Vascular topology reconstruction method based on image processing and numerical calculation and related device

Abstract

The invention discloses a vascular topology reconstruction method based on image processing and numerical calculation and a related device, and relates to the technical field of medical image processing, and the method comprises the steps: carrying out the preprocessing of obtained medical image data; performing vascular skeleton line extraction on the preprocessed medical image data; skeleton optimization processing and blood vessel segmentation are carried out on the blood vessel skeleton line, and a segmentation result is obtained; based on the segmentation result, classifying the skeleton points to obtain main blood vessels and branch blood vessels; constructing a tree-shaped data structure by taking the main blood vessel as a root node and the branch blood vessels as branch nodes; calculating blood vessel physical characteristics based on the tree data structure; based on the physical characteristics of the blood vessel, the energy minimum principle is applied, the optimal growth and formation process of the blood vessel structure is simulated, parameters in the simulation process are dynamically adjusted, and reconstruction of the blood vessel topological structure is completed. According to the application, the important demand of clinical application can be met, and quantitative analysis and further exploration of the intrinsic rule of blood vessel growth can be promoted.

Description

Technical Field

[0001] This application relates to the technical field of medical image processing, and particularly to a method for reconstructing vascular topology based on image processing and numerical calculation and related devices. Background Art

[0002] In medical image processing, the accurate reconstruction of vascular topology is crucial for disease diagnosis and treatment planning. Existing vascular grading algorithms mainly rely on medical image information and are achieved through steps such as vascular segmentation, thinning, and skeleton point classification. However, these methods are prone to structural breaks and branch ambiguities when dealing with complex vascular networks and lack consideration of the mechanism of vascular growth and formation. Summary of the Invention

[0003] The purpose of this application is to provide a method for reconstructing vascular topology based on image processing and numerical calculation and related devices, which can solve important clinical application requirements and also contribute to promoting the quantitative analysis and further exploration of the internal laws of vascular growth.

[0004] To achieve the above purpose, this application provides the following solutions:

[0005] In the first aspect, this application provides a method for reconstructing vascular topology based on image processing and numerical calculation. The method for reconstructing vascular topology based on image processing and numerical calculation includes:

[0006] Obtain medical image data containing vascular structures.

[0007] Preprocess the medical image data to obtain preprocessed medical image data.

[0008] Extract vascular skeleton lines from the preprocessed medical image data to obtain vascular skeleton lines.

[0009] Perform skeletonization optimization processing and vascular segmentation on the vascular skeleton lines to obtain a segmentation result.

[0010] Classify skeleton points based on the segmentation result to obtain main blood vessels and branch blood vessels.

[0011] Construct a tree-like data structure with the main blood vessels as root nodes and the branch blood vessels as branch nodes.

[0012] Calculate vascular physical properties based on the tree-like data structure; the vascular physical properties include: vascular radius, blood flow rate, and pressure distribution.

[0013] Based on the vascular physical properties, apply the principle of minimum energy to simulate the optimal growth and formation process of the vascular structure and dynamically adjust the parameters during the simulation process to complete the reconstruction of the vascular topology.

[0014] Optionally, perform vascular skeleton line extraction on the preprocessed medical image data to obtain a vascular skeleton line, specifically including:

[0015] Perform vascular skeleton line extraction on the preprocessed medical image data based on the image domain fast marching method to obtain a vascular skeleton line.

[0016] Optionally, perform skeletonization optimization processing and vascular segmentation on the vascular skeleton line to obtain a segmentation result, specifically including:

[0017] Perform variational optimization processing on the vascular skeleton line.

[0018] Perform vascular segmentation from the inside to the boundary of the blood vessel to obtain a segmentation result.

[0019] Optionally, after constructing the tree - shaped data structure, the vascular topology reconstruction method based on image processing and numerical calculation further includes:

[0020] Use a recursive traversal method to update and optimize the vascular network to ensure that each node contains child node information; the child node information includes: vascular radius, vascular length, bifurcation angle, blood flow rate, and parent - child node relationship.

[0021] Optionally, based on the tree - shaped data structure, calculate the vascular physical properties, specifically including:

[0022] Calculate the vascular radius according to Murray's law.

