Blood flow parameter calculation system, device, and storage medium

Abstract

The application discloses a blood flow parameter calculation system, device and storage medium. The system comprises a processor configured to execute the following method, which comprises: in the process of calculating the blood flow velocity of a target blood vessel based on a fast fluid dynamics simulation algorithm, determining the initial blood flow velocity of a current grid at a target time for each grid; determining the first blood flow velocity of the current grid at a first sub-time according to the initial blood flow velocity; inputting the first blood flow velocity or the second-order partial derivative of the first blood flow velocity into a trained mapping model to obtain the viscous force value of the current grid at a set time; and determining the initial blood flow velocity of the current grid at a next target time according to the viscous force value at the set time, and returning to the step of determining the first blood flow velocity of the current grid at the first sub-time until the next target time is the set end time. The technical scheme of the embodiment of the application achieves the technical effect of improving the determination speed of the blood flow velocity.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical image processing, and in particular to a blood flow parameter calculation system and device and a storage medium. BACKGROUND

[0002] The prior art usually uses a fast fluid dynamics simulation algorithm (FFD) or a computational fluid dynamics (CFD) algorithm to calculate blood flow parameters such as blood flow velocity. Whether it is an FFD algorithm or a CFD algorithm, the amount of data operation is relatively large. This results in the fact that the prior art is difficult to improve the determination speed of blood flow velocity. SUMMARY

[0003] The present application provides a blood flow parameter calculation system, device and storage medium to solve the problem of slow blood flow parameter determination in the prior art.

[0004] According to an aspect of the present application, a blood flow parameter calculation system is provided, which comprises a processor configured to perform the following method, the method comprising:

[0005] obtaining a target blood vessel image, wherein a target blood vessel in the target blood vessel image is divided into a set number of grids;

[0006] In the process of calculating the blood flow velocity of the target blood vessel based on the fast fluid dynamics simulation algorithm, for each grid, determining the initial blood flow velocity of the current grid at a target time;

[0007] determining a first blood flow velocity of the current grid at a first sub-time according to the initial blood flow velocity;

[0008] inputting the first blood flow velocity or the second-order partial derivative of the first blood flow velocity into a trained mapping model to obtain a viscous force value of the current grid at a set time;

[0009] determining the initial blood flow velocity of the current grid at a next target time according to the viscous force value at the set time, and returning to the step of determining the first blood flow velocity of the current grid at the first sub-time according to the initial blood flow velocity until the next target time is a set end time; wherein the target time, the first sub-time and the next target time arrive in sequence.

[0010] According to another aspect of the present application, a blood flow parameter calculation device is provided, comprising:

[0011] an acquisition module configured to obtain a target blood vessel image, wherein a target blood vessel in the target blood vessel image is divided into a set number of grids;

[0012] an initial blood flow velocity module configured to determine, for each grid, an initial blood flow velocity of a current grid at a target time in a process of calculating blood flow velocities corresponding to the target blood vessel based on a fast fluid dynamics simulation algorithm;

[0013] a first blood flow velocity module configured to determine a first blood flow velocity of the current grid at a first sub-time according to the initial blood flow velocity;

[0014] a mapping module configured to input the first blood flow velocity or a second-order partial derivative of the first blood flow velocity into a trained mapping model to obtain a viscous force value of the current grid at a set time;

[0015] an iteration module configured to determine an initial blood flow velocity of the current grid at a next target time according to the viscous force value of the set time, and return the step of determining the first blood flow velocity of the current grid at the first sub-time according to the initial blood flow velocity until the next target time is a set end time; wherein the target time, the first sub-time and the next target time arrive in sequence.

[0016] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for causing a processor to implement the following method when executed:

[0017] obtaining a target blood vessel image, a target blood vessel in the target blood vessel image being divided into a set number of grids;

[0018] determining, for each grid, an initial blood flow velocity of a current grid at a target time in a process of calculating blood flow velocities corresponding to the target blood vessel based on a fast fluid dynamics simulation algorithm;

[0019] determining a first blood flow velocity of the current grid at a first sub-time according to the initial blood flow velocity;

[0020] inputting the first blood flow velocity or a second-order partial derivative of the first blood flow velocity into a trained mapping model to obtain a viscous force value of the current grid at a set time;

[0021] determining an initial blood flow velocity of the current grid at a next target time according to the viscous force value of the set time, and returning the step of determining the first blood flow velocity of the current grid at the first sub-time according to the initial blood flow velocity until the next target time is a set end time; wherein the target time, the first sub-time and the next target time arrive in sequence.

