Hemodynamic analysis device, method, medium and electronic equipment

Abstract

The present invention provides a hemodynamic analysis device, method, medium and electronic device. The hemodynamic analysis device includes: a CT image acquisition module, used to acquire a CT image of a patient's heart; a CT image segmentation module, used to segment the CT image to acquire the stent area therein; a feature information acquisition module, used to acquire feature information of the stent according to the stent area; a stent model acquisition module, used to acquire a stent model according to the feature information of the stent; a coronary artery model acquisition module, used to acquire a coronary artery model of the patient according to the CT image; and a hemodynamic analysis module, used to perform hemodynamic analysis according to the coronary artery model and the stent model. The hemodynamic analysis device can acquire more accurate hemodynamic analysis results.

Description

Technical Field

[0001] The present invention relates to a simulation analysis device, and in particular to a hemodynamic analysis device, method, medium and electronic equipment. Background Art

[0002] Medical imaging is an important tool for medical diagnosis and is widely used in the diagnosis of various diseases in clinic. With the development of computer image processing technology and the application of artificial intelligence technology in the field of image processing technology in recent years, the use of computer image processing technology to post-process medical images can realize intelligent diagnosis of many diseases and obtain some physiological indicators of patients for doctors' diagnosis reference.

[0003] Cardiovascular disease is a disease with a high incidence in today's society, among which coronary artery disease is particularly common. Coronary arteries are arteries that surround the surface of the myocardium and supply blood to the myocardium. Cardiac CTA (CT angiography) images are an important basis for the diagnosis of coronary artery disease. Some existing medical image post-processing tools can segment CTA images to obtain a 3D model of the patient's coronary arteries, and can further process and calculate the coronary arteries to obtain the required hemodynamic indicators, such as fractional flow reserve (FFR), coronary flow reserve (CFR), etc.

[0004] However, the inventors have found in actual applications that the hemodynamic analysis of coronary arteries in the prior art has the following problems: some patients have stents placed in their coronary arteries, and the presence of the stents will change the morphology of the coronary blood flow pathway, thereby affecting the accuracy of the hemodynamic analysis, and further resulting in inaccurate hemodynamic indicators obtained. Summary of the invention

[0005] In view of the above-mentioned shortcomings of the prior art, an object of the present invention is to provide a hemodynamic analysis device, method, medium and electronic equipment for solving the above-mentioned problems existing in the prior art.

[0006] To achieve the above-mentioned purpose and other related purposes, the first aspect of the present invention provides a hemodynamic analysis device, which includes: a CT image acquisition module, used to acquire a CT image of the patient's heart area; a CT image segmentation module, used to segment the CT image to obtain the stent area therein; a feature information acquisition module, used to acquire feature information of the stent based on the stent area; a stent model acquisition module, used to acquire a stent model based on the feature information of the stent; a coronary artery model acquisition module, used to acquire the patient's coronary artery model based on the CT image; and a hemodynamic analysis module, used to perform hemodynamic analysis based on the coronary artery model and the stent model.

[0007] In an embodiment of the first aspect, the feature information acquisition module includes: a bracket category acquisition unit, used to acquire the category of the bracket according to the bracket area; and a feature information acquisition unit, used to acquire the feature information according to the category of the bracket.

[0008] In an embodiment of the first aspect, the stent category acquisition unit acquires characteristic parameters of the stent according to morphological features and CT values ​​of the stent region, and acquires the category of the stent according to the characteristic parameters.

[0009] In an embodiment of the first aspect, the stent category acquisition unit processes the stent region using an AI classification model to acquire the category of the stent.

[0010] In an embodiment of the first aspect, the stent model acquisition module acquires the stent model from a stent model library according to feature information of the stent.

[0011] In an embodiment of the first aspect, the hemodynamic analysis module includes: a stent model placement unit, used to place the stent model into the coronary artery model to obtain a revised coronary artery model; and a hemodynamic analysis unit, used to perform hemodynamic analysis based on the revised coronary artery model.

