A method, system, device, and medium for constructing a vascular injury assessment model

Abstract

The present application belongs to the technical field of blood vessel injury evaluation, and particularly relates to a method, system, device and medium for constructing a blood vessel injury evaluation model, which comprises the following steps: acquiring clinical image data of a patient, and reconstructing a three-dimensional blood vessel model of the patient according to the clinical image data; extracting corresponding morphological parameters based on the three-dimensional blood vessel model, and calculating corresponding biomechanical parameters based on the three-dimensional blood vessel model; calculating characteristic parameters of blood vessel injury according to the biomechanical parameters, and constructing a blood vessel injury evaluation model according to the characteristic parameters and the morphological parameters, so as to predict the degree of blood vessel injury of the patient by using the blood vessel injury evaluation model. The present application proposes a new mechanical parameter by performing biomechanical calculation based on clinical routine examination images, and combines key morphological parameters of blood vessels to construct a blood vessel injury evaluation model, so as to predict the degree of blood vessel injury of the patient by using the model, and meet the demand of clinical application.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of blood vessel injury evaluation, and particularly relates to a blood vessel injury evaluation model construction method, system, device and medium. BACKGROUND

[0002] Clinical studies have shown that hypertension, race, gender, age, genetic factors and connective tissue diseases are risk factors for blood vessel injury, but there is still a lack of blood vessel injury evaluation methods that can be effectively applied in clinical practice. With the progress of medical imaging technology, it is possible to evaluate the state of blood vessel injury. Commonly used blood vessel disease diagnosis imaging technologies in clinical practice include CT angiography, transesophageal echocardiography, angiography, magnetic resonance imaging and nuclear medicine imaging. However, CT angiography, transesophageal echocardiography and angiography can only visualize the structural characteristics of blood vessels and cannot present the stress on the vessel wall and the blood flow state, so functional evaluation cannot be achieved. Although magnetic resonance imaging can visualize blood flow characteristics, nuclear magnetic imaging takes a long time and has high requirements for patients, so it cannot be widely used in clinical practice at present. Although the high uptake of radionuclides in nuclear medicine imaging can be used as an indicator to judge the degree of inflammation activity for evaluating blood vessel injury, the cost of nuclear medicine imaging is high and the image resolution is low, so it cannot be widely used in clinical practice.

[0003] Therefore, there is still a lack of methods and strategies based on blood vessel structure imaging that can be used to effectively evaluate blood vessel injury. SUMMARY

[0004] In view of the above-mentioned shortcomings of the prior art, the purpose of the present application is to provide a method based on blood vessel structure imaging, such as CT angiography, transesophageal echocardiography, angiography, etc., and combined with biomechanical calculation to obtain the stress on the vessel wall and the blood flow state in the blood vessel, so as to evaluate the degree of blood vessel injury.

[0005] To achieve the above-mentioned purposes and other related purposes, the present application provides a blood vessel injury evaluation model construction method, which comprises: acquiring clinical imaging data of a patient, and reconstructing a three-dimensional blood vessel model of the patient according to the imaging data; extracting corresponding morphological parameters based on the three-dimensional blood vessel model, and calculating corresponding biomechanical parameters based on the three-dimensional blood vessel model; calculating characteristic parameters of blood vessel injury according to the biomechanical parameters, and constructing a blood vessel injury evaluation model according to the characteristic parameters and the morphological parameters, so as to predict the degree of blood vessel injury of the patient by using the blood vessel injury evaluation model.

[0006] According to an embodiment of the present application, the step of reconstructing the three-dimensional blood vessel model of the patient comprises: segmenting a region of interest from the clinical image data and reconstructing the three-dimensional blood vessel model according to the region of interest; and exporting the reconstructed three-dimensional blood vessel model in the form of triangular facets and performing smoothing and cutting processing; wherein the clinical image data is structural image data of blood vessels.

[0007] According to an embodiment of the present application, when the reconstructed three-dimensional blood vessel model is an aorta model, the aorta model comprises an aorta trunk and main branch blood vessels; wherein the main branch blood vessels comprise arch main branch blood vessels and abdominal main branch blood vessels.

