Hemodynamic parameter determination method and device, electronic equipment and storage medium

Abstract

The invention discloses a hemodynamic parameter determination method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a three-dimensional blood vessel segment model, and performing two-dimensional mapping on the three-dimensional blood vessel segment model to obtain a two-dimensional blood vessel segment model; carrying out nondimensionalization on the two-dimensional blood vessel segment model to obtain a nondimensionalized two-dimensional blood vessel segment model; determining dimensionless hemodynamic parameters on the basis of the dimensionless two-dimensional blood vessel segment model; and based on a preset dimensionless coefficient, converting the dimensionless hemodynamic parameters into actual hemodynamic parameters. According to the technical scheme, calculation of the hemodynamic parameters is simplified through nondimensionalization, and the determination speed of the hemodynamic parameters is increased.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method, device, electronic equipment and storage medium for determining hemodynamic parameters. Background Art

[0002] Vascular diseases are gradually becoming a threat to human health, such as coronary artery diseases, cerebrovascular diseases, and aortic diseases. Based on the above situation, the analysis of vascular dynamic parameters has become a key research direction.

[0003] In the process of implementing the present invention, it is found that there are at least the following technical problems in the prior art: Currently, the method for determining vascular dynamic parameters has the problem of slow calculation speed. Summary of the invention

[0004] The present invention provides a method, device, electronic equipment and storage medium for determining hemodynamic parameters, so as to improve the speed of determining hemodynamic parameters.

[0005] According to one aspect of the present invention, a method for determining hemodynamic parameters is provided, comprising:

[0006] Acquire a three-dimensional blood vessel segment model, and perform two-dimensional mapping on the three-dimensional blood vessel segment model to obtain a two-dimensional blood vessel segment model;

[0007] Non-dimensionalizing the two-dimensional blood vessel segment model to obtain a non-dimensionalized two-dimensional blood vessel segment model;

[0008] Determining dimensionless hemodynamic parameters based on the dimensionless two-dimensional vascular segment model;

[0009] Based on preset dimensionless coefficients, the dimensionless hemodynamic parameters are converted into actual hemodynamic parameters.

[0010] According to another aspect of the present invention, there is provided a device for determining hemodynamic parameters, comprising:

[0011] A model two-dimensional mapping module, used to obtain a three-dimensional blood vessel segment model, and perform two-dimensional mapping on the three-dimensional blood vessel segment model to obtain a two-dimensional blood vessel segment model;

[0012] A model dimensionless module, used for dimensionlessizing the two-dimensional blood vessel segment model to obtain a dimensionless two-dimensional blood vessel segment model;

[0013] A dimensionless parameter determination module, used for determining dimensionless hemodynamic parameters based on the dimensionless two-dimensional vascular segment model;

[0014] The actual parameter determination module is used to convert the dimensionless hemodynamic parameter into an actual hemodynamic parameter based on a preset dimensionless coefficient.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] at least one processor;

[0017] and a memory communicatively coupled to the at least one processor;

[0018] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the hemodynamic parameter determination method described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining hemodynamic parameters described in any embodiment of the present invention when executed.

[0020] The technical solution of the embodiment of the present invention obtains a three-dimensional vascular segment model, performs two-dimensional mapping on the three-dimensional vascular segment model, obtains a two-dimensional vascular segment model, and then performs dimensionless transformation on the two-dimensional vascular segment model to obtain a dimensionless two-dimensional vascular segment model, and then determines dimensionless hemodynamic parameters based on the dimensionless two-dimensional vascular segment model, and converts the dimensionless hemodynamic parameters into actual hemodynamic parameters based on preset dimensionless coefficients. The above technical solution simplifies the calculation of hemodynamic parameters by dimensionless transformation, and improves the speed of determining hemodynamic parameters.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 is a flow chart of a method for determining hemodynamic parameters provided according to Embodiment 1 of the present invention;

[0024] Figure 2 A schematic diagram of the structure of a three-dimensional blood vessel segment model provided by an embodiment of the present invention. A two-dimensional blood vessel segment model refers to a two-dimensional blood vessel segment model;

[0025] Figure 3 A schematic diagram of the structure of a two-dimensional blood vessel segment model provided by an embodiment of the present invention;

[0026] Figure 4 is a flow chart of a method for determining hemodynamic parameters provided according to Embodiment 2 of the present invention;

[0027] Figure 5 is a flow chart of a method for determining hemodynamic parameters provided according to Embodiment 3 of the present invention;

[0028] Figure 6 is a flow chart of a method for determining hemodynamic parameters provided according to a fourth embodiment of the present invention;

[0029] Figure 7 is a flow chart of a method for determining hemodynamic parameters provided in Embodiment 5 of the present invention;

[0030] Figure 8 is a flow chart of a method for determining hemodynamic parameters provided according to Embodiment 6 of the present invention;

