Method, device, storage medium and electronic device for constructing cerebral vascular model

By pre-processing and thresholding of three-dimensional grayscale images of the brain, brain tissue models are extracted and cerebrovascular models are optimized, and the problem of skin and bone interference in the construction of cerebrovascular models in the prior art is solved, and the accuracy of the model is improved. Universality improves construction efficiency.

CN116051745BActive Publication Date: 2024-11-12BEIJING BAIHUI WEIKANG SCI & TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202310033622.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-01-10
Publication Date
2024-11-12
Estimated Expiration
2043-01-10

AI Technical Summary

Technical Problem

The existing method of constructing cerebrovascular models based on cerebrovascular images cannot avoid interference from skin and bones, resulting in the constructed cerebrovascular models being inaccurate enough. In addition, deep learning methods require training different models for different cerebrovascular images, which are inefficient and universal. Poor sex.

Method used

By preprocessing the scanned three-dimensional grayscale images, the location and size information of the brain tissue area are extracted, so as to determine the cerebrovascular model from the brain tissue model, and use the preset grayscale threshold and voxel number threshold to remove miscellaneous materials Points, optimize the cerebrovascular model.

Benefits of technology

It has achieved the avoidance of skin and bone interference, improved the accuracy and versatility of the cerebrovascular model, and improved the construction efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116051745B_ABST
    Figure CN116051745B_ABST
Patent Text Reader

Abstract

The present invention provides a method, device, storage medium and electronic device for constructing a cerebrovascular model, preprocessing a scanned three-dimensional grayscale image of the brain to obtain a first three-dimensional grayscale image of the brain, wherein the size of the first three-dimensional grayscale image of the brain is smaller than the size of the three-dimensional grayscale image of the brain; determining the position information and size information of the brain tissue region in the first three-dimensional grayscale image of the brain according to the first three-dimensional grayscale image of the brain; extracting a brain tissue model from the first three-dimensional grayscale image of the brain according to the position information and size information of the brain tissue region; and determining a cerebrovascular model from the brain tissue model according to a preset grayscale threshold. The present application extracts a brain tissue model first and then extracts a cerebrovascular model from the brain tissue model, thereby avoiding interference from the skin and bones of the brain, so that the constructed cerebrovascular model is more accurate; and has good versatility and high efficiency.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method, device, storage medium and electronic device for constructing a cerebrovascular model. Background Art

[0002] During neurosurgery-related operations, using cerebrovascular images to construct a cerebrovascular model plays an important role in surgical planning. The cerebrovascular model can be used to avoid important cerebrovascular vessels when planning the surgical plan, thereby reducing damage to the patient during the operation.

[0003] The existing method of constructing cerebrovascular models based on cerebrovascular images cannot avoid the interference of skin and bones, resulting in the constructed cerebrovascular model being inaccurate. The use of deep learning methods to construct cerebrovascular models can avoid the interference of skin and bones, but different models need to be trained for different cerebrovascular images, which is inefficient and has poor versatility. Summary of the invention

[0004] In view of the above problems, an embodiment of the present application is proposed, which provides a method, device, storage medium and electronic device for constructing a cerebrovascular model to at least solve the above problems.

[0005] One or more embodiments of the present application provide a method for constructing a cerebrovascular model, comprising: preprocessing a scanned three-dimensional grayscale image of the brain to obtain a first three-dimensional grayscale image of the brain, wherein the size of the first three-dimensional grayscale image of the brain is smaller than the size of the three-dimensional grayscale image of the brain; determining, based on the first three-dimensional grayscale image of the brain, position information and size information of a brain tissue region in the first three-dimensional grayscale image of the brain; extracting a brain tissue model from the first three-dimensional grayscale image of the brain based on the position information and size information of the brain tissue region; and determining a cerebrovascular model from the brain tissue model based on a preset grayscale threshold.

[0006] Optionally, based on the first brain three-dimensional grayscale image, determining the position information and size information of the brain tissue area in the first brain three-dimensional grayscale image includes: determining a first grayscale threshold and a second grayscale threshold based on the grayscale value of each voxel in the first brain three-dimensional grayscale image, the first grayscale threshold being less than the second grayscale threshold; determining the brain tissue grayscale threshold based on the first grayscale threshold and the second grayscale threshold; determining the position information and size information of the brain tissue area in the first brain three-dimensional grayscale image based on the grayscale value of each voxel in the first brain three-dimensional grayscale image, the second grayscale threshold, the brain tissue grayscale threshold and the image information of the first brain three-dimensional grayscale image, the image information of the first brain three-dimensional grayscale image including the coordinate information of each voxel in the first brain three-dimensional grayscale image, the physical size information and the size information of the first brain three-dimensional grayscale image.

[0007] Optionally, the position information and size information of the brain tissue region in the first brain three-dimensional grayscale image are determined according to the grayscale value of each voxel in the first brain three-dimensional grayscale image, the second grayscale threshold, the brain tissue grayscale threshold and the image information of the first brain three-dimensional grayscale image, including: determining the number of voxels whose grayscale values ​​are greater than the brain tissue grayscale threshold according to the grayscale value of each voxel in the first brain three-dimensional grayscale image; determining the position information of the brain tissue region in the first brain three-dimensional grayscale image according to the grayscale value of each voxel in the first brain three-dimensional grayscale image, the second grayscale threshold, the brain tissue grayscale threshold and the image information of the first brain three-dimensional grayscale image; determining the size information of the brain tissue region in the first brain three-dimensional grayscale image according to the number of voxels whose grayscale values ​​are greater than the brain tissue grayscale threshold and the image information of the first brain three-dimensional grayscale image.

