A standardized cerebrovascular feature extraction method, device and medium

Abstract

The present application discloses a method, device and medium for extracting standardized cerebrovascular features, relating to the field of cerebrovascular feature extraction. The method includes: calculating the blood vessel length and blood vessel volume based on the three-dimensional segmentation image of the target cerebrovascular vessels, and determining the blood vessel centerline based on the Voronoi covariance metric; calculating the blood vessel diameter, blood vessel curvature radius, blood vessel bending degree, blood vessel bifurcation angle and blood vessel bifurcation density respectively according to the blood vessel centerline; performing non-linear registration on the three-dimensional segmentation image of the target cerebrovascular vessels and a preset standard brain template to obtain a plurality of target standard cerebrovascular partitions and the individual feature results within each target standard cerebrovascular partition; performing population-level analysis on the three-dimensional segmentation image of the target cerebrovascular vessels by means of voxel-based morphological measurement to obtain population feature results. The present application can achieve multi-level standardized, accurate and stable cerebrovascular feature extraction.

Description

Technical Field

[0001] The present application relates to the field of cerebrovascular feature extraction, and particularly to a method, device and medium for standardized cerebrovascular feature extraction. Background Art

[0002] In the prior art, the signal-to-noise ratios of different cerebrovascular magnetic resonance angiography images are different, and the accuracies of different cerebrovascular segmentation methods vary greatly, resulting in unstable and inconsistent feature extraction results. For these problems, there is currently no standardized and effective cerebrovascular feature extraction process. Summary of the Invention

[0003] The purpose of the present application is to provide a method, device and medium for standardized cerebrovascular feature extraction, which can achieve standardized, accurate and stable cerebrovascular feature extraction at the individual and population levels.

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

[0005] In a first aspect, the present application provides a method for standardized cerebrovascular feature extraction, including:

[0006] Obtaining a three-dimensional segmentation image of a target cerebrovascular vessel;

[0007] Based on the three-dimensional segmentation image of the target cerebrovascular vessel, calculating the vessel length and vessel volume, and determining the vessel centerline based on the Voronoi covariance metric;

[0008] Based on the three-dimensional segmentation image of the target cerebrovascular vessel, respectively calculating the vessel diameter, vessel curvature radius, vessel bending degree, vessel bifurcation angle and vessel bifurcation density according to the vessel centerline, so as to obtain individual feature results;

[0009] Performing non-linear registration on the three-dimensional segmentation image of the target cerebrovascular vessel and a preset standard brain template to obtain a plurality of target standard cerebrovascular partitions and individual feature results within each target standard cerebrovascular partition; the preset standard brain template includes a plurality of preset standard brain partitions;

[0010] Performing population-level analysis on the three-dimensional segmentation image of the target cerebrovascular vessel based on the voxel-based morphological measurement method to obtain population feature results.

[0011] In a second 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, and the processor executes the computer program to implement the method for standardized cerebrovascular feature extraction.

[0012] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements a standardized cerebral vascular feature extraction method.

[0013] According to the specific embodiments provided by the present application, the present application has the following technical effects: the present application provides a standardized cerebrovascular feature extraction method, device and medium, wherein the vascular centerline is determined based on the Voronoi covariance metric, which can assist in the three-dimensional reconstruction of cerebrovascular vessels, thereby reducing the cascade amplification of feature estimation errors caused by small errors in the vascular segmentation process, ensuring the stability and accuracy of vascular feature data, and being able to adapt to the three-dimensional segmentation images of cerebrovascular vessels generated by different segmentation methods. Based on the vascular centerline extracted above, the vascular diameter, vascular curvature radius, vascular bending degree, vascular bifurcation angle and vascular bifurcation density in the target standard cerebrovascular partition, as well as vascular length and vascular volume are calculated as individual feature results. Thus, the present application realizes the mathematical calculation of cerebrovascular basic features, topological features and geometric features on the three-dimensional plane, realizes the automatic extraction of multi-level and multi-dimensional features, and realizes the calculation of standardized personal cerebrovascular image features. Then, the target cerebrovascular three-dimensional segmentation image is nonlinearly registered with the preset standard brain template, and multiple target standard cerebrovascular partitions and individual feature results in each target standard cerebrovascular partition can be obtained. Finally, the voxel-based morphological measurement method performs group-level analysis on the three-dimensional segmentation images of the target cerebral vessels, which has strong representational interpretability. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0015] Figure 1 This is a diagram of the application environment of the standardized cerebral vascular feature extraction method in one embodiment of the present application.