[0008] According to an embodiment of the present application, the step of extracting corresponding morphological parameters based on the three-dimensional blood vessel model comprises: extracting a blood vessel centerline from the three-dimensional blood vessel model and interpolating the blood vessel centerline at intervals of image slice thickness; and calculating morphological parameters of the blood vessel along the blood vessel centerline according to the interpolated blood vessel centerline.

[0009] According to an embodiment of the present application, the morphological parameters are related to a lesion of the patient.

[0010] According to an embodiment of the present application, the morphological parameters comprise a volume of the blood vessel, and the step of calculating morphological parameters of the blood vessel along the blood vessel centerline according to the interpolated blood vessel centerline further comprises: dividing different sections of the blood vessel based on a clinical key anatomical position, and calculating the volume of the different sections of the blood vessel.

[0011] According to an embodiment of the present application, the morphological parameters at least comprise: a cross-sectional area, a perimeter, a major axis, a minor axis, an average diameter, and an equivalent diameter.

[0012] According to an embodiment of the present application, the step of calculating corresponding biomechanical parameters based on the three-dimensional blood vessel model comprises: performing grid discretization processing on the three-dimensional blood vessel model; and performing transient and / or steady-state biomechanical calculation according to the processed three-dimensional blood vessel model to obtain the corresponding biomechanical parameters.

[0013] According to an embodiment of the present application, the step of performing transient and / or steady-state biomechanical calculation according to the processed three-dimensional blood vessel model to obtain the corresponding biomechanical parameters comprises: discretizing each cardiac cycle into a plurality of time steps before performing the biomechanical calculation, and each time step is related to a heart rate of the patient and a number of time steps; performing biomechanical calculation for a plurality of cycles, and obtaining the corresponding biomechanical parameters according to a calculation result of the last cycle.

[0014] According to an embodiment of the present application, when the biomechanics calculation is a hemodynamics calculation, boundary conditions of blood are preset according to morphological structural features of a blood vessel through which the blood flows, and physical properties of the blood are preset during the calculation, wherein the boundary conditions include velocity boundary conditions and pressure boundary conditions.

[0015] According to an embodiment of the present application, when the biomechanics calculation is a fluid-structure interaction calculation, boundary conditions of blood are preset according to morphological structural features of a blood vessel through which the blood flows, and physical properties of the blood and wall properties of the blood vessel through which the blood flows are preset during the calculation, wherein the boundary conditions include velocity boundary conditions and pressure boundary conditions.

[0016] According to an embodiment of the present application, the biomechanics parameters include at least blood flow velocity, blood flow pressure, and wall shear stress.

[0017] According to an embodiment of the present application, the step of calculating the characteristic parameter of the blood vessel damage according to the biomechanics parameters includes: calculating corresponding resultant forces according to the wall shear stress and the stress of the blood flow pressure along the axial direction, and taking an average value of the resultant forces in a period as the characteristic parameter of the blood vessel damage.

[0018] According to an embodiment of the present application, a calculation formula of the resultant force is as follows:

[0019] ,

[0020] , and ,

[0021] ,

[0022] wherein, represents the blood flow pressure, represents a lumen radius of the blood vessel, represents a wall thickness of the blood vessel, represents a Poisson's ratio, represents the stress of the blood flow pressure along the axial direction, represents the wall shear stress, and respectively represent normalized and , and respectively represent and reference values of and are preset parameters, and ranges are , represents the resultant force.

[0023] According to a specific embodiment of the present invention, the formula for calculating the average value of the resultant force within one period is as follows:

[0024] ,

[0025] in, Represents the resultant force within one period The average value, Indicates the length of the period, and They represent the results after normalization. and , This represents the stress along the axial direction of blood flow pressure. This represents the wall shear stress.

[0026] According to a specific embodiment of the present invention, the step of calculating the characteristic parameters of vascular injury based on the biomechanical parameters further includes: using the uptake value of nuclear medicine imaging data as a standard value, and using it to verify the validity of the characteristic parameters of vascular injury.

[0027] According to a specific embodiment of the present invention, the steps of constructing a vascular injury assessment model include: dividing the uptake values ​​of nuclear medicine imaging data into a high uptake group and a low uptake group to characterize the degree of vascular injury; constructing a mixed-effects logistic regression model based on the characteristic parameters of the vascular injury and the morphological parameters, and in combination with the patient's clinical characteristic parameters, as the vascular injury assessment model.