[0008] Optionally, the position information of the brain tissue region is the center coordinates of the brain tissue region, and the size information is the radius of the brain tissue region.

[0009] Optionally, based on the position information and size information of the brain tissue region, a brain tissue model is extracted from the first brain three-dimensional grayscale image, including: taking the central coordinates of the brain tissue region as the center of the sphere and half the radius of the brain tissue region as the radius, and determining the initial contour of the brain tissue model from the first brain three-dimensional grayscale image; and expanding the initial contour of the brain tissue model until the brain tissue region is covered to obtain the brain tissue model.

[0010] Optionally, the scanned three-dimensional grayscale image of the brain is preprocessed to obtain a first three-dimensional grayscale image of the brain, including: determining the three-dimensional coordinate information of each voxel greater than a first preset grayscale threshold value based on the grayscale value and three-dimensional coordinate information of each voxel in the scanned three-dimensional grayscale image of the brain; determining the maximum value and minimum value of each coordinate axis in the three-dimensional coordinate system based on the three-dimensional coordinate information of each voxel; constructing an enclosing area with the maximum value and minimum value of each coordinate axis as boundaries, retaining the three-dimensional grayscale image of the brain located in the enclosing area, and obtaining the first three-dimensional grayscale image of the brain.

[0011] Optionally, the method further includes: determining, according to a preset voxel number threshold, independent regions in the cerebrovascular model whose voxel number is less than or equal to the preset voxel number threshold; and removing the independent regions to obtain an optimized cerebrovascular model.

[0012] According to another aspect of the present application, a cerebrovascular model construction device is provided, including: a preprocessing module, used to preprocess the scanned brain three-dimensional grayscale image to obtain a first brain three-dimensional grayscale image, the size of the first brain three-dimensional grayscale image is smaller than the size of the brain three-dimensional grayscale image; a brain tissue region determination module, used to determine the position information and size information of the brain tissue region in the first brain three-dimensional grayscale image according to the first brain three-dimensional grayscale image; a brain tissue model extraction module, used to extract the brain tissue model from the first brain three-dimensional grayscale image according to the position information and size information of the brain tissue region; a cerebrovascular model determination module, used to determine the cerebrovascular model from the brain tissue model according to a preset grayscale threshold.

[0013] According to another aspect of the present application, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable a computer to execute the method of the above aspect.

[0014] According to another aspect of the present application, an electronic device is provided, comprising: one or more processors; and a memory storing a program; wherein the program comprises instructions, and when the instructions are executed by the processor, the processor executes the method of the above aspect.

[0015] The present application provides a method, device, storage medium and electronic device for constructing a cerebrovascular model. The method preprocesses the scanned three-dimensional grayscale image of the brain to obtain a first three-dimensional grayscale image of the brain. The size of the first three-dimensional grayscale image of the brain is smaller than that of the three-dimensional grayscale image of the brain; based on the first three-dimensional grayscale image of the brain, the position information and size information of the brain tissue area in the first three-dimensional grayscale image of the brain are determined; based on the position information and size information of the brain tissue area, a brain tissue model is extracted from the first three-dimensional grayscale image of the brain; and based on a preset grayscale threshold, a cerebrovascular model is determined from the brain tissue model. The present application first extracts the brain tissue model and then extracts the cerebrovascular model from the brain tissue model, thereby avoiding interference from the skin and bones of the brain, so that the constructed cerebrovascular model is more accurate; and has good versatility and high efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] 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 or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 A schematic diagram of a process for constructing a cerebral vascular model according to an exemplary embodiment of the present application;

[0018] Figure 2A schematic diagram of a flow chart of a method for constructing a cerebral vascular model according to another exemplary embodiment of the present application;

[0019] Figure 3 A schematic diagram of the process of constructing a cerebral vascular model according to an exemplary embodiment of the present application;

[0020] Figure 4 A structural block diagram of a cerebral vascular model building device according to an exemplary embodiment of the present application;

[0021] Figure 5 It is a structural block diagram of an electronic device according to an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0022] In order to enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0023] For ease of understanding, before describing in detail the specific embodiments of the present application, the application scenarios of the cerebrovascular model construction method, device, storage medium and electronic device of the present application are exemplified.

[0024] The cerebrovascular model construction method of the present application can be used to construct a cerebrovascular model to assist in neurosurgery. In the process of neurosurgery-related surgery, using brain images to construct a cerebrovascular model plays an important role in surgical plan planning. The cerebrovascular model can be used to avoid important cerebrovascular vessels when planning the surgical plan, thereby reducing damage to the patient during the operation.

