Model-based cardiovascular image blood vessel identification marking method and system

Abstract

The invention discloses a model-based cardiovascular image blood vessel identification marking method and system, and the method comprises the steps: obtaining a cardiovascular image, and extracting the image features of the cardiovascular image, the image features comprise a local texture feature of each position on the cardiovascular image, a gray value of each position on the cardiovascular image and an average gray value of the cardiovascular image; respectively setting a first blood vessel recognition model, a second blood vessel recognition model, a third blood vessel recognition model and a fourth blood vessel recognition model, calculating a first blood vessel recognition value, a second blood vessel recognition value, a third blood vessel recognition value and a fourth blood vessel recognition value of each position on the cardiovascular image, and performing weighted summation operation to generate a final blood vessel recognition value; and comparing the final blood vessel recognition value with a preset blood vessel recognition value, and when the final blood vessel recognition value exceeds the preset blood vessel recognition value, recognizing a position corresponding to the final blood vessel recognition value as a blood vessel and labeling the blood vessel.

Description

Technical Field

[0001] The present invention belongs to the technical field of image recognition, and more specifically, relates to a method and system for identifying and marking blood vessels on cardiovascular images based on a model. Background Art

[0002] Cardiovascular images are medical images related to the heart and blood vessels, and are widely used in the diagnosis and treatment of cardiovascular diseases. Common types include CT angiography (CTA), magnetic resonance angiography (MRA), echocardiography, coronary angiography, electrocardiogram (ECG), optical coherence tomography (OCT), and nuclear medicine imaging (such as myocardial perfusion imaging). These technologies can clearly display the structure and function of blood vessels and the heart, help identify problems such as heart disease, arteriosclerosis, and coronary artery disease, and provide important support for the diagnosis and treatment of diseases.

[0003] However, there is currently no technical solution that can accurately identify blood vessels in cardiovascular images. Summary of the invention

[0004] In order to solve the above technical problems, the present invention proposes a model-based blood vessel identification and marking method on cardiovascular images, comprising:

[0005] Acquire a cardiovascular image, and extract image features of the cardiovascular image, wherein the image features include: a gradient at each position on the cardiovascular image, a local curvature at each position on the cardiovascular image, a local texture feature at each position on the cardiovascular image, a grayscale value at each position on the cardiovascular image, and an average grayscale value of the cardiovascular image;

[0006] respectively setting a first blood vessel identification model, a second blood vessel identification model, a third blood vessel identification model and a fourth blood vessel identification model, calculating a first blood vessel identification value, a second blood vessel identification value, a third blood vessel identification value and a fourth blood vessel identification value at each position on the cardiovascular image, and performing a weighted sum operation to generate a final blood vessel identification value;

[0007] The final blood vessel identification value is compared with a preset blood vessel identification value, and when the final blood vessel identification value exceeds the preset blood vessel identification value, a position corresponding to the final blood vessel identification value is identified as a blood vessel and marked.

[0008] Furthermore, the first blood vessel recognition model includes:

[0009]

[0010] Wherein, f1(x, y) is the first blood vessel recognition value at the position (x, y) on the cardiovascular image, α1 is the first adjustment factor of the first blood vessel recognition model, is the gradient at the position (x, y) on the cardiovascular image, β1 is the second adjustment factor of the first vessel recognition model, I(x, y) is the grayscale value at the position (x, y) on the cardiovascular image, and I avg is the average gray value of cardiovascular images, κ flow is the third adjustment factor of the first vessel identification model, is the local blood flow velocity at position (x, y) on the cardiovascular image.

[0011] Furthermore, the second blood vessel identification model includes:

[0012] f2(x, y) = γ1·(κ(x, y)) 2 ·exp(-δ1·(I(x,y)-I min ) 2 )·(1+θ elastic ∈(x,y));

[0013] Wherein, f2(x, y) is the second blood vessel recognition value at the position (x, y) on the cardiovascular image, γ1 is the first adjustment factor of the second blood vessel recognition model, κ(x, y) is the local curvature at the position (x, y) on the cardiovascular image, δ1 is the second adjustment factor of the second blood vessel recognition model, and I min is the minimum grayscale value of the cardiovascular image, θ elastic is the third adjustment factor of the second blood vessel recognition model, and ∈(x, y) is the local deformation of the blood vessel wall at the position (x, y) on the cardiovascular image.