[0031] Fig. 9 is a structural schematic diagram of a device for determining hemodynamic parameters provided according to Embodiment 7 of the present invention;

[0032] Fig.10 It is a structural schematic diagram of an electronic device for implementing the method for determining hemodynamic parameters according to an embodiment of the present invention. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices. The acquisition, storage, use, processing, etc. of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0035] Embodiment 1

[0036] Figure 1 This is a flow chart of a method for determining hemodynamic parameters provided in the first embodiment of the present invention. This embodiment is applicable to the case of simulating and calculating hemodynamic parameters. The method can be executed by a hemodynamic parameter determination device. The hemodynamic parameter determination device can be implemented in the form of hardware and / or software. The hemodynamic parameter determination device can be configured in an electronic device such as a terminal or a server. Figure 1 As shown, the method includes:

[0037] S110 , obtaining a three-dimensional blood vessel segment model, and performing two-dimensional mapping on the three-dimensional blood vessel segment model to obtain a two-dimensional blood vessel segment model.

[0038] In the embodiment of the present invention, the three-dimensional blood vessel segment model refers to a blood vessel segment model segmented from the three-dimensional blood vessel model. Figure 2 A schematic diagram of the structure of a three-dimensional blood vessel segment model provided by an embodiment of the present invention. A two-dimensional blood vessel segment model refers to a two-dimensional blood vessel segment model. For example, Figure 3 A schematic structural diagram of a two-dimensional blood vessel segment model provided by an embodiment of the present invention.

[0039] Illustratively, a computed tomography (CT) image or angiography image can be three-dimensionally reconstructed to obtain a three-dimensional vascular model, and then the blood vessels in the three-dimensional vascular model can be divided into multiple vascular segments to obtain three-dimensional vascular segment models corresponding to the multiple vascular segments. For the three-dimensional vascular segment model corresponding to any vascular segment, the three-dimensional vascular segment model can be two-dimensionally projected and mapped to obtain a two-dimensional vascular segment model corresponding to the vascular segment.

[0040] S120 , dimensionlessly transforming the two-dimensional blood vessel segment model to obtain a dimensionlessly transformed two-dimensional blood vessel segment model.

[0041] In the embodiment of the present invention, dimensionless conversion refers to converting dimensional physical quantities in the two-dimensional vascular segment model into dimensionless quantities to simplify the calculation of hemodynamic parameters in the two-dimensional vascular segment model, thereby increasing the speed of determining the hemodynamic parameters.

[0042] Exemplarily, the two-dimensional vascular segment model may be subjected to dimensionless processing such as extremization, standardization, averaging or standard deviation. The dimensional physical quantities in the two-dimensional vascular segment model may include but are not limited to the vascular segment inlet diameter, vascular segment outlet diameter and vascular segment centerline length, etc., which are not specifically limited here.

[0043] S130. Determine dimensionless hemodynamic parameters based on the dimensionless two-dimensional blood vessel segment model.

[0044] In some embodiments, the dimensionless two-dimensional vascular segment model can be subjected to computational fluid dynamics simulation to obtain dimensionless hemodynamic parameters. In some embodiments, the geometric parameters of the dimensionless two-dimensional vascular segment model can also be input into a pre-trained physical information neural network to predict dimensionless hemodynamic parameters, and the geometric parameters can include but are not limited to the vascular diameter and the vascular centerline length.

[0045] S140. Based on a preset dimensionless coefficient, convert the dimensionless hemodynamic parameter into an actual hemodynamic parameter.

[0046] In the embodiment of the present invention, the dimensionless hemodynamic parameter may include dimensionless blood vessel segment flow and dimensionless blood vessel segment pressure, etc., and the actual hemodynamic parameter refers to a dimensional hemodynamic parameter, which may include dimensional blood vessel segment flow and dimensional blood vessel segment pressure, etc. The preset dimensionless coefficient may include a length coefficient, a density coefficient, a time coefficient, etc., which are not specifically limited here.

[0047] For example, the dimensionless blood vessel segment flow rate may be 1, the dimensionless blood vessel segment pressure may be 1, the length coefficient may be 10, the density coefficient may be 1000, and the time coefficient may be 10. The specific conversion formula may be:

[0048]

[0049] Where q represents the dimensionless blood vessel segment flow, p represents the dimensionless blood vessel segment pressure, and C l Indicates the length coefficient, C ρ represents the density coefficient, C t represents the time coefficient, Q represents the dimensional blood vessel segment flow, and P represents the dimensional blood vessel segment pressure.

