentioned method for determining cerebral vascular blood flow parameters. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations of one or more embodiments of the device for determining cerebral vascular blood flow parameters provided below can refer to the limitations of the method for determining cerebral vascular blood flow parameters above, and will not be repeated here.

[0119] In one embodiment, Figure 5 As shown, a device for determining blood flow parameters of cerebral blood vessels is provided, comprising: a first processing module 510, a boundary determination module 530 and a parameter determination module 540, wherein:

[0120] A first processing module 510 is used to construct a corresponding brain blood vessel geometric model according to the brain medical image of the target object;

[0121] The second processing module 520 is used to construct a mesh model corresponding to the cerebral vascular geometry model, and input the cerebral vascular geometry model into a pre-trained model typer to obtain a model type corresponding to the cerebral vascular geometry model;

[0122] The boundary determination module 530 is used to determine the corresponding calculation model and boundary conditions according to the grid model and model classification;

[0123] The parameter determination module 540 is used to determine the blood flow parameters of the brain blood vessels of the target object through the calculation model and boundary conditions.

[0124] In one embodiment, the second processing module 520 is also used to mesh the geometric model of brain blood vessels to obtain a divided model; determine the inlet and outlet areas and wall areas of the divided model; and tetrahedron the divided model based on the inlet and outlet areas and wall areas to obtain a corresponding mesh model.

[0125] In one embodiment, the boundary determination module 530 is further used to determine the connected domain of the brain vascular geometric model based on the grid model and the model classification, and use the connected domain as the calculation model; determine the boundary parameters of the connected domain, and use the boundary parameters as the boundary conditions of the calculation model.

[0126] In one embodiment, the boundary determination module 530 is also used to determine the inlet parameters of the blood flow inlet and the outlet parameters of the blood flow outlet of the connected domain, as well as the blood vessel wall model and the blood model; and the inlet parameters, the outlet parameters, the blood vessel wall model and the blood model are determined as boundary parameters.

[0127] In one embodiment, the parameter determination module 540 is also used to obtain the control equations of fluid mechanics; determine the discrete equation group based on the computational model, boundary conditions and the control equations; and solve the discrete equation group by numerical calculation methods to determine the blood flow parameters of the brain blood vessels of the target object.

[0128] In one of the embodiments, the above-mentioned device also includes a cloud map drawing module, which is used to draw a cloud map of the brain blood vessels of the target object based on the blood flow parameters; based on the cloud map, the blood flow parameters at any position of the brain blood vessels are determined.

[0129] Each module in the above-mentioned device for determining cerebral vascular blood flow parameters can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0130] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 6 As shown. The computer device includes a processor, a memory and a network interface connected through 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, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data in the process of determining cerebral vascular blood flow parameters. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for determining cerebral vascular blood flow parameters is implemented.

[0131] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0132] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0133] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0134] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0135] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0136] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0137] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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, they should be considered to be within the scope of this specification.

[0138] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for determining cerebral vascular blood flow parameters, characterized in that: The method comprises: According to the brain medical image of the target object, a corresponding brain blood vessel geometric model is constructed; Constructing a mesh model corresponding to the cerebral vascular geometry model, and inputting the cerebral vascular geometry model into a pre-trained model classification device to obtain a model classification corresponding to the cerebral vascular geometry model; Determine the corresponding calculation model and boundary conditions according to the grid model and the model classification; The blood flow parameters of the brain blood vessels of the target object are determined by using the calculation model and the boundary conditions.

2. The method according to claim 1, characterized in that The step of constructing a mesh model corresponding to the cerebral blood vessel geometric model includes: Performing mesh division on the geometric model of brain blood vessels to obtain a divided model; Determining the inlet and outlet areas and the wall area of ​​the divided model; Based on the inlet and outlet areas and the wall area, the divided model is tetrahedronized to obtain a corresponding mesh model.

3. The method according to claim 1, characterized in that Determining the corresponding calculation model and boundary conditions according to the grid model and the model classification includes: Determine a connected domain of the cerebral vascular geometric model according to the grid model and the model classification, and use the connected domain as a calculation model; Determine the boundary parameters of the connected domain, and use the boundary parameters as boundary conditions of the calculation model.

4. The method according to claim 3, characterized in that The step of determining the boundary parameters of the connected domain comprises: Determining inlet parameters of the blood flow inlet and outlet parameters of the blood flow outlet of the connected domain, and determining a blood vessel wall model and a blood model; The inlet parameters, the outlet parameters, the blood vessel wall model and the blood model are determined as the boundary parameters.

5. The method according to claim 1, characterized in that Determining the blood flow parameters of the brain blood vessels of the target object by using the calculation model and the boundary conditions includes: Obtain the governing equations of fluid mechanics; Determine a discrete set of equations based on the computational model, the boundary conditions, and the control equations; The discrete equations are solved by numerical calculation method to determine the blood flow parameters of the brain blood vessels of the target object.

6. The method according to any one of claims 1 to 5, characterized in that: After the blood flow parameters of the cerebral blood vessels of the target object are determined by the calculation model and the boundary conditions, the method further includes: Based on the blood flow parameters, drawing a cloud map of the brain blood vessels of the target object; Based on the cloud map, a blood flow parameter at any position of the cerebral blood vessel is determined.

7. A device for determining blood flow parameters of cerebral blood vessels, characterized in that: The device comprises: A first processing module is used to construct a corresponding brain blood vessel geometric model according to the brain medical image of the target object; A second processing module is used to construct a mesh model corresponding to the cerebral vascular geometry model, and input the cerebral vascular geometry model into a pre-trained model typer to obtain a model type corresponding to the cerebral vascular geometry model; A boundary determination module, used to determine the corresponding calculation model and boundary conditions according to the grid model and the model classification; The parameter determination module is used to determine the blood flow parameters of the brain blood vessels of the target object through the calculation model and the boundary conditions.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the processor implements the steps of the method for determining cerebral vascular blood flow parameters according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the computer program implements the steps of the method for determining cerebral vascular blood flow parameters according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the computer program implements the steps of the method for determining cerebral vascular blood flow parameters according to any one of claims 1 to 6.

Images