Individualized partitioning method and device based on brain surface geometric features, medium and product

Abstract

The invention discloses an individualized partitioning method and device based on brain surface geometric features, a medium and a product, and relates to the technical field of neuroimagines.The method comprises the steps that all vertexes are divided into brain sulcus seed points, brain gyrus seed points and remaining vertexes based on shape indexes of all the vertexes, a plurality of cerebral sulcus seed initial areas and cerebral gyrus seed initial areas are obtained; respectively merging the communicated brain sulcus seed initial regions and brain gyrus seed initial regions to obtain a plurality of merged regions, and determining the non-communicated initial regions as independent regions; and determining all the vertexes and all the remaining vertexes in the merged region and the independent region of which the number of the vertexes is smaller than a preset number as transition vertexes. Determining the merging areas and the independent areas with the vertex number greater than and / or equal to the preset number as initial inclusion areas; and iteratively incorporating the transition vertexes to obtain a brain personalized partition map so as to realize the partition of the brain. According to the invention, the accuracy of brain region partitioning is improved.

Description

Technical Field

[0001] The present application relates to the field of neuroimaging technology, and particularly to an individualized partitioning method, device, medium and product based on brain surface geometric features. Background Art

[0002] Currently, brain region partitioning mainly relies on traditional brain atlases, such as Brodmann partitioning, etc. Although these standardized atlases are widely used, they have the following limitations: 1) Ignoring the anatomical differences between individuals and being unable to reflect individual characteristics; 2) Mainly being divided based on two-dimensional slices and not fully utilizing the three-dimensional geometric information of the brain surface; 3) The subjectivity of manual partitioning is relatively strong and lacks an objective mathematical basis; 4) It is difficult to meet the needs of precision medicine for individualized analysis. Therefore, the precision of traditional brain region partitioning methods for brain region partitioning is relatively low.

[0003] Therefore, developing an individualized partitioning method based on objective brain surface geometric features has important scientific significance and application value. Summary of the Invention

[0004] The purpose of the present application is to provide an individualized partitioning method, device, medium and product based on brain surface geometric features to solve the problem of relatively low precision of brain region partitioning.

[0005] To achieve the above purpose, the present application provides the following solutions:

[0006] In a first aspect, the present application provides an individualized partitioning method based on brain surface geometric features, including:

[0007] Obtaining three-dimensional mesh data of the brain surface; the three-dimensional mesh data includes a plurality of vertices and a plurality of edges connecting two adjacent vertices;

[0008] Based on the three-dimensional mesh data, determining the shape index of each vertex;

[0009] Based on the shape index of each vertex, dividing each vertex into sulcus seed points, gyrus seed points and remaining vertices;

[0010] Based on a plurality of mutually adjacent sulcus seed points, determining a plurality of initial sulcus seed regions, and based on a plurality of mutually adjacent gyrus seed points, determining a plurality of initial gyrus seed regions;

[0011] Respectively determining the connectivity between each initial sulcus seed region and the connectivity between each initial gyrus seed region; the connectivity is either connected or not connected; connected includes adjacent and intersecting;

[0012] Merge the initial sulcus seed regions with connectivity being connected to obtain multiple merged sulcus seed regions, and merge the initial gyrus seed regions with connectivity being connected to obtain multiple merged gyrus seed regions;

[0013] Determine all the initial sulcus seed regions with connectivity being disconnected as independent sulcus seed regions, and determine all the initial gyrus seed regions with connectivity being disconnected as independent gyrus seed regions;

[0014] Determine all the vertices and all the remaining vertices in the merged sulcus seed regions, merged gyrus seed regions, independent sulcus seed regions, and independent gyrus seed regions with the number of vertices less than a preset number as transitional vertices to obtain an initial set of transitional vertices;

[0015] Based on each initial inclusion region, iteratively include each transitional vertex in the initial set of transitional vertices to obtain multiple target sulcus seed regions and target gyrus seed regions, thereby obtaining a personalized brain parcellation atlas and realizing the parcellation of the brain.