[0023] Calculate the hydrodynamic properties inside the blood vessel according to Poiseuille's law; the hydrodynamic properties include: blood flow rate and pressure distribution.

[0024] Optionally, based on the vascular physical properties, apply the principle of minimum energy to simulate the optimal growth and formation process of the vascular structure, and dynamically adjust the parameters during the simulation process to complete the reconstruction of the vascular topology structure, specifically including:

[0025] Based on the vascular physical properties, construct a numerical calculation model based on the principle of minimum energy; the numerical calculation model is used to simulate the energy optimization during the vascular growth process.

[0026] Apply the numerical calculation model at the vascular bifurcation point to ensure that each bifurcation can reach the optimal energy state and conform to the biological bifurcation law.

[0027] Dynamically adjust the parameters during the simulation process, optimize the vascular growth path and morphology, ensure that the simulation results conform to the actual biological characteristics, and complete the reconstruction of the vascular topology structure.

[0028] Second aspect, the present application provides a vascular topology reconstruction device based on image processing and numerical calculation. The vascular topology reconstruction device based on image processing and numerical calculation includes:

[0029] An image data acquisition module, configured to acquire medical image data containing vascular structures.

[0030] A preprocessing module, configured to preprocess the medical image data to obtain preprocessed medical image data.

[0031] An extraction module, configured to extract vascular skeleton lines from the preprocessed medical image data to obtain vascular skeleton lines.

[0032] A segmentation module, configured to perform skeletonization optimization processing and vascular segmentation on the vascular skeleton lines to obtain a segmentation result;

[0033] A classification module, configured to classify skeleton points based on the segmentation result to obtain main blood vessels and branch blood vessels;

[0034] A tree - shaped data structure construction module, configured to construct a tree - shaped data structure with the main blood vessels as root nodes and the branch blood vessels as branch nodes.

[0035] A vascular physical property calculation module, configured to calculate vascular physical properties based on the tree - shaped data structure; the vascular physical properties include: vascular radius, blood flow rate, and pressure distribution.

[0036] A vascular topology structure reconstruction module, configured to apply the principle of minimum energy based on the vascular physical properties, simulate the optimal growth and formation process of the vascular structure, and dynamically adjust parameters during the simulation process to complete the reconstruction of the vascular topology structure.

[0037] Third aspect, the present application provides a computer device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor. The processor executes the computer program to implement the vascular topology reconstruction method based on image processing and numerical calculation described in any one of the above.

[0038] Fourth aspect, the present application provides a computer - readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements the vascular topology reconstruction method based on image processing and numerical calculation described in any one of the above.

[0039] Fifth aspect, the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the vascular topology reconstruction method based on image processing and numerical calculation described in any one of the above.

[0040] According to the specific embodiments provided by the present application, the following technical effects are disclosed in the present application:

[0041] The present application provides a method and related device for vascular topology reconstruction based on image processing and numerical calculation. The method includes: acquiring medical image data containing vascular structures; preprocessing the medical image data to obtain preprocessed medical image data; extracting vascular skeleton lines from the preprocessed medical image data to obtain vascular skeleton lines; performing skeletonization optimization processing and vascular segmentation on the vascular skeleton lines to obtain a segmentation result; classifying skeleton points based on the segmentation result to obtain main blood vessels and branch blood vessels; constructing a tree-shaped data structure with the main blood vessels as root nodes and the branch blood vessels as branch nodes; calculating vascular physical properties based on the tree-shaped data structure; the vascular physical properties include: vascular radius, blood flow rate, and pressure distribution; based on the vascular physical properties, applying the principle of minimum energy, simulating the optimal growth and formation process of the vascular structure, and dynamically adjusting parameters during the simulation process to complete the reconstruction of the vascular topology. The present application bypasses multiple stages such as error-prone vascular segmentation, skeletonization, and skeleton point classification, combines the obtained results such as vascular skeleton lines and vascular radii, sets a recursively nested tree-shaped data structure, and combines the principle of minimum energy to traverse, insert, and update the data structure relationship of the vascular system, and can obtain preliminary global topological information. The technical solution of the present application can solve important clinical application requirements and also contribute to promoting the quantitative analysis and further exploration of the internal laws of vascular growth. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application or in the prior art, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0043] Figure 1 It is an application environment diagram of a method for vascular topology reconstruction based on image processing and numerical calculation in an embodiment of the present application.