[0016] Figure 2 A schematic diagram of the process of extracting standardized cerebral vascular features according to an embodiment of the present application.

[0017] Figure 3 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0018] 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 creative efforts shall fall within the protection scope of the present application.

[0019] To make the objectives, 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 embodiments.

[0020] The standardized cerebrovascular feature extraction method provided by the embodiments of the present application can be applied to an application environment as Figure 1 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 up separately, integrated on the server 104, or placed on the cloud or other servers. The terminal 102 can send the target cerebrovascular three-dimensional segmentation image to the server 104. After receiving it, the server 104 calculates the blood vessel diameter, blood vessel length, blood vessel curvature radius, blood vessel bending degree, blood vessel bifurcation angle, and blood vessel bifurcation density as individual feature results; performs population-level analysis on the target cerebrovascular three-dimensional segmentation image by the voxel-based morphological measurement method to obtain population feature results. The server 104 can feedback the individual feature results and the population feature results to the terminal 102. In addition, in some embodiments, the standardized cerebrovascular feature extraction method can also be implemented separately by the server 104 or the terminal 102.

[0021] 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.

[0022] In an exemplary embodiment, as Figure 2 shown, a standardized cerebrovascular feature extraction method 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 as an example for illustration, it includes the following steps 201 to step 205.

[0023] Step 201, obtain a target cerebrovascular three-dimensional segmentation image.

[0024] Step 202: Based on the target three-dimensional cerebrovascular segmentation image, calculate the blood vessel length and blood vessel volume, and determine the blood vessel centerline based on the Voronoi covariance measure. The calculation process of the blood vessel length and the blood vessel volume includes the following steps (31)-(34).

[0025] (31) Obtain the individual brain tissue volume corresponding to the target three-dimensional cerebrovascular segmentation image through image segmentation; specifically, use the BET (Brain Extraction Tool) tool in the FSL (FMRIB Software Library) toolkit to extract the individual brain tissue volume.

[0026] (32) Count the number of voxels marked as cerebrovascular in the target three-dimensional cerebrovascular segmentation image, and calculate the absolute length and absolute volume of the cerebrovascular in combination with the voxel resolution. Specifically, the calculation process of the absolute volume of the cerebrovascular is: the number of voxels marked as cerebrovascular in the target three-dimensional cerebrovascular segmentation image, multiplied by the voxel volume size, to obtain the absolute volume of the cerebrovascular.

[0027] (33) Considering that the individual brain tissue size can significantly affect the cerebrovascular structure length and cerebrovascular volume, calculate the relative length of the cerebrovascular based on the absolute length of the cerebrovascular and the individual brain tissue volume as the blood vessel length. The specific calculation process is: the absolute length of the cerebrovascular divided by the individual brain tissue volume to obtain the blood vessel length.

[0028] (34) Calculate the relative volume of the cerebrovascular based on the absolute volume of the cerebrovascular and the individual brain tissue volume as the blood vessel volume, so as to reflect the average distribution density of the cerebrovascular tissue in the whole brain tissue. The specific calculation process is: the absolute volume of the cerebrovascular divided by the individual brain tissue volume to obtain the blood vessel volume.

[0029] In a specific practical application, use the publicly available software libraries GDAL and the "create_centerlines" function in centerline based on Python to stably extract the blood vessel centerline from the target three-dimensional cerebrovascular segmentation image based on the Voronoi covariance measure (Voronoi Covariance Measure, VCM), and reduce the problem of center point recognition drift and voxel discontinuity at the cerebrovascular bifurcation.

