WO2022161239A1

WO2022161239A1 - Methods and systems for obtaining flow loss model, loss ratio, and blood supply capability

Info

Publication number: WO2022161239A1
Application number: PCT/CN2022/072920
Authority: WO
Inventors: 刘广志; 王鹏; 王之元; 戴威
Original assignee: 苏州润迈德医疗科技有限公司
Priority date: 2021-01-29
Filing date: 2022-01-20
Publication date: 2022-08-04
Also published as: CN112932434A; CN112932434B

Abstract

Methods and systems for obtaining a flow loss model, a loss ratio, and a blood supply capability. The method for obtaining a flow loss model comprises: obtaining a blood vessel segment of interest (S100); obtaining feature values of the blood vessel segment of interest, comprising a vascular shape parameter, heart rate, blood flow speed, and blood flow volume (S200); and establishing a blood flow loss model according to the feature values (S300). By means of synthesizing a blood vessel segment of interest, blood vessel feature values are obtained from the blood vessel segment, a blood flow loss model is obtained according to the blood vessel feature values and deep learning, and then a flow loss ratio of different motion levels is obtained on the basis of a deep model, thereby implementing differential evaluation for an individual, and improving the blood supply capabilities and the accuracy of the evaluation of an ischemia situation.

Description

Method and system for obtaining flow loss model, loss ratio, and blood supply capacity

technical field

The present invention relates to the technical field of coronary medicine, in particular to a method and system for obtaining a flow loss model, a loss ratio and a blood supply capacity.

Background technique

Human blood vessels are the channels for blood transmission. Arteries are responsible for transporting blood to various tissues and organs for material exchange. Oxygen nutrients are absorbed by various tissues and organs, and at the same time, various tissues and organs discharge carbon dioxide and waste. The reduction of blood flow due to vascular injury will affect the function of various tissues and organs, such as myocardial ischemia caused by coronary artery occlusion. In the existing technology, invasive pressure guide wire is used to measure vascular pressure to obtain functional indicators (such as FFR, IMR), but it is necessary to use dilation drugs to simulate the maximum hyperemia state, and the surgical operation is complicated and time-consuming, and there are surgical risks, resulting in less application.

Therefore, in order to solve the problem of the pressure guide wire, the blood supply capacity is currently evaluated by imaging the blood vessel parameters, such as shape, blood flow rate and pressure. However, with the increase of age, the patient does not need to perform large-scale strenuous exercise, so the requirements for blood supply are reduced, and the blood supply capacity of the blood vessel is affected due to the difference in the cross-sectional area of the individual blood vessel lumen.

Combining the above factors, simply obtaining morphological parameters from images only considers the degree of vascular occlusion and cannot accurately assess whether the actual organ is ischemia under different load conditions, and there is a problem of inaccurate assessment.

SUMMARY OF THE INVENTION

The present invention provides a method and system for obtaining a flow loss model, a loss ratio and a blood supply capacity, so as to solve the problem that in the prior art, simply obtaining morphological parameters from an image only considers the degree of vascular occlusion and cannot accurately evaluate the actual organs in different load states. Whether it is ischemia or not, there is a problem of inaccurate assessment.

In order to achieve the above objects, in a first aspect, the present application provides a method for obtaining a blood flow loss model, including:

Obtain the vessel segment of interest;

obtaining the characteristic value of the blood vessel segment of interest;

Based on the characteristic values, a blood flow loss model is established.

Optionally, in the above method for obtaining a blood flow loss model, the characteristic values include: blood vessel shape parameters, heart rate, blood flow velocity and blood flow.

Optionally, in the above-mentioned method for obtaining a blood flow loss model, according to the characteristic value, the method for establishing the blood flow loss model includes:

blood flow loss ratio

where QR is the velocity loss ratio, ΔQ is the blood flow loss from the inlet to the outlet of the vessel segment of interest, and Q is the inlet flow of the vessel segment of interest;

According to the sample data, the relationship between the feature value and the blood flow loss ratio is obtained, and a blood flow loss model is created through deep learning.

Optionally, in the above-mentioned method for obtaining a blood flow loss model, the method for obtaining the relationship between the feature value and the blood flow loss ratio according to sample data, and creating a blood flow loss model through deep learning, include:

If the blood vessel shape parameters are the same, according to the sample data, obtain the relationship between blood flow velocity and blood flow loss ΔQ=h(v), where h(v) represents a function with v as an independent variable, and v represents blood flow speed;

If the blood flow velocity is the same, according to the sample data, obtain the relationship between the blood vessel shape parameter and the blood flow loss ΔQ=f(m), where f(m) represents an independent variable with m as an independent variable The function of , m represents the vascular morphological parameters, including: the reference lumen area S of the normal blood vessel, the minimum lumen cross-sectional area S' of the vascular stenosis area, and the vessel length L of the vascular stenosis area.