[0028] A system for constructing a vascular injury assessment model includes: a data preprocessing module for acquiring clinical imaging data of a patient and reconstructing a three-dimensional vascular model of the patient based on the data; a feature parameter extraction module for extracting corresponding morphological parameters based on the three-dimensional vascular model and calculating corresponding biomechanical parameters based on the three-dimensional vascular model; and a model construction module for calculating feature parameters of vascular injury based on the biomechanical parameters and constructing a vascular injury assessment model based on the biomechanical parameters and the morphological parameters, so as to predict the degree of vascular injury in the patient using the vascular injury assessment model.

[0029] An electronic device includes a processor coupled to a memory storing program instructions that, when executed by the processor, implement the method described above.

[0030] A computer-readable storage medium includes a program that, when run on a computer, causes the computer to perform the method described above.

[0031] The application provides a method for constructing a blood vessel injury evaluation model based on blood vessel structure image data, and a new mechanical parameter is proposed by performing biomechanical calculation based on clinical routine examination image, and a blood vessel injury evaluation model is constructed by combining a key morphological parameter of the blood vessel, so as to predict the blood vessel injury degree of a patient by using the model, and meet the clinical application requirement. BRIEF DESCRIPTION OF DRAWINGS

[0032] Figure 1 A flowchart of a specific embodiment of the method for constructing a blood vessel injury evaluation model provided by the application is shown in the figure.

[0033] Figure 2 A schematic diagram of an aorta model of a specific embodiment provided by the application is shown in the figure.

[0034] Figure 3 A stress diagram in the direction of blood provided by the application is shown in the figure.

[0035] Figure 4 A structural diagram of a specific embodiment of the construction system of a blood vessel injury evaluation model provided by the application is shown in the figure.

[0036] Figure 5 A structural block diagram of a specific embodiment of an electronic device provided by the application is shown in the figure. DETAILED DESCRIPTION

[0037] In order to facilitate the understanding of the present application, the present application will be described more fully below with reference to the accompanying drawings. The embodiments of the present application are shown in the drawings. However, the present application can be implemented in many different forms, and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.

[0038] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terminology used in the specification of the present application is only for the purpose of describing specific embodiments and is not intended to limit the present application.

[0039] The embodiments of the application are described below by way of specific examples. Those skilled in the art can easily understand other advantages and effects of the application from the disclosure of the specification. The application can also be implemented or applied by different specific embodiments, and the details in the specification can be modified or changed based on different views and applications without departing from the spirit of the application. It should be noted that the following examples and features in the examples can be combined with each other without conflict.

[0040] In the following description, numerous specific details are discussed in order to provide a thorough explanation of embodiments of the application. It will be apparent, however, to one of ordinary skill in the art that embodiments of the application can be practiced without these specific details. In other instances, well-known structures and devices are not described in detail in order to avoid obscuring embodiments of the application.

[0041] Embodiment 1

[0042] Referring to Figure 1 The method for constructing a vascular injury evaluation model comprises the following steps:

[0043] In step S100, clinical image data of a patient is acquired, and a three-dimensional vascular model of the patient is reconstructed based on the clinical image data.

[0044] It can be understood that, in order to reconstruct a three-dimensional vascular model of a patient, clinical image data of the patient needs to be acquired from a hospital, and a region of interest is segmented from the clinical image data, so as to reconstruct the three-dimensional vascular model. In a specific embodiment, the aorta is taken as an example, and the reconstructed aorta model ranges from the ascending aorta to the iliac branch blood vessels. If the patient has a dissection disease, the aorta model is constructed to the end of the dissection position.

[0045] Further, the reconstructed three-dimensional vascular model is exported in the form of a triangle sheet (STereoLithography, STL). Moreover, since the segmented and reconstructed STL is relatively rough, reverse engineering software needs to be used to perform smoothing and cutting processing, so as to obtain a final three-dimensional vascular model. In a specific embodiment, refer to Figure 2 The finally obtained aorta model comprises the aorta trunk and main branch blood vessels, and the main branch blood vessels include the arch main branch blood vessels and the abdominal main branch blood vessels. The arch main branch blood vessels include the innominate artery, the left common carotid artery, and the left subclavian artery; the abdominal main branch blood vessels include the celiac trunk, the superior mesenteric artery, the left and right renal arteries, and the iliac main branch blood vessels.