[0025] The existing method of constructing a cerebrovascular model based on brain images cannot avoid the interference of skin and bones, resulting in the inaccuracy of the constructed cerebrovascular model; while the use of deep learning methods to construct a cerebrovascular model can avoid the interference of skin and bones, but different models need to be trained for different brain images, which is inefficient and has poor versatility. In view of this, the present application proposes a cerebrovascular model construction method, device, storage medium and electronic device, which can solve the various problems existing in the above-mentioned prior art.

[0026] The specific embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0027] Figure 1 This is a flow chart of a method for constructing a cerebral vascular model according to an exemplary embodiment of the present application. As shown in the figure, this embodiment mainly includes the following steps:

[0028] S101 , preprocessing the scanned three-dimensional grayscale image of the brain to obtain a first three-dimensional grayscale image of the brain.

[0029] The size of the first brain three-dimensional grayscale image is smaller than the size of the brain three-dimensional grayscale image.

[0030] For example, a three-dimensional grayscale image of the brain, i.e., a brain model, can be obtained by techniques such as DSA angiography, CT angiography, contrast-enhanced magnetic resonance angiography, and MRI contrast-free angiography, including multiple parts such as skin, bones, brain tissue, and cerebral blood vessels. Preprocessing the three-dimensional grayscale image of the brain can be performed by cropping the three-dimensional grayscale image of the brain, cutting off the part of the three-dimensional grayscale image of the brain that does not include effective information such as skin, bones, brain tissue, and cerebral blood vessels, and obtaining a first three-dimensional grayscale image of the brain, so that the size of the obtained first three-dimensional grayscale image of the brain is smaller than the size of the three-dimensional grayscale image of the brain.

[0031] In a specific implementation, the scanned three-dimensional grayscale image of the brain is preprocessed to obtain a first three-dimensional grayscale image of the brain, including: determining the three-dimensional coordinate information of each voxel greater than a first preset grayscale threshold value based on the grayscale value and three-dimensional coordinate information of each voxel in the scanned three-dimensional grayscale image of the brain; determining the maximum value and minimum value of each coordinate axis in the three-dimensional coordinate system based on the three-dimensional coordinate information of each voxel; constructing an enclosing area with the maximum value and minimum value of each coordinate axis as boundaries, retaining the three-dimensional grayscale image of the brain located in the enclosing area, and obtaining the first three-dimensional grayscale image of the brain.

[0032] Exemplarily, the three-dimensional grayscale image of the brain is composed of a plurality of voxels, and the three-dimensional grayscale image of the brain includes the three-dimensional coordinate information and the corresponding grayscale value of each voxel. The grayscale value of each voxel is compared with a first preset grayscale threshold, and the three-dimensional coordinate information of each voxel greater than the first preset grayscale threshold is counted. The first preset grayscale threshold may be 10. From the three-dimensional coordinate information of each voxel greater than the first preset grayscale threshold, the maximum value and the minimum value on the x-axis, y-axis and z-axis are determined respectively, that is, the x min ,y min , z min 、x max ,y max and z max , according to x min ,y min , z min 、x max ,y max and z max Constructing an enclosing region, that is, forming a enclosing box, retaining the three-dimensional grayscale image of the brain in the enclosing region, and removing the portion outside the enclosing region to obtain a first three-dimensional grayscale image of the brain.

[0033] In this implementation, an enclosing area is constructed based on the three-dimensional coordinate information of voxels in the three-dimensional grayscale image of the brain that are greater than a first preset grayscale threshold, and the part outside the enclosing area is removed to obtain a first three-dimensional grayscale image of the brain. Then, a cerebrovascular model is extracted from the first three-dimensional grayscale image of the brain, thereby removing the part with a smaller grayscale value in the three-dimensional grayscale image of the brain, that is, removing the part of the three-dimensional grayscale image of the brain that does not include valid information. This can reduce the amount of calculation and improve processing efficiency in subsequent processing.

[0034] S102: Determine position information and size information of a brain tissue region in the first brain three-dimensional grayscale image according to the first brain three-dimensional grayscale image.

[0035] Exemplarily, a brain tissue extraction algorithm can be used to determine the position information and size information of a brain tissue region from a first brain three-dimensional grayscale image. For example, the position information and size information of a brain tissue region can be determined based on the difference in grayscale values ​​between the brain tissue region and other regions of the first brain three-dimensional grayscale image.

[0036] In a specific implementation, the position information of the brain tissue region is the center coordinates of the brain tissue region, and the size information is the radius of the brain tissue region. Since the brain tissue is similar to a sphere, it is easier to calculate using the center coordinates and the radius to represent it. The center coordinates of the brain tissue region and the radius of the brain tissue region can be used to facilitate the subsequent extraction of a brain tissue model from the first brain three-dimensional grayscale image.

[0037] S103 . Extracting a brain tissue model from the first brain three-dimensional grayscale image according to the position information and size information of the brain tissue region.

[0038] Exemplarily, based on the position information and size information of the brain tissue area in the first brain three-dimensional grayscale image, such as the center coordinates of the brain tissue area and the radius of the brain tissue area, the position and size of the brain tissue part in the brain model can be determined, so that the brain tissue model can be extracted from the first brain three-dimensional grayscale image, that is, the skin and bone parts of the brain in the first brain three-dimensional grayscale image are removed.

