Vascular system analysis method and device, computer equipment and storage medium

Abstract

The invention relates to a vascular system analysis method and device, computer equipment and a storage medium. Determining a model based on the vascular system, the target medical information of the vascular system and a pre-established target system function to obtain a target system function, obtaining target time domain excitation of the vascular system based on the target medical information, and determining a target time domain response of the vascular system according to the target time domain excitation of the vascular system and the target system function; the target time domain response is used for analyzing the vascular system. Due to the fact that numerical simulation is adopted for calculation in an existing fluid mechanics method, and a large number of equations need to be solved, in the embodiment of the invention, the target system function can be rapidly determined based on the target system function determination model, the complexity of target time domain response determination of the vascular system is reduced, and therefore the analysis efficiency of the vascular system is improved; and the target system function can indirectly reveal the system frequency domain characteristics of the vascular system, and experimental analysis on the vascular system is facilitated.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a method, device, computer equipment and storage medium for analyzing a vascular system. Background Art

[0002] The vascular system is an important part of the human body, responsible for transporting substances such as oxygen, nutrients and hormones to various parts of the body, and excreting carbon dioxide and metabolic waste from the body. Therefore, analyzing the vascular system can prevent cardiovascular diseases, conduct medical diagnosis and treatment, etc. For example, the coronary artery vascular system is responsible for supplying blood to the heart. When atherosclerotic lesions occur in the coronary artery vascular system, it may cause myocardial ischemia, hypoxia or necrosis and lead to heart disease, which is often called "coronary heart disease." Blood flow parameters such as blood flow reserve fraction can be used to evaluate the impact of stenosis caused by coronary artery lesions on downstream blood supply, so as to timely understand the degree of ischemia in the coronary arteries.

[0003] Currently, the vascular system is mainly analyzed by determining the blood flow reserve fraction through fluid dynamics algorithms. However, the fluid dynamics algorithm uses numerical simulation methods, which requires solving a large number of equations and is computationally complex, making it unsuitable for clinical application scenarios. Summary of the invention

[0004] Based on this, it is necessary to provide a vascular system analysis method, device, computer equipment and storage medium that can reduce computational complexity in order to address the above technical issues.

[0005] In a first aspect, the present application provides a method for analyzing a vascular system, comprising:

[0006] Determine a model based on the vascular system, target medical information of the vascular system and a pre-established target system function to obtain a target system function;

[0007] Acquire a target time-domain excitation of the vascular system based on the target medical information;

[0008] A target time-domain response of the vascular system is determined according to the target time-domain excitation of the vascular system and the target system function; the target time-domain response is used to analyze the vascular system.

[0009] In one embodiment, determining a target time domain response of the vascular system according to the target time domain excitation of the vascular system and the target system function comprises:

[0010] Performing a time-frequency transformation on the target time-domain excitation based on a pre-established first target time-frequency transformation model to obtain a frequency-domain transformation of the target time-domain excitation;

[0011] Determining a frequency domain transform of a target time domain response according to the frequency domain transform of the target time domain excitation and the target system function;

[0012] The frequency domain transform of the target time domain response is subjected to an inverse time-frequency transform to obtain a target time domain response of the vascular system.

[0013] In one embodiment, performing an inverse time-frequency transform on the frequency domain transform of the target time domain response to obtain the target time domain response of the vascular system includes:

[0014] Based on a pre-established second target time-frequency transformation model, an inverse time-frequency transformation is performed on the frequency domain transformation of the target time domain response to obtain a target time domain response.

[0015] In one embodiment, the determining model based on the vascular system, the target medical information of the vascular system and a pre-established target system function to obtain the target system function includes:

[0016] Inputting the vascular system and the target medical information into the target system function determination model to obtain target system function parameters;

[0017] The target system function is constructed based on the target system function parameters.

[0018] In one embodiment, the target system function parameters include the order of the denominator polynomial, the order of the numerator polynomial, the coefficients of the denominator polynomial and the coefficients of the numerator polynomial, and constructing the target system function based on the target system function parameters includes:

[0019] The target system function is determined according to the order of the denominator polynomial, the coefficients of the denominator polynomial, the order of the numerator polynomial and the coefficients of the numerator polynomial.

[0020] In one embodiment, the method further comprises:

[0021] Acquire a vascular data set; the vascular data set includes a plurality of sample vascular systems and sample medical information of the plurality of sample vascular systems;

[0022] Obtaining a sample time domain excitation of each of the sample vascular systems based on each of the sample medical information;

[0023] Obtaining a reference time domain response of each of the sample vascular systems according to each of the sample time domain excitations and the corresponding sample vascular system;

[0024] The initial system function determination model is trained according to each of the sample time-domain excitations, each of the sample vascular systems and each of the reference time-domain responses to obtain the target system function determination model.