[0046] It should be noted that the clinical image data mentioned in the embodiment is structural image data of blood vessels, such as CTA image data, nuclear magnetic resonance image data, or blood vessel structural image data obtained by using other imaging techniques, and the like. No excessive limitation is made on this, and modifications and refinements made by those skilled in the art to the embodiments of the application without departing from the spirit of the application still fall within the scope of the patent application of the application.

[0047] In step S200, morphological parameters corresponding to the three-dimensional vascular model are extracted based on the three-dimensional vascular model, and biomechanical parameters corresponding to the three-dimensional vascular model are calculated based on the three-dimensional vascular model.

[0048] Based on the above, the three-dimensional blood vessel model needs to be further extracted from the feature parameters, so as to construct the blood vessel injury evaluation model. In this embodiment, the morphological parameters of the blood vessel and the biomechanical parameters of the blood vessel and / or blood need to be extracted from the three-dimensional blood vessel model respectively.

[0049] Specifically, the blood vessel centerline is extracted according to the three-dimensional blood vessel model, and the blood vessel centerline is interpolated at the interval of the layer thickness of the image section. Further, based on the interpolated blood vessel centerline, the cross-sectional area, the circumference, the long axis, the short axis, the average diameter and the equivalent diameter of the blood vessel along the blood vessel centerline are calculated. At the same time, if there are different sections for the blood vessel division at the clinical key anatomical position, the volume of different sections of the blood vessel is calculated accordingly. The various parameters calculated above are collectively used as the morphological parameters of the blood vessel structure.

[0050] It should be noted that the morphological parameters of the blood vessel structure include but are not limited to the above, and more morphological parameters can be calculated in actual application for different types of blood vessel diseases, for example, the expansion degree parameter of the tumor region can be calculated for neoplastic expansion diseases, the stenosis rate can be calculated for stenosis diseases, and the parameters related to the tear opening can be calculated for dissection diseases, such as the area and circumference of the tear opening. Therefore, the required morphological parameters of the blood vessel structure can be extracted or calculated from the three-dimensional blood vessel model according to the actual lesion of the patient, so as to ensure the accuracy and reliability of the subsequent constructed blood vessel injury evaluation model. The modifications and decorations made by the person skilled in the art to the embodiments of the present application without departing from the spirit of the present application still fall within the scope of the present application.

[0051] Secondly, the biomechanical parameters of the blood vessel and / or blood can be obtained by biomechanical calculation. Among them, the blood vessel biomechanical calculation is to solve the mechanical equation for each grid point after the grid division of the three-dimensional blood vessel model, and obtain the mechanical parameter distribution of the whole blood vessel region.

[0052] Firstly, the three-dimensional blood vessel model needs to be discretized, that is, for the fluid region, a boundary layer grid needs to be set at the blood vessel wall. At the same time, the setting of the physical properties of the blood vessel wall and the blood, such as the density and dynamic viscosity of the blood, needs to be completed before calculation.

[0053] Secondly, the boundary conditions of the blood need to be given according to the morphological structure characteristics of the blood vessel, including the velocity and pressure boundary conditions. Among them, the velocity and pressure boundary conditions can be obtained by medical image measurement, or can be obtained by three-element windkessel model, and no more limitation is made, only as the preset condition of biomechanical calculation.

[0054] Finally, when performing biomechanical calculation, transient or steady calculation is needed according to actual requirements. When performing transient calculation, each cardiac cycle needs to be discretized into multiple time steps, each time step is determined according to the heart rate of the patient and the number of time steps, and before calculation, time sensitivity is tested to determine the rationality of the time step used. In order to exclude the initial effect and obtain stable calculation results, when performing steady calculation, multiple cycles of calculation are needed, and the calculation results of the last cycle are extracted to obtain the required biomechanical parameters.