[0044] Figure 2 It is a flowchart of a method for vascular topology reconstruction based on image processing and numerical calculation provided by an embodiment of the present application.

[0045] Figure 3 It is a schematic diagram of the vascular topology of traditional Chinese medicine images provided by an embodiment of the present application.

[0046] Figure 4 It is a schematic diagram of the functional modules of a device for vascular topology reconstruction based on image processing and numerical calculation provided by an embodiment of the present application.

[0047] Figure 5 A structural schematic diagram of a computer device provided by an embodiment of the present application. Specific implementation manners

[0048] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without making creative efforts belong to the scope of protection of the present application.

[0049] To make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners.

[0050] The vascular topology reconstruction method based on image processing and numerical calculation provided by the embodiments of the present application can be applied to, for example Figure 1In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be set separately, integrated on the server 104, placed on the cloud or other servers. The terminal 102 can send medical image data containing vascular structures to the server 104. After receiving the medical image data containing vascular structures, for the medical image data containing vascular structures, the server 104 preprocesses the medical image data to obtain preprocessed medical image data; extracts the vascular skeleton line from the preprocessed medical image data to obtain the vascular skeleton line; performs skeletonization optimization processing and vascular segmentation on the vascular skeleton line to obtain a segmentation result; classifies the skeleton points based on the segmentation result to obtain main blood vessels and branch blood vessels; constructs a tree-shaped data structure with the main blood vessels as the root nodes and the branch blood vessels as the branch nodes; calculates the vascular physical properties based on the tree-shaped data structure; the vascular physical properties include: vascular radius, blood flow rate, and pressure distribution; based on the vascular physical properties, applies the principle of minimum energy to simulate the optimal growth and formation process of the vascular structure, and dynamically adjusts the parameters during the simulation process to complete the reconstruction of the vascular topological structure. The server 104 can feedback the obtained vascular topological structure to the terminal 102. In addition, in some embodiments, the method for reconstructing the vascular topology based on image processing and numerical calculation can also be implemented separately by the server 104 or the terminal 102. For example, the terminal 102 can directly perform vascular topology reconstruction on the medical image data containing vascular structures, or the server 104 can obtain the medical image data containing vascular structures from the data storage system and perform vascular topology reconstruction on the medical image data containing vascular structures.

[0051] Among them, the terminal 102 can be, but is not limited to, various desktop computers, laptop computers, smart phones, and tablet computers. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers, and can also be a cloud server.

[0052] In an exemplary embodiment, as Figure 2 shown, a method for reconstructing the vascular topology based on image processing and numerical calculation is provided. This method is executed by a computer device, and can be specifically executed alone by a computer device such as a terminal or a server, or jointly executed by a terminal and a server. In the embodiments of the present application, taking this method applied to Figure 1 the server 104 therein as an example for illustration, it includes the following steps S1 to step S7. Among them:

[0053] S1: Obtain medical image data containing vascular structures.

[0054] S2: Preprocess the medical image data to obtain preprocessed medical image data.

[0055] S3: Extract the vascular skeleton lines from the preprocessed medical image data to obtain vascular skeleton lines.

[0056] S4: Perform skeletonization optimization processing and vascular segmentation on the vascular skeleton lines to obtain a segmentation result.

[0057] S5: Classify the skeleton points based on the segmentation result to obtain major blood vessels and branch blood vessels.

[0058] S6: Construct a tree - shaped data structure with the major blood vessels as root nodes and the branch blood vessels as branch nodes.

[0059] S7: Calculate the vascular physical properties based on the tree - shaped data structure; the vascular physical properties include: vascular radius, blood flow, and pressure distribution.

[0060] S8: Based on the vascular physical properties, apply the principle of minimum energy to simulate the optimal growth and formation process of the vascular structure, and dynamically adjust the parameters during the simulation process to complete the reconstruction of the vascular topological structure.