[0012] In an embodiment of the first aspect, the CT image segmentation module uses a deep learning stent detection model to segment the CT image to obtain the stent area.

[0013] The second aspect of the present invention provides a hemodynamic analysis method, which includes: obtaining a CT image of the patient's heart area; segmenting the CT image to obtain the stent area therein; obtaining characteristic information of the stent based on the stent area; obtaining a stent model based on the characteristic information of the stent; obtaining a coronary artery model of the patient based on the CT image; and performing hemodynamic analysis based on the coronary artery model and the stent model.

[0014] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the hemodynamic analysis method described in the second aspect of the present invention.

[0015] The fourth aspect of the present invention provides an electronic device, comprising: a memory storing a computer program; a processor communicatively connected to the memory, and executing the hemodynamic analysis method described in the second aspect of the present invention when calling the computer program.

[0016] As described above, the hemodynamic analysis device described in one or more embodiments of the present invention has the following beneficial effects:

[0017] The hemodynamic analysis device can obtain the stent area and the coronary artery model according to the CT image of the patient's heart, and can obtain the characteristic information of the stent according to the stent area and then obtain the stent model. The stent model and the coronary artery model enable the hemodynamic analysis device to fully consider the influence of the stent on the coronary blood flow pathway when performing hemodynamic analysis, so as to obtain more accurate hemodynamic analysis results. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 Shown is a schematic structural diagram of the hemodynamic analysis device of the present invention in a specific embodiment.

[0019] Figure 2 Shown is a schematic diagram of the structure of a characteristic information acquisition module in a specific embodiment of the hemodynamic analysis device of the present invention.

[0020] Figure 3A Shown is a schematic structural diagram of a hemodynamic analysis module in a specific embodiment of the hemodynamic analysis device of the present invention.

[0021] Figure 3B Shown is a schematic structural diagram of a hemodynamic analysis unit in a specific embodiment of the hemodynamic analysis device of the present invention.

[0022] Figure 4 Shown is a flow chart of the hemodynamic analysis method of the present invention in a specific embodiment.

[0023] Figure 5 Shown is a schematic structural diagram of the electronic device of the present invention in a specific embodiment.

[0024] Component number description

[0025] 1 Hemodynamic analysis device

[0026] 11 CT image acquisition module

[0027] 12 CT image segmentation module

[0028] 13 Feature Information Acquisition Module

[0029] 131 Bracket category acquisition unit

[0030] 132 Feature information acquisition unit

[0031] 14. Bracket model acquisition module

[0032] 15 Coronary artery model acquisition module

[0033] 16 Hemodynamic Analysis Module

[0034] 161 Bracket Model Placement Unit

[0035] 162 Hemodynamic Analysis Unit

[0036] 1621 Simulation Initialization Unit

[0037] 1622 Simulation execution unit

[0038] 500 Electronic equipment

[0039] 510 Memory

[0040] 520 processor

[0041] 530 Display

[0042] Steps S41 to S46 DETAILED DESCRIPTION

[0043] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0044] It should be noted that the illustrations provided in the following embodiments are only schematic illustrations of the basic concept of the present invention. The illustrations only show the components related to the present invention rather than the number, shape and size of the components in actual implementation. The type, quantity and proportion of each component in actual implementation may be changed at will, and the component layout type may also be more complicated. In addition, in this article, relational terms such as "first", "second", etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0045] The following problems exist in the hemodynamic analysis of coronary arteries in related technologies: some patients have stents placed in their coronary arteries, and the presence of the stents will change the morphology of the coronary blood flow pathway, thereby affecting the accuracy of the hemodynamic analysis, and thus resulting in inaccurate hemodynamic indicators. For this issue, please refer to Figure 1 In one embodiment of the present invention, a hemodynamic analysis device 1 is provided, and the hemodynamic analysis device 1 includes a CT image acquisition module 11, a CT image segmentation module 12, a feature information acquisition module 13, a stent model acquisition module 14, a coronary artery model acquisition module 15 and a hemodynamic analysis module 16.