[0016] Optionally, based on the three-dimensional mesh data, determine the shape index of each vertex, including:

[0017] According to the three-dimensional mesh data, determine the curvature parameters of each vertex; the curvature parameters include: Gaussian curvature sum and mean curvature;

[0018] Respectively, according to the curvature parameters of each vertex, determine the maximum principal vector and minimum principal vector of each vertex;

[0019] Respectively, according to the maximum principal vector and minimum principal vector of each vertex, determine the shape index of each vertex.

[0020] Optionally, according to the three-dimensional mesh data, determine the curvature parameters of each vertex, including:

[0021] Determine any vertex as the target vertex;

[0022] Using the curvature parameter calculation formula, calculate the curvature parameters of the target vertex according to the three-dimensional mesh data; the curvature parameter calculation formula includes:

[0023]

[0024] where K is the Gaussian curvature of the target vertex; S is the total area of the region formed by the target vertex and all its adjacent vertices; N is the number of adjacent vertices of the target vertex; θ i is the apex angle of the triangle formed by the target vertex, the i-th adjacent vertex, and the i + 1-th adjacent vertex. When i = N, the i + 1-th adjacent vertex is the first adjacent vertex; l i is the length of the edge formed by the target vertex and the i-th adjacent vertex; li+1 is the length of the edge formed by the target vertex and the (i + 1)-th adjacent vertex; k i is the length of the edge formed by the i-th adjacent vertex and the (i + 1)-th adjacent vertex of the target vertex; H is the average curvature of the target vertex; β i is the dihedral angle formed by the target vertex, the i-th adjacent vertex, and the (i + 1)-th adjacent vertex.

[0025] Optionally, respectively according to the bending parameters of each vertex, determine the maximum principal vector and the minimum principal vector of each vertex, including:

[0026] Using the principal vector calculation formula, respectively according to the bending parameters of each vertex, calculate the maximum principal vector and the minimum principal vector of each vertex; the principal vector calculation formula includes:

[0027]

[0028] where k max is the maximum principal vector; k min is the minimum principal vector.

[0029] Optionally, respectively according to the maximum principal vector and the minimum principal vector of each vertex, determine the shape index of each vertex, including:

[0030] Using the shape index calculation formula, respectively according to the maximum principal vector and the minimum principal vector of each vertex, calculate the shape index of each vertex; the shape index calculation formula includes:

[0031]

[0032] where SI is the shape index.

[0033] Optionally, based on the shape index of each vertex, divide each vertex into sulcus seed points, gyrus seed points, and remaining vertices, including:

[0034] Determine any vertex as the current vertex;

[0035] When the shape index of the current vertex is less than -0.5, determine the current vertex as a sulcus seed point;

[0036] When the shape index of the current vertex is greater than 0.5, determine the current vertex as a gyrus seed point;

[0037] When the shape index of the current vertex is between -0.5 and 0.5, determine the current vertex as a remaining vertex.

[0038] Optionally, based on each initial inclusion region, each transition vertex in the initial transition vertex set is iteratively included to obtain multiple sulcus seed target regions and gyrus seed target regions, thereby obtaining a personalized brain partition map and realizing the partition of the brain, including:

[0039] Based on each initial inclusion region, all the transition vertices in the initial transition vertex set are iteratively included multiple times to obtain sulcus seed target regions and gyrus seed target regions, thereby obtaining a personalized brain partition map and realizing the partition of the brain; wherein, the inclusion process at any current iteration number includes:

[0040] Respectively determine whether there is an adjacency relationship between each transition vertex in the pre-update transition vertex set at the current iteration number and any vertex in the pre-update inclusion region at the current iteration number; when the current iteration number is the initial iteration number, the pre-update transition vertex set at the current iteration number is the initial transition vertex set, and the pre-update inclusion region at the current iteration number is the initial inclusion region; when the current iteration number is not the initial iteration number, the pre-update transition vertex set at the current iteration number is the post-update transition vertex set at the previous iteration number, and the pre-update inclusion region at the current iteration number is the post-update inclusion region at the previous iteration number; the inclusion region includes: sulcus seed inclusion region and gyrus seed inclusion region;

[0041] Include all the transition vertices with an adjacency relationship into the pre-update inclusion region at the current iteration number with an adjacency relationship to obtain the post-update inclusion region at the current iteration number;

[0042] Delete all the transition vertices with an adjacency relationship from the pre-update transition vertex set at the current iteration number, and retain all the transition vertices without an adjacency relationship in the pre-update transition vertex set at the current iteration number to obtain the post-update transition vertex set at the current iteration number;

[0043] Judge whether the number of transition vertices in the post-update transition vertex set at the current iteration number is 0;

[0044] If not, determine the post-update transition vertex set at the current iteration number as the pre-update transition vertex set at the next iteration number, determine the post-update inclusion region at the current iteration number as the pre-update inclusion region at the next iteration number, update the current iteration number to the next iteration number, and return to "Respectively determine whether there is an adjacency relationship between each transition vertex in the pre-update transition vertex set at the current iteration number and any vertex in the pre-update inclusion region at the current iteration number";

[0045] If so, the updated sulcus seed inclusion regions and gyrus seed inclusion regions at the current iteration are respectively determined as the sulcus seed target region and the gyrus seed target region, thereby obtaining an individual brain parcellation atlas and realizing the parcellation of the brain.

[0046] 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, where the processor executes the computer program to implement the individualized parcellation method based on brain surface geometric features described in any one of the above.

[0047] In a third aspect, the present application provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, it implements the individualized parcellation method based on brain surface geometric features described in any one of the above.

[0048] In a fourth aspect, the present application provides a computer program product, including a computer program, and when the computer program is executed by a processor, it implements the individualized parcellation method based on brain surface geometric features described in any one of the above.

[0049] According to the specific embodiments provided by the present application, the following technical effects are disclosed:

[0050] The present application discloses an individualized partitioning method, device, medium and product based on brain surface geometric features. First, three-dimensional mesh data of the brain surface is obtained; based on the three-dimensional mesh data, the shape index of each vertex is determined; based on the shape index of each vertex, each vertex is divided into sulcus seed points, gyrus seed points and remaining vertices; based on multiple mutually adjacent sulcus seed points, multiple initial sulcus seed regions are determined, and based on multiple mutually adjacent gyrus seed points, multiple initial gyrus seed regions are determined; secondly, the connectivity between each initial sulcus seed region and the connectivity between each initial gyrus seed region are respectively determined; the initial sulcus seed regions with connectivity being connected are merged to obtain multiple merged sulcus seed regions, and the initial gyrus seed regions with connectivity being connected are merged to obtain multiple merged gyrus seed regions; the initial sulcus seed regions with connectivity being unconnected are all determined as independent sulcus seed regions, and the initial gyrus seed regions with connectivity being unconnected are all determined as independent gyrus seed regions; then, all vertices in the merged sulcus seed regions, merged gyrus seed regions, independent sulcus seed regions and independent gyrus seed regions with the number of vertices less than the preset number and all the remaining vertices are determined as transition vertices to obtain an initial set of transition vertices; the merged sulcus seed regions, merged gyrus seed regions, independent sulcus seed regions and independent gyrus seed regions with the number of vertices greater than and / or equal to the preset number are all determined as initial inclusion regions; finally, based on each initial inclusion region, each transition vertex in the initial set of transition vertices is iteratively included to obtain multiple target sulcus seed regions and target gyrus seed regions, thereby obtaining a personalized brain partitioning map and realizing the partitioning of the brain. The present application determines the three-dimensional geometric information, i.e., the shape index, based on the objective three-dimensional mesh data of the brain surface and further performs automatic partitioning, avoiding the subjectivity of manual partitioning and improving the accuracy of brain partitioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0052] Figure 1 Schematic flowchart of an individualized partitioning method based on brain surface geometric features provided by an embodiment of the present application;