According to ΔQ=h(v), ΔQ=f(m),

Deep learning is performed on the sample through a multi-layer fully connected neural network to obtain a blood flow loss model.

Optionally, in the above-mentioned method for obtaining a blood flow loss model, the method of the multi-layer fully connected neural network includes: an input layer, at least two hidden layers, each hidden layer includes 50-150 neurons, and an activation function , the output layer.

Optionally, in the above method for obtaining a blood flow loss model, the activation function includes: a sigmod function.

Optionally, the above-mentioned method for obtaining a blood flow loss model further includes: generating a simulated sample according to the relationship between the characteristic value and the blood flow loss, adding the simulated sample to the sample data, and expanding the sample. quantity.

Optionally, in the above-mentioned method for obtaining a blood flow loss model, the method for obtaining the relationship ΔQ=h(v) between blood flow velocity and blood flow loss according to sample data if the vascular morphological parameters are the same, includes: :

If the blood vessel shape parameters are the same, the abscissa is established as

The ordinate is

coordinate system, set the sample data points in the coordinate system, and obtain the relationship between blood flow velocity and blood flow loss ΔQ=h(v), where ΔQ _p represents when the average blood flow velocity is v _p , the flow loss of the vessel segment of interest from the inlet to the outlet, ΔQ _a represents the flow loss of the vessel segment of interest from the inlet to the outlet under the real vessel shape, v _p represents the average blood flow velocity when the relative v _a changes by k%, -50<k<50, v _a represents the average blood flow velocity of the vessel segment of interest from the inlet to the outlet under the real vessel shape.

Optionally, in the above method for obtaining a blood flow loss model, -30<k<30.

Optionally, in the above-mentioned method for obtaining a blood flow loss model, if the blood flow velocity is the same, the method for obtaining the relationship ΔQ=f(m) between the blood vessel shape parameter and the blood flow loss according to the sample data, comprising: :

If the blood flow velocity is the same, the abscissa is established as

The ordinate is

coordinate system, set the sample data points in the coordinate system, and obtain the relationship between the vascular morphological parameters and blood flow loss ΔQ=f(m), where ΔQ _p represents when the vascular morphological parameter is m _p , the flow loss from the inlet to the outlet of the vessel segment of interest, ΔQ _a represents the flow loss from the inlet to the outlet of the vessel segment of interest under the real vessel shape, _mp represents the vessel morphology parameter when e% of the relative m _a changes, - 50<e<50, m _a represents the blood vessel shape parameters of the blood vessel segment of interest from the inlet to the outlet under the real blood vessel shape.

Optionally, in the above-mentioned method for obtaining a blood flow loss model, -30<e<30.

In a second aspect, the present application provides a method for obtaining blood flow loss ratios of different exercise levels, including:

The above method for obtaining a blood flow loss model;

measure the heart rate and average blood flow velocity from the inlet to the outlet of the vessel segment of interest;

obtaining the exercise level according to the heart rate;

According to the exercise level, obtain the blood flow speed at each level of exercise level;

According to the blood flow loss model, the vascular morphological parameters, and the blood flow velocity under various exercise levels, the flow loss ratios under different exercise levels are obtained.

Optionally, in the above-mentioned method for obtaining the blood flow loss ratio of different exercise levels, the method for obtaining the exercise level according to the heart rate includes:

If p≤80 times/min, it is in the resting state, and the exercise level is M=1;

If 80 times/min<p≤120 times/min, it is in the state of exercise load, and the exercise level is M=2;

If 120 times/min<p≤180 times/min, it is in the state of maximum load, and the exercise level is M=3.

Optionally, in the above-mentioned method for obtaining blood flow loss ratios of different exercise levels, the method for obtaining blood flow velocity at each exercise level according to the exercise level includes:

If the blood flow speed of exercise level M=1 is v ₁ , then the blood flow speed of exercise level M=2 is v ₂ =av ₁ , then the blood flow speed of exercise level M=3 is v ₃ =bv ₁ , where 1<a<b, 2≤b≤4.

Optionally, in the above method for obtaining blood flow loss ratios of different exercise levels, a=4/3, 2≤b≤3.