[0014] Furthermore, the third blood vessel identification model includes:

[0015]

[0016] Wherein, f3(x, y) is the third blood vessel identification value at the position (x, y) on the cardiovascular image, ζ1 is the first adjustment factor of the third blood vessel identification model, is the local texture feature at position (x, y) on the cardiovascular image, and the local texture feature is extracted through the gray level co-occurrence matrix α′ is the second adjustment factor of the third blood vessel recognition model, β′ is the third adjustment factor of the third blood vessel recognition model, θ1 is the fourth adjustment factor of the third blood vessel recognition model, I mid is the gray value mean of cardiovascular image, σ abs is the fifth adjustment factor of the third vessel identification model, is the local absorbance at position (x, y) on the cardiovascular image.

[0017] Furthermore, the fourth blood vessel identification model includes:

[0018]

[0019] Wherein, f4(x, y) is the fourth blood vessel identification value at the position (x, y) on the cardiovascular image, λ1 is the first adjustment factor of the fourth blood vessel identification model, is a Gaussian filter, σ r is the standard deviation of the rth scale used to control the width of the Gaussian filter, α1′ is the second adjustment factor of the fourth blood vessel recognition model, ρ1 is the third adjustment factor of the fourth blood vessel recognition model, β1′ is the fourth adjustment factor of the fourth blood vessel recognition model, κ biomech is the fifth adjustment factor of the fourth vessel identification model, is the thickness of the blood vessel wall at the position (x, y) on the cardiovascular image, wherein the cardiovascular image is divided into multiple scales according to the resolution.

[0020] The present invention also proposes a model-based blood vessel identification and marking system on cardiovascular images, comprising:

[0021] An image feature acquisition module is used to acquire a cardiovascular image and extract image features of the cardiovascular image, wherein the image features include: a gradient at each position on the cardiovascular image, a local curvature at each position on the cardiovascular image, a local texture feature at each position on the cardiovascular image, a gray value at each position on the cardiovascular image, and an average gray value of the cardiovascular image;

[0022] a final blood vessel identification value calculation module, used to respectively set a first blood vessel identification model, a second blood vessel identification model, a third blood vessel identification model and a fourth blood vessel identification model, calculate the first blood vessel identification value, the second blood vessel identification value, the third blood vessel identification value and the fourth blood vessel identification value at each position on the cardiovascular image, and perform a weighted sum operation to generate a final blood vessel identification value;

[0023] The identification and marking module is used to compare the final blood vessel identification value with a preset blood vessel identification value, and when the final blood vessel identification value exceeds the preset blood vessel identification value, identify the position corresponding to the final blood vessel identification value as a blood vessel and mark it.

[0024] Furthermore, the first blood vessel recognition model includes:

[0025]

[0026] Wherein, f1(x, y) is the first blood vessel recognition value at the position (x, y) on the cardiovascular image, α1 is the first adjustment factor of the first blood vessel recognition model, is the gradient at the position (x, y) on the cardiovascular image, β1 is the second adjustment factor of the first vessel recognition model, I(x, y) is the grayscale value at the position (x, y) on the cardiovascular image, and I avg is the average gray value of cardiovascular images, κ flow is the third adjustment factor of the first vessel identification model, is the local blood flow velocity at position (x, y) on the cardiovascular image.

[0027] Furthermore, the second blood vessel identification model includes:

[0028] f2(x, y) = γ1·(κ(x, y)) 2 ·exp(-δ1·(I(x,y)-I min ) 2 )·(1+θ elastic ∈(x,y));

[0029] Wherein, f2(x, y) is the second blood vessel recognition value at the position (x, y) on the cardiovascular image, γ1 is the first adjustment factor of the second blood vessel recognition model, κ(x, y) is the local curvature at the position (x, y) on the cardiovascular image, δ1 is the second adjustment factor of the second blood vessel recognition model, and I min is the minimum grayscale value of the cardiovascular image, θ elastic is the third adjustment factor of the second blood vessel recognition model, and ∈(x, y) is the local deformation of the blood vessel wall at the position (x, y) on the cardiovascular image.