[0061] Implementing the above steps S1 to S8 can reduce the completely unnecessary computational domain space and optimize the algorithm efficiency; it not only has high accuracy but also better practicality, ensuring that the quantitative analysis results are more in line with the actual anatomical structure. This method can be widely applied in the field of medical image analysis, especially in the construction of the liver vascular system, with remarkable effects, providing a reliable basis for medical diagnosis and treatment. In addition, it has a high degree of automation, and the calculation results are more reasonable and stable.

[0062] As an alternative implementation, in step S1, the data obtained is medical image data containing vascular structures collected from the medical image database of a hospital, such as CT or MRI image data of the abdominal liver area, and the sample size collected is 5000 cases. These data need to cover different anatomical parts and pathological conditions to ensure the diversity and representativeness of the training set.

[0063] As an alternative implementation, in step S2, preprocess the medical image data to obtain a high - quality vascular image dataset. Specifically, it includes: Image normalization: Normalize the collected images to uniformly adjust the image size to ensure data consistency. Image calibration: Calibrate the blood vessels in the normalized images to verify the accuracy and convergence of the proposed method. Licensed physicians outline the major blood vessels and branch blood vessel areas according to the conventional medical image recognition rules.

[0064] As an alternative implementation, in step S3, it specifically includes: extracting the vascular skeleton line from the preprocessed medical image data based on the fast marching method in the image domain to obtain the vascular skeleton line.

[0065] It should be noted that the fast marching method in the image domain can automatically extract the vascular skeleton, that is, the skeleton point results. Then, by combining the physical mechanisms of vascular expansion such as Murray's quantification and the calculation methods of the tree structure, the skeleton points can be classified and calibrated, so as to distinguish the main blood vessels and branch blood vessels. It does not first segment and then extract the skeleton line, so there is no need for segmentation, which is also the difference from the prior art.

[0066] As an alternative implementation, in step S4, it specifically includes:

[0067] S41: Perform variational optimization processing on the vascular skeleton line.

[0068] S42: Achieve vascular segmentation from the inside of the blood vessel to the boundary to obtain the segmentation result.

[0069] Specifically, skeletonization optimization processing and vascular segmentation: Perform variational optimization processing on the vascular skeleton line obtained in the previous step, calculate the vascular radius, and achieve vascular segmentation from the inside of the blood vessel to the boundary. This method ensures that the vascular segmentation result must be continuous, and the accuracy is improved due to the constraints of the vascular physical mechanism, which is convenient for subsequent vascular structure analysis.

[0070] The classification of skeleton points in step S5 refers to: classifying the skeleton points to distinguish the main blood vessels and branch blood vessels to ensure the accuracy of the reconstructed vascular structure. (Skeleton points are generally divided into three categories: end points, bifurcation points, and path points, so that the main blood vessels and branch blood vessels can be distinguished).

[0071] As an alternative implementation, in step S6, a recursive nested tree data structure is designed and implemented to represent the hierarchical structure of the vascular system, and this structure can flexibly handle the complexity of the vascular network.

[0072] In step S6, it specifically includes:

[0073] S61: Construct a tree data structure, with the root node representing the main blood vessel and the branch nodes representing branch blood vessels at all levels.

[0074] S62: Recursively define the tree data structure to ensure that each node can contain the information of its child nodes, so as to flexibly represent the complex vascular network.

[0075] Specifically, the tree structure design: Use the main blood vessel as the root node, and generate child nodes layer by layer according to the vascular bifurcation characteristics to form a multi-level vascular network. This recursive construction process continues until the vascular growth condition reaches the set threshold, and the vascular topological structure is completely reconstructed.

[0076] Recursive Traversal and Update of Tree - shaped Data Structure: After the vascular topological structure is constructed, a recursive traversal method is used to update and optimize the vascular network. Each node includes the following information: vascular radius (radius), vascular length (length), bifurcation angle (bifurcationAngle), blood flow rate (flowRate), parent - child node relationship (parent, children), which supports the dynamic expansion and optimization of the vascular network. This structure can flexibly represent complex vascular networks.