[0055] In a specific embodiment, the biomechanical calculation adopts hemodynamic calculation, and takes the aortic model as an example. When performing biomechanical calculation, the ascending aorta inlet is given a velocity boundary condition, the innominate artery, left common carotid and subclavian artery are given an outlet velocity boundary condition, and the abdominal branch vessels and iliac branch vessels are given an outlet pressure boundary condition. Among them, the velocity boundary condition is obtained from the ultrasound data, and the pressure boundary condition is obtained by a three-element windkessel model. At the same time, the blood can be regarded as a Newtonian fluid, the density of the blood is set to 1044 kg / m 3 , the blood dynamic viscosity is set to 0.00365 kg / (m·s), and the aortic wall is set as a rigid no-slip wall for calculation. Finally, according to the time sensitivity test results, each cardiac cycle is discretized into 50 time steps, and the time step is determined according to the heart rate of the patient. In order to exclude the initial effect and obtain stable calculation results, a total of 4 cycles of calculation are performed, and the calculation results of the last cycle are extracted to obtain the biomechanical parameters.

[0056] As can be seen, when hemodynamic calculation is adopted, the boundary conditions and physical properties of blood need to be preset in advance.

[0057] In another specific embodiment, the biomechanical calculation adopts fluid-structure interaction calculation, and takes the aortic model as an example. When performing biomechanical calculation, for the solid domain, the blood vessel wall thickness is set to 2mm, the Young's modulus is set to 0.8MPa, and the Poisson's ratio is set to 0.45. For the fluid domain, the settings can be consistent with the above hemodynamic calculation, that is, the boundary conditions and physical properties of blood are consistent. When performing fluid-structure interaction calculation, the pressure obtained by fluid calculation acts on the solid surface, similarly, the change of the solid changes the fluid domain to realize the coupling of fluid and solid, so that the dynamic parameters of the blood vessel and the blood can be obtained through the combination of transient and steady calculation.

[0058] As can be seen, when fluid-structure interaction calculation is adopted, not only the boundary conditions and physical properties of blood need to be preset in advance, but also the pipe wall properties of the blood vessel need to be preset.

[0059] Based on the above, the morphological parameters and the biomechanical parameters corresponding to the three-dimensional blood vessel model can be obtained, and the biomechanical parameters at least include blood flow velocity, blood pressure, and wall shear stress.

[0060] In step S300, the characteristic parameters of the blood vessel injury are calculated according to the biomechanical parameters, and a blood vessel injury evaluation model is constructed according to the characteristic parameters and the morphological parameters, so as to predict the degree of blood vessel injury of the patient by using the blood vessel injury evaluation model.

[0061] It can be understood that after biomechanical calculation, parameters such as blood flow velocity, pressure, and wall shear stress can be obtained. The stress in the direction of blood flow is closely related to the blood vessel injury, and the stress in the direction of blood flow includes the wall shear stress and the stress in the axial direction generated by the blood flow pressure. The resultant force of the two is also closely related to the blood vessel injury, as shown in the following formula: Figure 3

[0062] In this embodiment, the resultant force of the wall shear stress and the stress in the axial direction generated by the blood flow pressure is defined as in-wall stress (IWS), and the calculation method can be referred to as follows:

[0063] Firstly, the thickness of the blood vessel wall is much smaller than the lumen radius of the blood vessel, so the blood vessel wall can be regarded as a thin-walled isotropic linear model, and it can be known from Hooke's law that:

[0064]

[0065] wherein, represents the deformation degree of the blood vessel wall, is the Young's modulus, represents the Poisson's ratio, represents the stress in the axial direction generated by the blood flow pressure, represents the hoop stress generated by the blood pressure, represents the circumferential stress generated by the blood pressure.

[0066] Secondly, it is assumed that the deformation degree of the blood vessel wall is 0, and since the thin-walled assumption, so .And the hoop stress generated by the blood pressure can be calculated according to the following formula:

[0067]

[0068] wherein, represents the blood flow pressure.

[0069] Based on the above, the axial stress generated by the blood flow pressure on the wall is as follows: ​​​​​​

[0070] ,

[0071] Further, endothelial cells are able to sense the axial stress on the vessel wall, which includes the axial stress generated by the blood flow pressure and the wall shear stress generated by the blood flow . Considering and are quite different in magnitude, the following normalization is performed for and respectively:

[0072] ,

[0073] ,

[0074] where and denote the reference values of and respectively, and the reference values are obtained by calculating the blood flow of normal cases in the same age group. and are defined from the biomechanical point of view to represent the sensitivity of the cells to the stress, and both of them range from , and indicate that the cells can well sense the mechanical stimulation.