[0030] Furthermore, the third blood vessel identification model includes:

[0031]

[0032] Wherein, f3(x, y) is the third blood vessel identification value at the position (x, y) on the cardiovascular image, ζ1 is the first adjustment factor of the third blood vessel identification model, is the local texture feature at position (x, y) on the cardiovascular image, and the local texture feature is extracted through the gray level co-occurrence matrix α′ is the second adjustment factor of the third blood vessel recognition model, β′ is the third adjustment factor of the third blood vessel recognition model, θ1 is the fourth adjustment factor of the third blood vessel recognition model, I mid is the gray value mean of cardiovascular image, σ abs is the fifth adjustment factor of the third vessel identification model, is the local absorbance at position (x, y) on the cardiovascular image.

[0033] Furthermore, the fourth blood vessel identification model includes:

[0034]

[0035] Wherein, f4(x, y) is the fourth blood vessel identification value at the position (x, y) on the cardiovascular image, λ1 is the first adjustment factor of the fourth blood vessel identification model, is a Gaussian filter, σ r is the standard deviation of the rth scale used to control the width of the Gaussian filter, α1′ is the second adjustment factor of the fourth blood vessel recognition model, ρ1 is the third adjustment factor of the fourth blood vessel recognition model, β1′ is the fourth adjustment factor of the fourth blood vessel recognition model, κ biomech is the fifth adjustment factor of the fourth vessel identification model, is the thickness of the blood vessel wall at the position (x, y) on the cardiovascular image, wherein the cardiovascular image is divided into multiple scales according to the resolution.

[0036] In general, compared with the prior art, the above technical solution conceived by the present invention has at least the following beneficial effects: by setting a first blood vessel recognition model, a second blood vessel recognition model, a third blood vessel recognition model and a fourth blood vessel recognition model, the present invention can accurately identify blood vessels in cardiovascular images, thereby completing blood vessel labeling and providing diagnostic support for doctors. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 is a flow chart of a method according to Embodiment 1 of the present invention;

[0038] Figure 2 It is a system structure diagram of the second embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0040] The method provided by the present invention can be implemented in the following terminal environment, and the terminal may include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, and the instruction is loaded and executed by the processor to implement the method described in the following embodiment.

[0041] The processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts in the entire terminal, and executes various functions of the terminal and processes data by running or executing instructions, programs, code sets or instruction sets stored in the storage medium, and calling data stored in the storage medium.

[0042] The storage medium may include a random access memory (RAM) or a read-only memory (ROM). The storage medium may be used to store instructions, programs, codes, code sets or instructions.

[0043] The display screen is used to display the user interface of each application.

[0044] In addition, those skilled in the art can understand that the structure of the above terminal does not constitute a limitation on the terminal, and the terminal may include more or fewer components, or combine certain components, or arrange the components differently. For example, the terminal also includes components such as a radio frequency circuit, an input unit, a sensor, an audio circuit, and a power supply, which will not be described in detail here.

[0045] Embodiment 1

[0046] like Figure 1 As shown, the embodiment of the present invention provides a method for identifying and marking blood vessels on cardiovascular images based on a model, comprising:

[0047] Step 101, acquiring a cardiovascular image, and extracting image features of the cardiovascular image as an optional implementation, wherein the image features as an optional implementation include: a gradient at each position on the cardiovascular image as an optional implementation, a local curvature at each position on the cardiovascular image as an optional implementation, a local texture feature at each position on the cardiovascular image as an optional implementation, a gray value at each position on the cardiovascular image as an optional implementation, and an average gray value of the cardiovascular image as an optional implementation;

[0048] Step 102, respectively setting a first blood vessel identification model, a second blood vessel identification model, a third blood vessel identification model, and a fourth blood vessel identification model, calculating a first blood vessel identification value, a second blood vessel identification value, a third blood vessel identification value, and a fourth blood vessel identification value at each position on the cardiovascular image as an optional implementation manner, and performing a weighted sum operation to generate a final blood vessel identification value;

[0049] Specifically, the first blood vessel recognition model includes:

[0050]