[0077] For ease of implementation, the vascular tree - shaped data structure can be defined in the following form:

[0078] struct VesselNode{

[0079] double radius; / / Vascular radius

[0080] double length; / / Vascular length

[0081] double bifurcationAngle; / / Bifurcation angle

[0082] double flowRate; / / Blood flow rate

[0083] std::vector<VesselNode*> branches; / / Sub - branch vessels

[0084] };

[0085] As an alternative implementation, in step S7, a method combining image - processing technology and numerical calculation is designed to calculate, demonstrate, and verify the vascular structure using the physical mechanisms of blood vessels (such as Murray's law and Poiseuille's law).

[0086] In step S7, it specifically includes:

[0087] S71: Calculate the vascular radius according to Murray's law.

[0088] S72: Calculate the hydrodynamic characteristics inside the blood vessel according to Poiseuille's law; the hydrodynamic characteristics include: blood flow rate and pressure distribution.

[0089] Specifically, the application of Murray's law: Based on the principle of energy optimization of the biological vascular system, Murray's law states that the distribution of vascular radius should minimize the total energy consumption between blood flow resistance and the metabolic cost of maintaining blood vessels. Let the blood flow velocity be v, blood flow rate Q = πR 2 v, the flow resistance of viscous fluid in a pipe is related to R-4 It is inversely proportional. To minimize the total energy consumption (flow energy consumption and metabolic energy consumption for maintaining blood vessels), the following formula can be obtained:

[0090]

[0091] where \(R_0\) is the radius of the parent blood vessel; \(R_1\) is the radius of the first daughter blood vessel; \(R_2\) is the radius of the second daughter blood vessel.

[0092] Apply Murray's law for the prediction and verification of blood vessel radius to ensure that the change of blood vessel radius conforms to biological laws.

[0093] Application of Poiseuille's law: Poiseuille's law is the basic equation for the steady laminar flow of a viscous incompressible fluid in a circular pipe and is applicable to describe the flow characteristics of blood in human blood vessels. By solving the flow in a circular pipe under steady and laminar conditions using the N - S equation, it can be obtained that the blood flow is proportional to the fourth power of the radius, and the following formula is obtained:

[0094] Q = (πR 4 ΔP) / (8μL);

[0095] where \(Q\) is the blood flow per unit time; \(R\) is the blood vessel radius; \(\Delta P\) is the pressure difference across the blood vessel; \(\mu\) is the dynamic viscosity of blood; \(L\) is the blood vessel length.

[0096] Use Poiseuille's law to calculate the hydrodynamic characteristics in the blood vessel to ensure reasonable simulated blood flow and pressure distribution.

[0097] Finally, combined with numerical calculation methods, perform physical verification and adjustment on the image processing results.

[0098] As an alternative implementation, in step S8, apply the principle of minimum energy to simulate the optimal growth and formation process of the blood vessel structure to ensure that each blood vessel bifurcation conforms to biological laws.

[0099] In step S8, it specifically includes:

[0100] S81: Based on the physical characteristics of the blood vessel, construct a numerical calculation model based on the principle of minimum energy; the numerical calculation model is used to simulate the energy optimization during the blood vessel growth process.

[0101] S82: Apply the numerical calculation model at the blood vessel bifurcation point to ensure that each bifurcation can reach the optimal energy state and conform to the biological bifurcation law.

[0102] S83: Dynamically adjust the parameters during the simulation process to optimize the blood vessel growth path and morphology to ensure that the simulation results conform to actual biological characteristics and complete the reconstruction of the blood vessel topological structure. The blood vessel topological structure of traditional Chinese medicine images is as Figure 3 shown.

[0103] Specifically, mathematical model construction: Construct a numerical calculation model based on the principle of minimum energy to simulate the energy optimization during blood vessel growth.

[0104] Energy minimization algorithm: Apply the energy minimization numerical calculation model at the blood vessel bifurcation points to ensure that each bifurcation reaches the optimal energy state and conforms to the biological bifurcation law. The optimization process takes into account factors such as blood flow and blood vessel wall stress.

[0105] Dynamic parameter adjustment: Dynamically adjust the parameters during the simulation process to optimize the blood vessel growth path and morphology, ensuring that the simulation results conform to the actual biological characteristics, thereby achieving the hybrid optimization of image processing and the numerical calculation model of blood vessel mechanism. (Based on the tree structure constructed from image information, with the energy minimization model realized through the calculation of blood vessel physical characteristics, to optimize the accuracy of blood vessel structure extraction and calculation).