[0053] Figure 2 Schematic diagram of three-dimensional mesh data;

[0054] Figure 3 Schematic diagram of the region optimization process;

[0055] Figure 4Schematic diagram of a computer device provided by an embodiment of the present application. Detailed implementation manners

[0056] 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. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0057] The purpose of the present application is to provide an individualized partitioning method, device, medium and product based on brain surface geometric features, aiming to improve the accuracy of brain region partitioning.

[0058] To make the above objects, features and advantages of the present application more obvious and understandable, the present application will be further described in detail below in conjunction with the accompanying drawings and specific implementation manners.

[0059] In an exemplary embodiment, as Figure 1 shown, an individualized partitioning method based on brain surface geometric features is provided, including:

[0060] Step 01: Obtain three-dimensional mesh data of the brain surface; the three-dimensional mesh data includes a plurality of vertices and a plurality of edges connecting two adjacent vertices.

[0061] Specifically, the three-dimensional mesh data of the brain surface is obtained from magnetic resonance data. Magnetic resonance can use various devices and models such as 1.5T and 3T for clinical or scientific research applications. When collecting magnetic resonance, conventional 1mm slice thickness T1-weighted imaging parameters are used. The collected T1-weighted imaging data can be stored in various forms and is applied to generate three-dimensional mesh data using various mature software such as Freesurfer and Brainsuite. The final format of the three-dimensional mesh data is the.ply format.

[0062] As Figure 2 shown, the adjacency relationship of vertices in the three-dimensional mesh data refers to the information of all adjacent vertices included in the vertex. Each vertex in the three-dimensional mesh data has a unique label and corresponding spatial coordinates. The contact between two vertices forms a line segment (i.e., an edge), which is adjacent. Figure 2 In, the solid line represents the connection in the same layer, and the dotted line represents the connection between layers. Vertex V3 is adjacent to vertex V1, vertex V2, and vertex V6 respectively. That is, the adjacent vertices of vertex V3 include vertex V1, vertex V2, and vertex V6. This adjacency relationship is mainly applied to the calculation of Gaussian curvature and mean curvature, and the processing of vertices when generating a personalized partition map.

[0063] Step 02: Determine the shape index of each vertex based on the three-dimensional mesh data.

[0064] As an alternative implementation, step 02 includes:

[0065] Step 021: Determine the bending parameters of each vertex according to the three-dimensional mesh data; the bending parameters include: Gaussian curvature sum and mean curvature.

[0066] As an alternative implementation, step 021 includes:

[0067] Step 0211: Determine any vertex as the target vertex.

[0068] Step 0212: Use the bending parameter calculation formula to calculate the bending parameters of the target vertex according to the three-dimensional mesh data; the bending parameter calculation formula includes:

[0069]

[0070] Wherein, K is the Gaussian curvature of the target vertex; S is the total area of the region formed by the target vertex and all adjacent vertices; N is the number of adjacent vertices of the target vertex; θ i is the apex angle of the triangle formed by the target vertex, the i-th adjacent vertex and the (i + 1)-th adjacent vertex. When i = N, the (i + 1)-th adjacent vertex is the 1st adjacent vertex; l i is the length of the side formed by the target vertex and the i-th adjacent vertex; l i+1 is the length of the side formed by the target vertex and the (i + 1)-th adjacent vertex; k i is the length of the side formed by the i-th adjacent vertex and the (i + 1)-th adjacent vertex of the target vertex; H is the mean curvature of the target vertex; β i is the dihedral angle formed by the target vertex, the i-th adjacent vertex and the (i + 1)-th adjacent vertex.