[0050] The technical solution of the embodiment of the present invention obtains a three-dimensional vascular segment model, performs two-dimensional mapping on the three-dimensional vascular segment model, obtains a two-dimensional vascular segment model, and then performs dimensionless transformation on the two-dimensional vascular segment model to obtain a dimensionless two-dimensional vascular segment model, and then determines dimensionless hemodynamic parameters based on the dimensionless two-dimensional vascular segment model, and converts the dimensionless hemodynamic parameters into actual hemodynamic parameters based on preset dimensionless coefficients. The above technical solution simplifies the calculation of hemodynamic parameters by dimensionless transformation, and improves the speed of determining hemodynamic parameters.

[0051] Embodiment 2

[0052] Figure 4 This is a flow chart of a method for determining hemodynamic parameters provided in the second embodiment of the present invention. The method of this embodiment can be combined with the various optional solutions in the method for determining hemodynamic parameters provided in the above embodiments. The method for determining hemodynamic parameters provided in this embodiment further optimizes the "two-dimensional mapping". Figure 4 As shown, the method includes:

[0053] S210: Acquire a three-dimensional blood vessel segment model.

[0054] S220 . Determine a first port normal vector and a second port normal vector of the three-dimensional blood vessel segment model.

[0055] The first port normal vector may be a normal vector of the blood vessel segment entrance, which is perpendicular to the blood vessel segment entrance cross section. The second port normal vector may be a normal vector of the blood vessel segment exit, which is perpendicular to the blood vessel segment exit cross section. In some embodiments, the first port may also be an exit, and the second port may also be an entrance, which is not specifically limited here.

[0056] S230: Determine a normal vector of a mapping plane based on the first port normal vector and the second port normal vector.

[0057] Exemplarily, a normal vector obtained by cross-producting a normal vector at an inlet of the blood vessel segment and a normal vector at an outlet of the blood vessel segment may be used as a normal vector of the mapping plane.

[0058] S240: Determine a first port diameter, a second port diameter, a blood vessel centerline, and a blood vessel wall surface of the three-dimensional blood vessel segment model.

[0059] The first port diameter may be an inlet diameter of the blood vessel segment, and the second port diameter may be an outlet diameter of the blood vessel segment.

[0060] For example, the vessel segment inlet diameter, vessel segment outlet diameter, vessel centerline and vessel wall surface of the three-dimensional vessel segment model may be identified by an image processing method.

[0061] S250 , mapping the first port diameter, the second port diameter, the blood vessel centerline and the blood vessel wall surface of the three-dimensional blood vessel segment model onto the mapping plane to obtain a two-dimensional blood vessel segment model.

[0062] The geometric parameters of the two-dimensional blood vessel segment model may include a first port diameter mapped on the mapping plane, a second port diameter mapped on the mapping plane, a blood vessel centerline mapped on the mapping plane, and a blood vessel wall surface mapped on the mapping plane.

[0063] For example, Figure 3 As shown, the left edge of the two-dimensional blood vessel segment model represents the first port diameter mapped to the mapping plane, the right edge of the two-dimensional blood vessel segment model represents the second port diameter mapped to the mapping plane, the upper and lower edges of the two-dimensional blood vessel segment model represent the blood vessel wall mapped to the mapping plane, and the symmetry axis (not shown) of the two-dimensional blood vessel segment model represents the blood vessel centerline mapped to the mapping plane.

[0064] S260 , dimensionlessly transforming the two-dimensional blood vessel segment model to obtain a dimensionlessly transformed two-dimensional blood vessel segment model.

[0065] S270. Determine dimensionless hemodynamic parameters based on the dimensionless two-dimensional blood vessel segment model.

[0066] S280. Based on a preset dimensionless coefficient, convert the dimensionless hemodynamic parameter into an actual hemodynamic parameter.

[0067] The technical solution of the embodiment of the present invention determines the first port normal vector and the second port normal vector of the three-dimensional vascular segment model, and then determines the normal vector of the mapping plane based on the first port normal vector and the second port normal vector, determines the first port diameter, the second port diameter, the vascular centerline and the vascular wall of the three-dimensional vascular segment model, and then maps the first port diameter, the second port diameter, the vascular centerline and the vascular wall of the three-dimensional vascular segment model to the mapping plane to obtain a two-dimensional vascular segment model, thereby realizing automatic mapping of the three-dimensional vascular segment model to the two-dimensional vascular segment model, and converting the three-dimensional calculation problem into a two-dimensional axisymmetric problem, so as to simplify the subsequent hemodynamic parameter determination steps and improve the hemodynamic parameter determination speed.

[0068] Embodiment 3

[0069] Figure 5 This is a flow chart of a method for determining hemodynamic parameters provided in Embodiment 3 of the present invention. The method of this embodiment can be combined with the various optional solutions in the method for determining hemodynamic parameters provided in the above embodiments. The method for determining hemodynamic parameters provided in this embodiment further optimizes "dimensionless".