[0106] After obtaining the tree structure of the blood vessel skeleton, in order to optimize the blood vessel growth path and morphology, the dynamic parameter adjustment can be carried out through the following steps:

[0107] (1) Define the energy function.

[0108] Blood vessel growth optimization can be based on the energy minimization model to construct the energy function:

[0109] E total = E flow + E structure + E metabolic ;

[0110] Among them, E total is the energy function; E flow is the energy of blood flow resistance, based on Poiseuille's law:

[0111]

[0112] E structure is the structural constraint energy, which restricts the curvature and bifurcation angle of the blood vessel structure:

[0113] E structure = ∑α(θ i - θ opt ) 2 ;

[0114] Among them, θ i is the current bifurcation angle, θ opt is the biologically optimal bifurcation angle, and α is the weight coefficient.

[0115] E metabolic is the blood vessel maintenance and metabolism energy, based on Murray's law:

[0116]

[0117] Among them, β is the metabolic cost coefficient; R i is the radius of the i-th blood vessel; L i is the length of the i-th blood vessel.

[0118] (2) Parameter update rule.

[0119] The gradient descent method is used to dynamically adjust the radius R i of the i-th blood vessel, the length L i of the i-th blood vessel, and the bifurcation angle θ i :

[0120] Radius update:

[0121]

[0122] Length update:

[0123]

[0124] Bifurcation angle update:

[0125]

[0126] Among them, η is the learning rate.

[0127] (3) Iterative optimization process.

[0128] Initialize the blood vessel network parameters (radius, length, bifurcation angle).

[0129] Calculate the current total energy E total .

[0130] Adjust the parameters according to the gradient update rule.

[0131] Judge whether the energy change converges (ΔE total < ε).

[0132] If not converged, return to step (2) to continue iteration until the optimal structure.

[0133] This application bypasses multiple stages such as error-prone blood vessel segmentation, skeletonization, and skeleton point classification. Combining the obtained results such as the skeleton line of the blood vessel system and blood vessel radius, a recursive nested tree-shaped data structure is set up. Combining the principle of minimum energy and Murray's law, the data structure relationship of the blood vessel system is traversed, inserted, and updated to obtain preliminary global topological information. Within the above calculation framework, while calculating based on image data, the physical mechanisms of blood vessels themselves such as Murray's law and Poiseuille's law are integrated for the calculation, demonstration, and verification of blood vessel structures, and an optimization method driven by the fusion of image processing and numerical calculation is proposed. After adopting the above technical solution, it can solve the important requirements of clinical applications and also contribute to promoting the quantitative analysis and further exploration of the internal laws of blood vessel growth.

[0134] This application also provides an application scenario that applies the above-mentioned blood vessel topology reconstruction method based on image processing and numerical calculation. Specifically: The blood vessel topology reconstruction method based on image processing and numerical calculation provided in this embodiment can be applied in the medical image processing scenario. The medical image processing scenario includes: image data acquisition link, preprocessing link, extraction link, segmentation link, classification link, tree-shaped data structure construction link, blood vessel physical property calculation link, and blood vessel topology structure reconstruction link; First, medical image data containing blood vessel structures is acquired; the medical image data is preprocessed to obtain preprocessed medical image data; Secondly, blood vessel skeleton lines are extracted from the preprocessed medical image data to obtain blood vessel skeleton lines; the blood vessel skeleton lines are subjected to skeletonization optimization processing and blood vessel segmentation to obtain segmentation results; based on the segmentation results, skeleton points are classified to obtain main blood vessels and branch blood vessels; Thirdly, a tree-shaped data structure is constructed with the main blood vessels as root nodes and the branch blood vessels as branch nodes; Then, based on the tree-shaped data structure, blood vessel physical properties are calculated; the blood vessel physical properties include: blood vessel radius, blood flow rate, and pressure distribution; Finally, based on the blood vessel physical properties, applying the principle of minimum energy, simulating the optimal growth and formation process of the blood vessel structure, and dynamically adjusting the parameters during the simulation process, the reconstruction of the blood vessel topology structure can be completed.