[0071] Specifically, all adjacent vertices of each target vertex are pre-numbered (from 1 to N). All adjacent vertices of the target vertex are arranged in a ring around the target vertex. Therefore, adjacent vertex 1 and adjacent vertex 2 plus the target vertex form a triangle, and adjacent vertex 1 and the last adjacent vertex, that is, adjacent vertex N plus the target vertex form another triangle. Therefore, when i = N, the (i + 1)-th adjacent vertex is the 1st adjacent vertex.

[0072] Step 022: Determine the maximum principal vector and the minimum principal vector of each vertex according to the bending parameters of each vertex respectively.

[0073] As an alternative implementation, step 022 includes:

[0074] Use the principal vector calculation formula to calculate the maximum principal vector and the minimum principal vector of each vertex according to the bending parameters of each vertex respectively; the principal vector calculation formula includes:

[0075]

[0076] where k max is the maximum principal vector; k min is the minimum principal vector.

[0077] Step 023: Determine the shape index of each vertex according to the maximum principal vector and the minimum principal vector of each vertex, respectively.

[0078] As an alternative implementation, Step 023 includes:

[0079] Using the shape index calculation formula, calculate the shape index of each vertex according to the maximum principal vector and the minimum principal vector of each vertex, respectively; the shape index calculation formula includes:

[0080]

[0081] where SI is the shape index.

[0082] Step 03: Based on the shape index of each vertex, divide each vertex into sulcus seed points, gyrus seed points and remaining vertices.

[0083] As an alternative implementation, Step 03 includes:

[0084] Step 031: Determine any vertex as the current vertex.

[0085] Step 032: When the shape index of the current vertex is less than -0.5, determine the current vertex as a sulcus seed point.

[0086] Step 033: When the shape index of the current vertex is greater than 0.5, determine the current vertex as a gyrus seed point.

[0087] Step 034: When the shape index of the current vertex is between -0.5 and 0.5, determine the current vertex as a remaining vertex.

[0088] Step 04: Determine a plurality of initial sulcus seed regions based on a plurality of mutually adjacent sulcus seed points, and determine a plurality of initial gyrus seed regions based on a plurality of mutually adjacent gyrus seed points.

[0089] Specifically, when the SI of a vertex is greater than 0.5, it is marked as a gyrus. Since the gyri in the brain are scattered, and a gyrus has an area, that is, it consists of multiple adjacent vertices, it is necessary to mark the adjacent vertices as a group to form gyrus seed points. Similarly, when the SI of a vertex is less than -0.5, it is marked as a sulcus. Since the sulci in the brain are scattered, and a sulcus has an area, that is, it consists of multiple adjacent vertices, it is necessary to mark the adjacent vertices as a group to form sulcus seed points. In fact, there are some transition regions (where SI is between -0.5 and 0.5) between strict gyri and sulci. Therefore, subsequently, starting from the sulcus seed points and gyrus seed points, the transition regions need to be incorporated into the ranges of sulci and gyri to finally form a continuous personalized brain parcellation atlas.

[0090] Step 05: Determine the connectivity between the initial regions of each sulcus seed and the connectivity between the initial regions of each gyrus seed respectively; the connectivity is either connected or not connected; connected includes adjacent and intersecting.

[0091] Step 06: Merge the initial regions of each sulcus seed with connected connectivity to obtain multiple merged regions of sulcus seeds, and merge the initial regions of each gyrus seed with connected connectivity to obtain multiple merged regions of gyrus seeds.

[0092] Step 07: Determine all the initial regions of each sulcus seed with non - connected connectivity as independent regions of sulcus seeds, and determine all the initial regions of each gyrus seed with non - connected connectivity as independent regions of gyrus seeds.

[0093] Step 08: Determine all the vertices in the merged regions of sulcus seeds, merged regions of gyrus seeds, independent regions of sulcus seeds, and independent regions of gyrus seeds with the number of vertices less than the preset number, as well as all the remaining vertices, as transition vertices to obtain an initial set of transition vertices.