[0051] Wherein, f1(x, y) is the first blood vessel recognition value at the position (x, y) on the cardiovascular image, α1 is the first adjustment factor of the first blood vessel recognition model, is the gradient at the position (x, y) on the cardiovascular image, β1 is the second adjustment factor of the first vessel recognition model, I(x, y) is the grayscale value at the position (x, y) on the cardiovascular image, and I avg is the average gray value of cardiovascular images, κflow is the third adjustment factor of the first vessel identification model, The local blood flow velocity at the position (x, y) on the cardiovascular image is simulated by the fluid dynamics (CFD) model to simulate the flow of blood in the blood vessels, and then the local blood flow velocity at different positions in the blood vessels is calculated.

[0052] As an optional implementation, the morphology and edge of a blood vessel are usually affected by blood flow, especially between different blood vessel segments, where differences in blood flow speed and direction can lead to different image features (e.g., blood vessel expansion or contraction). By setting the first blood vessel recognition model, the ability to label blood vessel edges can be improved.

[0053] Specifically, the second blood vessel recognition model includes:

[0054] f2(x, y) = γ1·(κ(x, y)) 2 ·exp(-δ1·(I(x,y)-I min ) 2 )·(1+θ elastic ∈(x, y)).

[0055] Wherein, f2(x, y) is the second blood vessel recognition value at the position (x, y) on the cardiovascular image, γ1 is the first adjustment factor of the second blood vessel recognition model, κ(x, y) is the local curvature at the position (x, y) on the cardiovascular image, δ1 is the second adjustment factor of the second blood vessel recognition model, and I min is the minimum grayscale value of the cardiovascular image, θ elastic is the third adjustment factor of the second blood vessel recognition model, and ∈(x, y) is the local deformation of the blood vessel wall at the position (x, y) on the cardiovascular image.

[0056] As an optional implementation, since the elasticity and shape changes of blood vessels are closely related to blood pressure and the biomechanical properties of the blood vessel wall, the greater the elasticity of the blood vessel wall, the more obvious the change in the curvature of the blood vessel, which manifests as a stronger structural change in the image. The above state is described by setting a second blood vessel recognition model.

[0057] Specifically, the third blood vessel recognition model includes:

[0058]

[0059] Wherein, f3(x, y) is the third blood vessel identification value at the position (x, y) on the cardiovascular image, ζ1 is the first adjustment factor of the third blood vessel identification model, is the local texture feature at position (x, y) on the cardiovascular image, and the local texture feature is extracted through the gray level co-occurrence matrix α′ is the second adjustment factor of the third blood vessel recognition model, β′ is the third adjustment factor of the third blood vessel recognition model, θ1 is the fourth adjustment factor of the third blood vessel recognition model, I mid is the gray value mean of cardiovascular image, σ abs is the fifth adjustment factor of the third vessel identification model, The local absorbance at the position (x, y) on the cardiovascular image is estimated using an inversion algorithm (such as least squares method, Bayesian inference, etc.) based on the tissue reflection or transmission light data combined with a known optical model (such as Monte Carlo simulation).

[0060] As an optional implementation, the blood vessel annotation in the image is affected by the absorbance and light scattering properties of the tissue. Different types of tissues (such as muscle, fat, and blood vessels) have different light absorption and scattering properties. Therefore, the third blood vessel recognition model is set to use these physical properties as features to enhance the blood vessel annotation.

[0061] Specifically, the fourth blood vessel recognition model includes:

[0062]

[0063] Wherein, f4(x, y) is the fourth blood vessel identification value at the position (x, y) on the cardiovascular image, λ1 is the first adjustment factor of the fourth blood vessel identification model, is a Gaussian filter, σ r is the standard deviation of the rth scale used to control the width of the Gaussian filter, α1′ is the second adjustment factor of the fourth blood vessel recognition model, ρ1 is the third adjustment factor of the fourth blood vessel recognition model, β1′ is the fourth adjustment factor of the fourth blood vessel recognition model, κ biomech is the fifth adjustment factor of the fourth vessel identification model, is the thickness of the blood vessel wall at the position (x, y) on the cardiovascular image, wherein the cardiovascular image is divided into multiple scales according to the resolution.