[0030] Step 203: Based on the target three-dimensional cerebrovascular segmentation image, calculate the blood vessel diameter, blood vessel curvature radius, blood vessel bending degree, blood vessel bifurcation angle, and blood vessel bifurcation density respectively according to the blood vessel centerline as the individual feature results.

[0031] In a specific application, calculating the blood vessel diameter according to the blood vessel centerline includes the following steps (41)-(43).

[0032] Based on the vascular centerline, the tangent vectors corresponding to each voxel on the vascular centerline are calculated using the λ-maximal segment tangent (λ-MST) method; the calculation formula for the tangent vectors corresponding to each voxel on the vascular centerline is as follows:

[0033] .

[0034] Wherein, t ( x ) represents the tangent vector corresponding to the voxel x on the vascular centerline; P ( x ) represents the set of maximum line segments passing through the voxel x , M i is an element in the line segment set P ( x ), referring to a line segment; λ() is a preset conversion function, which can take ; t i represents the tangent vector of the line segment M i ; e i ( x ) represents the eccentricity of the line segment M i relative to the voxel x , and the calculation formula is:

[0035] .

[0036] Wherein, the numerator represents the distance from the voxel x to the near endpoint M i of the line segment m i , L i represents the distance of the line segment M i .

[0037] (42) Based on the tangent vectors corresponding to each voxel, the normal plane corresponding to each voxel on the vascular centerline is determined by the method of weighted averaging of adjacent voxel normal planes; thus, a robust estimation of the normal plane of each voxel on the vascular centerline is achieved by the method of weighted averaging of adjacent voxel normal planes, that is, after removing noise, outliers or uncertain data, a reliable and reasonable result is generated. Robust estimation can reduce the influence of bad data (such as noise, outliers, bifurcation complexity, etc.) on the final estimated value, making the result more accurate, smoother, and more consistent with the real data structure.

[0038] For each voxel on the blood vessel centerline, fit the largest circle in the normal plane corresponding to the voxel to calculate the corresponding blood vessel diameter.

[0039] Based on the obtained blood vessel centerline and the blood vessel diameters corresponding to the voxels on the blood vessel centerline, three-dimensional reconstruction of the tubular tree-like blood vessel structure can be achieved. Through the above steps of calculating the blood vessel diameter, local micro errors that may be introduced by the structure segmentation algorithm can be effectively prevented from being cascaded and amplified in the blood vessel feature estimation, ensuring the robustness of the three-dimensional reconstruction.

[0040] In a specific application, calculate the blood vessel curvature radius and the degree of blood vessel bending based on the blood vessel centerline, including the following steps (44)-(47).

[0041] (44)According to the tangent vectors corresponding to the voxels on the blood vessel centerline, calculate the included angle between the tangent vectors corresponding to adjacent voxels as the tangent vector turning angle; the tangent vector turning angle represents the direction change amount between two consecutive voxels; the calculation formula for the tangent vector turning angle is:

[0042] .

[0043] Among them, is the vector dot product, is the arccosine function, used to calculate the included angle between two tangent vectors; is the tangent vector at the i-th voxel, is the tangent vector at the (i + 1)-th voxel, is the tangent vector turning angle at the i-th voxel.

[0044] (45)Calculate the blood vessel curvature radius according to the tangent vector turning angle.

[0045] (46)Based on the blood vessel centerline, establish the Frenet frame for each voxel. The Frenet frame is a tool for describing the geometric characteristics of a space curve, defining a set of orthogonal vectors related to the local characteristics of the curve. It can provide geometric information such as the tangent direction, curvature, and normal vector of the curve at each point. The Frenet frame is an orthogonal coordinate system that completely describes the local geometric properties of the curve at each point. At each point on the space curve, the Frenet frame consists of the following three orthogonal vectors:

[0046] Tangent vector represents the local direction of the curve (corresponding to the tangent vector in this article), and the principal normal vector N(s) represents the bending direction of the curve, defined as:

[0047] .

[0048] Among them, is the derivative of the tangent vector, representing the rate of change of the tangent vector.

[0049] The binormal vector B(s) represents the normal vector of the plane where the curve lies and is defined as: 。 represents the vector cross product.