[0070] like Figure 5 As shown, the method includes:

[0071] S310 , obtaining a three-dimensional blood vessel segment model, and performing two-dimensional mapping on the three-dimensional blood vessel segment model to obtain a two-dimensional blood vessel segment model.

[0072] S320, standardizing the first port diameter, the second port diameter, the blood vessel centerline and the blood vessel wall surface of the two-dimensional blood vessel segment model to obtain a dimensionless two-dimensional blood vessel segment model.

[0073] S330 , determining dimensionless hemodynamic parameters based on the dimensionless two-dimensional blood vessel segment model.

[0074] S340. Based on a preset dimensionless coefficient, convert the dimensionless hemodynamic parameter into an actual hemodynamic parameter.

[0075] In some embodiments, the inlet diameter of the blood vessel segment can be equivalent to 1 or other preset values, and the outlet diameter of the blood vessel segment, the blood vessel centerline and the blood vessel wall can be scaled in the same proportion according to the equivalent value of the inlet diameter of the blood vessel segment, thereby completing the standardization of the two-dimensional blood vessel segment model.

[0076] The technical solution of the embodiment of the present invention obtains a dimensionless two-dimensional vascular segment model by standardizing at least one of the first port diameter, the second port diameter, the vascular centerline and the vascular wall surface of the two-dimensional vascular segment model, thereby simplifying the geometric parameters of the two-dimensional vascular segment model and effectively improving the speed of determining subsequent hemodynamic parameters.

[0077] Embodiment 4

[0078] Figure 6 This is a flowchart of a method for determining hemodynamic parameters provided in Embodiment 4 of the present invention. The method of this embodiment can be combined with the various optional solutions in the method for determining hemodynamic parameters provided in the above embodiments. The method for determining hemodynamic parameters provided in this embodiment further defines "determining dimensionless hemodynamic parameters". Figure 6 As shown, the method includes:

[0079] S410 , obtaining a three-dimensional blood vessel segment model, and performing two-dimensional mapping on the three-dimensional blood vessel segment model to obtain a two-dimensional blood vessel segment model.

[0080] S420 , dimensionlessly transforming the two-dimensional blood vessel segment model to obtain a dimensionlessly transformed two-dimensional blood vessel segment model.

[0081] S430, matching the dimensionless two-dimensional vascular segment model in a model library to obtain a target two-dimensional vascular segment model, wherein the model library includes a plurality of two-dimensional vascular segment models that have completed computational fluid dynamics simulation.

[0082] The target two-dimensional blood vessel segment model is a model that is the same as or similar to the dimensionless two-dimensional blood vessel segment model.

[0083] Exemplarily, the dimensionless two-dimensional blood vessel segment model and / or boundary conditions may be matched in a model library to obtain a target two-dimensional blood vessel segment model, wherein the boundary conditions may be an inlet flow velocity or an outlet pressure, etc.

[0084] S440, acquiring flow field information and pressure field information of the target two-dimensional vascular segment model, and performing computational fluid dynamics simulation on the dimensionless two-dimensional vascular segment model based on the flow field information and pressure field information of the target two-dimensional vascular segment model to obtain dimensionless hemodynamic parameters.

[0085] Exemplarily, since the target two-dimensional vascular segment model is a model that has completed computational fluid dynamics simulation, the flow field information and pressure field information of the target two-dimensional vascular segment model can be directly applied to the computational fluid dynamics simulation of the dimensionless two-dimensional vascular segment model, which can simplify the steps of computational fluid dynamics simulation of the dimensionless two-dimensional vascular segment model, thereby improving the calculation speed of dimensionless hemodynamic parameters.

[0086] S450: Based on a preset dimensionless coefficient, convert the dimensionless hemodynamic parameter into an actual hemodynamic parameter.

[0087] The technical solution of the embodiment of the present invention can simplify the steps of computational fluid dynamics simulation of the dimensionless two-dimensional vascular segment model by applying the flow field information and pressure field information of the target two-dimensional vascular segment model to the computational fluid dynamics simulation of the dimensionless two-dimensional vascular segment model, thereby improving the calculation speed of dimensionless hemodynamic parameters.

[0088] Embodiment 5

[0089] Figure 7 This is a flowchart of a method for determining hemodynamic parameters provided in Embodiment 5 of the present invention. The method of this embodiment can be combined with the various optional solutions in the method for determining hemodynamic parameters provided in the above embodiments. The method for determining hemodynamic parameters provided in this embodiment is further limited to "determining dimensionless hemodynamic parameters".

[0090] like Figure 7 As shown, the method includes:

[0091] S510 , obtaining a three-dimensional blood vessel segment model, and performing two-dimensional mapping on the three-dimensional blood vessel segment model to obtain a two-dimensional blood vessel segment model.

[0092] S520 , dimensionlessly transforming the two-dimensional blood vessel segment model to obtain a dimensionlessly transformed two-dimensional blood vessel segment model.