[0064] As an optional implementation, the biomechanical properties of blood vessels (such as stiffness and wall thickness) affect the structure and morphology of blood vessels. Therefore, by setting a fourth blood vessel recognition model and combining multi-scale analysis and a biomechanical model, blood vessels can be extracted and labeled more accurately.

[0065] Step 103: Compare the final blood vessel identification value of the optional implementation scheme with the preset blood vessel identification value. When the final blood vessel identification value of the optional implementation scheme exceeds the preset blood vessel identification value of the optional implementation scheme, identify the position corresponding to the final blood vessel identification value of the optional implementation scheme as a blood vessel and mark it.

[0066] Embodiment 2

[0067] like Figure 2 As shown, an embodiment of the present invention further provides a model-based blood vessel identification and marking system on a cardiovascular image, comprising:

[0068] An image feature acquisition module is used to acquire a cardiovascular image and extract image features of the cardiovascular image as an optional implementation method, wherein the image features as an optional implementation method include: a gradient at each position on the cardiovascular image as an optional implementation method, a local curvature at each position on the cardiovascular image as an optional implementation method, a local texture feature at each position on the cardiovascular image as an optional implementation method, a gray value at each position on the cardiovascular image as an optional implementation method, and an average gray value of the cardiovascular image as an optional implementation method;

[0069] a final vessel identification value calculation module, used to respectively set a first vessel identification model, a second vessel identification model, a third vessel identification model and a fourth vessel identification model, calculate a first vessel identification value, a second vessel identification value, a third vessel identification value and a fourth vessel identification value at each position on a cardiovascular image as an optional implementation manner, and perform a weighted sum operation to generate a final vessel identification value;

[0070] Specifically, the first blood vessel recognition model includes:

[0071]

[0072] Wherein, f1(x, y) is the first blood vessel recognition value at the position (x, y) on the cardiovascular image, α1 is the first adjustment factor of the first blood vessel recognition model, is the gradient at the position (x, y) on the cardiovascular image, β1 is the second adjustment factor of the first vessel recognition model, I(x, y) is the grayscale value at the position (x, y) on the cardiovascular image, and I avg is the average gray value of cardiovascular images, κ flow is the third adjustment factor of the first vessel identification model, The local blood flow velocity at the position (x, y) on the cardiovascular image is simulated by the fluid dynamics (CFD) model to simulate the flow of blood in the blood vessels, and then the local blood flow velocity at different positions in the blood vessels is calculated.

[0073] As an optional implementation, the morphology and edge of a blood vessel are usually affected by blood flow, especially between different blood vessel segments, where differences in blood flow speed and direction can lead to different image features (e.g., blood vessel expansion or contraction). By setting the first blood vessel recognition model, the ability to label blood vessel edges can be improved.

[0074] Specifically, the second blood vessel recognition model includes:

[0075] f2(x, y) = γ1·(κ(x, y)) 2 ·exp(-δ1·(I(x,y)-I min ) 2 )·(1+θ elastic ∈(x, y)).

[0076] Wherein, f2(x, y) is the second blood vessel recognition value at the position (x, y) on the cardiovascular image, γ1 is the first adjustment factor of the second blood vessel recognition model, κ(x, y) is the local curvature at the position (x, y) on the cardiovascular image, δ1 is the second adjustment factor of the second blood vessel recognition model, and I min is the minimum grayscale value of the cardiovascular image, θ elastic is the third adjustment factor of the second blood vessel recognition model, and ∈(x, y) is the local deformation of the blood vessel wall at the position (x, y) on the cardiovascular image.

[0077] As an optional implementation, since the elasticity and shape changes of blood vessels are closely related to blood pressure and the biomechanical properties of the blood vessel wall, the greater the elasticity of the blood vessel wall, the more obvious the change in the curvature of the blood vessel, which manifests as a stronger structural change in the image. The above state is described by setting a second blood vessel recognition model.