[0022] The technical scheme of the blood flow parameter calculation system provided by the embodiment of the application is that the first blood flow velocity of the current grid at the first time point or the second-order partial derivative of the first blood flow velocity is input into the trained mapping model, the viscous force value of the current grid at the set time point is determined, and the initial blood flow velocity of the current grid at the next target time point is determined according to the viscous force value. Compared with directly solving the corresponding viscous force item formula, the data operation amount is greatly reduced under the premise of ensuring the accuracy of three-dimensional global fields (such as a velocity field and a pressure field), the determination speed of the initial blood flow velocity at the next target time point is improved, and therefore the determination speed of the blood flow velocity of the current grid at each time point is improved.

[0023] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the application, nor is it used to limit the scope of the application. Other features of the application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments description. Obviously, the drawings in the following description are only some embodiments of the application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0025] Figure 1 is a structural schematic diagram of the blood flow parameter calculation system provided by the embodiment of the application;

[0026] Figure 2 is a flowchart of the blood flow parameter calculation method provided by the embodiment of the application;

[0027] Figure 3 is a flowchart of the model training method provided by the embodiment of the application;

[0028] Figure 4 is a structural schematic diagram of the blood flow parameter calculation device provided by the embodiment of the application. DETAILED DESCRIPTION

[0029] In order to enable persons skilled in the art to better understand the application scheme, the technical solutions in the embodiments of the application will be described clearly and completely in the following with reference to the drawings of the embodiments of the application. Obviously, the described embodiments are only some of the embodiments of the application, not all. Based on the embodiments in the application, all other embodiments obtained by those skilled in the art without creative labor should be within the scope of protection of the application.

[0030] It is to be understood that the terms "first", "second", and the like, used in the description and the claims of the application, as well as above-described figure, are used to distinguish similar objects, and are not necessarily used to describe a particular sequential or chronological order. It is to be understood that the use of data herein so described makes it possible, in appropriate cases, to adapt the application described herein to a sequence other than that depicted herein without departing from the scope of the application. Furthermore, the terms "comprising" and "including" and any of their derivatives, are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or apparatus that comprises a list of steps or units is not necessarily limited to those steps or units that are clearly listed, but can include other steps or units that are not clearly listed or inherent to such processes, methods, products, or apparatuses.

[0031] Before the technical solutions of the application are described in detail, the formula for calculating blood flow velocity based on FFD algorithm is introduced, which is as follows:

[0032]

[0033] Wherein, i and j are free index and dummy index in Einstein summation convention respectively. In the embodiment, i is corresponding to the set direction, and U is blood flow velocity; U i represents blood flow velocity in the set direction, v represents kinematic viscosity, and the specific is: u is dynamic viscosity, p represents density, P represents hydrostatic pressure, x j represents (spatial coordinates, j is a dummy index), x i represents spatial coordinates, f i represents the volume force term

[0034] The discrete form of the above formula can be expressed as:

[0035]

[0036] Wherein, n represents the target time, and n+1 represents the next target time.

[0037] It is to be noted that the embodiment only focuses on the discretization in the time dimension.

[0038] The time interval between the adjacent two target times in formula (2) is further divided, which can be divided into the following three steps, which are:

[0039] Equation 1 is:

[0040]

[0041] After the discretization of equation 1, it is:

[0042]

[0043] Wherein, represents the blood flow velocity at the first sub-time point, the first sub-time point being between the target time point and the next target time point.

[0044] Equation 2 is:

[0045]

[0046] wherein, the blood flow velocity at the second sub-time point; is a viscous force term. The second sub-time point is between the first sub-time point corresponding to the target time point and the next target time point.

[0047] It can be understood that, since the formula on the left and right respectively includes and second-order partial derivatives, the data operation amount of determined based on the formula is large, which is the main reason why the blood flow velocity determined based on the FFD algorithm has a large operation amount.

[0048] Equation 3 is:

[0049]

[0050] wherein, is a pressure term.

[0051] Equation 1, Equation 2 and Equation 3 are superimposed to obtain the following result:

[0052]

[0053] It can be seen that the value of the second term on the right side has changed, which will bring about a slight error, but in many scenarios, the error is acceptable.