[0039] S104: Determine a cerebral blood vessel model from the brain tissue model according to a preset grayscale threshold.

[0040] Exemplarily, the gray value of each voxel in the brain tissue model is compared with a preset gray threshold, wherein the voxels with gray values ​​greater than or equal to the preset gray threshold represent cerebral blood vessels, thereby extracting a cerebral blood vessel model from the brain tissue model. The preset gray threshold can be adjusted according to the three-dimensional gray image of the brain obtained in different ways, and this embodiment does not limit this.

[0041] In a specific implementation, the method further includes: determining, according to a preset voxel number threshold, independent regions in the cerebrovascular model whose voxel number is less than or equal to the preset voxel number threshold; and removing the independent regions to obtain an optimized cerebrovascular model.

[0042] For example, the cerebrovascular model extracted from the brain tissue model in step S104 may have some noise points, i.e., independent regions with smaller volumes. The number of voxels in each independent region in the cerebrovascular model is compared with a preset voxel number threshold. If the number of voxels in an independent region is less than or equal to the preset voxel number threshold, it means that the independent region is a noise point, and the independent region is removed to obtain an optimized cerebrovascular model. The preset voxel number threshold may be 30.

[0043] In this implementation, by counting the volume of each region in the cerebrovascular model and removing independent regions with smaller volumes, that is, removing the noise points in the cerebrovascular model, the cerebrovascular model can be made more accurate and have better effects.

[0044] The present embodiment provides a method for constructing a cerebrovascular model, which pre-processes the scanned three-dimensional grayscale image of the brain to obtain a first three-dimensional grayscale image of the brain, wherein the size of the first three-dimensional grayscale image of the brain is smaller than that of the three-dimensional grayscale image of the brain; based on the first three-dimensional grayscale image of the brain, the position information and size information of the brain tissue region in the first three-dimensional grayscale image of the brain are determined; based on the position information and size information of the brain tissue region, a brain tissue model is extracted from the first three-dimensional grayscale image of the brain; and based on a preset grayscale threshold, a cerebrovascular model is determined from the brain tissue model. The present application extracts the brain tissue model first, and then extracts the cerebrovascular model from the brain tissue model, thereby avoiding interference from the skin and bones of the brain, so that the constructed cerebrovascular model is more accurate; and has good versatility and high efficiency.

[0045] Figure 2 FIG. 1 is a flow chart of a method for constructing a cerebral vascular model according to another exemplary embodiment of the present application. This embodiment mainly shows a specific implementation scheme of the above step S102. As shown in the figure, this embodiment mainly includes the following steps:

[0046] S201 , preprocessing the scanned three-dimensional grayscale image of the brain to obtain a first three-dimensional grayscale image of the brain.

[0047] S202 : Determine a first grayscale threshold and a second grayscale threshold according to the grayscale value of each voxel in the first three-dimensional brain grayscale image.

[0048] S203: Determine a brain tissue grayscale threshold according to the first grayscale threshold and the second grayscale threshold.

[0049] S204, determining position information and size information of a brain tissue region in the first brain three-dimensional grayscale image according to the grayscale value of each voxel in the first brain three-dimensional grayscale image, the second grayscale threshold, the brain tissue grayscale threshold, and the image information of the first brain three-dimensional grayscale image.

[0050] S205 . Extracting a brain tissue model from the first brain three-dimensional grayscale image according to the position information and size information of the brain tissue region.

[0051] S206: Determine a cerebral blood vessel model from the brain tissue model according to a preset grayscale threshold.

[0052] The first grayscale threshold is smaller than the second grayscale threshold, and the image information of the first brain three-dimensional grayscale image includes coordinate information and physical size information of each voxel in the first brain three-dimensional grayscale image and size information of the first brain three-dimensional grayscale image.

[0053] It should be noted that steps S201, S205 and S206 of this embodiment can be specifically implemented with reference to steps S101, S103 and S104 in the first embodiment, and will not be described in detail here.

[0054] Exemplarily, according to the gray value of each voxel in the first brain three-dimensional gray image, the gray histogram of the first brain three-dimensional gray image is calculated, and the first gray threshold and the second gray threshold are determined from the gray histogram, wherein the first gray threshold may refer to a gray minimum value with robustness, and the second gray threshold may refer to a gray maximum value with robustness. Specifically, the gray values ​​of the voxels in the first brain three-dimensional gray image may be arranged in ascending order, and the gray value t2 at 2% of the ascending order is used as the first gray threshold, and the gray value t at 98% is used as the second gray threshold. 98 As the second gray threshold. 98 , determine the brain tissue grayscale threshold t:

[0055] t=t2+0.1×(t 98 -t2)

[0056] According to the gray value M of each voxel in the first brain three-dimensional gray image i,j,k , the second gray threshold t 98 , brain tissue grayscale threshold t and the image information of the first brain three-dimensional grayscale image, determine the position information and size information of the brain tissue region in the first brain three-dimensional grayscale image. The image information of the first brain three-dimensional grayscale image includes the coordinate information (i, j, k) and physical size information (S of each voxel in the first brain three-dimensional grayscale image. x , S y , S z ) and the size information of the first brain three-dimensional grayscale image (Vx , V y , V z ). The position information of the brain tissue region in the first brain three-dimensional grayscale image may be the center coordinates (X0, Y0, Z0), and the size information may be the radius R.