[0046] The CT image acquisition module 11 is used to acquire a CT image of the patient's heart, wherein the CT image is a three-dimensional image. Preferably, the CT image is a three-dimensional CTA image.

[0047] The CT image segmentation module 12 is connected to the CT image acquisition module 11 and is used to segment the CT image to obtain the stent region therein. For example, the CT image segmentation module 12 can segment the CT image to obtain the stent region using a trained neural network model, but the present invention is not limited thereto.

[0048] The characteristic information acquisition module 13 is connected to the CT image segmentation module 12, and is used to acquire characteristic information of the stent according to the stent region. The characteristic information of the stent refers to information that can reflect the characteristics of the stent, including but not limited to size, material, model, etc.

[0049] The stent model acquisition module 14 is connected to the feature information acquisition module 13 and is used to acquire the stent model according to the feature information of the stent, wherein the stent model is a three-dimensional model.

[0050] The coronary artery model acquisition module 15 is connected to the CT image acquisition module 11 and is used to acquire the patient's coronary artery model according to the CT image.

[0051] The hemodynamic analysis module 16 is connected to the stent model acquisition module 14 and the coronary artery model acquisition module 15, and is used to perform hemodynamic analysis based on the coronary artery model and the stent model. For example, the hemodynamic analysis module 16 can use existing hemodynamic simulation software to implement the analysis, thereby obtaining desired hemodynamic parameters.

[0052] According to the above description, the hemodynamic analysis device 1 provided in this embodiment can obtain the stent area and the coronary artery model according to the CT image of the patient's heart area, and can obtain the characteristic information of the stent according to the stent area and then obtain the stent model. The stent model and the coronary artery model enable the hemodynamic analysis module 16 to fully consider the impact of the stent on the coronary blood flow pathway when performing hemodynamic analysis, so that more accurate hemodynamic analysis results can be obtained. Therefore, compared with the related art, the hemodynamic parameters obtained by the hemodynamic analysis device 1 in this embodiment have higher accuracy.

[0053] It should be noted that there are relatively mature blood vessel segmentation methods in the related art that can obtain the coronary model, such as U-Net, V-Net, etc. Therefore, the coronary model acquisition module 15 can obtain the coronary model by segmenting the CT image. The stent is located in the coronary vessel cavity, and it is difficult to directly obtain its model based on the CT image. Therefore, this embodiment uses the CT image segmentation module 12 to obtain the stent area and then obtain the stent feature information, and finally obtain the stent model to obtain the stent model. The stent model obtained in this way has higher accuracy.

[0054] See also Figure 2 In one embodiment of the present invention, the feature information acquisition module 13 includes a bracket category acquisition unit 131 and a feature information acquisition unit 132 .

[0055] The stent category acquisition unit 131 is connected to the CT image segmentation module 12 and is used to acquire the category of the stent according to the stent region.

[0056] Optionally, the stent category acquisition unit 131 may acquire characteristic parameters of the stent according to the morphological features and CT values ​​of the stent region, and acquire the category of the stent according to the characteristic parameters.

[0057] The morphological features of the stent region include, for example, the radial dimension and axial dimension of the stent region. The radial dimension is, for example, the diameter or radius of the stent region in the radial direction of the blood vessel, and the axial dimension is, for example, the length of the stent region along the extension direction of the blood vessel.

[0058] The characteristic parameters of the stent include, for example, the size and material of the stent. The diameter of the stent can be obtained based on the radial size of the stent area, the length of the stent can be obtained based on the axial size of the stent area, and the attenuation coefficient of the stent to X-rays can be obtained based on the CT value of the stent area, and thus the material of the stent can be obtained.