[0054] Figure 1 A block diagram of a blood flow parameter computing system 10 that can be used to implement embodiments of the present application is shown. The blood flow parameter computing system is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The blood flow parameter computing system can also represent various forms of mobile devices such as personal digital assistants, cellular telephones, smart phones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit implementations of the applications described and / or claimed in this document.

[0055] As Figure 1As shown, the blood flow parameter calculation system 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11, wherein the memory stores a computer program executable by the at least one processor 11, 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 loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the blood flow parameter calculation system 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0056] Various components in the blood flow parameter calculation system 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 magnetic 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 blood flow parameter calculation system 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0057] The processor 11 can be various general-purpose and / or special-purpose 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-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described below, such as the blood flow parameter calculation method.

[0058] Figure 2 A flowchart of a blood flow parameter calculation method is provided for an embodiment of the present application. The embodiment can be applicable to the case of determining blood flow velocity based on a target blood vessel image. The method can be performed by a blood flow parameter calculation device, which can be realized in the form of hardware and / or software, and can be configured in a processor. As shown, the method includes: Figure 2

[0059] S110, obtaining a target blood vessel image, a target blood vessel in the target blood vessel image is divided into a set number of grids.

[0060] The target blood vessel image is a clinical medical image including a target blood vessel, such as a CT image, a DSA image, a magnetic resonance image, etc.

[0061] ​The target vessel is the vessel used to calculate blood flow velocity.

[0062] The number of grids is related to the accuracy of the blood flow velocity calculation; the larger the value, the higher the accuracy of the blood flow velocity, and the smaller the number, the lower the accuracy. This embodiment does not specifically limit the number of grids; users can set it according to their actual needs.

[0063] S120. In the process of calculating the blood flow velocity corresponding to the target blood vessel based on the fast fluid dynamics simulation algorithm, the initial blood flow velocity of the current grid at the target time is determined for each grid.

[0064] In this embodiment, in formula (4) This represents the initial blood flow velocity of the current grid at the target time, where n represents the target time or the current time.

[0065] S130. Determine the first blood flow velocity of the current grid at the first sub-time based on the initial blood flow velocity.

[0066] Based on formula (4), the first blood flow velocity of the current grid at the first sub-time is determined according to the initial blood flow velocity corresponding to the current grid, i.e.

[0067] In one embodiment, formula (4) can be transformed into This modified formula is called the mass derivative formula for velocity. It can be understood that after the initial blood flow velocity of the current grid at the target time is determined, the first blood flow velocity of the current grid at the first sub-time can be determined based on formula (4) or the mass derivative formula for velocity.

[0068] S140. Input the first blood flow velocity or the second-order partial derivative of the first blood flow velocity into the trained mapping model to obtain the viscous force value of the current grid at a set time.

[0069] The set time is either the next target time or the second sub-time corresponding to the target time. The target time, the first sub-time, the second sub-time, and the next target time arrive sequentially.

[0070] In one embodiment, two adjacent target moments are divided into three equal durations by corresponding first and second sub-moments.

[0071] This step aims to decouple the problem of solving a system of equations into an explicit advancement method by coupling the FFD algorithm with machine learning methods. It uses machine learning models to solve the complex problem of calculating viscous force terms, which greatly improves the calculation efficiency of blood flow virtuality while ensuring the accuracy of each three-dimensional global field (such as velocity field and pressure field).

[0072] In one embodiment, the time is set as a second sub-time corresponding to a target time. The first blood flow velocity of the current grid at the first sub-time is input into the trained mapping model to obtain the viscous force value of the current grid at the second sub-time, that is, a numerical value corresponding to the whole (viscous force term). It can be understood that the trained mapping model is used to map the first blood flow velocity of the current grid at the first sub-time into the viscous force value at the corresponding second sub-time, which can be specifically represented as:

[0073]

[0074] In one embodiment, the time is set as a second sub-time corresponding to a target time. The second-order partial derivative of the first blood flow velocity of the current grid at the first sub-time is input into the trained mapping model to obtain the viscous force value of the current grid at the second sub-time, that is, a numerical value corresponding to the whole (viscous force term). It can be understood that the trained mapping model can map the second-order partial derivative of the first blood flow velocity of the current grid at the first sub-time into the viscous force value at the corresponding second sub-time, which can be specifically represented as:

[0075]