[0057] In this embodiment, the position information and size information of the brain tissue area in the first brain three-dimensional grayscale image is determined by calculation, and the brain tissue model is extracted from the first brain three-dimensional grayscale image. The skin and bone parts in the brain three-dimensional grayscale image are removed, and then the cerebrovascular model is extracted from the brain tissue model. In this way, the obtained cerebrovascular model will not be interfered by the skin and bones of the brain, and the model result is more accurate.

[0058] In a specific implementation, the position information and size information of the brain tissue region in the first brain three-dimensional grayscale image are determined according to the grayscale value of each voxel in the first brain three-dimensional grayscale image, the second grayscale threshold, the brain tissue grayscale threshold, and the image information of the first brain three-dimensional grayscale image, including: determining the number of voxels whose grayscale values ​​are greater than the brain tissue grayscale threshold according to the grayscale value of each voxel in the first brain three-dimensional grayscale image; determining the position information of the brain tissue region in the first brain three-dimensional grayscale image according to the grayscale value of each voxel in the first brain three-dimensional grayscale image, the second grayscale threshold, the brain tissue grayscale threshold, and the image information of the first brain three-dimensional grayscale image; determining the size information of the brain tissue region in the first brain three-dimensional grayscale image according to the number of voxels whose grayscale values ​​are greater than the brain tissue grayscale threshold and the image information of the first brain three-dimensional grayscale image.

[0059] Exemplarily, the gray value M of each voxel in the first brain three-dimensional gray image is i,j,k The gray value M of each voxel in the first brain three-dimensional gray image is compared with the brain tissue gray threshold t, and the number p of voxels whose gray value is greater than the brain tissue gray threshold t is counted. i,j,k , the second grayscale threshold t98, the brain tissue grayscale threshold t and the image information of the first brain three-dimensional grayscale image, determine the position information of the brain tissue area in the first brain three-dimensional grayscale image, that is, the center coordinates (X0, Y0, Z0) of the brain tissue area:

[0060]

[0061]

[0062]

[0063] Then, according to the number of voxels p and the image information of the first brain three-dimensional grayscale image, the size information of the brain tissue area in the first brain three-dimensional grayscale image, that is, the radius of the brain tissue area, is determined:

[0064]

[0065] This implementation method calculates the position information and size information of the brain tissue area in the first brain three-dimensional grayscale image through the grayscale value of each voxel in the first brain three-dimensional grayscale image, the second grayscale threshold, the brain tissue grayscale threshold and the image information of the first brain three-dimensional grayscale image, so as to facilitate the subsequent extraction of the brain tissue model.

[0066] In a specific implementation, a brain tissue model is extracted from a first brain three-dimensional grayscale image based on position information and size information of a brain tissue region, including: taking the central coordinates of the brain tissue region as the center of a sphere and half of the radius of the brain tissue region as the radius, and determining an initial contour of the brain tissue model from the first brain three-dimensional grayscale image; and expanding the initial contour of the brain tissue model until the brain tissue region is covered to obtain a brain tissue model.

[0067] Exemplarily, the center coordinates (X0, Y0, Z0) of the brain tissue region are taken as the center of the sphere, and half of the radius R of the brain tissue region is taken as the radius, i.e., R / 2, and the initial outline of the brain tissue model is determined from the first three-dimensional grayscale image of the brain. A mosaic sphere can be constructed, starting from an icosahedron, each face of which is a triangle, and each triangle is iteratively subdivided into 4 smaller triangles, while adjusting the distance from the vertex of each triangle to the center coordinates (X0, Y0, Z0) to form a curved surface close to a sphere, which is composed of a plurality of triangles. The curved surface is the initial outline of the brain tissue model, and the first three-dimensional grayscale image of the brain inside the curved surface is the initial part of the brain tissue model. The initial outline of the brain tissue model is expanded, i.e., the initial model of the brain tissue model is expanded until the brain tissue region is covered, and the brain tissue model can be obtained.

[0068] The expansion of the initial contour of the brain tissue model can be achieved by pushing each point on the initial contour of the brain tissue model to the edge of the brain tissue area through the deformation force u. The deformation force can be composed of three forces, and the points on the initial contour of the brain tissue model refer to the vertices of the above triangle. The three forces are the tension u1 parallel to the tangent of the surface of the initial contour of the brain tissue model; the smoothing force u2 perpendicular to the tangent of the surface of the initial contour of the brain tissue model; and the expansion force u3 perpendicular to the tangent of the surface of the initial contour of the brain tissue model. The calculation method of the three forces is as follows:

[0069] Reference Figure 3 , assuming that there is point O on the initial contour of the brain tissue model, point A and point B are two points adjacent to point O on the initial contour of the brain tissue model, the position between point A and point B is point D, and the vector s represents the vector from vertex O to point D, and the decomposition vector of s is s n and t Among them, the direction of the force u1 is the same as the vector st The direction of the force u2 and the force u3 are parallel to the direction of the vector s n direction parallel to .