[0093] S530: Acquire geometric parameters and boundary conditions of the dimensionless two-dimensional blood vessel segment model.

[0094] The dimensionless geometric parameters of the two-dimensional blood vessel segment model may include coordinate information corresponding to the inlet, outlet, blood vessel centerline and blood vessel wall surface. Boundary conditions may include inlet flow rate and outlet pressure.

[0095] S540, inputting the dimensionless geometric parameters and boundary conditions of the two-dimensional blood vessel segment model into a pre-trained physical information neural network to obtain dimensionless hemodynamic parameters.

[0096] In an embodiment of the present invention, the physical information neural network training process includes: obtaining multiple sets of dimensionless geometric parameters and boundary conditions of the two-dimensional vascular segment model, using the multiple sets of dimensionless geometric parameters and boundary conditions of the two-dimensional vascular segment model as input data of the physical information neural network, and using the Navier-Stokes equation as a loss function to adjust the network parameters of the physical information neural network until the training stop condition is met, thereby obtaining a trained physical information neural network.

[0097] S550: Based on a preset dimensionless coefficient, convert the dimensionless hemodynamic parameter into an actual hemodynamic parameter.

[0098] The technical solution of the embodiment of the present invention, by inputting the dimensionless geometric parameters and boundary conditions of the two-dimensional vascular segment model into a pre-trained physical information neural network, can predict the dimensionless hemodynamic parameters without complex logical operations, thereby improving the speed of determining the hemodynamic parameters compared to the prior art.

[0099] Embodiment 6

[0100] Figure 8This is a flow chart of a method for determining hemodynamic parameters provided in Embodiment 6 of the present invention. The method of this embodiment can be combined with the various optional solutions in the method for determining hemodynamic parameters provided in the above embodiments. The method for determining hemodynamic parameters provided in this embodiment is further optimized. Optionally, after determining the dimensionless hemodynamic parameters based on the dimensionless two-dimensional vascular segment model, it also includes: obtaining the irregularity of the vascular lumen of the three-dimensional vascular segment model, the dimensionless vascular segment length of the three-dimensional vascular segment model, and the dimensionless vascular segment length of the two-dimensional vascular segment model; inputting the irregularity of the vascular lumen of the three-dimensional vascular segment model, the dimensionless vascular segment length of the three-dimensional vascular segment model, and the dimensionless vascular segment length of the two-dimensional vascular segment model into the hemodynamic parameter correction model to obtain the hemodynamic parameter correction coefficient; determining the corrected dimensionless hemodynamic parameters based on the hemodynamic parameter correction coefficient and the dimensionless hemodynamic parameters; accordingly, converting the dimensionless hemodynamic parameters into actual hemodynamic parameters based on the preset dimensionless coefficients includes: converting the corrected dimensionless hemodynamic parameters into actual hemodynamic parameters based on the preset dimensionless coefficients.

[0101] like Figure 8 As shown, the method includes:

[0102] S610 , obtaining a three-dimensional blood vessel segment model, and performing two-dimensional mapping on the three-dimensional blood vessel segment model to obtain a two-dimensional blood vessel segment model.

[0103] S620 , dimensionlessly transforming the two-dimensional blood vessel segment model to obtain a dimensionlessly transformed two-dimensional blood vessel segment model.

[0104] S630: Determine dimensionless hemodynamic parameters based on the dimensionless two-dimensional blood vessel segment model.

[0105] S640: Obtain the irregularity of the blood vessel lumen of the three-dimensional blood vessel segment model, the dimensionless blood vessel segment length of the three-dimensional blood vessel segment model, and the dimensionless blood vessel segment length of the two-dimensional blood vessel segment model.

[0106] In the embodiment of the present invention, the irregularity of the blood vessel lumen refers to the irregularity of the blood vessel lumen contour compared to a regular circle.

[0107] Specifically, the vascular lumen contour of the three-dimensional vascular segment model is sampled to obtain a plurality of vascular lumen contour points; the distances between the plurality of vascular lumen contour points and the vascular centerline are determined; and the irregularity of the vascular lumen of the three-dimensional vascular segment model is determined based on the distances between the plurality of vascular lumen contour points and the vascular centerline.

[0108] Exemplarily, the irregularity of the blood vessel lumen of the three-dimensional blood vessel segment model may include the irregularity of the blood vessel outlet lumen and the irregularity of the blood vessel inlet lumen. Specifically, 36 points are sampled from the blood vessel inlet lumen contour of the three-dimensional blood vessel segment model to obtain 36 blood vessel inlet lumen contour points, and the distances between the 36 blood vessel inlet lumen contour points and the blood vessel centerline are determined, and the standard deviation of the distances between the 36 blood vessel inlet lumen contour points and the blood vessel centerline is determined as the irregularity of the blood vessel inlet lumen of the three-dimensional blood vessel segment model. Similarly, the irregularity calculation process of the blood vessel outlet lumen is the same as the irregularity calculation process of the blood vessel inlet lumen, which will not be repeated here.