[0075] Based on the above, the IWS defined in the present embodiment can be referred to as follows:

[0076] ,

[0077] In addition, since the blood flow has different flow characteristics in a cycle, in order to capture the effect of IWS on endothelial cells in a cycle, the average value of IWS in a cycle is also calculated in the present embodiment, which is defined as Time-averaged in-wall stress (TAIWS), and is used as a characteristic parameter of vascular injury. For details, please refer to the following:

[0078] ,

[0079] where denotes the length of a cycle.

[0080] It needs to be added here that in order to show that TAIWS is closely related to vascular injury, the patient's nuclear medicine image data can be used for verification. It can be understood that the above-mentioned construction of a three-dimensional vascular model, extraction of morphological parameters, calculation of biomechanical parameters, and calculation of TAIWS all depend on structural image data of the blood vessels, and the uptake value of the nuclear medicine image data can be used as a standard value to quantify whether the results calculated using the structural image data are related to vascular injury.

[0081] For this purpose, taking aortic dissection as an example, the nuclear medicine uptake value (SUVmax) of the key part is extracted, and univariate linear mixed effect analysis is performed by mixing morphological parameters, clinical parameters, etc., and the linear mixed effect analysis results are shown in Table 1.

[0082] Table 1. Univariate linear mixed effect analysis results

[0083]

[0084] As can be seen, the coefficient of TAIWS is significantly greater than that of other parameters, proving the effectiveness of the TAIWS parameter, i.e., TAIWS is closely related to vascular injury.

[0085] Finally, based on the above-obtained characteristic parameter TAIWS of vascular injury, a vascular injury evaluation model is constructed in combination with morphological parameters of the blood vessels. Specifically, first, the value of SUVmax is divided into a high uptake group and a low uptake group to represent whether the blood vessels are injured, and a binary classification model is constructed therefrom. Among them, the upper quartile of the SUVmax of the dissection region is used as the classification threshold. Then, the characteristic parameter TAIWS of vascular injury and the morphological parameters of the blood vessels are used in combination with the clinical characteristic parameters of the patient, including but not limited to patient gender, age, history of coronary heart disease, history of diabetes, blood pressure, BMI index, etc. to construct a mixed effect logistic regression model (binary classification model) for predicting high SUVmax, which is used as the vascular injury evaluation model. After the model is constructed, the vascular injury degree of the patient can be predicted accordingly.

[0086] It should be noted that the step division of the above methods is only for the purpose of clear description, and in implementation, one step can be combined or some steps can be split and decomposed into multiple steps, as long as the same logical relationship is included, and all are within the protection scope of the present application. Irrelevant modifications or irrelevant designs can be added to the algorithm or process, but the core design of the algorithm and process is within the protection scope of the present application.

[0087] Embodiment 2

[0088] Please refer to Figure 4 The present embodiment also provides a system for constructing a vascular injury evaluation model, which comprises:

[0089] The data preprocessing module 10 is configured to acquire clinical image data of a patient and reconstruct a three-dimensional vascular model of the patient according to the clinical image data.

[0090] The feature parameter extraction module 20 is configured to extract a corresponding morphological parameter based on the three-dimensional vascular model and calculate a corresponding biomechanical parameter based on the three-dimensional vascular model.

[0091] The model construction module 30 is configured to calculate a feature parameter of vascular injury according to the biomechanical parameter and construct a vascular injury evaluation model according to the feature parameter and the morphological parameter, so as to predict the degree of vascular injury of the patient by using the vascular injury evaluation model.

[0092] It should be noted that the construction system of the vascular injury evaluation model provided in the above embodiment and the construction method of the vascular injury evaluation model provided in the above embodiment 1 belong to the same concept, and the specific manner in which each module and unit performs operations has been described in detail in the method embodiment, which will not be described here. The construction method of the vascular injury evaluation model provided in the above embodiment 1 can be used in actual application, and the above functions can be completed by different functional modules according to the needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the above described functions, and this is not limited here.

[0093] Embodiment 3

[0094] Please refer to Figure 5 The embodiment of the present application also provides an electronic device, which comprises a memory 2, a processor 1 and a program stored in the memory and capable of running on the processor, and the processor executes the steps of the above method.