[0070] The force u1 can be calculated by the following formula:

[0071]

[0072] The force u2 can be calculated by the following formula:

[0073]

[0074] in l is the average distance from point O to its adjacent points. Usually, r min =3.33mm, r max =10mm.

[0075] The force u3 can be calculated by the following formula:

[0076]

[0077] Where: I min It represents the minimum gray value of the voxel extending from point O along the direction parallel to its local surface normal vector into the initial contour of the brain tissue model by a distance d1. min The initial value is t m , t m is the median gray value of the voxels within the initial contour of the brain tissue model; I max It represents the maximum gray value of the voxel extending from point O along the direction parallel to its local surface normal vector into the initial contour of the brain tissue model, and I max The initial value of is the brain tissue grayscale threshold t. “^” represents a unit vector.

[0078] Usually, d1 = 20 mm, d2 = d1 / 2, t2 is the first grayscale threshold, t1 = (I max -t2)b i +t2,b t is 0.5.

[0079] The deformation force u can be calculated by the following formula: u=u1+u2+u3.

[0080] When the three forces reach equilibrium, it means that the initial model of the brain tissue model expands to cover the brain tissue area, and the brain tissue model is obtained. That is, when the deformation force u is 0, point O is located in the middle of point A and point B, and the vector s t is 0, then the force u1 is 0, and the sum of the force u2 and the force u3 is also 0.

[0081] In this implementation, the initial contour of the brain tissue model is determined from the first brain three-dimensional grayscale image by taking the central coordinates of the brain tissue area as the center of the sphere and half of the radius of the brain tissue area as the radius; the initial contour of the brain tissue model is expanded to cover the brain tissue area, thereby achieving the extraction of the brain tissue model from the first brain three-dimensional grayscale image with high accuracy and good effect.

[0082] Figure 4 It is a structural block diagram of a cerebral vascular model building device according to an exemplary embodiment of the present application.

[0083] As shown in the figure, the cerebrovascular model construction device 400 of this embodiment mainly includes: a preprocessing module 401, a brain tissue region determination module 402, a brain tissue model extraction module 403 and a cerebrovascular model determination module 404.

[0084] Among them, the preprocessing module 401 is used to preprocess the scanned brain three-dimensional grayscale image to obtain a first brain three-dimensional grayscale image, and the size of the first brain three-dimensional grayscale image is smaller than the size of the brain three-dimensional grayscale image; the brain tissue area determination module 402 is used to determine the position information and size information of the brain tissue area in the first brain three-dimensional grayscale image based on the first brain three-dimensional grayscale image; the brain tissue model extraction module 403 is used to extract the brain tissue model from the first brain three-dimensional grayscale image based on the position information and size information of the brain tissue area; the cerebrovascular model determination module 404 is used to determine the cerebrovascular model from the brain tissue model according to a preset grayscale threshold.

[0085] In a specific implementation, the brain tissue region determination module 402 is further used to determine a first grayscale threshold and a second grayscale threshold according to the grayscale value of each voxel in the first brain three-dimensional grayscale image, wherein the first grayscale threshold is less than the second grayscale threshold; determine the brain tissue grayscale threshold according to the first grayscale threshold and the second grayscale threshold; determine the position information and size information of the brain tissue region in the first brain three-dimensional grayscale image according to the grayscale value of each voxel in the first brain three-dimensional grayscale image, the second grayscale threshold, the brain tissue grayscale threshold and the image information of the first brain three-dimensional grayscale image, wherein the image information of the first brain three-dimensional grayscale image includes the coordinate information and size information of each voxel in the first brain three-dimensional grayscale image and the size information of the first brain three-dimensional grayscale image.

[0086] In a specific implementation, the brain tissue region determination module 402 is further used to determine the number of voxels whose grayscale values ​​are greater than the brain tissue grayscale threshold according to the grayscale value of each voxel in the first brain three-dimensional grayscale image; determine the position information of the brain tissue region in the first brain three-dimensional grayscale image according to the grayscale value of each voxel in the first brain three-dimensional grayscale image, the second grayscale threshold, the brain tissue grayscale threshold and the image information of the first brain three-dimensional grayscale image; determine the size information of the brain tissue region in the first brain three-dimensional grayscale image according to the number of voxels and the image information of the first brain three-dimensional grayscale image.

[0087] In a specific implementation, the position information of the brain tissue region is the center coordinates of the brain tissue region, and the size information is the radius of the brain tissue region.

[0088] In a specific implementation, the brain tissue model extraction module 403 is also used to determine the initial contour of the brain tissue model from the first brain three-dimensional grayscale image with the central coordinates of the brain tissue area as the center of the sphere and half of the radius of the brain tissue area as the radius; the initial contour of the brain tissue model is expanded until the brain tissue area is covered to obtain the brain tissue model.

[0089] In a specific implementation, the preprocessing module 401 is also used to determine the three-dimensional coordinate information of each voxel greater than a first preset grayscale threshold value based on the grayscale value and three-dimensional coordinate information of each voxel in the scanned three-dimensional grayscale image of the brain; determine the maximum value and minimum value of each coordinate axis in the three-dimensional coordinate system according to the three-dimensional coordinate information of each voxel; construct an enclosing area with the maximum value and minimum value of each coordinate axis as boundaries, retain the three-dimensional grayscale image of the brain located in the enclosing area, and obtain a first three-dimensional grayscale image of the brain.