In a third aspect, the present application provides a method for obtaining blood supply capacity at different exercise levels according to the blood flow loss ratio, including:

Obtain the heart rate at the same moment, and the average blood flow velocity of the vessel segment of interest;

Obtain the current exercise level according to the heart rate;

According to the current exercise level and the average blood flow speed under the current exercise level, obtain the blood flow speed under each exercise level;

According to the angiography image, obtain the vascular morphological parameters;

According to the blood flow loss model, calculate the blood flow loss ratio under different exercise levels;

According to the blood flow loss ratio and physiological parameters, the blood supply capacity of the blood vessel segment of interest is obtained.

Optionally, the above-mentioned method for obtaining the blood supply capacity of different exercise levels according to the blood flow loss ratio, the method for obtaining the blood supply capacity of the blood vessel segment of interest according to the blood flow loss ratio and physiological parameters includes:

If the blood flow loss ratio QR ₁ >0.25 when the exercise level M=1, the blood supply capacity of the blood vessel segment of interest is at level A;

If the exercise level M=1, the blood flow loss ratio QR ₁ ≤ 0.25, and the blood flow loss ratio QR ₂ ≥ 0.2 of the exercise level M=2, the blood supply capacity of the blood vessel segment of interest is at level B;

If the exercise level M=2, the blood flow loss ratio QR ₂ ≤ 0.25, and the blood flow loss ratio QR ₃ ≥ 0.2 of the exercise level M=3, the blood supply capacity of the blood vessel segment of interest is at level C;

If the exercise level M=3 and the blood flow loss ratio QR ₃ <0.2, the blood supply capacity of the blood vessel segment of interest is at level D;

Wherein, A, B, C, and D represent that the adequacy of the blood supply capacity increases sequentially.

In a fourth aspect, the present application provides a system for obtaining a blood flow loss model, comprising:

a vessel segment obtaining device, used to obtain a vessel segment of interest;

an eigenvalue acquiring device, connected to the blood vessel segment acquiring device, for acquiring the eigenvalues of the blood vessel segment of interest;

A blood flow loss model device is connected to the feature value acquisition device, and is used for establishing a blood flow loss model according to the feature value.

In a fifth aspect, the present application provides a computer storage medium, comprising: when a computer program is executed by a processor, the above-mentioned method for obtaining a blood flow loss model is implemented.

The beneficial effects brought by the solutions provided in the embodiments of the present application include at least:

The present application provides a method and system for obtaining a flow loss model, a loss ratio, and a blood supply capacity. By synthesizing a blood vessel segment of interest, a blood vessel characteristic value is obtained from the blood vessel segment, and a blood flow loss model is obtained according to the blood vessel characteristic value and deep learning. , and then based on the blood flow loss model, the flow loss ratio of different exercise levels is obtained, thereby realizing the differentiated evaluation for individuals, and improving the accuracy of blood supply capacity and ischemia evaluation.

Description of drawings

The accompanying drawings described herein are used to provide further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the attached image:

1 is a flowchart of a method for obtaining a blood flow loss model according to the present application;

Fig. 2 is the flowchart of S300 of this application;

Fig. 3 is the coordinate diagram of step (1) in S320 of the application;

Fig. 4 is the coordinate diagram of step (2) in S320 of this application;

5 is a flowchart of a method for obtaining blood flow loss ratios of different exercise levels according to the present application;

Fig. 6 is the flow chart of the method for obtaining the blood supply capacity of different exercise levels according to the blood flow loss ratio of the present application;

7 is a structural block diagram of an embodiment of a system for obtaining a blood flow loss model according to the present application;

FIG. 8 is a structural block diagram of another embodiment of a system for obtaining a blood flow loss model according to the present application.

Detailed ways

In order to make the objectives, technical solutions and advantages of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the specific embodiments of the present invention and the corresponding drawings. Obviously, the described embodiments are only some, but not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

Various embodiments of the present invention will be disclosed in the drawings below, and for the sake of clarity, many practical details will be described together in the following description. It should be understood, however, that these practical details should not be used to limit the invention. That is, in some embodiments of the invention, these practical details are unnecessary. In addition, for the purpose of simplifying the drawings, some well-known structures and components will be shown in a simple schematic manner in the drawings.

In the prior art, morphological parameters are simply obtained from images, and only the degree of vascular occlusion is considered, but it is impossible to accurately assess whether the actual organ is ischemia under different loading states, and the assessment is inaccurate.

Example 1:

In order to solve the above problems, as shown in FIG. 1 , the present application provides a method for obtaining a blood flow loss model, including:

S100, acquire the blood vessel segment of interest, including:

1) Acquiring at least two body positions of two-dimensional coronary angiography image groups; preferably, the angles of the two body positions differ by 30° or more.