[0050] (47) Determine the degree of vascular curvature based on the Frenet frame.

[0051] In a specific application, calculate the vascular bifurcation angle and vascular bifurcation density based on the vascular centerline, including the following steps (48)-(412).

[0052] (48) Use a tree structure to characterize the neighborhood relationship of each voxel on the vascular centerline to construct a three-dimensional tree structure; specifically, use a tree structure to characterize the 26-neighborhood of each voxel on the vascular centerline, define the adjacency relationship of nodes and edges, and construct a three-dimensional tree structure.

[0053] (49) Traverse the adjacency list in the three-dimensional tree structure and count the degree of each voxel.

[0054] (410) If the degree of the voxel is within a preset range, mark the voxel as a bifurcation point; for example, when the degree is greater than 2, it is a bifurcation point, so as to realize the automatic identification of bifurcation points in the vascular tree structure, and then count the number of bifurcations and their spatial distribution.

[0055] (411) Calculate the included angle of the tangent vectors of the adjacent voxels of the bifurcation point as the corresponding vascular bifurcation angle.

[0056] (412) Count the number of bifurcation points in the three-dimensional segmentation image of the target cerebral blood vessels, combine the individual brain tissue volume corresponding to the three-dimensional segmentation image of the target cerebral blood vessels, and calculate the vascular bifurcation density based on the ratio of the number of bifurcation points to the individual brain tissue volume, so as to obtain the distribution characteristics of the vascular bifurcation statistic in the brain region space. Specifically, divide the number of bifurcation points by the volume of the target standard cerebral blood vessel partition to obtain the vascular bifurcation density.

[0057] Step 204, perform non-linear registration on the three-dimensional segmentation image of the target cerebral blood vessels and a preset standard brain template to obtain multiple target standard cerebral blood vessel partitions and the individual feature results within each target standard cerebral blood vessel partition; the preset standard brain template includes multiple preset standard brain partitions.

[0058] Specifically, a two-step registration method including linear initial registration and non-linear fine registration is used to perform non-linear registration on the MNI standard brain template (i.e., the preset standard brain template) and the cerebral vascular magnetic resonance image (i.e., the target three-dimensional segmentation image of cerebral blood vessels), so as to transform the Harvard-Oxford brain partition map in the MNI standard brain template into the space of the magnetic resonance angiography image at the individual level, thereby dividing the image into multiple partitions, namely the target standard cerebral vascular partitions. Through individual characteristic results such as the blood vessel length and blood vessel volume in each target standard cerebral vascular partition, the heterogeneity of the basic blood vessel characteristics (including blood vessel length and blood vessel volume) in the spatial distribution of each brain region can be reflected.

[0059] Step 205, based on the voxel-based morphometry (VBM), perform a population-level analysis on the target three-dimensional segmentation image of cerebral blood vessels to obtain population characteristic results. In a specific application example, step 205 includes the following steps (51)-(53).

[0060] (51) Obtain the cerebral vascular distribution density map at the population level of healthy people; specifically, through multiple non-linear registration iterations, register the cerebral vascular segmentation images of healthy people to generate the cerebral vascular distribution density map at the population level of healthy people.

[0061] (52) Perform non-linear registration on the target three-dimensional segmentation image of cerebral blood vessels and the cerebral vascular distribution density map at the population level of healthy people to obtain the transformation Jacobian matrix.

[0062] (53) Based on the transformation Jacobian matrix, standardize the target three-dimensional segmentation image of cerebral blood vessels after non-linear registration to obtain the distribution density of the target cerebral blood vessels in the standard atlas space, and mark it as the population characteristic result. Among them, this distribution density can quantitatively evaluate the differences at the local or overall level between the individual blood vessel distribution network density and the population.