[0109] In the embodiment of the present invention, the dimensionless blood vessel segment length of the three-dimensional blood vessel segment model refers to the dimensionless blood vessel segment length measured under the three-dimensional blood vessel segment model. The dimensionless blood vessel segment length of the two-dimensional blood vessel segment model refers to the dimensionless blood vessel segment length measured under the two-dimensional blood vessel segment model.

[0110] S650, inputting the irregularity of the vascular lumen of the three-dimensional vascular segment model, the dimensionless vascular segment length of the three-dimensional vascular segment model, and the dimensionless vascular segment length of the two-dimensional vascular segment model into a hemodynamic parameter correction model to obtain a hemodynamic parameter correction coefficient.

[0111] In an embodiment of the present invention, the training process of the hemodynamic parameter correction model includes: taking the irregularity of multiple vascular outlet lumens, the irregularity of multiple vascular inlet lumens, and the ratio of the dimensionless vascular segment length of multiple three-dimensional vascular segment models to the dimensionless vascular segment length of the two-dimensional vascular segment model as inputs to the neural network model, and taking the hemodynamic parameter correction coefficient as a label; further, training the neural network model based on the above training samples until the model training stop condition is met to obtain the hemodynamic parameter correction model, wherein the neural network model can be a deep learning model of any network architecture, which is not specifically limited here.

[0112] Exemplarily, the calculation formula of the hemodynamic parameter correction coefficient is as follows:

[0113] c = f(std1,std2,A / B);

[0114] Among them, c represents the hemodynamic parameter correction coefficient, f represents the hemodynamic parameter correction model, std1 represents the irregularity of the inlet vascular lumen, std2 represents the irregularity of the outlet vascular lumen, A represents the dimensionless vascular segment length of the three-dimensional vascular segment model, and B represents the dimensionless vascular segment length of the two-dimensional vascular segment model.

[0115] S660. Determine a corrected dimensionless hemodynamic parameter based on the hemodynamic parameter correction coefficient and the dimensionless hemodynamic parameter.

[0116] Exemplarily, the calculation formula of the modified dimensionless hemodynamic parameter is:

[0117] Corrected dimensionless hemodynamic parameter = dimensionless hemodynamic parameter × c.

[0118] S670: Based on a preset dimensionless coefficient, convert the corrected dimensionless hemodynamic parameter into an actual hemodynamic parameter.

[0119] The technical solution of the embodiment of the present invention corrects the dimensionless hemodynamic parameters by using the hemodynamic parameter correction coefficient, thereby effectively improving the accuracy of the dimensionless hemodynamic parameters.

[0120] Embodiment 7

[0121] Fig. 9 This is a schematic diagram of the structure of a device for determining hemodynamic parameters provided by Embodiment 7 of the present invention. Fig. 9 As shown, the device comprises:

[0122] A model two-dimensional mapping module 710 is used to obtain a three-dimensional blood vessel segment model, and perform two-dimensional mapping on the three-dimensional blood vessel segment model to obtain a two-dimensional blood vessel segment model;

[0123] A model dimensionless conversion module 720 is used to perform dimensionless conversion on the two-dimensional blood vessel segment model to obtain a dimensionless two-dimensional blood vessel segment model;

[0124] A dimensionless parameter determination module 730, configured to determine dimensionless hemodynamic parameters based on the dimensionless two-dimensional blood vessel segment model;

[0125] The actual parameter determination module 740 is used to convert the dimensionless hemodynamic parameter into an actual hemodynamic parameter based on a preset dimensionless coefficient.

[0126] The technical solution of the embodiment of the present invention obtains a three-dimensional vascular segment model, performs two-dimensional mapping on the three-dimensional vascular segment model, obtains a two-dimensional vascular segment model, and then performs dimensionless transformation on the two-dimensional vascular segment model to obtain a dimensionless two-dimensional vascular segment model, and then determines dimensionless hemodynamic parameters based on the dimensionless two-dimensional vascular segment model, and converts the dimensionless hemodynamic parameters into actual hemodynamic parameters based on preset dimensionless coefficients. The above technical solution simplifies the calculation of hemodynamic parameters by dimensionless transformation, and improves the speed of determining hemodynamic parameters.

[0127] In some optional implementations, the model two-dimensional mapping module 710 may be specifically used for:

[0128] determining a first port normal vector and a second port normal vector of the three-dimensional blood vessel segment model;

[0129] determining a normal vector of a mapping plane based on the first port normal vector and the second port normal vector;

[0130] Determining a first port diameter, a second port diameter, a blood vessel centerline, and a blood vessel wall surface of the three-dimensional blood vessel segment model;

[0131] The first port diameter, the second port diameter, the blood vessel centerline and the blood vessel wall surface of the three-dimensional blood vessel segment model are mapped onto the mapping plane to obtain a two-dimensional blood vessel segment model.