[0059] According to relevant regulations, the brands and models of stents that can be legally used in clinical practice are limited. Therefore, the brand and model of the stent, that is, the category of the stent, can be obtained from the limited brands and models based on the characteristic parameters of the stent.

[0060] Optionally, the bracket category acquisition unit 131 may process the bracket region using a trained AI classification model to obtain the bracket category, wherein the AI ​​classification model is, for example, a random forest model, an Adaboost model, etc., and the bracket category is, for example, the brand and model of the bracket.

[0061] The training method of the AI ​​classification model includes: obtaining training data, wherein the training data includes images of multiple stent areas and corresponding stent category labels; using the training data to train the AI ​​classification model; obtaining test data, wherein the test data includes images of multiple stent areas and corresponding stent category labels, and there is no intersection between the training data and the test data; and using the test data to test the AI ​​classification model.

[0062] The characteristic information acquisition unit 132 is connected to the bracket category acquisition unit 131, and is used to acquire the characteristic information according to the category of the bracket. Specifically, the standard model of the bracket can be acquired according to the brand and model of the bracket, and further characteristic information of the bracket can be acquired according to the standard model of the bracket. It can be understood that the characteristic parameters in this embodiment are included in the characteristic information.

[0063] In one embodiment of the present invention, the stent model acquisition module acquires the stent model from a stent model library according to the characteristic information of the stent. The stent model library is, for example, a standard model library, which stores a variety of standard stent models, and the standard stent model can be provided by a stent manufacturer. The stent model acquisition module can select the closest standard stent model from the stent model library as the stent model according to the characteristic information of the stent.

[0064] See also Figure 3A In one embodiment of the present invention, the hemodynamic analysis module 16 includes a stent model placement unit 161 and a hemodynamic analysis unit 162 .

[0065] The stent model placement unit 161 is connected to the stent model acquisition module 14 and the coronary artery model acquisition module 15, and is used to place the stent model into the coronary artery model to obtain a modified coronary artery model, wherein the modified coronary artery model is a coronary artery vascular model after the stent model is placed. The stent model and the coronary artery model are both three-dimensional models. In practical applications, the stent model can be virtually placed into the coronary artery model using existing simulation software to obtain the modified coronary artery model.

[0066] The hemodynamic analysis unit 162 is connected to the stent model placement unit 161, and is used to perform hemodynamic analysis according to the modified coronary artery model. At this time, since the stent model is virtually placed in the coronary artery model, the hemodynamic analysis result obtained by the hemodynamic analysis unit 162 can reflect the influence of the stent on the coronary blood flow pathway, and thus has higher accuracy.

[0067] Optionally, see Figure 3B The hemodynamic analysis unit 162 includes a simulation initialization unit 1621 and a simulation execution unit 1622 .

[0068] The simulation initialization unit 1621 is connected to the stent model placement unit 161 and is used to initialize the modified coronary artery model and the flow resistance model as a boundary condition. The flow resistance model can be obtained by formula To obtain, where L represents the oscillation suppression of coronary artery flow after the stent model is implanted, Q represents the flow at the coronary artery outlet after the stent model is implanted, P is the pressure at the coronary artery outlet after the stent model is implanted, and R is the flow resistance at the coronary artery outlet after the stent model is implanted.

[0069] The simulation execution unit 1622 is connected to the simulation initialization unit 1621, and is used to use the initialized flow resistance model as a boundary condition to perform hemodynamic simulation on the coronary artery after the stent model is implanted.

[0070] Preferably, after a hemodynamic simulation is completed, the simulation execution unit 1622 is further used to determine whether the termination condition is met according to the simulation result. If not, a new flow resistance model is obtained according to the P value obtained by the current hemodynamic simulation, and the hemodynamic simulation is performed again with the new flow resistance model as the boundary condition, and this process is repeated until the result of the hemodynamic simulation meets the termination condition. The termination condition is, for example,

[0071] Optionally, when performing hemodynamic simulation, the simulation execution unit 1622 obtains the average blood vessel flow according to the size of the coronary artery after the stent model is implanted and the flow conditions of each point inside the coronary artery.