[0063] In summary, the present application extracts the basic physical signs of cerebral blood vessels (including vessel length, vessel diameter, and vessel volume), geometric features of cerebral blood vessels (including vessel curvature radius and vessel bending degree), and topological features of cerebral blood vessels (including vessel bifurcation angle and vessel bifurcation density), and realizes the accurate and stable extraction of multi-level standardized cerebral blood vessel features on three-dimensional segmentation data of cerebral blood vessels, effectively preventing the interference of local errors that may be introduced by the structure segmentation algorithm in the estimation of vessel features. That is, by three-dimensionally reconstructing the cerebral blood vessel segmentation image, the present application can effectively suppress the noise in the segmentation image and greatly improve the accuracy and consistency of three-dimensional vessel segmentation. The present application also adopts VBM analysis, constructs a standard cerebral blood vessel distribution atlas of healthy people by using the method of iterative registration, transforms and registers the individual-level cerebral blood vessel segmentation image into the standard cerebral blood vessel distribution space, realizes the comparative analysis of cerebral blood vessel distribution density at the population level, and has strong representational interpretability.

[0064] In another exemplary application example, to systematically solve the problem of feature extraction of common three-dimensional segmentation structures of cerebral blood vessels in clinical and scientific research work, the present application constructs a complete and automatic feature extraction process, which can conveniently extract a series of objective features with clinical and scientific research guiding significance, such as the diameter, length, bending degree, bifurcation density, and network features of blood vessels, from the three-dimensional segmentation image of cerebral blood vessels, quantitatively describes complex structures such as cerebral blood vessels, and proposes a standard feature group of cerebral blood vessel structures including the above features to assist relevant clinical and scientific research practical work.

[0065] When establishing cerebral blood vessel characterization statistics and performing population-level analysis, the present application adopts two methods: standard space registration and VBM. The former eliminates the interference of local outliers on downstream analysis through weighted average statistics of local brain regions; the latter realizes the conversion from the individual level to the population level through the transformation Jacobian matrix by establishing a standard template of cerebral blood vessels, reduces the noise at the individual level, and realizes the robust estimation of cerebral blood vessel density and population comparative analysis.

[0066] 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 3As 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 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 external terminals through a network connection. When the computer program is executed by the processor, it realizes the method for extracting standardized cerebrovascular characteristics.

[0067] Those skilled in the art can understand that Figure 3 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. In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are realized.

[0068] 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 steps in the above method embodiments are realized.

[0069] 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 steps in the above method embodiments are realized.

[0070] 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.

[0071] Those of ordinary skill in the art can understand that by executing the methods of the above embodiments through computer program instructions related to hardware, 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 (ReRAM), magnetoresistive random access memories (MRAM), ferroelectric random access memories (FRAM), phase change memories (PCM), graphene memories, etc. Volatile memories can include random access memory (RAM) 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.

[0072] 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.

[0073] 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 to be within the scope described in this specification.

[0074] In this article, the principles and implementation manners of the present application are elaborated through specific examples. 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 standardized cerebrovascular feature extraction method, characterized in that The described standardized cerebrovascular feature extraction method includes: Obtain a three-dimensional segmented image of the target cerebrovascular vessels; Based on the three-dimensional segmented image of the target cerebrovascular vessels, calculate the vessel length and vessel volume, and determine the vessel centerline based on the Voronoi covariance metric; Based on the three-dimensional segmented image of the target cerebrovascular vessels, calculate the vessel diameter, vessel curvature radius, vessel bending degree, vessel bifurcation angle, and vessel bifurcation density respectively according to the vessel centerline, so as to obtain individual feature results; Calculating the vessel bifurcation angle and vessel bifurcation density according to the vessel centerline includes: using a tree structure to represent the neighborhood relationship of each voxel on the vessel centerline to construct a three-dimensional tree structure; traversing the adjacency list in the three-dimensional tree structure and counting the degree of each voxel; if the degree of the voxel is within a preset range, mark the voxel as a bifurcation point; calculate the included angle of the tangent vectors of the adjacent voxels of the bifurcation point as the corresponding vessel bifurcation angle; count the number of bifurcation points in the three-dimensional segmented image of the target cerebrovascular vessels to calculate the vessel bifurcation density; Perform non-linear registration on the three-dimensional segmented image of the target cerebrovascular vessels and a preset standard brain template to obtain multiple target standard cerebrovascular partitions and the individual feature results within each target standard cerebrovascular partition; the preset standard brain template includes multiple preset standard brain partitions; specifically, convert the Harvard-Oxford brain partition map in the preset standard brain template to the space of the individual-level magnetic resonance angiography image; Based on the voxel-based morphological measurement method, perform population-level analysis on the three-dimensional segmented image of the target cerebrovascular vessels to obtain population feature results.