[0132] In some optional implementations, the model dimensionless module 720 may be specifically used to:

[0133] The first port diameter, the second port diameter, the blood vessel centerline and the blood vessel wall surface of the two-dimensional blood vessel segment model are standardized to obtain a dimensionless two-dimensional blood vessel segment model.

[0134] In some optional implementations, the dimensionless parameter determination module 730 may be specifically used to:

[0135] Matching the dimensionless two-dimensional blood vessel segment model in a model library to obtain a target two-dimensional blood vessel segment model, wherein the model library includes a plurality of two-dimensional blood vessel segment models that have completed computational fluid dynamics simulation;

[0136] The flow field information and the pressure field information of the target two-dimensional vascular segment model are obtained, and based on the flow field information and the pressure field information of the target two-dimensional vascular segment model, computational fluid dynamics simulation is performed on the dimensionless two-dimensional vascular segment model to obtain dimensionless hemodynamic parameters.

[0137] In some optional implementations, the dimensionless parameter determination module 730 may be specifically used to:

[0138] Acquiring geometric parameters and boundary conditions of the dimensionless two-dimensional blood vessel segment model;

[0139] The dimensionless geometric parameters and boundary conditions of the two-dimensional blood vessel segment model are input into a pre-trained physical information neural network to obtain dimensionless hemodynamic parameters.

[0140] In some optional embodiments, the hemodynamic parameter determination device further includes:

[0141] A hemodynamic parameter correction data acquisition unit, used to acquire the irregularity of the vascular lumen of the three-dimensional vascular segment model, the dimensionless vascular segment length of the three-dimensional vascular segment model, and the dimensionless vascular segment length of the two-dimensional vascular segment model;

[0142] a hemodynamic parameter correction coefficient determination unit, used for inputting the irregularity of the vascular lumen of the three-dimensional vascular segment model, the dimensionless vascular segment length of the three-dimensional vascular segment model, and the dimensionless vascular segment length of the two-dimensional vascular segment model into the hemodynamic parameter correction model to obtain the hemodynamic parameter correction coefficient;

[0143] A dimensionless hemodynamic parameter correction unit, used for determining a corrected dimensionless hemodynamic parameter based on the hemodynamic parameter correction coefficient and the dimensionless hemodynamic parameter;

[0144] Accordingly, the actual parameter determination module 740 is further used for:

[0145] Based on the preset dimensionless coefficients, the corrected dimensionless hemodynamic parameters are converted into actual hemodynamic parameters.

[0146] In some optional implementations, the hemodynamic parameter correction data acquisition unit may also be specifically used for:

[0147] Sampling the vascular lumen contour of the three-dimensional vascular segment model to obtain a plurality of vascular lumen contour points;

[0148] Determine the distances between a plurality of vascular lumen contour points and the vascular centerline;

[0149] The irregularity of the blood vessel lumen of the three-dimensional blood vessel segment model is determined based on the distances between the multiple blood vessel lumen contour points and the blood vessel centerline.

[0150] The hemodynamic parameter determination device provided in the embodiment of the present invention can execute the hemodynamic parameter determination method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0151] Embodiment 8

[0152] Fig.10 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0153] like Fig.10 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The I / O interface 15 is also connected to the bus 14.

[0154] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0155] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The processor 11 executes the various methods and processes described above, such as a hemodynamic parameter determination method, which includes:

[0156] Acquire a three-dimensional blood vessel segment model, and perform two-dimensional mapping on the three-dimensional blood vessel segment model to obtain a two-dimensional blood vessel segment model;

[0157] Non-dimensionalizing the two-dimensional blood vessel segment model to obtain a non-dimensionalized two-dimensional blood vessel segment model;

[0158] Determining dimensionless hemodynamic parameters based on the dimensionless two-dimensional vascular segment model;

[0159] Based on preset dimensionless coefficients, the dimensionless hemodynamic parameters are converted into actual hemodynamic parameters.

[0160] In some embodiments, the hemodynamic parameter determination method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the hemodynamic parameter determination method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the hemodynamic parameter determination method in any other appropriate manner (e.g., by means of firmware).

[0161] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system-on-chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0162] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0163] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0164] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0165] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0166] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0167] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0168] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for determining hemodynamic parameters, characterized in that: include: Acquire a three-dimensional blood vessel segment model, and perform two-dimensional mapping on the three-dimensional blood vessel segment model to obtain a two-dimensional blood vessel segment model; Non-dimensionalizing the two-dimensional blood vessel segment model to obtain a non-dimensionalized two-dimensional blood vessel segment model; Determining dimensionless hemodynamic parameters based on the dimensionless two-dimensional vascular segment model; Based on preset dimensionless coefficients, the dimensionless hemodynamic parameters are converted into actual hemodynamic parameters.