2) Screening out at least one two-dimensional angiography image of at least one body position of the same vessel segment from each group of the two-dimensional coronary angiography image groups, that is, obtaining the vessel segment of interest.

S200: Obtain characteristic values of the blood vessel segment of interest, including: blood vessel shape parameters, heart rate, blood flow velocity and blood flow.

1) The morphological parameters include: the real-time diameter D _n of the blood vessel, stenosis information, the length of the blood vessel segment of interest, and the like.

2) Heart rate, which can be measured by non-invasive blood pressure meter, sports bracelet, sports watch, etc., which is convenient to record heart rate data in real time;

3) Blood flow velocity, the method for obtaining the average blood flow velocity v from the coronary inlet of the vessel segment of interest to the distal end of the coronary stenosis includes:

Obtain the number of coronary angiography image frames contained in the heartbeat cycle area;

Among them, L represents the length of the blood vessel through which the contrast agent flows in a heartbeat cycle area in the vessel segment of interest, N represents the number of coronary angiography image frames contained in a heartbeat cycle area in the vessel segment of interest, and fps represents the number of frames transmitted per second. .

S300, as shown in Figure 2, establishes a blood flow loss model according to the characteristic values, including:

S310, blood flow loss ratio

S320, according to the sample data, obtain the relationship between the feature value and the blood flow loss ratio, and create a blood flow loss model through deep learning, including:

(1) As shown in Figure 3, if the morphological parameters of the blood vessels are the same, according to the sample data, obtain the relationship between the blood flow velocity and the blood flow loss ΔQ=h(v), where h(v) represents a value with v as the self A function of variables, v representing the blood flow velocity, including:

The ordinate is

coordinate system, set the sample data points in the coordinate system, and obtain the relationship between blood flow velocity and blood flow loss ΔQ=h(v), where ΔQ _p represents when the average blood flow velocity is v _p , the flow loss of the vessel segment of interest from the inlet to the outlet, ΔQ _a represents the flow loss of the vessel segment of interest from the inlet to the outlet under the real vessel shape, v _p represents the average blood flow velocity when the relative v _a changes by k%, -50< _k <50, va represents the average blood flow velocity of the blood vessel segment of interest from the inlet to the outlet under the real blood vessel shape; preferably, -30<k<30.

(2) As shown in Figure 4, if the blood flow velocity is the same, according to the sample data, obtain the relationship between the blood vessel shape parameters and the blood flow loss ΔQ=f(m), where f(m) represents a A function of variables, m represents the vascular morphological parameters, including: the reference lumen area S of the normal blood vessel, the minimum lumen cross-sectional area S' of the vascular stenosis area, and the blood vessel length L of the vascular stenosis area, including:

If the blood flow velocity is the same, the abscissa is established as

The ordinate is

coordinate system, set the sample data points in the coordinate system, and obtain the relationship between the vascular morphological parameters and blood flow loss ΔQ=f(m), where ΔQ _p represents when the vascular morphological parameter is m _p , the flow loss from the inlet to the outlet of the vessel segment of interest, ΔQ _a represents the flow loss from the inlet to the outlet of the vessel segment of interest under the real vessel shape, _mp represents the vessel morphology parameter when e% of the relative m _a changes, - 50<e<50, ma represents the blood vessel shape parameters of the blood vessel segment of interest from the inlet to the outlet under the real blood vessel shape _; preferably, -30<e<30.

(3) According to ΔQ=h(v), ΔQ=f(m),

Deep learning is performed on the samples through a multi-layer fully connected neural network to obtain a blood flow loss model. Preferably, the method of the multi-layer fully connected neural network includes: an input layer, at least two hidden layers, each hidden layer includes 50-150 neurons, an activation function, and an output layer; wherein, the activation function includes: a sigmod function.

If the sample data in S320 is not enough, a simulated sample can be generated according to the relationship between the characteristic value and the blood flow loss, that is, (1) and (2) in S320, and the simulated sample is added to the sample data in S320, and after the number of samples is expanded, the Step (3) in S320.

The present application is more intelligent by synthesizing the blood vessel segment of interest, obtaining the blood vessel characteristic value from the blood vessel segment, and obtaining the blood flow loss model according to the blood vessel characteristic value and deep learning.