[0076] In one embodiment, the time is set as a next target time. The second-order partial derivative of the first blood flow velocity of the current grid at the first sub-time is input into the trained mapping model to obtain the viscous force value of the current grid at the next target time, that is, a numerical value corresponding to the whole (viscous force term). It can be understood that the trained mapping model can map the second-order partial derivative of the first blood flow velocity of the current grid at the first sub-time into the viscous force value at the corresponding second sub-time, which can be specifically represented as:

[0077]

[0078] S150, determining the initial blood flow velocity of the current grid at the next target time according to the viscous force value at the set time, and returning to the step of determining the first blood flow velocity of the current grid at the first sub-time according to the initial blood flow velocity, until the next target time is the set end time; wherein the target time, the first sub-time and the next target time arrive in sequence.

[0079] In one embodiment, the time corresponding to a flow field is set as a target time, and the end time is set as the target time corresponding to the last flow field. The flow field refers to the space occupied by the movement of blood.

[0080] After the viscosity force value corresponding to the second sub-time of the current grid is determined, the second blood flow velocity of the current grid at the second sub-time can be determined according to the viscosity force value; and the initial blood flow velocity of the current grid at the next target time is determined according to formula (6) and the second blood flow velocity of the current grid at the second sub-time. By improving the determination speed of the viscosity force value corresponding to the second sub-time of the current grid, the determination speed of the second blood flow velocity of the current grid at the second sub-time is improved, thereby improving the determination speed of the initial blood flow velocity of the current grid at the next target time.

[0081] After the viscosity force value corresponding to the next target time of the current grid is determined, the initial blood flow velocity of the current grid at the next target time is determined according to the viscosity force value. By improving the determination speed of the viscosity force value of the current grid at the next target time, the determination speed of the initial blood flow velocity of the current grid at the next target time is improved.

[0082] In one embodiment, after the blood flow velocity of each grid at each time is determined, the pressure of the blood flow in the set direction is determined, and at least one of the target kinetic parameters such as the viscosity force value, the flow, the wall shear stress, and the plaque axial stress of the blood vessel at any position at any time is determined according to the blood flow velocity and / or the pressure. The determination method of the pressure of the blood flow in the set direction includes: obtaining the static pressure of the blood flow in the set direction and the blood flow density, and determining the pressure of the blood flow in the set direction according to the static pressure of the blood flow in the set direction and the blood flow density, which is specifically shown in the pressure term in formula (6). By improving the determination speed of the blood flow velocity, the determination speed of other kinetic parameters based on the blood flow velocity is improved.

[0083] The technical scheme of the blood flow parameter calculation system provided by the embodiment of the application is that the first blood flow velocity of the current grid at the first sub-time or the second-order partial derivative of the first blood flow velocity is input into the trained mapping model to determine the viscosity force value of the current grid at the set time, and the initial blood flow velocity of the current grid at the next target time is determined according to the viscosity force value. Compared with directly solving the corresponding viscosity force term formula, the data operation amount is greatly reduced under the premise of ensuring the accuracy of three-dimensional global fields (such as the velocity field and the pressure field), the determination speed of the initial blood flow velocity at the next target time is improved, and thus the determination speed of the blood flow velocity of the current grid at each time is improved.

[0084] Figure 3 The flowchart of the mapping model training method provided by the embodiment of the application. The embodiment is used for training the mapping model to obtain the trained mapping model in the foregoing embodiment. The method comprises:

[0085] S2001, acquire a training sample set, the training sample set includes a set sample number of training samples, the training sample includes a label and fluid data, the fluid data includes first blood flow velocity or second-order partial derivative of the first blood flow velocity of each grid at the first sub-time determined based on a fast fluid dynamics simulation algorithm, and the label includes viscous force values of each grid at a set time determined based on a fluid dynamics method.

[0086] It can be understood that the greater the set sample number, the higher the robustness and generalizability of the trained mapping model, i.e., the trained mapping model. The embodiment does not specifically limit the set sample number, and the user can set it according to the actual situation during actual model training.

[0087] One training sample corresponds to a target blood vessel image of a target object. The FFD algorithm is used to simulate blood flow, and the blood flow velocity of each grid at each target time and the corresponding first sub-time and second sub-time of each target time is saved. In the case of obtaining the blood flow velocity of each grid at each target time and the corresponding first sub-time and second sub-time of each target time based on the FFD algorithm, the blood flow velocity at each time is input as input data into the CFD algorithm to obtain the target blood flow velocity of each grid at each target time and the corresponding first sub-time and second sub-time of each target time. According to the target blood flow velocity of each grid at each target time and the corresponding first sub-time and second sub-time of each target time, the viscous force values of each grid at each target time and the corresponding first sub-time and second sub-time of each target time are determined.