[0135] Based on the same inventive concept, the embodiments of this application also provide a blood vessel topology reconstruction device based on image processing and numerical calculation for implementing the above-mentioned blood vessel topology reconstruction method based on image processing and numerical calculation. The solution provided by this device to solve problems is similar to the solution described in the above method. Therefore, the specific limitations in one or more of the following embodiments of the blood vessel topology reconstruction device based on image processing and numerical calculation can refer to the limitations on the blood vessel topology reconstruction method based on image processing and numerical calculation in the above text, and will not be repeated here.

[0136] In an exemplary embodiment, such as Figure 4As shown, a vascular topology reconstruction device based on image processing and numerical calculation includes:

[0137] An image data acquisition module M1 for acquiring medical image data containing vascular structures.

[0138] A preprocessing module M2 for preprocessing the medical image data to obtain preprocessed medical image data.

[0139] An extraction module M3 for extracting vascular skeleton lines from the preprocessed medical image data to obtain vascular skeleton lines.

[0140] A segmentation module M4 for performing skeletonization optimization processing and vascular segmentation on the vascular skeleton lines to obtain a segmentation result.

[0141] A classification module M5 for classifying skeleton points based on the segmentation result to obtain main blood vessels and branch blood vessels.

[0142] A tree - shaped data structure construction module M6 for constructing a tree - shaped data structure with the main blood vessels as root nodes and the branch blood vessels as branch nodes.

[0143] A vascular physical property calculation module M7 for calculating vascular physical properties based on the tree - shaped data structure; the vascular physical properties include: vascular radius, blood flow rate, and pressure distribution.

[0144] A vascular topology structure reconstruction module M8 for simulating the optimal growth and formation process of the vascular structure based on the vascular physical properties, applying the principle of minimum energy, and dynamically adjusting parameters during the simulation process to complete the reconstruction of the vascular topology structure.

[0145] The device has a computer program that can implement the above steps, ensuring that the program can be efficiently executed on a processor to achieve the processing of vascular image data, the construction of a vascular tree - shaped structure, the calculation and optimization of vascular physical properties.

[0146] As an optional implementation, the device further includes: a user interface; providing functions for operating and viewing the vascular reconstruction results through the user interface, enabling users to intuitively understand the structure and characteristics of the vascular network.

[0147] In an exemplary embodiment, a computer device is provided. The computer device can be a server or a terminal, and its internal structure diagram can be as Figure 5As shown in the figure. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store medical image data including vascular structures. The input / output interface of the computer device is used to exchange information between the processor and external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a method for reconstructing vascular topology based on image processing and numerical calculation.

[0148] Those skilled in the art can understand that Figure 5 the structure shown in the figure is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0149] In an exemplary embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the above method embodiments are implemented.

[0150] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by the processor, the above method embodiments are implemented.

[0151] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by the processor, the above method embodiments are implemented.

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

[0153] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memories can include read-only memory (ROM), magnetic tapes, floppy disks, flash memories, optical memories, high-density embedded non-volatile memories, resistive random access memories (ReRAMs), magnetoresistive random access memories (MRAMs), ferroelectric random access memories (FRAMs), phase change memories (PCMs), graphene memories, etc. Volatile memories can include random access memories (RAMs) or external cache memories, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0154] The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logics, data processing logics based on quantum computing, etc., without limitation.

[0155] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0156] Specific examples are used in this article to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A method for reconstructing vascular topology based on image processing and numerical calculation, characterized in that: The vascular topology reconstruction method based on image processing and numerical calculation includes: Acquiring medical image data including vascular structures; Preprocessing the medical image data to obtain preprocessed medical image data; Extracting blood vessel skeleton lines from the preprocessed medical image data to obtain blood vessel skeleton lines; Performing skeleton optimization processing and blood vessel segmentation on the blood vessel skeleton line to obtain a segmentation result; Based on the segmentation result, the skeleton points are classified to obtain main blood vessels and branch blood vessels; Taking the main blood vessel as a root node and the branch blood vessels as branch nodes, a tree data structure is constructed; Based on the tree data structure, calculating blood vessel physical characteristics; the blood vessel physical characteristics include: blood vessel radius, blood flow and pressure distribution; Based on the physical characteristics of the blood vessels, the energy minimization principle is applied to simulate the optimal growth and formation process of the blood vessel structure, and the parameters in the simulation process are dynamically adjusted to complete the reconstruction of the blood vessel topology.