[0090] In a specific implementation, the cerebrovascular model construction device 400 also includes an optimization module, which is used to determine, based on a preset voxel number threshold, independent regions in the cerebrovascular model whose voxel number is less than or equal to a preset voxel number threshold; remove the independent regions to obtain an optimized cerebrovascular model.

[0091] In addition, the cerebrovascular model construction device 400 of the embodiment of the present application can also be used to implement other steps in the aforementioned cerebrovascular model construction method embodiments, and has the beneficial effects of the corresponding method step embodiments, which will not be repeated here.

[0092] The exemplary embodiments of the present application also provide a non-transitory computer-readable storage medium storing computer instructions, wherein the computer instructions are used to enable a computer to execute the methods of the various embodiments of the present application.

[0093] The exemplary embodiments of the present application also provide an electronic device, including: one or more processors; and a memory storing a program; wherein the program includes instructions, and when the instructions are executed by the processor, the processor executes the method of each embodiment of the present application.

[0094] refer to Figure 5 , the structural block diagram of the electronic device 500 that can be used as the server or client of the present application will now be described, which is an example of hardware devices that can be applied to various aspects of the present application. The electronic device is intended to represent various forms of digital electronic computer equipment, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples, and are not intended to limit the implementation of the present application described and / or required herein.

[0095] like Figure 5 As shown, the electronic device 500 may also include a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the device 500 may also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0096] A plurality of components in the electronic device 500 are connected to the I / O interface 505, including: an input unit 506, an output unit 507, a storage unit 508, and a communication unit 509. The input unit 506 may be any type of device capable of inputting information to the electronic device 500, and the input unit 506 may receive input digital or character information, and generate key signal inputs related to user settings and / or function control of the electronic device. The output unit 507 may be any type of device capable of presenting information, and may include, but is not limited to, a display, a speaker, a video / audio output terminal, a vibrator, and / or a printer. The storage unit 504 may include, but is not limited to, a disk, an optical disk. The communication unit 509 allows the electronic device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication transceiver, and / or a chipset, such as a Bluetooth™ device, a WiFi device, a WiMax device, a cellular communication device, and / or the like.

[0097] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above. For example, in some embodiments, the methods of the foregoing embodiments may be implemented as a computer software program, which is tangibly included in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 500 via the ROM 502 and / or the communication unit 509. In some embodiments, the computing unit 501 may be configured to perform the foregoing method in any other appropriate manner (e.g., by means of firmware).

[0098] The program code for implementing the method of the present application can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, implements the functions / operations specified in the flow chart and / or block diagram. The program code can be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0099] It should be noted that in the description of this application, the terms "first" and "second" are only used to facilitate the description of different components or names, and cannot be understood as indicating or implying a sequential relationship, relative importance, or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features.

[0100] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0101] It should be noted that although the specific embodiments of the present application are described in detail in conjunction with the accompanying drawings, this should not be construed as limiting the scope of protection of the present application. Within the scope described in the claims, various modifications and variations that can be made by those skilled in the art without creative work still fall within the scope of protection of the present application.

[0102] The examples of the embodiments of the present application are intended to concisely illustrate the technical features of the embodiments of the present application so that those skilled in the art can intuitively understand the technical features of the embodiments of the present application, and are not intended to be improper limitations of the embodiments of the present application.

[0103] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for constructing a cerebral vascular model, characterized in that: include: Preprocessing the scanned three-dimensional grayscale image of the brain to obtain a first three-dimensional grayscale image of the brain, wherein the size of the first three-dimensional grayscale image of the brain is smaller than the size of the three-dimensional grayscale image of the brain; Determining, according to the first brain three-dimensional grayscale image, position information and size information of a brain tissue region in the first brain three-dimensional grayscale image; extracting a brain tissue model from the first brain three-dimensional grayscale image according to the position information and size information of the brain tissue region; Determining a cerebral blood vessel model from the brain tissue model according to a preset grayscale threshold; Wherein, the determining the position information and size information of the brain tissue region in the first brain three-dimensional grayscale image according to the first brain three-dimensional grayscale image includes: determining a first grayscale threshold and a second grayscale threshold according to the grayscale value of each voxel in the first brain three-dimensional grayscale image, wherein the first grayscale threshold is less than the second grayscale threshold; determining the brain tissue grayscale threshold according to the first grayscale threshold and the second grayscale threshold; determining the position information and size information of the brain tissue region in the first brain three-dimensional grayscale image according to the grayscale value of each voxel in the first brain three-dimensional grayscale image, the second grayscale threshold, the brain tissue grayscale threshold and the image information of the first brain three-dimensional grayscale image, wherein the image information of the first brain three-dimensional grayscale image includes the coordinate information and the physical size information of each voxel in the first brain three-dimensional grayscale image and the size information of the first brain three-dimensional grayscale image; The method of determining the position information and size information of the brain tissue region in the first brain three-dimensional grayscale image according to the grayscale value of each voxel in the first brain three-dimensional grayscale image, the second grayscale threshold, the brain tissue grayscale threshold and the image information of the first brain three-dimensional grayscale image includes: determining the number of voxels whose grayscale values ​​are greater than the brain tissue grayscale threshold according to the grayscale value of each voxel in the first brain three-dimensional grayscale image; determining the position information of the brain tissue region in the first brain three-dimensional grayscale image according to the grayscale value of each voxel in the first brain three-dimensional grayscale image, the second grayscale threshold, the brain tissue grayscale threshold and the image information of the first brain three-dimensional grayscale image; and determining the size information of the brain tissue region in the first brain three-dimensional grayscale image according to the number of voxels whose grayscale values ​​are greater than the brain tissue grayscale threshold and the image information of the first brain three-dimensional grayscale image.