Example 2:

As shown in Figure 5, the present application provides a method for obtaining blood flow loss ratios of different exercise levels, including:

A100, the method for obtaining the blood flow loss model in the above-mentioned embodiment 1;

A200, measure the heart rate and the average blood flow velocity of the vessel segment of interest from the inlet to the outlet;

A300, get exercise level based on heart rate, including:

1), if p≤80 times/min, it is in a resting state, and the exercise level is M=1;

2), if 80 times/min<p≤120 times/min, it is in the state of exercise load, and the exercise level is M=2;

3), if 120 times/min<p≤180 times/min, it is in the state of maximum load, and the exercise level is M=3:

A400, according to the exercise level, obtains the blood flow speed at each exercise level, the specific formula is:

Among them, M represents the exercise level, v1 represents the blood flow speed when the exercise level is _one , v2 represents the blood flow speed when the exercise level is _two , and _v3 represents the blood flow speed when the exercise level is three. ground, a=4/3, 2≤b≤3.

Since the heart rate is measured by non-invasive blood pressure meters, sports bracelets, sports watches, etc., it is convenient to record heart rate data in real time, so that it is convenient to record the maximum heart rate within a period of time, as well as the usual exercise intensity, for example: 1) The elderly or heart disease patients usually Basically do not exercise, and the heart rate is in the M=1 exercise state, then only the flow loss ratio when the exercise level is level 1 needs to be considered; 2) The patient only occasionally does extreme exercise, or the exercise intensity is basically light, basically at exercise level M = 2, it is recommended not to exercise vigorously, and the flow loss ratio when the exercise level is two can be considered; 3) If the frequency of the patient's exercise is high, and the frequency of reaching the maximum load state is high, such as a 10% probability If the maximum load state can be achieved, it is recommended to consider the flow loss ratio when the exercise level M=3; and then perform the corresponding ischemic state assessment according to different flow loss ratios.

A500, according to the blood flow loss model, the vascular morphological parameters, and the blood flow velocity under various exercise levels, to obtain the flow loss ratio under different exercise levels.

Based on individual differences, for example, the elderly, heart patients, etc. cannot or cannot perform extreme exercise, so even if ischemia under exercise load, but not ischemia under resting state, it can meet the individual requirements of patients. Interventional surgery may not be required. Therefore, since the ischemic requirements are different in the resting state, the exercise load state, and the maximum exercise load state, the present application divides the exercise levels based on the blood flow loss model, and then obtains the flow loss ratios of different exercise levels. more scientific.

Example 3:

As shown in Figure 6, the present application provides a method for obtaining blood supply capacity at different exercise levels according to the blood flow loss ratio, including:

B100, obtain the heart rate at the same moment, and the average blood flow velocity of the vessel segment of interest;

B200, obtain the current exercise level according to the heart rate;

B300, according to the current exercise level and the average blood flow speed under the current exercise level, obtain the blood flow speed under each exercise level;

B400, according to the angiography image, obtain the vascular morphological parameters;

B500, according to the blood flow loss model, calculate the blood flow loss ratio under different exercise levels;

B600, according to the blood flow loss ratio and physiological parameters, to obtain the blood supply capacity of the blood vessel segment of interest, including:

①If the exercise level M=1, and the blood flow loss ratio QR ₁ >0.25, the blood supply capacity of the vessel segment of interest is at level A;

Because when the exercise level M=1, the patient is in a resting state at this time. The resting state means that the person is lying still, which is equivalent to stillness. The blood flow loss ratio at this time is already higher than 0.25. According to clinical data and experiments At this time, the blood flow reserve fraction must be less than 0.75, then the blood supply capacity of the blood vessel is seriously insufficient, and it must be more ischemia under the state of exercise load. Therefore, the vascular segment of interest needs interventional surgery and other revascularization.

②If the exercise level M=1, the blood flow loss ratio QR ₁ ≤ 0.25, and the blood flow loss ratio QR ₂ ≥ 0.2 of the exercise level M=2, the blood supply capacity of the vessel segment of interest is at level B;

Because when the exercise level M=1, the patient is in a resting state at this time. The resting state means that the person is lying still, which is equivalent to stillness, and the blood flow loss ratio at this time is already lower than 0.25. According to clinical data and experiments At this time, the blood flow reserve fraction must be greater than or equal to 0.75, which is in the situation of further observation; and the exercise level M=2, the patient is in a state of exercise load at this time, but not the maximum exercise load state, and the blood flow loss ratio at this time is already high. At 0.2, according to clinical data and experiments, the blood flow reserve fraction must be less than or equal to 0.8 at this time, so in the case of less extreme load exercise, conservative treatment, drugs or observation can be used; but if more needs to be done For extreme load exercise, revascularization through interventional surgery is recommended.