[0094] Specifically, since the undulations on the brain surface (i.e., sulci and gyri) vary in size (i.e., the shape fluctuations of sulci and gyri have different scales), very small fluctuations (i.e., the initial regions of sulcus seeds and gyrus seeds with the number of vertices less than the preset number, and the preset number is 10) may be noise, or not recognizable by the naked eye, or have no clinical significance. Therefore, all the vertices in the merged regions of sulcus seeds and gyrus seeds with the number of vertices less than 10 are disaggregated and merged into the transition region, that is, updated as transition vertices.

[0095] Step 09: Determine all the merged regions of sulcus seeds, merged regions of gyrus seeds, independent regions of sulcus seeds, and independent regions of gyrus seeds with the number of vertices greater than and / or equal to the preset number as initial inclusion regions.

[0096] Step 10: Based on each initial inclusion region, iteratively include each transition vertex in the initial transition vertex set to obtain multiple sulcus seed target regions and gyrus seed target regions, thereby obtaining a personalized brain partition map and achieving the partition of the brain.

[0097] As an alternative implementation, Step 10 includes:

[0098] Step 101: Based on each initial inclusion region, iteratively include all transition vertices in the initial transition vertex set multiple times to obtain sulcus seed target regions and gyrus seed target regions, thereby obtaining a personalized brain partition map and achieving the partition of the brain; where the inclusion process at any current iteration number includes:

[0099] Step 1011: Determine whether there is an adjacency relationship between each transition vertex in the pre-update transition vertex set at the current iteration number and any vertex in the pre-update inclusion region at the current iteration number; when the current iteration number is the initial iteration number, the pre-update transition vertex set at the current iteration number is the initial transition vertex set, and the pre-update inclusion region at the current iteration number is the initial inclusion region; when the current iteration number is not the initial iteration number, the pre-update transition vertex set at the current iteration number is the post-update transition vertex set at the previous iteration number, and the pre-update inclusion region at the current iteration number is the post-update inclusion region at the previous iteration number; the inclusion region includes: sulcus seed inclusion region and gyrus seed inclusion region.

[0100] Step 1012: Include all transition vertices with an adjacency relationship in the pre-update inclusion region at the current iteration number with an adjacency relationship to obtain the post-update inclusion region at the current iteration number.

[0101] Step 1013: Delete all transition vertices with an adjacency relationship from the pre-update transition vertex set at the current iteration number, and retain all transition vertices without an adjacency relationship in the pre-update transition vertex set at the current iteration number to obtain the post-update transition vertex set at the current iteration number.

[0102] Step 1014: Determine whether the number of transition vertices in the post-update transition vertex set at the current iteration number is 0.

[0103] Step 1015: If not, determine the updated transition vertex set at the current iteration as the transition vertex set before update at the next iteration, determine the updated inclusion region at the current iteration as the inclusion region before update at the next iteration, update the current iteration number to the next iteration number, and return "respectively determine whether there is an adjacency relationship between each transition vertex in the transition vertex set before update at the current iteration and any vertex in the inclusion region before update at the current iteration".

[0104] Step 1016: If so, respectively determine the updated sulcus seed inclusion regions and gyrus seed inclusion regions at the current iteration as the sulcus seed target regions and gyrus seed target regions, thereby obtaining a personalized brain partition map and realizing the partition of the brain.

[0105] Specifically, in the process of region optimization from Step 05 to Step 10, the process of region optimization is as Figure 3 shown.

[0106] In an exemplary embodiment, a computer device is provided, 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 an individualized partitioning method based on brain surface geometric features.

[0107] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, it implements an individualized partitioning method based on brain surface geometric features.

[0108] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, it implements an individualized partitioning method based on brain surface geometric features.

[0109] In an exemplary embodiment, a computer device is provided, and the computer device can be a server or a terminal, and its internal structure diagram can be as Figure 4As shown. 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 an external terminal through a network connection. When the computer program is executed by the processor, it implements an individualized partitioning method based on brain surface geometric features.