[0088] In one embodiment, the blood flow velocity of each grid at the corresponding first sub-time of each target time based on the FFD algorithm, i.e., the first blood flow velocity, is used as the fluid data of the training sample; and the viscous force values of each grid at the corresponding second sub-time of each target time based on the CFD algorithm are used as the label of the training sample.

[0089] In one embodiment, the second-order partial derivative of the blood flow velocity of each grid at the corresponding first sub-time of each target time based on the FFD algorithm, i.e., the second-order partial derivative of the first blood flow velocity, is used as the fluid data of the training sample; and the viscous force values of each grid at the corresponding second sub-time of each target time based on the CFD algorithm are used as the label of the training sample.

[0090] In one embodiment, the second-order partial derivative of the blood flow velocity of each grid at the corresponding first sub-time of each target time based on the FFD algorithm, i.e., the second-order partial derivative of the first blood flow velocity, is used as the fluid data of the training sample; and the viscous force values of each grid at the next target time based on the CFD algorithm are used as the label of the training sample.

[0091] It can be understood that, since the accuracy of the CFD algorithm is higher than that of the FFD algorithm, taking the viscous force value of each grid at the second sub-time corresponding to each target time determined based on the CFD algorithm as the label of the training sample can ensure the effectiveness of the training sample, thereby ensuring the accuracy of the model training.

[0092] S2002, input the training sample in the training sample set into the mapping model, so that the mapping model completes the optimization of the network parameters in the training process to obtain the trained mapping model.

[0093] The training sample is input into the mapping model, and the mapping model optimizes the model network parameters based on the predicted viscous force value and the viscous force value in the label, until the model network parameters meet the set threshold condition, the model training of the mapping model is completed, and the trained mapping model is obtained.

[0094] The embodiment of the application determines the fluid data of the training sample in the form of blood flow simulation based on the FFD algorithm, and determines the label of the training sample in the form of blood flow simulation based on the combination of the CFD algorithm and the FFD algorithm, thereby ensuring the accuracy of the training sample setting, and ensuring the accuracy and generalization of the trained mapping model.

[0095] Figure 4 The structure diagram of the blood flow parameter calculation device provided by the embodiment of the application is shown in the figure. Figure 4 As shown in the figure, the device comprises:

[0096] The acquisition module 41 is configured to acquire a target blood vessel image, and a target blood vessel in the target blood vessel image is divided into a plurality of grids with a set number of grids.

[0097] The initial blood flow velocity module 42 is configured to, in the process of calculating the blood flow velocity corresponding to the target blood vessel based on the fast fluid dynamics simulation algorithm, determine, for each grid, an initial blood flow velocity of the current grid at a target time.

[0098] The first blood flow velocity module 43 is configured to determine a first blood flow velocity of the current grid at a first sub-time according to the initial blood flow velocity.

[0099] The mapping module 44 is configured to input the first blood flow velocity or the second-order partial derivative of the first blood flow velocity into the trained mapping model to obtain a viscous force value of the current grid at a set time.

[0100] The iteration module 45 is configured to determine an initial blood flow velocity of the current grid at a next target time according to the viscosity force value at the setting time, and return the step of determining a first blood flow velocity of the current grid at a first sub-time according to the initial blood flow velocity until the next target time is a setting end time; wherein the target time, the first sub-time and the next target time arrive in sequence.

[0101] In one embodiment, the setting time is the next target time, or the target time corresponds to a second sub-time, and the first sub-time, the second sub-time and the next target time arrive in sequence.

[0102] In one embodiment, the setting time is the second sub-time corresponding to the target time. The iteration module 45 is specifically configured to:

[0103] determine a second blood flow velocity of the current grid at a second sub-time according to the viscosity force value;

[0104] determine an initial blood flow velocity of the current grid at the next target time according to the second blood flow velocity of the current grid at the second sub-time.

[0105] In one embodiment, the setting time is the next target time. The iteration module 45 is specifically configured to:

[0106] determine an initial blood flow velocity of the current grid at the next target time according to the viscosity force value of the current grid at the next target time.