[0095] The memory comprises at least one type of readable storage medium, including flash memory, mobile hard disk, multimedia card, card-type memory (such as SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory can be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory can also be an external storage device of the electronic device, such as a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory can include both the internal storage unit and the external storage device of the electronic device. The memory can be used not only to store application software and various data installed in the electronic device, but also to temporarily store data that has been output or will be output.

[0096] The processor can be composed of integrated circuits in some embodiments, for example, can be composed of a single packaged integrated circuit, or can be composed of multiple packaged integrated circuits with the same function or different functions, including one or more central processing units (CPU), microprocessors, digital processing chips, graphics processors, combinations of various control chips, etc. The processor is the control core (Control Unit) of the electronic device, which connects various components of the entire electronic device through various interfaces and lines, and executes programs or modules stored in the memory and calls data stored in the memory to perform various functions and process data of the electronic device.

[0097] The processor executes the operating system of the electronic device and various installed application programs. The processor executes the application programs to implement the steps in the above method embodiments.

[0098] For example, the program can be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present application. The one or more modules can be a series of program instruction segments that can complete a specific function, which are used to describe the execution process of the program in the electronic device.

[0099] The integrated units implemented in the form of software function modules described above can be stored in a computer readable storage medium. The software function modules described above are stored in a storage medium, including a plurality of instructions for causing a computer device (which can be a personal computer, a computer device, or a network device, etc.) or a processor to execute part of the functions of various embodiments of the present application.

[0100] In summary, the present application provides a method for constructing a blood vessel injury evaluation model based on structural image data of blood vessels, which proposes a new mechanical parameter by performing biomechanical calculation based on clinical routine examination images, and constructs a blood vessel injury evaluation model by combining key morphological parameters of blood vessels, so as to predict the degree of blood vessel injury of a patient by using the model, and meet the demand of clinical application.

[0101] The above embodiments only exemplarily illustrate the principles and effects of the present application, and are not used to limit the present application. Any person skilled in the art can modify or change the above embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by those skilled in the art without departing from the spirit and technical idea disclosed by the present application should be covered by the claims of the present application.

Claims

1. A method for constructing a vascular injury assessment model, characterized in that, The method comprises the following steps: acquiring clinical image data of a patient and reconstructing a three-dimensional vascular model of the patient according to the clinical image data; extracting morphological parameters corresponding to the three-dimensional vascular model and calculating biomechanical parameters corresponding to the three-dimensional vascular model, and the step comprises grid discretization processing of the three-dimensional vascular model; performing transient and / or steady-state biomechanical calculation according to the processed three-dimensional vascular model to obtain the corresponding biomechanical parameters; wherein, before the biomechanical calculation, each cardiac cycle is discretized into a plurality of time steps, each time step is related to the heart rate of the patient and the number of time steps, and the biomechanical calculation of multiple cycles is performed according to the time steps, and the corresponding biomechanical parameters are obtained according to the calculation results of the last cycle; calculating characteristic parameters of vascular injury according to the biomechanical parameters, and constructing a vascular injury evaluation model according to the characteristic parameters and the morphological parameters to predict the degree of vascular injury of the patient by using the vascular injury evaluation model; wherein, the biomechanical parameters at least include blood flow velocity, blood flow pressure, wall shear stress, the resultant force is calculated according to the wall shear stress and the stress of the blood flow pressure along the axial direction, and the average value of the resultant force in a cycle is taken as the characteristic parameter of vascular injury.

2. The method of claim 1, wherein, The step of reconstructing the three-dimensional vascular model of the patient comprises: segmenting a region of interest from the clinical image data and reconstructing a three-dimensional vascular model according to the region of interest; exporting the reconstructed three-dimensional vascular model in the form of triangular patches and performing smoothing and cutting processing; wherein, the clinical image data is structural image data of blood vessels.

3. The method of claim 1, wherein the blood vessel injury assessment model is constructed by using a machine learning algorithm. The step of extracting the corresponding morphological parameters based on the three-dimensional vascular model comprises: extracting a blood vessel centerline from the three-dimensional vascular model and interpolating the blood vessel centerline at intervals of image slice thickness; calculating the morphological parameters of the blood vessel along the blood vessel centerline according to the interpolated blood vessel centerline.