[0025] In one embodiment, the training of the initial system function determination model according to each of the sample time domain excitations, each of the sample vascular systems and each of the reference time domain responses to obtain the target system function determination model includes:

[0026] Performing a time-frequency transformation on each of the sample time-domain excitations based on a first initial time-frequency transformation model to obtain a frequency-domain transformation of each of the sample time-domain excitations;

[0027] Determine the frequency domain transformation of the sample time domain response based on the frequency domain transformation of each of the sample time domain excitations and the sample system function; the sample system function is obtained by determining the model based on each of the sample vascular systems, each of the sample medical information and the initial system function;

[0028] Performing an inverse time-frequency transform on the frequency domain transform of each of the sample time domain responses based on a second initial time-frequency transform model to obtain the sample time domain response;

[0029] Based on each of the sample time domain responses and the reference time domain response, the first initial time-frequency transform model, the initial system function determination model and the second initial time-frequency transform model are trained to obtain the target system function determination model.

[0030] In a second aspect, the present application also provides a vascular system analysis device, comprising:

[0031] A first determination module is used to determine a model based on a vascular system, target medical information of the vascular system and a pre-established target system function to obtain a target system function;

[0032] A first acquisition module, configured to acquire a target time-domain excitation of the vascular system based on the target medical information;

[0033] The second determination module is used to determine the target time domain response of the vascular system according to the target time domain excitation of the vascular system and the target system function; the target time domain response is used to analyze the vascular system.

[0034] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0035] Determine a model based on the vascular system, target medical information of the vascular system and a pre-established target system function to obtain a target system function;

[0036] Acquire a target time-domain excitation of the vascular system based on the target medical information;

[0037] A target time-domain response of the vascular system is determined according to the target time-domain excitation of the vascular system and the target system function; the target time-domain response is used to analyze the vascular system.

[0038] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0039] Determine a model based on the vascular system, target medical information of the vascular system and a pre-established target system function to obtain a target system function;

[0040] Acquire a target time-domain excitation of the vascular system based on the target medical information;

[0041] A target time-domain response of the vascular system is determined according to the target time-domain excitation of the vascular system and the target system function; the target time-domain response is used to analyze the vascular system.

[0042] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0043] Determine a model based on the vascular system, target medical information of the vascular system and a pre-established target system function to obtain a target system function;

[0044] Acquire a target time-domain excitation of the vascular system based on the target medical information;

[0045] A target time-domain response of the vascular system is determined according to the target time-domain excitation of the vascular system and the target system function; the target time-domain response is used to analyze the vascular system.

[0046] The above-mentioned analysis method, device, computer equipment and storage medium of the vascular system obtain the target system function based on the vascular system, the target medical information of the vascular system and the pre-established target system function determination model, obtain the target time domain excitation of the vascular system based on the target medical information, and determine the target time domain response of the vascular system according to the target time domain excitation of the vascular system and the target system function; the target time domain response is used to analyze the vascular system. Since the existing fluid mechanics methods use numerical simulation for calculation and need to solve a large number of equations, in the embodiments of the present application, the target system function can be quickly determined based on the target system function determination model, which reduces the complexity of determining the target time domain response of the vascular system, thereby improving the analysis efficiency of the vascular system; further, the target system function is constructed through the target system function determination model, and the target system function indirectly reveals the system frequency domain characteristics of the vascular system and is easy to perform experimental analysis on the vascular system. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0048] FIG1 is a diagram showing an application environment of a method for analyzing a vascular system in one embodiment;

[0049] FIG2 is a schematic flow chart of a method for analyzing a vascular system in one embodiment;

[0050] FIG3 is a schematic flow chart of a method for determining a target time domain response in one embodiment;

[0051] FIG4 is a schematic flow chart of a method for determining a target system function model in one embodiment;

[0052] FIG5 is a schematic flow chart of a method for determining a target system function model in another embodiment;

[0053] FIG6 is a schematic flow chart of a method for analyzing a vascular system in another embodiment;

[0054] FIG7 is a block diagram of a device for analyzing a vascular system in one embodiment;

[0055] FIG. 8 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] Taking the coronary artery system as an example, coronary atherosclerotic heart disease is a heart disease caused by atherosclerotic lesions in the coronary arteries, which causes stenosis or obstruction of the vascular lumen, resulting in myocardial ischemia, hypoxia or necrosis. It is often called "coronary heart disease". Coronary heart disease has a high incidence and mortality rate. Generally speaking, when the stenosis of the coronary artery lumen is less than 50%, it has little effect on blood flow, and drug treatment can have a satisfactory effect. When the stenosis reaches 75%, it will significantly affect the smoothness of blood flow and produce angina symptoms. At this time, interventional stent surgery or surgical bypass surgery is required. Therefore, it is necessary to evaluate the current state of the vascular system through blood flow parameters.