[0110] Those skilled in the art can understand that Figure 4 the structure shown in is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this 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.

[0111] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, 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.

[0112] 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.

[0113] 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.

[0114] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0115] In this text, specific examples are used to elaborate on the principles and implementation manners of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. 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. An individualized partitioning method based on brain surface geometric features, characterized in that: The individualized partitioning method based on brain surface geometric features includes: Acquire three-dimensional mesh data of the brain surface; the three-dimensional mesh data includes a plurality of vertices and a plurality of edges connecting two adjacent vertices; Based on the three-dimensional mesh data, determining a shape index of each vertex; Based on the shape index of each vertex, each vertex is divided into sulcus seed points, gyrus seed points and remaining vertices; Determine a plurality of sulcus seed initial regions based on a plurality of mutually adjacent sulcus seed points, and determine a plurality of gyrus seed initial regions based on a plurality of mutually adjacent gyrus seed points; Determine the connectivity between the initial regions of the sulcus seeds and the connectivity between the initial regions of the gyrus seeds respectively; the connectivity is connected or disconnected; the connectivity includes adjacent and intersecting; Merge the initial regions of the sulci seeds whose connectivity is connected to obtain multiple sulci seed merged regions, and merge the initial regions of the gyri seeds whose connectivity is connected to obtain multiple gyri seed merged regions; The initial regions of the sulcus seeds with disconnected connectivity are all determined as independent sulcus seed regions, and the initial regions of the gyrus seeds with disconnected connectivity are all determined as independent gyrus seed regions; All vertices in the sulcus seed merged region, the gyrus seed merged region, the sulcus seed independent region and the gyrus seed independent region with a number of vertices less than a preset number and all remaining vertices are determined as transition vertices to obtain an initial transition vertex set; The sulcus seed merged region, gyrus seed merged region, sulcus seed independent region and gyrus seed independent region whose vertices are greater than and / or equal to a preset number are all determined as initial inclusion regions; Based on each initially included area, each transition vertex in the initial transition vertex set is iteratively included to obtain multiple sulcus seed target areas and gyrus seed target areas, thereby obtaining a personalized brain partitioning map to achieve brain partitioning.

2. The individualized partitioning method based on brain surface geometric features according to claim 1, characterized in that: Based on the three-dimensional mesh data, determining a shape index of each vertex includes: Determine the curvature parameters of each vertex according to the three-dimensional mesh data; the curvature parameters include: Gaussian curvature and average curvature; According to the bending parameters of each vertex, the maximum principal vector and the minimum principal vector of each vertex are determined; The shape index of each vertex is determined according to the maximum principal vector and the minimum principal vector of each vertex.

3. The individualized partitioning method based on brain surface geometric features according to claim 2, characterized in that: Determining the bending parameters of each vertex according to the three-dimensional mesh data includes: Determine any vertex as the target vertex; The bending parameter calculation formula is used to calculate the bending parameter of the target vertex according to the three-dimensional mesh data; the bending parameter calculation formula includes: Where K is the Gaussian curvature of the target vertex; S is the total area of ​​the target vertex and all adjacent vertices; N is the number of adjacent vertices of the target vertex; θ i is the vertex angle of the triangle formed by the target vertex, the i-th adjacent vertex and the i+1-th adjacent vertex. When i=N, the i+1-th adjacent vertex is the first adjacent vertex; l i is the length of the edge between the target vertex and the i-th adjacent vertex; l i+1 k is the length of the edge between the target vertex and the i+1th adjacent vertex; i is the length of the edge formed by the i-th adjacent vertex and the i+1-th adjacent vertex of the target vertex; H is the average curvature of the target vertex; β i It is the dihedral angle formed by the target vertex, the i-th adjacent vertex and the i+1-th adjacent vertex.