2. The method according to claim 1, characterized in that The performing two-dimensional mapping on the three-dimensional blood vessel segment model to obtain a two-dimensional blood vessel segment model includes: determining a first port normal vector and a second port normal vector of the three-dimensional blood vessel segment model; determining a normal vector of a mapping plane based on the first port normal vector and the second port normal vector; Determining a first port diameter, a second port diameter, a blood vessel centerline, and a blood vessel wall surface of the three-dimensional blood vessel segment model; The first port diameter, the second port diameter, the blood vessel centerline and the blood vessel wall surface of the three-dimensional blood vessel segment model are mapped onto the mapping plane to obtain a two-dimensional blood vessel segment model.

3. The method according to claim 1, characterized in that The step of non-dimensionalizing the two-dimensional blood vessel segment model to obtain the non-dimensionalized two-dimensional blood vessel segment model includes: The first port diameter, the second port diameter, the blood vessel centerline and the blood vessel wall surface of the two-dimensional blood vessel segment model are standardized to obtain a dimensionless two-dimensional blood vessel segment model.

4. The method according to claim 1, characterized in that: The determining of dimensionless hemodynamic parameters based on the dimensionless two-dimensional vascular segment model comprises: Matching the dimensionless two-dimensional blood vessel segment model in a model library to obtain a target two-dimensional blood vessel segment model, wherein the model library includes a plurality of two-dimensional blood vessel segment models that have completed computational fluid dynamics simulation; The flow field information and the pressure field information of the target two-dimensional vascular segment model are obtained, and based on the flow field information and the pressure field information of the target two-dimensional vascular segment model, computational fluid dynamics simulation is performed on the dimensionless two-dimensional vascular segment model to obtain dimensionless hemodynamic parameters.

5. The method according to claim 1, characterized in that The determining of dimensionless hemodynamic parameters based on the dimensionless two-dimensional vascular segment model comprises: Acquiring geometric parameters and boundary conditions of the dimensionless two-dimensional blood vessel segment model; The dimensionless geometric parameters and boundary conditions of the two-dimensional blood vessel segment model are input into a pre-trained physical information neural network to obtain dimensionless hemodynamic parameters.

6. The method according to any one of claims 1 to 5, characterized in that: After determining the dimensionless hemodynamic parameters based on the dimensionless two-dimensional blood vessel segment model, the method further includes: Acquire the irregularity of the blood vessel lumen of the three-dimensional blood vessel segment model, the dimensionless blood vessel segment length of the three-dimensional blood vessel segment model, and the dimensionless blood vessel segment length of the two-dimensional blood vessel segment model; Inputting the irregularity of the vascular lumen of the three-dimensional vascular segment model, the dimensionless vascular segment length of the three-dimensional vascular segment model, and the dimensionless vascular segment length of the two-dimensional vascular segment model into a hemodynamic parameter correction model to obtain a hemodynamic parameter correction coefficient; Determining a corrected dimensionless hemodynamic parameter based on the hemodynamic parameter correction coefficient and the dimensionless hemodynamic parameter; Accordingly, the step of converting the dimensionless hemodynamic parameter into an actual hemodynamic parameter based on the preset dimensionless coefficient includes: Based on the preset dimensionless coefficients, the corrected dimensionless hemodynamic parameters are converted into actual hemodynamic parameters.

7. The method according to claim 6, characterized in that The step of obtaining the irregularity of the vascular lumen of the three-dimensional vascular segment model includes: Sampling the vascular lumen contour of the three-dimensional vascular segment model to obtain a plurality of vascular lumen contour points; Determine the distances between a plurality of vascular lumen contour points and the vascular centerline; The irregularity of the blood vessel lumen of the three-dimensional blood vessel segment model is determined based on the distances between the multiple blood vessel lumen contour points and the blood vessel centerline.

8. A device for determining hemodynamic parameters, characterized in that: include: A model two-dimensional mapping module, used to obtain a three-dimensional blood vessel segment model, and perform two-dimensional mapping on the three-dimensional blood vessel segment model to obtain a two-dimensional blood vessel segment model; A model dimensionless module, used for dimensionlessizing the two-dimensional blood vessel segment model to obtain a dimensionless two-dimensional blood vessel segment model; A dimensionless parameter determination module, used for determining dimensionless hemodynamic parameters based on the dimensionless two-dimensional vascular segment model; The actual parameter determination module is used to convert the dimensionless hemodynamic parameter into an actual hemodynamic parameter based on a preset dimensionless coefficient.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the hemodynamic parameter determination method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining hemodynamic parameters according to any one of claims 1 to 7 when executed.

Images