[0058] Fractional Flow Reserve (FFR) can be used as a way to evaluate the blood flow system. FFR and hemodynamic simulation are mature and effective functional evaluation methods for coronary artery lesions, and their accuracy and convenience are widely accepted. FFR can evaluate the impact of stenosis caused by coronary artery lesions on downstream blood supply. Furthermore, hemodynamics can evaluate the possible impact of the mechanical environment of blood vessels on coronary artery lesions from a mechanical perspective.

[0059] At present, blood flow parameters such as blood flow reserve fraction, heart rate, and vascular dilation are mainly determined by fluid dynamics algorithms to analyze the vascular system. However, fluid dynamics algorithms use numerical simulation methods, which require solving a large number of equations and are complex in calculation, and are not suitable for clinical application scenarios. Therefore, this application proposes a method, device, computer equipment, and storage medium for analyzing the vascular system that can solve the above technical problems.

[0060] The analysis method of the vascular system provided in the embodiment of the present application can be applied in the application environment shown in Figure 1. The application environment includes a computer device, which can be a server, and its internal structure diagram can be shown in Figure 1. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store relevant data for calculating the analysis of the vascular system. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for analyzing the vascular system is implemented. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services.

[0061] In an exemplary embodiment, as shown in FIG2 , a method for analyzing a vascular system is provided, which is described by taking the method applied to the computer device in FIG1 as an example, and includes the following S201 to S203 . Among them:

[0062] S201, determining a model based on a vascular system, target medical information of the vascular system and a pre-established target system function to obtain a target system function.

[0063] Among them, the target medical information can be medical images, physiological characteristics of patients, characteristic parameters of the vascular system obtained based on medical images, such as blood pressure, blood flow velocity, fragility, permeability, etc. of the vascular system; geometric characteristics of the vascular system, such as the diameter of the vascular system, the wall thickness of the blood vessels, the length of the vascular system, etc.

[0064] The target system function G(s) is a vascular nonlinear system description function, which can characterize impedance, admittance or system frequency domain characteristics of other physical quantity relationships.

[0065] Since the analysis of the vascular system by directly calculating blood flow parameters from medical images through a fluid mechanics model is greatly affected by the number and distribution of samples, the prediction of a model that is more consistent with the sample distribution can obtain relatively good accuracy, but for a sample distribution with a small training data set and a sparse distribution, the prediction accuracy is low. Therefore, the embodiment of the present application inputs the vascular system and the target medical information of the vascular system into a pre-trained target system function determination model to obtain the target system function parameters. For example, the transfer system, the number of poles, and the number of zeros. The target system function is obtained based on the target system function parameters, that is, the vascular system and the target medical information X are transformed into the generalized frequency space Φ space based on the target system function determination model, which can be expressed by the following formula: .

[0066] The output channel of the target system function determination model is determined according to the number of target system function parameters. If the target system function parameters are two, a target system function determination model with dual-channel output can be constructed. The target system function parameters can characterize the real and imaginary parts of the target system function, and can also characterize the amplitude and phase of the target system function, etc. The target system function parameters in the embodiment of the present application are only an example.

[0067] Optionally, the target system function determination model can be a deep learning network, such as a convolutional neural network, a deep belief network, or a long short-term memory network, etc., which is determined based on the medical information that needs to be processed.

[0068] In a possible implementation, the vascular system, the target medical information of the vascular system, and a pre-established target system function may be directly modeled to directly obtain the target system function.

[0069] S202, acquiring a target time-domain excitation of the vascular system based on the target medical information.

[0070] In this embodiment, the target medical information may be a medical image, and the medical image may be analyzed to obtain blood flow, blood pressure, etc., and obtain target time domain excitation about blood flow and blood pressure, and the target time domain excitation is a function expression about time t.

[0071] If the target medical information is the characteristic parameters of the vascular system, the target time domain excitation can be directly constructed based on the characteristic parameters of the vascular system.

[0072] S203, determining a target time domain response of the vascular system according to the target time domain excitation and the target system function of the vascular system; the target time domain response is used to analyze the vascular system.

[0073] In this embodiment, the target time domain excitation can be transformed in time-frequency based on a pre-established first target time-frequency transformation model, and the target time domain excitation can be converted into a generalized frequency space to obtain a frequency domain transformation of the target time domain excitation. According to the frequency domain transformation of the target time domain excitation and the target system function, the frequency domain transformation of the target time domain response is determined, and then the frequency domain transformation of the target time domain response is inversely transformed in time-frequency to obtain the target time domain response, and the vascular system is analyzed based on the target time domain response.

[0074] For example, the target time domain excitation is the blood flow of the vascular system. When the blood flow is converted to the frequency domain space, the target time domain response can be the blood pressure of the vascular system based on the blood flow in the frequency domain space and the target system function. The target time domain excitation is the blood pressure of the vascular system. When the blood pressure is converted to the frequency domain space, the target time domain response can be the blood flow of the vascular system based on the blood pressure in the frequency domain space and the target system function.