2. The method according to any one of claim 1, characterized in that: The position information of the brain tissue region is the center coordinates of the brain tissue region, and the size information is the radius of the brain tissue region.

3. The method according to claim 2, characterized in that The step of extracting a brain tissue model from the first brain three-dimensional grayscale image according to the position information and size information of the brain tissue region comprises: Taking the central coordinates of the brain tissue region as the center of the sphere and half of the radius of the brain tissue region as the radius, determining the initial contour of the brain tissue model from the first brain three-dimensional grayscale image; The initial outline of the brain tissue model is expanded until the brain tissue area is covered to obtain the brain tissue model.

4. The method according to claim 1, characterized in that The step of preprocessing the scanned three-dimensional grayscale image of the brain to obtain a first three-dimensional grayscale image of the brain includes: Determine the three-dimensional coordinate information of each voxel greater than a first preset grayscale threshold value according to the grayscale value and three-dimensional coordinate information of each voxel in the three-dimensional grayscale image of the brain obtained by scanning; According to the three-dimensional coordinate information of each voxel, respectively determine the maximum value and the minimum value of each coordinate axis in the three-dimensional coordinate system; An enclosing region is constructed with the maximum and minimum values ​​of the coordinate axes as boundaries, and the three-dimensional grayscale image of the brain located in the enclosing region is retained to obtain the first three-dimensional grayscale image of the brain.

5. The method according to claim 1, characterized in that The method further comprises: According to a preset voxel number threshold, determining an independent region in the cerebrovascular model whose voxel number is less than or equal to the preset voxel number threshold; The independent region is removed to obtain the optimized cerebral vascular model.

6. A device for constructing a cerebral vascular model, characterized in that: include: A preprocessing module, used for preprocessing the scanned three-dimensional grayscale image of the brain to obtain a first three-dimensional grayscale image of the brain, wherein the size of the first three-dimensional grayscale image of the brain is smaller than the size of the three-dimensional grayscale image of the brain; A brain tissue region determination module, configured to determine position information and size information of a brain tissue region in the first brain three-dimensional grayscale image according to the first brain three-dimensional grayscale image; A brain tissue model extraction module, used to extract a brain tissue model from the first brain three-dimensional grayscale image according to the position information and size information of the brain tissue region; A cerebrovascular model determination module, used to determine a cerebrovascular model according to the brain tissue model and a preset grayscale threshold; Wherein, the determining the position information and size information of the brain tissue region in the first brain three-dimensional grayscale image according to the first brain three-dimensional grayscale image includes: determining a first grayscale threshold and a second grayscale threshold according to the grayscale value of each voxel in the first brain three-dimensional grayscale image, wherein the first grayscale threshold is less than the second grayscale threshold; determining the brain tissue grayscale threshold according to the first grayscale threshold and the second grayscale threshold; determining the position information and size information of the brain tissue region in the first brain three-dimensional grayscale image according to the grayscale value of each voxel in the first brain three-dimensional grayscale image, the second grayscale threshold, the brain tissue grayscale threshold and the image information of the first brain three-dimensional grayscale image, wherein the image information of the first brain three-dimensional grayscale image includes the coordinate information and the physical size information of each voxel in the first brain three-dimensional grayscale image and the size information of the first brain three-dimensional grayscale image; The method of determining the position information and size information of the brain tissue region in the first brain three-dimensional grayscale image according to the grayscale value of each voxel in the first brain three-dimensional grayscale image, the second grayscale threshold, the brain tissue grayscale threshold and the image information of the first brain three-dimensional grayscale image includes: determining the number of voxels whose grayscale values ​​are greater than the brain tissue grayscale threshold according to the grayscale value of each voxel in the first brain three-dimensional grayscale image; determining the position information of the brain tissue region in the first brain three-dimensional grayscale image according to the grayscale value of each voxel in the first brain three-dimensional grayscale image, the second grayscale threshold, the brain tissue grayscale threshold and the image information of the first brain three-dimensional grayscale image; and determining the size information of the brain tissue region in the first brain three-dimensional grayscale image according to the number of voxels whose grayscale values ​​are greater than the brain tissue grayscale threshold and the image information of the first brain three-dimensional grayscale image.

7. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to enable a computer to execute the method according to any one of claims 1 to 6.

8. An electronic device, characterized in that: include: one or more processors; as well as A memory for storing programs; The program includes instructions, which, when executed by the processor, cause the processor to perform the method according to any one of claims 1 to 6.