[0107] In one embodiment, the device further comprises a parameter determination module, which is configured to:

[0108] determine a pressure of blood flow in a setting direction;

[0109] determine a target kinetic parameter in the setting direction based on the blood flow velocity and / or the pressure, the target kinetic parameter including at least one of a viscosity force value, a flow, a wall shear stress and a plaque axial stress.

[0110] In one embodiment, the first blood flow velocity module is specifically configured to determine a first blood flow velocity of the current grid at a first sub-time based on a velocity-based material derivative formula and the initial blood flow velocity.

[0111] In one embodiment, the device further comprises a model training module, which comprises:

[0112] obtain a training sample set, the training sample set comprising a preset number of training samples, each training sample comprising a label and fluid data, the fluid data comprising a first blood flow velocity of each grid at a first sub-time or a second-order partial derivative of the first blood flow velocity determined based on a fast fluid dynamics simulation algorithm, and the label comprising a viscous force value of each grid at the preset time determined based on a CFD simulation method;

[0113] input the training samples in the training sample set into the mapping model, so that the mapping model optimizes network parameters in a training process to obtain a trained mapping model.

[0114] In one embodiment, the label corresponding to the first blood flow velocity is a viscous force value at a second sub-time corresponding to the target time;

[0115] The label corresponding to the second-order partial derivative of the first blood flow velocity is a viscous force value at a second sub-time corresponding to the target time or a viscous force value at a next target time.

[0116] The technical scheme of the blood flow parameter calculation device provided in the embodiments of the present application and the technical scheme of the blood flow parameter calculation system provided in the embodiments of the present application, the manner of inputting the first blood flow velocity of the current grid at the first sub-time or the second-order partial derivative of the first blood flow velocity into the trained mapping model, determining the viscous force value of the current grid at the preset time, and determining the initial blood flow velocity of the current grid at the next target time according to the viscous force value. Compared with directly solving the corresponding viscous force item formula, the data operation amount is greatly reduced under the premise of ensuring the accuracy of three-dimensional global fields (such as velocity field and pressure field), the determination speed of the initial blood flow velocity at the next target time is improved, and thus the determination speed of the blood flow velocity of the current grid at each time is improved.

[0117] The blood flow parameter calculation device provided in the embodiments of the present application can execute the blood flow parameter calculation method provided in any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0118] In some embodiments, the blood flow parameter calculation method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the blood flow parameter calculation system 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 blood flow parameter calculation method described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the blood flow parameter calculation method by any other appropriate means (for example, by means of firmware).

[0119] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0120] Computer programs used to implement the processes of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program, when executed, can cause instructions defined in the flow charts and / or block diagrams to be implemented. The computer program can be executed entirely on a machine, partially on a machine, partially on a machine as a standalone software package and partially on a remote machine or entirely on a remote machine or server.

[0121] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of electrical connections, portable computer disks, hard disk drives, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fibers, portable compact disc read-only memories (CD-ROMs), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0122] The systems and techniques described herein can be implemented in a computing system that includes a back end component, e.g., as a data server, or that includes a middleware component, e.g., an application server, or that includes a front end component, e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described herein, or any combination of such back end, middleware, or front end components. The components of the system can 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.

[0123] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can 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 large management difficulty and weak business scalability in traditional physical host and VPS service.

[0124] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be performed in parallel, in series, or in a different order, and the present disclosure is not limited in this regard.

[0125] The specific embodiments described above are not intended to limit the scope of the present disclosure. Those skilled in the art will understand that various modifications, combinations, sub-combinations, and alternatives can be made to the specific embodiments without departing from the spirit and principles of the present disclosure. Any further modifications, equivalents, and / or alternatives come within the scope of the present disclosure as recited by the claims.

Claims

1. A blood flow parameter calculation system, characterized in that, The system includes a processor configured to perform the following method: Acquire a target blood vessel image, wherein the target blood vessel in the target blood vessel image is divided into a set number of grids; In the process of calculating the blood flow velocity corresponding to the target blood vessel based on the fast fluid dynamics simulation algorithm, the initial blood flow velocity of the current grid at the target time is determined for each grid. The first blood flow velocity of the current grid at the first sub-time is determined based on the initial blood flow velocity; The first blood flow velocity or the second-order partial derivative of the first blood flow velocity is input into the trained mapping model to obtain the viscous force value of the current grid at a set time. The initial blood flow velocity of the current grid at the next target time is determined based on the viscous force value at the set time, and the process returns to the step of determining the first blood flow velocity of the current grid at the first sub-time based on the initial blood flow velocity, until the next target time is the set end time; wherein the target time, the first sub-time, and the next target time arrive sequentially.