[0078] Specifically, the third blood vessel recognition model includes:

[0079]

[0080] Wherein, f3(x, y) is the third blood vessel identification value at the position (x, y) on the cardiovascular image, ζ1 is the first adjustment factor of the third blood vessel identification model, is the local texture feature at position (x, y) on the cardiovascular image, and the local texture feature is extracted through the gray level co-occurrence matrix α′ is the second adjustment factor of the third blood vessel recognition model, β′ is the third adjustment factor of the third blood vessel recognition model, θ1 is the fourth adjustment factor of the third blood vessel recognition model, I mid is the gray value mean of cardiovascular image, σ abs is the fifth adjustment factor of the third vessel identification model, The local absorbance at the position (x, y) on the cardiovascular image is estimated using an inversion algorithm (such as least squares method, Bayesian inference, etc.) based on the tissue reflection or transmission light data combined with a known optical model (such as Monte Carlo simulation).

[0081] As an optional implementation, the blood vessel annotation in the image is affected by the absorbance and light scattering properties of the tissue. Different types of tissues (such as muscle, fat, and blood vessels) have different light absorption and scattering properties. Therefore, the third blood vessel recognition model is set to use these physical properties as features to enhance the blood vessel annotation.

[0082] Specifically, the fourth blood vessel recognition model includes:

[0083]

[0084] Wherein, f4(x, y) is the fourth blood vessel identification value at the position (x, y) on the cardiovascular image, λ1 is the first adjustment factor of the fourth blood vessel identification model, is a Gaussian filter, σ r is the standard deviation of the rth scale used to control the width of the Gaussian filter, α1′ is the second adjustment factor of the fourth blood vessel recognition model, ρ1 is the third adjustment factor of the fourth blood vessel recognition model, β1′ is the fourth adjustment factor of the fourth blood vessel recognition model, κ biomech is the fifth adjustment factor of the fourth vessel identification model, is the thickness of the blood vessel wall at the position (x, y) on the cardiovascular image, wherein the cardiovascular image is divided into multiple scales according to the resolution.

[0085] As an optional implementation, the biomechanical properties of blood vessels (such as stiffness and wall thickness) affect the structure and morphology of blood vessels. Therefore, by setting a fourth blood vessel recognition model and combining multi-scale analysis and a biomechanical model, blood vessels can be extracted and labeled more accurately.

[0086] The identification and labeling module is used to compare the final blood vessel identification value with a preset blood vessel identification value, and when the final blood vessel identification value exceeds the preset blood vessel identification value as an optional implementation method, identify the position corresponding to the final blood vessel identification value as an optional implementation method as a blood vessel and label it.

[0087] Embodiment 3

[0088] The embodiment of the present invention further provides a storage medium storing a plurality of instructions, wherein the instructions are used to implement the aforementioned model-based blood vessel identification and marking method on cardiovascular images.

[0089] Optionally, in this embodiment, the above storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.

[0090] Optionally, in this embodiment, the storage medium is configured to store program codes for executing the steps of the first embodiment.

[0091] Embodiment 4

[0092] An embodiment of the present invention also proposes an electronic device, including a processor and a storage medium connected to the processor, wherein the storage medium stores multiple instructions that can be loaded and executed by the processor to enable the processor to execute the aforementioned model-based blood vessel identification and marking method on cardiovascular images.

[0093] Specifically, the electronic device of this embodiment may be a computer terminal. As an optional implementation, the computer terminal may include: one or more processors and a storage medium.

[0094] Among them, the storage medium can be used to store software programs and modules, such as a model-based method for identifying and marking blood vessels on cardiovascular images in an embodiment of the present invention, and corresponding program instructions / modules. The processor executes various functional applications and data processing by running the software programs and modules stored in the storage medium, that is, realizing the aforementioned model-based method for identifying and marking blood vessels on cardiovascular images. The storage medium may include a high-speed random storage medium, and may also include a non-volatile storage medium, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include a storage medium remotely disposed relative to the processor, and these remote storage media may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0095] The processor may call the information and application programs stored in the storage medium through the transmission system to execute the steps of the first embodiment.

[0096] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0097] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0098] In the several embodiments provided by the present invention, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the system embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0099] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0100] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0101] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only storage medium (ROM, Read-Only Memory), random access storage medium (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.

[0102] Obviously, the above embodiments are merely examples for the purpose of clear explanation, and are not intended to limit the implementation methods. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived from these are still within the scope of protection of the invention.