2. The standardized cerebrovascular feature extraction method according to claim 1, wherein The calculation process of the vessel length and the vessel volume includes: Obtain the individual brain tissue volume corresponding to the three-dimensional segmented image of the target cerebrovascular vessels through image segmentation; Count the number of voxels marked as cerebrovascular vessels in the three-dimensional segmented image of the target cerebrovascular vessels to calculate the absolute length and absolute volume of the cerebrovascular vessels; Based on the absolute length of the cerebrovascular vessels and the individual brain tissue volume, calculate the relative length of the cerebrovascular vessels as the vessel length; Based on the absolute volume of the cerebrovascular vessels and the individual brain tissue volume, calculate the relative volume of the cerebrovascular vessels as the vessel volume.

3. The standardized cerebrovascular feature extraction method according to claim 1, wherein Calculating the vessel diameter according to the vessel centerline includes: Based on the vessel centerline, use the λ-maximum segment tangent method to calculate the tangent vectors corresponding to each voxel on the vessel centerline; Based on the tangent vectors corresponding to each voxel, use the method of plane weighted average of adjacent voxels to determine the normal plane corresponding to each voxel on the vessel centerline; For each voxel on the vessel centerline, fit the largest circle in the normal plane corresponding to the voxel to calculate the corresponding vessel diameter.

4. The standardized cerebrovascular feature extraction method according to claim 3, wherein, The calculation formula for the tangent vectors corresponding to each voxel on the vessel centerline is: ； Among them, t ( x ) represents the tangent vector corresponding to the voxel on the blood vessel centerline x ; P ( x ) represents the set of maximum line segments passing through the voxel x ; M i is an element in the line segment set P ( x ), referring to a line segment; λ() is a preset conversion function; t i represents the tangent vector of the line segment M i ; e i ( x ) represents the eccentricity of the line segment M i relative to the voxel x .

5. The standardized cerebrovascular feature extraction method according to claim 3, characterized in that Calculating the vessel curvature radius and vessel bending degree according to the vessel centerline includes: According to the tangent vectors corresponding to each voxel on the vessel centerline, calculate the included angle of the tangent vectors corresponding to adjacent voxels as the tangent vector flip angle; the tangent vector flip angle represents the direction change amount between two consecutive voxels; Calculate the vascular curvature radius according to the tangent vector flipping angle; Establish the Frenet frame of each voxel according to the vascular centerline; Determine the degree of vascular bending according to the Frenet frame; 6. The standardized cerebrovascular feature extraction method according to claim 5, wherein The calculation formula of the tangent vector flipping angle is: ； wherein, is the dot product of vectors, is the arccosine function, is the tangent vector at the i-th voxel, is the tangent vector at the (i + 1)-th voxel, is the flip angle of the tangent vector at the i-th voxel.

7. The standardized cerebrovascular feature extraction method according to claim 1, wherein Based on the morphological measurement method of voxels, perform population-level analysis on the three-dimensional segmentation image of the target cerebral blood vessels to obtain population characteristic results, including: Obtain the cerebral blood vessel distribution density map at the population level of healthy people; Perform non-linear registration on the three-dimensional segmentation image of the target cerebral blood vessels and the cerebral blood vessel distribution density map at the population level of healthy people to obtain the transformation Jacobian matrix; Based on the transformation Jacobian matrix, standardize the three-dimensional segmentation image of the target cerebral blood vessels after non-linear registration to obtain the distribution density of the target cerebral blood vessels in the standard atlas space, and mark it as the population characteristic result.

8. A computer device, comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the computer program to implement the standardized cerebral blood vessel feature extraction method according to any one of claims 1-7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the standardized cerebral blood vessel feature extraction method according to any one of claims 1-7.

Images