2. The system according to claim 1, characterized in that, The set time is the next target time, or the second sub-time corresponding to the target time, and the first sub-time, the second sub-time, and the next target time arrive sequentially.

3. The system according to claim 2, characterized in that, The set time is the second sub-time corresponding to the target time, and the step of determining the initial blood flow velocity of the current grid at the next target time based on the viscous force value includes: The second blood flow velocity of the current grid at the second sub-time is determined based on the viscous force value; Based on the second blood flow velocity of the current grid at the second sub-time, the initial blood flow velocity of the current grid at the next target time is determined.

4. The system according to claim 2, characterized in that, The set time is the next target time, and the step of determining the initial blood flow velocity of the current grid at the next target time based on the viscous force value includes: The initial blood flow velocity of the current grid at the next target time is determined based on the viscous force value of the current grid at the next target time.

5. The system according to claim 1, characterized in that, Also includes: Determine the pressure of blood flow in a set direction; The target dynamic parameters in the set direction are determined based on the blood flow velocity and / or the pressure, and the target dynamic parameters include at least one of viscous force, flow rate, wall shear stress, and plaque axial stress.

6. The system according to claim 1, characterized in that, Determining the first blood flow velocity of the current grid at the first sub-time based on the initial blood flow velocity includes: The velocity-based material derivative formula and the initial blood flow velocity determine the first blood flow velocity of the current grid at the first sub-time.

7. The system according to claim 1, characterized in that, The trained mapping model is determined through the following steps: Obtain a training sample set, which includes a set number of training samples. The training samples include labels and fluid data. The fluid data includes the first blood flow velocity or the second-order partial derivative of the first blood flow velocity of each grid at the first sub-time determined based on a fast fluid dynamics simulation algorithm. The labels include the viscous force values ​​of each grid at the set time determined based on fluid dynamics methods. The training samples in the training sample set are input into the mapping model so that the mapping model can optimize the network parameters during the training process to obtain the trained mapping model.

8. The system according to claim 7, characterized in that, The label corresponding to the first blood flow velocity is the viscous force value of the second sub-time corresponding to the target time. The label corresponding to the second-order partial derivative of the first blood flow velocity is the viscous force value at the second sub-time corresponding to the target time or the viscous force value at the next target time.

9. A blood flow parameter calculation device, characterized in that, include: The acquisition module is used to acquire a target blood vessel image, wherein the target blood vessel in the target blood vessel image is divided into a grid of a set number of grids; The initial blood flow velocity module is used to determine the initial blood flow velocity of the current grid at the target time for each grid during the process of calculating the blood flow velocity corresponding to the target blood vessel based on the fast fluid dynamics simulation algorithm. The first blood flow velocity module is used to determine the first blood flow velocity of the current grid at the first sub-time based on the initial blood flow velocity; The mapping module is used to input the first blood flow velocity or the second-order partial derivative of the first blood flow velocity into the trained mapping model to obtain the viscous force value of the current grid at a set time. An iterative module is used to determine the initial blood flow velocity of the current grid at the next target time based on the viscous force value at the set time, and return to the step of determining the first blood flow velocity of the current grid at the first sub-time based on the initial blood flow velocity, until the next target time is the set end time; wherein the target time, the first sub-time, and the next target time arrive sequentially.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to perform the following methods: Acquire a target blood vessel image, wherein the target blood vessel in the target blood vessel image is divided into a set number of grids; In the process of calculating the blood flow velocity corresponding to the target blood vessel based on the fast fluid dynamics simulation algorithm, the initial blood flow velocity of the current grid at the target time is determined for each grid. The first blood flow velocity of the current grid at the first sub-time is determined based on the initial blood flow velocity; The first blood flow velocity or the second-order partial derivative of the first blood flow velocity is input into the trained mapping model to obtain the viscous force value of the current grid at a set time. The initial blood flow velocity of the current grid at the next target time is determined based on the viscous force value at the set time, and the process returns to the step of determining the first blood flow velocity of the current grid at the first sub-time based on the initial blood flow velocity, until the next target time is the set end time; wherein the target time, the first sub-time, and the next target time arrive sequentially.

Images