[0075] Optionally, the target time domain excitation can be converted into a generalized frequency space based on Fourier transform, fast Fourier transform, short-time Fourier transform, etc. to obtain a frequency domain transform of the target time domain excitation, and the target time domain response of the vascular system can be determined based on the frequency domain transform of the target time domain excitation and the target system function.

[0076] Furthermore, after obtaining the blood pressure of the vascular system based on the blood flow, a ratio relationship between the blood pressure of the vascular system and the blood pressure at the blood vessel opening may be obtained to analyze the vascular system based on the ratio relationship.

[0077] It should be noted that the blood flow parameters such as blood flow reserve fraction, heart rate, and vasodilation degree involved in this application are intermediate parameter information obtained by medical information simulation evaluation.

[0078] In the above-mentioned analysis method of the vascular system, a target system function is obtained based on the vascular system, the target medical information of the vascular system and a pre-established target system function determination model, a target time domain excitation of the vascular system is obtained based on the target medical information, and a target time domain response of the vascular system is determined according to the target time domain excitation of the vascular system and the target system function; the target time domain response is used to analyze the vascular system. Since the existing fluid mechanics methods use numerical simulation for calculation and need to solve a large number of equations, in the embodiment of the present application, the target system function can be quickly determined based on the target system function determination model, which reduces the complexity of determining the target time domain response of the vascular system, thereby improving the analysis efficiency of the vascular system; further, the target system function is constructed through the target system function determination model, and the target system function indirectly reveals the system frequency domain characteristics of the vascular system and is easy to perform experimental analysis on the vascular system.

[0079] FIG3 is a flow chart of a method for determining a target time domain response in an embodiment. As shown in FIG3 , the embodiment of the present application relates to a possible implementation method of determining a target time domain response of the vascular system according to the target time domain excitation of the vascular system and the target system function, including the following steps:

[0080] S301 , performing a time-frequency transform on a target time-domain excitation based on a pre-established first target time-frequency transform model to obtain a frequency-domain transform of the target time-domain excitation.

[0081] In this embodiment, the target time domain excitation is the excitation function about time t, and the target time domain excitation is transformed into a time-frequency one through the first target time-frequency transformation model. , convert the target time domain excitation into a generalized frequency space, and obtain the frequency domain transform of the target time domain excitation , where the target time domain excitation can be different types of time domain excitations, such as blood flow, blood pressure, stress, etc., and s is an unknown parameter in the frequency domain space, that is, the complex frequency.

[0082] Optionally, the first target time-frequency transformation model may also be a deep learning network, for example, a convolutional neural network, a recurrent neural network, a long short-term memory network, a generative adversarial network, an autoencoder, etc.

[0083] S302, determining a frequency domain transform of a target time domain response according to the frequency domain transform of the target time domain excitation and the target system function.

[0084] In this embodiment, the frequency domain of the target time domain excitation is transformed and the target system function Multiplying them together, we can get the frequency domain transform of the target time domain response. , that is, the response in frequency space .

[0085] S303, performing an inverse time-frequency transform on the frequency domain transform of the target time domain response to obtain a target time domain response of the vascular system.

[0086] In this embodiment, the target frequency domain response can be inversely transformed in time-frequency based on a pre-established second target time-frequency transformation model, and the frequency domain transformation of the target time domain response can be converted to the frequency space to obtain the target time domain response, which is a response function with respect to time t.

[0087] In a possible implementation, the frequency domain transform of the target time domain response can be converted to the frequency space based on the inverse Fourier transform or other methods to obtain the target time domain response, and the corresponding time t can be input to obtain the blood flow parameters of the vascular system.

[0088] In the embodiment of the present application, the target time domain excitation is transformed in time-frequency based on the pre-established first target time-frequency transformation model to obtain the frequency domain transformation of the target time domain excitation; the frequency domain transformation of the target time domain response is determined according to the frequency domain transformation of the target time domain excitation and the target system function; the frequency domain transformation of the target time domain response is inversely transformed in time-frequency to obtain the target time domain response of the vascular system. The embodiment of the present application converts the target time domain excitation to the frequency space through the first target time-frequency transformation model, thereby determining the target time domain response based on the frequency domain transformation of the target time domain excitation and the target system function, thereby accelerating the determination speed of the target time domain response.

[0089] In one embodiment, performing an inverse time-frequency transform on the frequency domain transform of the target time domain response to obtain the target time domain response of the vascular system includes: performing an inverse time-frequency transform on the frequency domain transform of the target time domain response based on a pre-established second target time-frequency transform model to obtain the target time domain response.

[0090] In this embodiment, the frequency domain transform of the target time domain response is a response function about the complex frequency s, and the target frequency domain response is inversely transformed based on the second target time-frequency transform model, and the frequency domain transform of the target time domain response is converted to the time domain space to obtain the target time domain response about time t. ,Right now The target time domain response may be a function of any vascular system parameter of the vascular system in response to the time domain excitation. Alternatively, it may be a response function of blood pressure, blood flow, etc.