[0072] Specifically, in, is the average flow rate in the blood vessel, x1 and x2 are the starting and ending positions of the coronary artery, |x1-x2| is the distance between the starting and ending points of the coronary artery, that is, the length of the coronary artery, S(x) is the cross-sectional area at point x in the coronary artery after the stent model is implanted, Q(x) is the volume flow rate at point x in the coronary artery after the stent model is implanted, and v(x) is the flow velocity at point x in the coronary artery after the stent model is implanted.

[0073] Based on the average blood vessel flow, the momentum equation used by the simulation execution unit 1622 when performing hemodynamic simulation is, for example: Among them, ρ is the blood density in the coronary artery after the stent model is implanted, S0 represents the average cross-sectional area of ​​the coronary artery at rest after the stent model is implanted, and K R is the viscous resistance coefficient, P2 and P1 are the average pressures at positions x2 and x1 in the coronary artery after the stent model is implanted.

[0074] The momentum equation used in this embodiment fully considers the impact of the placement of the stent model on the blood density, cross-sectional area and average pressure of the coronary vessels. The simulation results obtained based on the momentum equation can truly reflect the patient's hemodynamic parameters.

[0075] In one embodiment of the present invention, the hemodynamic analysis module 16 is further configured to edit the modified coronary artery model according to a model processing instruction input by a user.

[0076] Optionally, the hemodynamic analysis module 16 can determine the position that needs to be completed according to the model processing instruction input by the user, and complete the modified coronary model at this position. The position that needs to be completed can be located in the model missing area, the model broken area, etc. By completing the modified coronary model, the missing area and the broken area in the modified coronary model can be reduced, thereby improving the accuracy of subsequent hemodynamic analysis.

[0077] Optionally, the hemodynamic analysis module 16 can adjust the terminal blood vessel position of the modified coronary model according to the model processing instructions input by the user. Specifically, since the terminal end of the coronary artery is relatively small, the segmentation of the terminal end is more prone to errors, and the slight differences in the terminal part or the presence of small lesions will affect the accuracy of the overall hemodynamic data. In this embodiment, the hemodynamic analysis module 16 can adjust the terminal blood vessel position of the modified coronary model according to the model processing instructions input by the user, thereby obtaining a more accurate coronary model, which is conducive to further improving the accuracy of subsequent hemodynamic analysis.

[0078] In one embodiment of the present invention, the CT image segmentation module uses a deep learning stent detection model to segment the CT image to obtain the stent area. The training method of the deep learning stent detection model includes: using a plurality of vascular images annotated with stent position information as a training set, and after training, the deep learning stent detection model can automatically determine the location of the stent in the vascular image.

[0079] Based on the above description of the hemodynamic analysis device, the present invention also provides a hemodynamic analysis method.

[0080] See also Figure 4 In one embodiment of the present invention, the hemodynamic analysis method comprises:

[0081] S41, obtaining a CT image of the patient's heart.

[0082] S42, segmenting the CT image to obtain the stent region therein.

[0083] S43, acquiring characteristic information of the stent according to the stent area.

[0084] S44, acquiring the stent model according to the characteristic information of the stent.

[0085] S45, acquiring a coronary artery model of the patient according to the CT image.

[0086] S46, performing hemodynamic analysis based on the coronary artery model and the stent model.

[0087] The above steps S41 to S46 are Figure 1 The corresponding modules in the hemodynamic analysis device 1 are in one-to-one correspondence. It can be understood that the optional scheme of the hemodynamic analysis device 1 can also be applied to the hemodynamic analysis method described in this embodiment. In order to save space in the specification, it will not be described in detail here.

[0088] Based on the above description of the hemodynamic analysis method, the present invention further provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement Figure 4 The hemodynamic analysis method is shown.