2. The method for vascular topology reconstruction based on image processing and numerical calculation according to claim 1, characterized in that: Extracting the blood vessel skeleton line from the preprocessed medical image data to obtain the blood vessel skeleton line specifically includes: The blood vessel skeleton line is extracted from the preprocessed medical image data based on the image domain fast expansion random number method to obtain the blood vessel skeleton line.

3. The method for vascular topology reconstruction based on image processing and numerical calculation according to claim 1, characterized in that: The vascular skeleton line is subjected to skeleton optimization processing and vascular segmentation to obtain a segmentation result, specifically including: performing variational optimization processing on the blood vessel skeleton line; The blood vessel segmentation is realized from the inside of the blood vessel to the boundary, and the segmentation result is obtained.

4. The method for vascular topology reconstruction based on image processing and numerical calculation according to claim 1, characterized in that: After constructing the tree data structure, the vascular topology reconstruction method based on image processing and numerical calculation further includes: The vascular network is updated and optimized by using a recursive traversal method to ensure that each node contains child node information; the child node information includes: vascular radius, vascular length, bifurcation angle, blood flow and parent-child node relationship.

5. The method for vascular topology reconstruction based on image processing and numerical calculation according to claim 1, characterized in that: Based on the tree data structure, calculating the physical properties of the blood vessels specifically includes: According to Murray's law, the vessel radius was calculated; According to Poiseuille's law, the fluid dynamics characteristics in the blood vessel are calculated; the fluid dynamics characteristics include: blood flow and pressure distribution.

6. The method for vascular topology reconstruction based on image processing and numerical calculation according to claim 1, characterized in that: Based on the physical characteristics of the blood vessels, the energy minimization principle is applied to simulate the optimal growth and formation process of the blood vessel structure, and the parameters in the simulation process are dynamically adjusted to complete the reconstruction of the blood vessel topology, specifically including: Based on the physical characteristics of the blood vessels, a numerical calculation model based on the energy minimization principle is constructed; the numerical calculation model is used to simulate energy optimization in the process of blood vessel growth; Applying the numerical calculation model at the bifurcation point of the blood vessel ensures that each bifurcation can reach the optimal energy state and conform to the biological bifurcation law; Dynamically adjust the parameters in the simulation process to optimize the blood vessel growth path and morphology, ensure that the simulation results are consistent with the actual biological characteristics, and complete the reconstruction of the vascular topology.

7. A vascular topology reconstruction device based on image processing and numerical calculation, wherein the vascular topology reconstruction device based on image processing and numerical calculation is used to implement the vascular topology reconstruction method based on image processing and numerical calculation according to any one of claims 1 to 6, characterized in that: The vascular topology reconstruction device based on image processing and numerical calculation includes: An image data acquisition module, used for acquiring medical image data containing vascular structures; A preprocessing module, used for preprocessing the medical image data to obtain preprocessed medical image data; An extraction module, used to extract the vascular skeleton line from the preprocessed medical image data to obtain the vascular skeleton line; A segmentation module, used for performing skeleton optimization processing on the blood vessel skeleton line and blood vessel segmentation to obtain a segmentation result; A classification module, used for classifying the skeleton points based on the segmentation result to obtain main blood vessels and branch blood vessels; A tree data structure construction module, used to construct a tree data structure with the main blood vessel as a root node and the branch blood vessels as branch nodes; A blood vessel physical property calculation module, used to calculate blood vessel physical properties based on the tree data structure; the blood vessel physical properties include: blood vessel radius, blood flow and pressure distribution; The vascular topology reconstruction module is used to simulate the optimal growth and formation process of the vascular structure based on the physical characteristics of the blood vessels and the principle of energy minimization, and dynamically adjust the parameters in the simulation process to complete the reconstruction of the vascular topology.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the vascular topology reconstruction method based on image processing and numerical calculation as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the vascular topology reconstruction method based on image processing and numerical calculation described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the vascular topology reconstruction method based on image processing and numerical calculation described in any one of claims 1 to 6 is implemented.

Images