4. The method of claim 3, wherein, The morphological parameters are related to the patient's lesions.

5. The method of claim 3, wherein the blood vessel injury assessment model is constructed by using a machine learning algorithm. The morphological parameters include the volume of the blood vessel, and calculating the morphological parameters of the blood vessel along the blood vessel centerline according to the interpolated blood vessel centerline further comprises: calculating the volume of different sections of the blood vessel based on the division of the different sections of the blood vessel according to the key anatomical positions in the clinic.

6. The method of constructing a blood vessel lesion assessment model according to claim 1 or 3, characterized by, The morphological parameters at least include: cross-sectional area, perimeter, major axis, minor axis, average diameter, and equivalent diameter.

7. The method of claim 1, wherein the method further comprises: When the biomechanical calculation adopts hemodynamic calculation, the boundary conditions of blood and the physical properties of blood are preset according to the morphological structure characteristics of the blood vessels through which the blood flows during the calculation process; wherein, the boundary conditions include velocity boundary conditions and pressure boundary conditions.

8. The method of claim 1, wherein, When the biomechanical calculation adopts fluid-structure interaction calculation, the boundary conditions of blood, the physical properties of blood and the properties of the pipe wall of the blood vessels through which the blood flows are preset according to the morphological structure characteristics of the blood vessels through which the blood flows during the calculation process; wherein, the boundary conditions include velocity boundary conditions and pressure boundary conditions.

9. The method of claim 1, wherein, The formula for calculating the resultant force is as follows: ， , and , ， wherein, represents the blood flow pressure, represents the lumen radius of the blood vessel, represents the wall thickness of the blood vessel, represents the Poisson's ratio, represents the stress of the blood flow pressure along the axial direction, represents the wall shear stress, and respectively represent the normalized and , and respectively represent and the reference values of and are preset parameters, and range from , represents the resultant force.

10. The method of claim 1, wherein, The formula for calculating the average value of the resultant force in a cycle is as follows: ， wherein, represents an average value of the resultant force in one cycle, represents a cycle length, and respectively represent normalized values of the and , represents a stress of the blood flow pressure in the axial direction, represents a wall shear stress.​ 11. The method of claim 1, wherein, The step of constructing the vascular injury evaluation model comprises: The uptake value of the nuclear medicine image data is divided into a high uptake group and a low uptake group to represent the degree of vascular injury; According to the characteristic parameters of the vascular injury and the morphological parameters, and combined with the clinical characteristic parameters of the patient, a mixed effect logistic regression model is constructed as the vascular injury evaluation model.

12. A system for constructing a vascular injury assessment model, characterized in that, The method comprises the following steps: A data preprocessing module is configured to acquire clinical image data of a patient and reconstruct a three-dimensional vascular model of the patient based on the clinical image data; A characteristic parameter extraction module is configured to extract corresponding morphological parameters based on the three-dimensional vascular model and calculate corresponding biomechanical parameters based on the three-dimensional vascular model, and the steps comprise: performing grid discretization processing on the three-dimensional vascular model; performing transient and / or steady-state biomechanical calculation based on the processed three-dimensional vascular model to obtain corresponding biomechanical parameters; wherein, before performing the biomechanical calculation, each cardiac cycle is discretized into a plurality of time steps, each time step is related to the heart rate and the number of time steps of the patient, and the biomechanical calculation is performed for multiple cycles, and the corresponding biomechanical parameters are obtained based on the calculation result of the last cycle; A model construction module is configured to calculate the characteristic parameters of the vascular injury based on the biomechanical parameters, and construct a vascular injury evaluation model based on the characteristic parameters and the morphological parameters, so as to predict the degree of vascular injury of the patient by using the vascular injury evaluation model; wherein, the biomechanical parameters at least include blood flow velocity, blood flow pressure, wall shear stress, the resultant force is calculated based on the wall shear stress and the stress of the blood flow pressure along the axial direction, and the average value of the resultant force in a cycle is taken as the characteristic parameter of the vascular injury.

13. An electronic device, comprising: The computer program product comprises a processor coupled to a memory, and the memory stores program instructions which, when executed by the processor, implement the method of any one of claims 1 to 11.

14. A computer-readable storage medium, characterized in that, The computer program product comprises a processor coupled to a memory, and the memory stores program instructions which, when executed by the processor, implement the method of any one of claims 1 to 11.

Images