[0091] Optionally, the second target time-frequency transformation model may also be a deep learning network, for example, a convolutional neural network, a recurrent neural network, a long short-term memory network, a generative adversarial network, an autoencoder, etc.

[0092] According to the above embodiments, it can be known that when the target time domain response a is obtained, the target time domain response b can be obtained based on the target time domain response a, etc.; or when the target time domain response a and the target time domain response c are obtained, the target time domain response d can be obtained based on the target time domain response a and the target time domain response c.

[0093] In an embodiment of the present application, an inverse time-frequency transform is performed on the frequency domain transform of the target time domain response based on a pre-established second target time-frequency transform model to obtain the target time domain response. The efficiency of determining the target time domain response is improved by the second target time-frequency transform model, thereby improving the efficiency of the analysis of the vascular system.

[0094] In one embodiment, a target system function is obtained based on a vascular system, target medical information of the vascular system and a pre-established target system function determination model, including: inputting the vascular system and the target medical information into the target system function determination model to obtain target system function parameters; and constructing the target system function based on the target system function parameters.

[0095] In this embodiment, the target system function G(s) may be a transfer function in the form of a rational fraction, a zero-pole, or a time constant.

[0096] If the target system function is a zero-pole transfer function, the target system function parameters include a transfer coefficient, a first number of zeros and a second number of poles. The zero-pole transfer function is determined based on the transfer coefficient, the first number of zeros and the second number of poles.

[0097] If the target system function is a transfer function in the form of a rational fraction, the target system function parameters include coefficients of the numerator polynomial, the order of the numerator polynomial, coefficients of the denominator polynomial and the order of the denominator polynomial. The transfer function in the form of a rational fraction is determined based on the coefficients of the numerator polynomial and the coefficients of the denominator polynomial.

[0098] If the target system function is a transfer function in a constant form, the target system function parameters include a gain factor and a time constant, and the transfer function in a constant form is determined based on the time constant and the gain factor.

[0099] In the embodiment of the present application, a target system function is obtained based on target system function parameters, and the target system function is used to represent the system frequency domain characteristics of the vascular system, so as to facilitate experimental analysis of the vascular system.

[0100] In one embodiment, the target system function parameters include the order of the denominator polynomial, the order of the numerator polynomial, the coefficients of the denominator polynomial and the coefficients of the numerator polynomial. Constructing the target system function based on the target system function parameters includes: determining the target system function according to the order of the denominator polynomial, the coefficients of the denominator polynomial, the order of the numerator polynomial and the coefficients of the numerator polynomial.

[0101] In this embodiment, the target system function parameters include the order of the denominator polynomial, the order of the numerator polynomial, the coefficients of the denominator polynomial and the coefficients of the numerator polynomial. The target system function obtained based on the order of the denominator polynomial, the order of the numerator polynomial, the coefficients of the denominator polynomial and the coefficients of the numerator polynomial can be expressed as: , where m is the order of the numerator polynomial, n is the order of the denominator polynomial, b0, b1, ..., b m are the coefficients of the numerator polynomial, a0, a1, ..., a n are the coefficients of the denominator polynomial.

[0102] In this embodiment, the denominator polynomial and the numerator polynomial of the above-mentioned target coefficient function can also be transformed into a monic polynomial, and then factorized within the complex number range. The target system function can be expressed as , i.e. the zero-pole transfer function in the above embodiment. The parameters of the target system function may include the transfer coefficient , zero point z i , the pole p i , the number of poles m (which has the same value as the order of the numerator polynomial above, but is represented differently in different forms of the objective coefficient function), and the number of zeros n (which has the same value as the order of the denominator polynomial above, but is represented differently in different forms of the objective coefficient function).

[0103] In an embodiment of the present application, the target system function is determined based on the order of the denominator polynomial, the coefficients of the denominator polynomial, the order of the numerator polynomial and the coefficients of the numerator polynomial. The target system function provides a concise mathematical model that intuitively reflects the relationship between input and output, and can facilitate performance analysis of the vascular system through frequency domain analysis methods.

[0104] FIG4 is a flow chart of a method for determining a target system function model in an embodiment, as shown in FIG4 , comprising the following steps:

[0105] S401, obtaining a vascular data set; the vascular data set includes a plurality of sample vascular systems and sample medical information of the plurality of sample vascular systems.

[0106] S402 , obtaining a sample time domain excitation of each sample vascular system based on each sample medical information.

[0107] S403 , obtaining a reference time domain response of each sample vascular system according to each sample time domain excitation and the corresponding sample vascular system.

[0108] S404 , training the initial system function determination model according to each sample time domain excitation, each sample vascular system and each reference time domain response to obtain a target system function determination model.