Claims

1. A model-based method for identifying and marking blood vessels in cardiovascular images, characterized in that: include: Acquire a cardiovascular image, and extract image features of the cardiovascular image, wherein the image features include: a gradient at each position on the cardiovascular image, a local curvature at each position on the cardiovascular image, a local texture feature at each position on the cardiovascular image, a grayscale value at each position on the cardiovascular image, and an average grayscale value of the cardiovascular image; respectively setting a first blood vessel identification model, a second blood vessel identification model, a third blood vessel identification model and a fourth blood vessel identification model, calculating a first blood vessel identification value, a second blood vessel identification value, a third blood vessel identification value and a fourth blood vessel identification value at each position on the cardiovascular image, and performing a weighted sum operation to generate a final blood vessel identification value; The final blood vessel identification value is compared with a preset blood vessel identification value, and when the final blood vessel identification value exceeds the preset blood vessel identification value, a position corresponding to the final blood vessel identification value is identified as a blood vessel and marked.

2. A method for identifying and marking blood vessels on cardiovascular images based on a model as claimed in claim 1, characterized in that: The first vessel identification model includes: Wherein, f1(x, y) is the first blood vessel recognition value at the position (x, y) on the cardiovascular image, α1 is the first adjustment factor of the first blood vessel recognition model, is the gradient at the position (x, y) on the cardiovascular image, β1 is the second adjustment factor of the first vessel recognition model, I(x, y) is the grayscale value at the position (x, y) on the cardiovascular image, and I avg is the average gray value of cardiovascular images, κ flow is the third adjustment factor of the first vessel identification model, is the local blood flow velocity at position (x, y) on the cardiovascular image.

3. A method for identifying and marking blood vessels on cardiovascular images based on a model as claimed in claim 2, characterized in that: The second vessel recognition model includes: f2(x,y)=γ1·(κ(x,y)) 2 ·exp(-δ1·(I(x,y)-I min ) 2 )·(1+θ elastic ·∈(x,y)); Wherein, f2(x, y) is the second blood vessel recognition value at the position (x, y) on the cardiovascular image, γ1 is the first adjustment factor of the second blood vessel recognition model, κ(x, y) is the local curvature at the position (x, y) on the cardiovascular image, δ1 is the second adjustment factor of the second blood vessel recognition model, and I min is the minimum gray value of the cardiovascular image, θ elastic is the third adjustment factor of the second blood vessel recognition model, and ∈(x, y) is the local deformation of the blood vessel wall at the position (x, y) on the cardiovascular image.

4. A method for identifying and marking blood vessels on cardiovascular images based on a model as claimed in claim 3, characterized in that: The third vessel recognition model includes: Wherein, f3(x, y) is the third blood vessel identification value at the position (x, y) on the cardiovascular image, ζ1 is the first adjustment factor of the third blood vessel identification model, is the local texture feature at position (x, y) on the cardiovascular image, and the local texture feature is extracted through the gray level co-occurrence matrix α′ is the second adjustment factor of the third blood vessel recognition model, β′ is the third adjustment factor of the third blood vessel recognition model, θ1 is the fourth adjustment factor of the third blood vessel recognition model, I mid is the gray value mean of cardiovascular image, σ abs is the fifth adjustment factor of the third vessel identification model, is the local absorbance at position (x, y) on the cardiovascular image.

5. The method for identifying and marking blood vessels on cardiovascular images based on a model as claimed in claim 4, characterized in that: The fourth vessel recognition model includes: Wherein, f4(x, y) is the fourth blood vessel identification value at the position (x, y) on the cardiovascular image, λ1 is the first adjustment factor of the fourth blood vessel identification model, is a Gaussian filter, σ r is the standard deviation of the rth scale used to control the width of the Gaussian filter, α1′ is the second adjustment factor of the fourth blood vessel recognition model, ρ1 is the third adjustment factor of the fourth blood vessel recognition model, β1′ is the fourth adjustment factor of the fourth blood vessel recognition model, κ biomech is the fifth adjustment factor of the fourth vessel identification model, is the thickness of the blood vessel wall at the position (x, y) on the cardiovascular image, wherein the cardiovascular image is divided into multiple scales according to the resolution.