4. The individualized partitioning method based on brain surface geometric features according to claim 3, characterized in that: According to the bending parameters of each vertex, the maximum principal vector and the minimum principal vector of each vertex are determined, including: The maximum and minimum principal vectors of each vertex are calculated using the principal vector calculation formula according to the bending parameters of each vertex; the principal vector calculation formula includes: Among them, k max is the maximum principal vector; k min is the minimum principal vector.

5. The individualized partitioning method based on brain surface geometric features according to claim 4, characterized in that: The shape index of each vertex is determined according to the maximum principal vector and the minimum principal vector of each vertex, including: The shape index calculation formula is used to calculate the shape index of each vertex according to the maximum principal vector and the minimum principal vector of each vertex; the shape index calculation formula includes: Among them, SI is the shape index.

6. The individualized partitioning method based on brain surface geometric features according to claim 1, characterized in that: Based on the shape index of each vertex, each vertex is divided into sulcus seed points, gyrus seed points and remaining vertices, including: Determine any vertex as the current vertex; When the shape index of the current vertex is less than -0.5, the current vertex is determined as the sulcus seed point; When the shape index of the current vertex is greater than 0.5, the current vertex is determined as the gyrus seed point; When the shape index of the current vertex is between -0.5 and 0.5, the current vertex is determined as a remaining vertex.

7. The individualized partitioning method based on brain surface geometric features according to claim 1, characterized in that: Based on each initial inclusion area, each transition vertex in the initial transition vertex set is iteratively included to obtain multiple sulcus seed target areas and gyrus seed target areas, thereby obtaining a personalized brain partitioning map to achieve brain partitioning, including: Based on each initial inclusion region, all transition vertices in the initial transition vertex set are iteratively included multiple times to obtain sulcus seed target regions and gyrus seed target regions, thereby obtaining a personalized brain partitioning map to achieve brain partitioning; wherein, the inclusion process under any current number of iterations includes: Determine whether each transition vertex in the transition vertex set before the update under the current iteration number has an adjacent relationship with any vertex in the included area before the update under the current iteration number; when the current iteration number is the initial iteration number, the transition vertex set before the update under the current iteration number is the initial transition vertex set, and the included area before the update under the current iteration number is the initial included area; when the current iteration number is not the initial iteration number, the transition vertex set before the update under the current iteration number is the updated transition vertex set under the previous iteration number, and the included area before the update under the current iteration number is the updated included area under the previous iteration number; the included area includes: sulcus seed included area and gyrus seed included area; Including all transition vertices that have an adjacent relationship into the inclusion region before updating at the current iteration number that has an adjacent relationship, and obtaining the inclusion region after updating at the current iteration number; Deleting all transition vertices that have an adjacent relationship from the transition vertex set before updating at the current number of iterations, and retaining all transition vertices that do not have an adjacent relationship in the transition vertex set before updating at the current number of iterations, to obtain an updated transition vertex set at the current number of iterations; Determine whether the number of transition vertices in the updated transition vertex set under the current iteration number is 0; If not, the updated transition vertex set under the current iteration number is determined as the transition vertex set before updating under the next iteration number, the updated included area under the current iteration number is determined as the included area before updating under the next iteration number, the current iteration number is updated to the next iteration number, and "respectively determine whether each transition vertex in the transition vertex set before updating under the current iteration number is adjacent to any vertex in the included area before updating under the current iteration number" is returned; If so, the updated sulcus seed inclusion areas and gyrus seed inclusion areas under the current iteration number are respectively determined as sulcus seed target areas and gyrus seed target areas, so as to obtain a personalized brain partitioning map and realize brain partitioning.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the individualized partitioning method based on brain surface geometric features as described in any one of claims 1 to 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the individualized partitioning method based on brain surface geometric features as described in any one of claims 1 to 7 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the individualized partitioning method based on brain surface geometric features as described in any one of claims 1 to 7 is implemented.

Images