[0109] In this embodiment, a plurality of sample vascular systems and sample medical information of the plurality of sample vascular systems may be input into an initial system function determination model to obtain a sample system function.

[0110] In a possible implementation, the sample time domain excitation can be transformed into a frequency domain using Fourier transform to obtain the frequency domain transform of the sample time domain excitation, the frequency domain transform of the sample time domain response is determined according to the frequency domain transform of the sample time domain excitation and the sample system function, and the frequency domain transform of the sample time domain response is converted to the time domain using inverse Fourier transform to obtain the sample time domain response. The sample system function is updated according to the difference between the sample time domain response and the reference time domain response, that is, the initial system function determination model is trained to obtain the target system function determination model.

[0111] In another possible implementation, the sample time domain excitation can be transformed in time-frequency mode based on the first initial time-frequency transformation model to obtain the frequency domain transformation of the sample time domain excitation; based on the frequency domain transformation of the sample time domain excitation and the sample system function, the frequency domain transformation of the sample time domain response can be determined; based on the second initial time-frequency transformation model, the frequency domain transformation of the sample time domain response can be inversely transformed in time-frequency mode to obtain the sample time domain response; based on the difference between the sample time domain response and the reference time domain response, the first initial time-frequency transformation model, the initial system function determination model and the second initial time-frequency transformation model can be trained to obtain the target system function determination model.

[0112] In an embodiment of the present application, a sample time domain excitation of each sample vascular system is obtained based on each sample medical information; a reference time domain response of each sample vascular system is obtained based on each sample time domain excitation and the corresponding sample vascular system; an initial system function determination model is trained based on each sample time domain excitation, each sample vascular system and each reference time domain response to obtain a target system function determination model, thereby laying a foundation for subsequently determining the target time domain response based on the target system function determination model, the vascular system, the target medical information of each vascular system and the target time domain excitation.

[0113] FIG5 is a flow chart of a method for determining a target system function determination model in another embodiment. As shown in FIG5 , the embodiment of the present application relates to a possible implementation method of how to train an initial system function determination model based on each sample time domain excitation, each sample vascular system and each reference time domain response to obtain a target system function determination model, including the following steps:

[0114] S501 , performing time-frequency transformation on each sample time-domain excitation based on a first initial time-frequency transformation model to obtain a frequency-domain transformation of each sample time-domain excitation.

[0115] S502, determining the frequency domain transformation of the sample time domain response based on the frequency domain transformation of each sample time domain excitation and the sample system function; the sample system function is obtained based on the model determined by each sample vascular system, each sample medical information and the initial system function.

[0116] S503: Perform inverse time-frequency transformation on the frequency domain transformation of each sample time domain response based on the second initial time-frequency transformation model to obtain a sample time domain response.

[0117] S504: Based on the time domain responses of each sample and the reference time domain responses, the first initial time-frequency transformation model, the initial system function determination model and the second initial time-frequency transformation model are trained to obtain a target system function determination model.

[0118] In this embodiment, the first initial time-frequency transformation model, the initial system function determination model and the second initial time-frequency transformation model can be trained in sequence to obtain the first intermediate time-frequency transformation model, the intermediate system function determination model and the second intermediate time-frequency transformation model.

[0119] Finally, the sample medical information, sample time domain excitation and sample vascular system are input into the first intermediate time-frequency transformation model, the intermediate system function determination model and the second intermediate time-frequency transformation model to obtain the sample time domain response. The first intermediate time-frequency transformation model, the intermediate system function determination model and the second intermediate time-frequency transformation model are trained simultaneously by the sample time domain response and the reference time domain response to obtain the first target time-frequency transformation model, the target system function determination model and the second target time-frequency transformation model.

[0120] In the embodiment of the present application, a time-frequency transformation is performed on each sample time-domain excitation based on the first initial time-frequency transformation model to obtain a frequency domain transformation of each sample time-domain excitation, and a frequency domain transformation of the sample time-domain response is determined based on the frequency domain transformation of each sample time-domain excitation and the sample system function, and an inverse time-frequency transformation is performed on the frequency domain transformation of each sample time-domain response based on the second initial time-frequency transformation model to obtain a sample time-domain response, and the first initial time-frequency transformation model, the initial system function determination model, and the second initial time-frequency transformation model are trained based on each sample time-domain response and the reference time-domain response to obtain a target system function determination model. In the embodiment of the present application, the target time-domain response can be determined end-to-end based on three network models, that is, the target time-domain response can be obtained by only inputting the target medical information, the target time-domain excitation, and the vascular system, thereby improving the efficiency and accuracy of the analysis of the vascular system.

[0121] It should be noted that the present application obtains the time domain response end-to-end through the first target time-frequency transformation model, the second target time-frequency transformation model and the target system function determination model, which is different from directly extracting medical image features based on the neural network model and medical images to obtain blood flow parameters. The present application constructs the frequency domain characteristic function of the vascular system through the target system function determination model to describe the frequency domain performance of the vascular system, thereby obtaining different system responses based on different system excitations.