[0089] Based on the above description of the hemodynamic analysis method, the present invention also provides an electronic device. Figure 5 In one embodiment of the present invention, the electronic device 500 includes a memory 510 and a processor 520. The memory 510 stores a computer program. The processor 520 is connected to the memory 510 for communication and executes the computer program when the computer program is called. Figure 1 The hemodynamic analysis method is shown.

[0090] Optionally, the electronic device 500 further includes a display 530. The display 530 is communicatively connected with the memory 510 and the processor 520, and is used to display a GUI interaction interface related to the hemodynamic analysis method.

[0091] The protection scope of the hemodynamic analysis method described in the present invention is not limited to the execution order of the steps listed in this embodiment. All solutions implemented by adding, reducing or replacing steps in the prior art based on the principles of the present invention are included in the protection scope of the present invention.

[0092] The present invention also provides a hemodynamic analysis device, which can implement the hemodynamic analysis method described in the present invention. However, the device for implementing the hemodynamic analysis method described in the present invention includes but is not limited to the structure of the hemodynamic analysis device listed in this embodiment. All structural deformations and replacements of the prior art made according to the principles of the present invention are included in the protection scope of the present invention.

[0093] In summary, the hemodynamic analysis device described in one or more embodiments of the present invention can obtain the stent area and coronary artery model according to the CT image of the patient's heart area, and can obtain the characteristic information of the stent according to the stent area and then obtain the stent model. The stent model and coronary artery model make it possible to fully consider the impact of the stent on the coronary blood flow pathway during the hemodynamic analysis process, thereby obtaining more accurate hemodynamic analysis results. Therefore, the present invention effectively overcomes various shortcomings in the prior art and has a high industrial utilization value.

[0094] The above embodiments are merely illustrative of the principles and effects of the present invention, and are not intended to limit the present invention. Anyone familiar with the art may modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by a person of ordinary skill in the art without departing from the spirit and technical concept disclosed by the present invention shall still be covered by the claims of the present invention.

Claims

1. A hemodynamic analysis device, characterized in that: The hemodynamic analysis device comprises: A CT image acquisition module, used for acquiring a CT image of a patient's heart; A CT image segmentation module, used for segmenting the CT image to obtain the stent area therein; A feature information acquisition module, used to acquire feature information of the stent according to the stent area; A stent model acquisition module, used to acquire a stent model according to characteristic information of the stent; A coronary artery model acquisition module, used for acquiring a coronary artery model of a patient according to the CT image; A hemodynamic analysis module, used for performing hemodynamic analysis based on the coronary artery model and the stent model; The hemodynamic analysis module includes a stent model placement unit and a hemodynamic analysis unit, wherein the stent model placement unit is used to place the stent model into the coronary artery model to obtain a revised coronary artery model, and the hemodynamic analysis unit is used to perform hemodynamic analysis according to the revised coronary artery model; The hemodynamic analysis unit includes a simulation initialization subunit and a simulation execution subunit, wherein the simulation initialization subunit is used to initialize the modified coronary model and the flow resistance model as a boundary condition, and the simulation execution subunit is used to perform hemodynamic simulation on the coronary vessel after the stent model is implanted by using the initialized flow resistance model as a boundary condition; The flow resistance model is expressed by the following formula: Where L represents the oscillation suppression of the coronary blood flow after the stent model is implanted, Q represents the flow at the coronary blood vessel outlet after the stent model is implanted, P represents the pressure at the coronary blood vessel outlet after the stent model is implanted, and R represents the flow resistance at the coronary blood vessel outlet after the stent model is implanted; The simulation execution subunit obtains the average blood vessel flow rate through the following formula: in is the average flow rate of the blood vessel, x1 and x2 are the starting point and end point of the coronary blood vessel, |x1-x2| is the distance between the starting point and the end point of the coronary blood vessel, that is, the length of the coronary blood vessel, S(x) is the cross-sectional area at x in the coronary blood vessel after the stent model is implanted, Q(x) is the volume flow rate at x in the coronary blood vessel after the stent model is implanted, and v(x) is the flow velocity at x in the coronary blood vessel after the stent model is implanted; The momentum equation used by the simulation execution subunit when performing hemodynamic simulation is: Among them, ρ is the blood density in the coronary artery after the stent model is implanted, S0 represents the average cross-sectional area of ​​the coronary artery at rest after the stent model is implanted, and K R is the viscous resistance coefficient, P2 and P1 are the average pressures at positions x2 and x1 in the coronary artery after the stent model is implanted.