③ If the exercise level M=2, the blood flow loss ratio QR ₂ ≤ 0.25, and the blood flow loss ratio QR ₃ ≥ 0.2 of the exercise level M=3, the blood supply capacity of the vessel segment of interest is in grade C;

Since the exercise level M=2, the patient is in a state of exercise load, but not the maximum exercise load state, and the blood flow loss ratio at this time is already lower than 0.25. According to clinical data and experiments, the blood flow reserve fraction at this time must be greater than is equal to 0.75, which is under further observation; while the exercise level M=3, the patient is in the state of maximum exercise load, and the blood flow loss ratio at this time is already higher than 0.2. According to clinical data and experiments, the blood flow reserve fraction is certain at this time. Less than or equal to 0.8, so if you do not do extreme load exercise at all, you can use conservative treatment, drugs or observation; but you must never do maximum load exercise, otherwise it will be life-threatening. For stress exercise, revascularization through interventional surgery is recommended.

④ If the exercise level is M=3 and the blood flow loss ratio QR ₃ <0.2, the blood supply capacity of the vessel segment of interest is at the D level; A, B, C, and D represent the adequacy of the blood supply capacity increasing in turn.

Since the exercise level is M=3, the patient is in the state of maximum exercise load at this time, and the blood flow loss ratio at this time is lower than 0.2. According to clinical data and experiments, the blood flow reserve fraction must be greater than or equal to 0.8 at this time, so the blood vessel segment of interest is If the blood supply is sufficient, conservative treatment, drugs or observation can be used.

The blood supply capacity of grades B and C, the doctor can give advice on whether to perform interventional surgery according to the patient's physiological parameters, such as age, gender, disease history, etc.

The above blood supply capacity rating can effectively give guidance to doctors, which is conducive to differentiated blood supply capacity evaluation for different individuals.

As shown in FIG. 7 , the present application provides a system for obtaining a blood flow loss model, including: a vessel segment obtaining device 100 for obtaining a blood vessel segment of interest; a feature value obtaining device 200 , and a vessel segment obtaining device 100 is connected to obtain the characteristic value of the blood vessel segment of interest; the blood flow loss model device 300 is connected to the characteristic value acquisition device 200 and used to establish a blood flow loss model according to the characteristic value.

As shown in FIG. 8 , it also includes: an exercise level acquisition device 400 and a vascular blood supply capacity acquisition device 500 . The vascular blood supply capacity acquisition device 500 is respectively connected with the blood vessel segment acquisition device 100 , the feature value acquisition device 200 , the blood flow loss model device 300 , and the exercise device. The level obtaining device 400 is connected, and the exercise level obtaining device 400 is used for obtaining the exercise level according to the heart rate;

The present application provides a computer storage medium, comprising: when a computer program is executed by a processor, the above-mentioned method for obtaining blood supply capability of a blood vessel is implemented.

As will be appreciated by one skilled in the art, various aspects of the present invention may be embodied as a system, method or computer program product. Accordingly, various aspects of the present invention may be embodied in the form of an entirely hardware implementation, an entirely software implementation (including firmware, resident software, microcode, etc.), or a combination of hardware and software aspects, It may be collectively referred to herein as a "circuit," "module," or "system." Furthermore, in some embodiments, various aspects of the present invention may also be implemented in the form of a computer program product on one or more computer-readable media having computer-readable program code embodied thereon. Implementation of the method and/or system of embodiments of the present invention may involve performing or completing selected tasks manually, automatically, or a combination thereof.

For example, hardware for performing selected tasks according to embodiments of the invention may be implemented as a chip or a circuit. As software, selected tasks according to embodiments of the invention may be implemented as a plurality of software instructions executed by a computer using any suitable operating system. In an exemplary embodiment of the invention, one or more tasks according to exemplary embodiments of a method and/or system as herein are performed by a data processor, such as a computing platform for executing a plurality of instructions. Optionally, the data processor includes volatile storage for storing instructions and/or data and/or non-volatile storage for storing instructions and/or data, such as a magnetic hard disk and/or a Move media. Optionally, a network connection is also provided. A display and/or user input device, such as a keyboard or mouse, is optionally also provided.

Any combination of one or more computer readable may be utilized. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or a combination of any of the above. More specific examples (non-exhaustive list) of computer-readable storage media would include the following:

Electrical connection with one or more wires, portable computer disk, hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read only memory (EPROM or flash memory), optical fiber, portable compact disk Read only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

A computer-readable signal medium may include a propagated data signal in baseband or as part of a carrier wave, with computer-readable program code embodied thereon. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device .

Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

For example, computer program code for performing operations for various aspects of the invention may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages, such as The "C" programming language or similar programming language. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network - including a local area network (LAN) or a wide area network (WAN) - or may be connected to an external computer (eg using an Internet service provider via Internet connection).

It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to the processor of a general purpose computer, special purpose computer or other programmable data processing apparatus to produce a machine that causes the computer program instructions when executed by the processor of the computer or other programmable data processing apparatus , resulting in means for implementing the functions/acts specified in one or more blocks of the flowchart and/or block diagrams.

These computer program instructions can also be stored on a computer-readable medium, the instructions cause a computer, other programmable data processing apparatus, or other device to operate in a particular manner, whereby the instructions stored on the computer-readable medium produce a An article of manufacture of instructions implementing the functions/acts specified in one or more blocks of the flowcharts and/or block diagrams.

Computer program instructions can also be loaded on a computer (eg, a coronary artery analysis system) or other programmable data processing device to cause a series of operational steps to be performed on the computer, other programmable data processing device or other device to produce a computer-implemented process , such that instructions executing on a computer, other programmable apparatus, or other device provide a process for implementing the functions/acts specified in the flowchart and/or one or more block diagram blocks.

The above specific examples of the present invention further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above are only specific embodiments of the present invention, and are not intended to limit the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

A method for obtaining a blood flow loss model, comprising:

Obtain the vessel segment of interest;

obtaining the characteristic value of the blood vessel segment of interest;

Based on the characteristic values, a blood flow loss model is established.
The method for obtaining a blood flow loss model according to claim 1, wherein the characteristic values include: blood vessel morphology parameters, heart rate, blood flow velocity and blood flow.
The method for obtaining a blood flow loss model according to claim 1, wherein, according to the characteristic value, the method for establishing the blood flow loss model comprises:

blood flow loss ratio
where QR is the velocity loss ratio, ΔQ is the blood flow loss from the inlet to the outlet of the vessel segment of interest, and Q is the inlet flow of the vessel segment of interest;

According to the sample data, the relationship between the feature value and the blood flow loss ratio is obtained, and a blood flow loss model is created through deep learning.
The method for obtaining a blood flow loss model according to claim 3, wherein the relationship between the characteristic value and the blood flow loss ratio is obtained according to sample data, and the blood flow is created by deep learning Methods for loss models, including:

If the blood vessel shape parameters are the same, according to the sample data, obtain the relationship between blood flow velocity and blood flow loss ΔQ=h(v), where h(v) represents a function with v as an independent variable, and v represents blood flow speed;

If the blood flow velocity is the same, according to the sample data, obtain the relationship between the blood vessel shape parameter and the blood flow loss ΔQ=f(m), where f(m) represents an independent variable with m as an independent variable The function of , m represents the vascular morphological parameters, including: the reference lumen area S of the normal blood vessel, the minimum lumen cross-sectional area S' of the vascular stenosis area, and the vessel length L of the vascular stenosis area.

According to ΔQ=h(v), ΔQ=f(m),
Deep learning is performed on the sample through a multi-layer fully connected neural network to obtain a blood flow loss model.
The method for obtaining a blood flow loss model according to claim 4, wherein the method for the multi-layer fully connected neural network comprises: an input layer and at least two hidden layers, and each hidden layer includes 50-150 Neurons, activation functions, output layers.
The method for obtaining a blood flow loss model according to claim 5, wherein the activation function comprises: a sigmod function.
The method for obtaining a blood flow loss model according to claim 3, further comprising: generating a simulated sample according to the relationship between the characteristic value and the blood flow loss, and adding the simulated sample to the sample data, expand the number of samples.
The method for obtaining a blood flow loss model according to claim 4, wherein, if the morphological parameters of the blood vessels are the same, the relationship between the blood flow velocity and the blood flow loss is obtained according to the sample data ΔQ=h(v ) methods, including:

If the blood vessel shape parameters are the same, the abscissa is established as
The ordinate is
coordinate system, set the sample data points in the coordinate system, and obtain the relationship between blood flow velocity and blood flow loss ΔQ=h(v), where ΔQ p represents when the average blood flow velocity is v p , the flow loss of the vessel segment of interest from the inlet to the outlet, ΔQ a represents the flow loss of the vessel segment of interest from the inlet to the outlet under the real vessel shape, v p represents the average blood flow velocity when the relative v a changes by k%, -50<k<50, v a represents the average blood flow velocity of the vessel segment of interest from the inlet to the outlet under the real vessel shape.
The method for obtaining a blood flow loss model according to claim 4, wherein, if the blood flow velocity is the same, according to the sample data, obtain the relationship between the blood vessel shape parameter and the blood flow loss ΔQ=f(m ) methods, including:

If the blood flow velocity is the same, the abscissa is established as
The ordinate is
coordinate system, set the sample data points in the coordinate system, and obtain the relationship between the vascular morphological parameters and blood flow loss ΔQ=f(m), where ΔQ p represents when the vascular morphological parameter is m p , the flow loss of the vessel segment of interest from the inlet to the outlet, ΔQ a represents the flow loss of the vessel segment of interest from the inlet to the outlet under the real vessel shape, mp represents the vessel morphology parameter when the relative m a changes e%, - 50<e<50, m a represents the blood vessel shape parameters of the blood vessel segment of interest from the inlet to the outlet under the real blood vessel shape.
A method for obtaining blood flow loss ratios of different exercise levels, comprising:

The method for obtaining a blood flow loss model according to any one of claims 1 to 9;

measure the heart rate and average blood flow velocity from the inlet to the outlet of the vessel segment of interest;

obtaining the exercise level according to the heart rate;

According to the exercise level, obtain the blood flow speed at each level of exercise level;

According to the blood flow loss model, the vascular morphological parameters, and the blood flow velocity under various exercise levels, the flow loss ratios under different exercise levels are obtained.
The method for obtaining blood flow loss ratios of different exercise levels according to claim 10, wherein the method for obtaining exercise levels according to the heart rate comprises:

If p≤80 times/min, it is in the resting state, and the exercise level is M=1;

If 80 times/min<p≤120 times/min, it is in the state of exercise load, and the exercise level is M=2;

If 120 times/min<p≤180 times/min, it is in the state of maximum load, and the exercise level is M=3.
The method for obtaining blood flow loss ratios of different exercise levels according to claim 11, wherein the method for obtaining blood flow velocity at various exercise levels according to the exercise levels comprises:

If the blood flow speed of exercise level M=1 is v 1 , then the blood flow speed of exercise level M=2 is v 2 =av 1 , then the blood flow speed of exercise level M=3 is v 3 =bv 1 , where 1<a<b, 2≤b≤4.
The method for obtaining blood flow loss ratios of different exercise levels according to claim 12, wherein a=4/3, 2≤b≤3.
A method for obtaining blood supply capacity at different exercise levels according to the blood flow loss ratio, comprising:

Obtain the heart rate at the same moment, and the average blood flow velocity of the vessel segment of interest;

Obtain the current exercise level according to the heart rate;

According to the current exercise level and the average blood flow speed under the current exercise level, obtain the blood flow speed under each exercise level;

According to the angiography image, obtain the vascular morphological parameters;

According to the blood flow loss model, calculate the blood flow loss ratio under different exercise levels;

According to the blood flow loss ratio and physiological parameters, the blood supply capacity of the blood vessel segment of interest is obtained.
The method for obtaining the blood supply capacity of different exercise levels according to the blood flow loss ratio according to claim 14, wherein the method for obtaining the blood supply capacity of the blood vessel segment of interest according to the blood flow loss ratio and physiological parameters comprises the following steps: :

If the blood flow loss ratio QR 1 >0.25 when the exercise level M=1, the blood supply capacity of the blood vessel segment of interest is at level A;

If the exercise level M=1, the blood flow loss ratio QR 1 ≤ 0.25, and the blood flow loss ratio QR 2 ≥ 0.2 of the exercise level M=2, the blood supply capacity of the blood vessel segment of interest is at level B;

If the exercise level M=2, the blood flow loss ratio QR 2 ≤ 0.25, and the blood flow loss ratio QR 3 ≥ 0.2 of the exercise level M=3, the blood supply capacity of the blood vessel segment of interest is at level C;

If the exercise level M=3 and the blood flow loss ratio QR 3 <0.2, the blood supply capacity of the blood vessel segment of interest is at level D;

Wherein, A, B, C, and D represent that the adequacy of the blood supply capacity increases sequentially.
A system for obtaining a blood flow loss model according to any one of claims 1 to 9, characterized in that it comprises:

a vessel segment obtaining device, used to obtain a vessel segment of interest;

an eigenvalue acquiring device, connected to the blood vessel segment acquiring device, for acquiring the eigenvalues of the blood vessel segment of interest;

A blood flow loss model device is connected to the feature value acquisition device, and is used for establishing a blood flow loss model according to the feature value.
A computer storage medium, comprising: when a computer program is executed by a processor, the method for obtaining a blood flow loss model according to any one of claims 1 to 9 is implemented.