6. A model-based blood vessel identification and marking system on cardiovascular images, characterized in that: include: An image feature acquisition module is used to acquire a cardiovascular image and extract image features of the cardiovascular image, wherein the image features include: a gradient at each position on the cardiovascular image, a local curvature at each position on the cardiovascular image, a local texture feature at each position on the cardiovascular image, a gray value at each position on the cardiovascular image, and an average gray value of the cardiovascular image; a final blood vessel identification value calculation module, used to respectively set a first blood vessel identification model, a second blood vessel identification model, a third blood vessel identification model and a fourth blood vessel identification model, calculate the first blood vessel identification value, the second blood vessel identification value, the third blood vessel identification value and the fourth blood vessel identification value at each position on the cardiovascular image, and perform a weighted sum operation to generate a final blood vessel identification value; The identification and marking module is used to compare the final blood vessel identification value with a preset blood vessel identification value, and when the final blood vessel identification value exceeds the preset blood vessel identification value, identify the position corresponding to the final blood vessel identification value as a blood vessel and mark it.

7. A model-based blood vessel identification and marking system on cardiovascular images as claimed in claim 6, characterized in that: The first vessel identification model includes: Wherein, f1(x, y) is the first blood vessel recognition value at the position (x, y) on the cardiovascular image, α1 is the first adjustment factor of the first blood vessel recognition model, is the gradient at the position (x, y) on the cardiovascular image, β1 is the second adjustment factor of the first vessel recognition model, I(x, y) is the grayscale value at the position (x, y) on the cardiovascular image, and I avg is the average gray value of cardiovascular images, κ flow is the third adjustment factor of the first vessel identification model, is the local blood flow velocity at position (x, y) on the cardiovascular image.

8. The model-based blood vessel identification and marking system on cardiovascular images as claimed in claim 7, characterized in that: The second vessel recognition model includes: f2(x,y)=γ1·(κ(x,y)) 2 ·exp(-δ1·(I(x,y)-I min ) 2 )·(1+θ elastic ·∈(x,y)); Wherein, f2(x, y) is the second blood vessel recognition value at the position (x, y) on the cardiovascular image, γ1 is the first adjustment factor of the second blood vessel recognition model, κ(x, y) is the local curvature at the position (x, y) on the cardiovascular image, δ1 is the second adjustment factor of the second blood vessel recognition model, and I min is the minimum gray value of the cardiovascular image, θ elastic is the third adjustment factor of the second blood vessel recognition model, and ∈(x, y) is the local deformation of the blood vessel wall at the position (x, y) on the cardiovascular image.

9. A model-based blood vessel identification and marking system on cardiovascular images as claimed in claim 8, characterized in that: The third vessel recognition model includes: Wherein, f3(x, y) is the third blood vessel identification value at the position (x, y) on the cardiovascular image, ζ1 is the first adjustment factor of the third blood vessel identification model, is the local texture feature at position (x, y) on the cardiovascular image, and the local texture feature is extracted through the gray level co-occurrence matrix α′ is the second adjustment factor of the third blood vessel recognition model, β′ is the third adjustment factor of the third blood vessel recognition model, θ1 is the fourth adjustment factor of the third blood vessel recognition model, I mid is the gray value mean of cardiovascular image, σ abs is the fifth adjustment factor of the third vessel identification model, is the local absorbance at position (x, y) on the cardiovascular image.

10. The model-based blood vessel identification and marking system on cardiovascular images according to claim 9, characterized in that: The fourth vessel recognition model includes: Wherein, f4(x, y) is the fourth blood vessel identification value at the position (x, y) on the cardiovascular image, λ1 is the first adjustment factor of the fourth blood vessel identification model, is a Gaussian filter, σ r is the standard deviation of the rth scale used to control the width of the Gaussian filter, α1′ is the second adjustment factor of the fourth blood vessel recognition model, ρ1 is the third adjustment factor of the fourth blood vessel recognition model, β1′ is the fourth adjustment factor of the fourth blood vessel recognition model, κ biomech is the fifth adjustment factor of the fourth vessel identification model, is the thickness of the blood vessel wall at the position (x, y) on the cardiovascular image, wherein the cardiovascular image is divided into multiple scales according to the resolution.

Images