2. The hemodynamic analysis device according to claim 1, characterized in that: The feature information acquisition module includes: A bracket category acquisition unit, used for acquiring the category of the bracket according to the bracket area; A characteristic information acquisition unit is used to acquire the characteristic information according to the category of the bracket.

3. The hemodynamic analysis device according to claim 2, characterized in that: The stent category acquisition unit acquires characteristic parameters of the stent according to the morphological characteristics and CT values ​​of the stent region, and acquires the category of the stent according to the characteristic parameters.

4. The hemodynamic analysis device according to claim 2, characterized in that: The stent category acquisition unit processes the stent region using an AI classification model to acquire the category of the stent.

5. The hemodynamic analysis device according to claim 1, characterized in that: The stent model acquisition module acquires the stent model from a stent model library according to the characteristic information of the stent.

6. The hemodynamic analysis device according to claim 1, characterized in that: The CT image segmentation module uses a deep learning stent detection model to segment the CT image to obtain the stent area.

7. A hemodynamic analysis method, characterized in that: The hemodynamic analysis method comprises: Obtaining a CT image of the patient's heart; Segmenting the CT image to obtain the stent region therein; Acquire characteristic information of the stent according to the stent area; Acquire a stent model according to the characteristic information of the stent; Acquire a coronary artery model of the patient according to the CT image; Performing hemodynamic analysis according to the coronary artery model and the stent model, including: placing the stent model into the coronary artery model to obtain a modified coronary artery model, initializing the modified coronary artery model and a flow resistance model as a boundary condition, and performing hemodynamic simulation on the coronary artery after the stent model is implanted by using the initialized flow resistance model as a boundary condition; The flow resistance model is expressed by the following formula: Where L represents the oscillation suppression of the coronary blood flow after the stent model is implanted, Q represents the flow at the coronary blood vessel outlet after the stent model is implanted, P represents the pressure at the coronary blood vessel outlet after the stent model is implanted, and R represents the flow resistance at the coronary blood vessel outlet after the stent model is implanted; In the hemodynamic simulation, the average blood vessel flow is obtained by the following formula: in is the average flow rate of the blood vessel, x1 and x2 are the starting point and end point of the coronary blood vessel, |x1-x2| is the distance between the starting point and the end point of the coronary blood vessel, that is, the length of the coronary blood vessel, S(x) is the cross-sectional area at x in the coronary blood vessel after the stent model is implanted, Q(x) is the volume flow rate at x in the coronary blood vessel after the stent model is implanted, and v(x) is the flow velocity at x in the coronary blood vessel after the stent model is implanted; The momentum equation used in the hemodynamic simulation is: Among them, ρ is the blood density in the coronary artery after the stent model is implanted, S0 represents the average cross-sectional area of ​​the coronary artery at rest after the stent model is implanted, and K R is the viscous resistance coefficient, P2 and P1 are the average pressures at positions x2 and x1 in the coronary artery after the stent model is implanted.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the hemodynamic analysis method according to claim 7 is implemented.

9. An electronic device, characterized in that: The electronic device comprises: A memory storing a computer program; A processor is communicatively connected to the memory and executes the hemodynamic analysis method of claim 7 when calling the computer program.

Images