[0122] FIG6 is a flow chart of a method for analyzing a vascular system in another embodiment, as shown in FIG6 , comprising the following steps:

[0123] S601, inputting the vascular system and target medical information into a target system function determination model to obtain target system function parameters; the target system function parameters include a transfer coefficient, a first number of zeros, and a second number of poles;

[0124] S602, determining a target system function according to the order of the denominator polynomial, the coefficients of the denominator polynomial, the order of the numerator polynomial, and the coefficients of the numerator polynomial;

[0125] S603, acquiring a target time-domain excitation of the vascular system based on the target medical information;

[0126] S604, performing a time-frequency transformation on the target time-domain excitation based on a pre-established first target time-frequency transformation model to obtain a frequency domain transformation of the target time-domain excitation;

[0127] S605, determining a frequency domain transform of a target time domain response according to the frequency domain transform of the target time domain excitation and the target system function;

[0128] S606: Perform an inverse time-frequency transform on the frequency domain transform of the target time domain response based on a pre-established second target time-frequency transform model to obtain a target time domain response.

[0129] Since existing fluid mechanics methods use numerical simulation for calculations and require solving a large number of equations, in the embodiments of the present application, a target system function can be quickly determined based on the target system function determination model, which reduces the complexity of determining the target time domain response of the vascular system, thereby improving the analysis efficiency of the vascular system; further, the target system function is constructed by determining the model through the target system function, and the target system function indirectly reveals the system frequency domain characteristics of the vascular system and facilitates experimental analysis of the vascular system.

[0130] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0131] Based on the same inventive concept, the embodiment of the present application also provides a vascular system analysis device for implementing the above-mentioned vascular system analysis method. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the one or more vascular system analysis device embodiments provided below can refer to the limitations of the vascular system analysis method above, and will not be repeated here.

[0132] In an exemplary embodiment, as shown in FIG7 , a vascular system analysis device is provided, comprising: a first determination module 11 , a first acquisition module 12 , and a second determination module 13 , wherein:

[0133] A first determination module 11 is used to determine a model based on the vascular system, target medical information of the vascular system and a pre-established target system function to obtain a target system function;

[0134] A first acquisition module 12, configured to acquire a target time domain excitation of a vascular system based on target medical information;

[0135] The second determination module 13 is used to determine the target time domain response of the vascular system according to the target time domain excitation and the target system function of the vascular system; the target time domain response is used to analyze the vascular system.

[0136] In one embodiment, the second determination module 13 is specifically used to perform a time-frequency transform on the target time domain excitation based on a pre-established first target time-frequency transform model to obtain a frequency domain transform of the target time domain excitation; determine the frequency domain transform of the target time domain response according to the frequency domain transform of the target time domain excitation and the target system function; and perform an inverse time-frequency transform on the frequency domain transform of the target time domain response to obtain a target time domain response of the vascular system.

[0137] In one embodiment, the second determination module 13 is specifically configured to perform an inverse time-frequency transform on the frequency domain transform of the target time domain response based on a pre-established second target time-frequency transform model to obtain the target time domain response.

[0138] In one embodiment, the first determination module 11 is specifically configured to input the vascular system and target medical information into a target system function determination model to obtain target system function parameters; and obtain the target system function based on the target system function parameters.

[0139] In one embodiment, the first acquisition module 12 is specifically configured to determine the target system function according to the order of the denominator polynomial, the coefficients of the denominator polynomial, the order of the numerator polynomial, and the coefficients of the numerator polynomial.

[0140] In one embodiment, the vascular system analysis device further comprises:

[0141] A second acquisition module is used to acquire a blood vessel data set; the blood vessel data set includes a plurality of sample blood vessel systems and sample medical information of the plurality of sample blood vessel systems;

[0142] A third determination module is used to obtain a sample time domain excitation of each sample vascular system based on each sample medical information;

[0143] A fourth determination module, configured to obtain a reference time domain response of each sample vascular system according to each sample time domain excitation and the corresponding sample vascular system;

[0144] The training module is used to train the initial system function determination model according to each sample time domain excitation, each sample vascular system and each reference time domain response to obtain a target system function determination model.

[0145] In one embodiment, the training module is specifically used to perform time-frequency transformation on each sample time-domain excitation based on the first initial time-frequency transformation model to obtain the frequency domain transformation of each sample time-domain excitation; determine the frequency domain transformation of the sample time-domain response based on the frequency domain transformation of each sample time-domain excitation and the sample system function; the sample system function is obtained based on each sample vascular system, each sample medical information and the initial system function determination model; perform time-frequency inverse transformation on the frequency domain transformation of each sample time-domain response based on the second initial time-frequency transformation model to obtain the sample time-domain response; train the first initial time-frequency transformation model, the initial system function determination model and the second initial time-frequency transformation model based on each sample time-domain response and the reference time-domain response to obtain the target system function determination model.

[0146] Each module in the above-mentioned vascular system analysis device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the corresponding operations of each of the above modules.

[0147] In an exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be shown in FIG8. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. The processor, the memory, and the input / output interface are connected via a system bus, and the communication interface, the display unit, and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner may be implemented through WIFI, a mobile cellular network, near field communication (NFC) or other technologies. When the computer program is executed by the processor, a method for analyzing a vascular system is implemented. The display unit of the computer device is used to form a visually visible picture, which may be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0148] Those skilled in the art will understand that the structure shown in FIG. 8 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0149] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of any of the above embodiments when executing the computer program.

[0150] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above embodiments are implemented.

[0151] In one embodiment, a computer program product is provided, including a computer program, which implements the steps of any of the above embodiments when executed by a processor.

[0152] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0153] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0154] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0155] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the present application. It should be noted that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for analyzing a vascular system, characterized in that: The method comprises: Determine a model based on the vascular system, target medical information of the vascular system and a pre-established target system function to obtain a target system function; Acquire a target time-domain excitation of the vascular system based on the target medical information; A target time-domain response of the vascular system is determined according to the target time-domain excitation of the vascular system and the target system function; the target time-domain response is used to analyze the vascular system.

2. The method according to claim 1, characterized in that Determining a target time-domain response of the vascular system according to the target time-domain excitation of the vascular system and the target system function comprises: Performing a time-frequency transformation on the target time-domain excitation based on a pre-established first target time-frequency transformation model to obtain a frequency-domain transformation of the target time-domain excitation; Determining a frequency domain transform of a target time domain response according to the frequency domain transform of the target time domain excitation and the target system function; The frequency domain transform of the target time domain response is subjected to an inverse time-frequency transform to obtain a target time domain response of the vascular system.

3. The method according to claim 2, characterized in that The step of performing an inverse time-frequency transform on the frequency domain transform of the target time domain response to obtain the target time domain response of the vascular system includes: Based on a pre-established second target time-frequency transformation model, an inverse time-frequency transformation is performed on the frequency domain transformation of the target time domain response to obtain a target time domain response.

4. The method according to claim 1, characterized in that: The method of determining a model based on the vascular system, target medical information of the vascular system and a pre-established target system function to obtain the target system function includes: Inputting the vascular system and the target medical information into the target system function determination model to obtain target system function parameters; The target system function is constructed based on the target system function parameters.

5. The method according to claim 4, characterized in that The target system function parameters include the order of the denominator polynomial, the order of the numerator polynomial, the coefficients of the denominator polynomial and the coefficients of the numerator polynomial. The constructing the target system function based on the target system function parameters includes: The target system function is determined according to the order of the denominator polynomial, the coefficients of the denominator polynomial, the order of the numerator polynomial and the coefficients of the numerator polynomial.

6. The method according to claim 1, characterized in that The method further comprises: Acquire a vascular data set; the vascular data set includes a plurality of sample vascular systems and sample medical information of the plurality of sample vascular systems; Obtaining a sample time domain excitation of each of the sample vascular systems based on each of the sample medical information; Obtaining a reference time domain response of each of the sample vascular systems according to each of the sample time domain excitations and the corresponding sample vascular system; The initial system function determination model is trained according to each of the sample time-domain excitations, each of the sample vascular systems and each of the reference time-domain responses to obtain the target system function determination model.

7. The method according to claim 6, characterized in that The training of the initial system function determination model according to each of the sample time domain excitations, each of the sample vascular systems and each of the reference time domain responses to obtain the target system function determination model includes: Performing a time-frequency transformation on each of the sample time-domain excitations based on a first initial time-frequency transformation model to obtain a frequency-domain transformation of each of the sample time-domain excitations; Determine the frequency domain transformation of the sample time domain response based on the frequency domain transformation of each of the sample time domain excitations and the sample system function; the sample system function is obtained by determining the model based on each of the sample vascular systems, each of the sample medical information and the initial system function; Performing an inverse time-frequency transform on the frequency domain transform of each of the sample time domain responses based on a second initial time-frequency transform model to obtain the sample time domain response; Based on each of the sample time domain responses and the reference time domain response, the first initial time-frequency transform model, the initial system function determination model and the second initial time-frequency transform model are trained to obtain the target system function determination model.

8. A device for analyzing a vascular system, characterized in that: The device comprises: A first determination module is used to determine a model based on a vascular system, target medical information of the vascular system and a pre-established target system function to obtain a target system function; A first acquisition module, configured to acquire a target time-domain excitation of the vascular system based on the target medical information; The second determination module is used to determine the target time domain response of the vascular system according to the target time domain excitation of the vascular system and the target system function; the target time domain response is used to analyze the vascular system.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images