Brain network construction method, system, medium and equipment based on mechanical parameters

Abstract

The present invention provides a method, system, medium, and device for constructing a brain network based on mechanical parameters, comprising: step S1: acquiring a brain structural image and a mechanical parameter distribution image using magnetic resonance elastography, registering the brain structural image and the mechanical parameter distribution image, segmenting them using a standard spatial atlas, and extracting the mechanical modulus value of each pixel in each brain region; step S2: calculating the probability distribution function of each brain region and estimating the similarity of the probability distribution functions of each brain region using KL divergence; and step S3: using the calculated KL divergence values ​​as connections between different brain regions, constructing a mechanical network and performing graph theory analysis, comparing graph theory indicators between healthy individuals and patients with neurodegenerative diseases. The present invention can improve the efficiency of early diagnosis of neurodegenerative diseases.

Description

Technical Field

[0001] The present invention relates to the field of computer-aided diagnosis technology, and in particular to a method, system, medium and device for constructing a brain network based on mechanical parameters. Background Art

[0002] Magnetic resonance elastography (MRI) can reflect the biomechanical properties of brain tissue by measuring elastic parameters such as shear modulus and viscosity, thereby detecting and evaluating changes in brain structure and function, such as those associated with brain tumors, epilepsy, traumatic brain injury, and neurodegenerative diseases. These parameters are closely related to the health of brain tissue and can be used to distinguish normal from diseased tissue, assess the severity of disease, and assess treatment efficacy.

[0003] Existing direct measurements of biomechanical parameters of brain tissue in degenerative diseases have the following technical defects: for spatially distributed tissue mechanical parameters, they cannot comprehensively display the correlation between changes in mechanical parameters between brain regions, as well as the correlation between their biological characteristics. This makes magnetic resonance elastography less than ideal in the diagnosis of neurodegenerative diseases, with low sensitivity and specificity.

[0004] Here we propose a brain network construction method based on mechanical parameters, which can more effectively detect neurodegenerative diseases. Summary of the Invention

[0005] In response to the deficiencies in the prior art, the present invention provides a method, system, medium and device for constructing a brain network based on mechanical parameters.

[0006] According to the present invention, a method, system, medium and device for constructing a brain network based on mechanical parameters are provided as follows:

[0007] In a first aspect, a method for constructing a brain network based on mechanical parameters is provided, the method comprising:

[0008] Step S1: Acquire brain structure images and mechanical parameter distribution images using magnetic resonance elastography, register the brain structure images and mechanical parameter distribution images, segment them using a standard spatial atlas, and extract the mechanical parameter values ​​of each pixel in each brain region;

[0009] Step S2: Calculate the probability distribution function of each brain region and use KL divergence to estimate the similarity of the probability distribution functions of each brain region;

[0010] Step S3: Using the calculated KL divergence values ​​as the connections between different brain regions, a mechanical network is constructed and graph theory analysis is performed to compare the graph theory indicators of healthy people and patients with neurodegenerative diseases.

[0011] Preferably, the step S1 includes:

[0012] Step S1.1: registering the brain structure image with the mechanical parameter distribution image, and registering the mechanical parameter distribution image to a standard space;

[0013] Use the antsRegistrationSyN command in the ANTs software to register the brain structure image T1WI to the MNI152 standard space, and at the same time register the mechanical parameter distribution image to the T1WI. Then use the antsApplyTransforms command to combine the rigid body transformation and non-rigid body transformation deformation field conversion matrix generated in the first two steps to register the mechanical parameter distribution image to the MNI152 standard space.

[0014] Step S1.2: Use the brain structure image in the MNI152 standard space to perform mask extraction on the mechanical parameter distribution image to obtain the mechanical parameter value of each pixel in each brain region.

[0015] Preferably, step S2 includes:

[0016] Step S2.1: Use Gaussian kernel function Where xc is the center of the kernel function and σ is the width parameter of the function to perform kernel density estimation and calculate the probability distribution function PDF of the mechanical parameters of each brain region;

[0017] Step S2.2: Calculate the KL divergence between each pair of brain regions:

[0018]

[0019] Where P and Q are the probability distribution functions PDF of two pairs of target brain regions, e is the natural base, and n is the number of sampling points. Here, n = 2 8 , KLDs range from 0 to 1, where 0 represents completely different PDFs and 1 represents completely identical PDFs.

[0020] Preferably, step S3 includes:

[0021] Step S3.1: Use the KLDs values ​​obtained in step S2 as the mechanical network connection strength values ​​of two pairs of brain regions to construct a mechanical parameter brain network;

[0022] Step S3.2: Analyze the constructed mechanical parameter brain network using graph theory. The mechanical parameter brain network is represented as an undirected graph G, consisting of N nodes and K edges. Nodes represent each brain region, and edges represent KLDs. Binarize the mechanical parameter brain network at different sparsities to obtain a binary undirected graph.

[0023] Step S3.3: Calculate the characteristics of the binary undirected graph, including the normalized clustering coefficient NormalizedC p, normalized shortest path length NormalizedL p , Normalized local efficiency NormalizedE glob , normalized global efficiency NormalizedE loc , Normalized modularity NormalizedQ, node degree value K i , node betweenness value B i and node efficiency E i :

[0024]

[0025] Among them, C i is the clustering coefficient of node i, representing the number of nodes connected to node i, N is the total number of nodes in the undirected graph G; L ijmin is the shortest path length required to connect node i and node j. If node i and node j are directly connected, then A ij or a ij is 1, otherwise it is 0; G i is an undirected graph representing the mechanical parameter brain network (containing i nodes), G represents a graph, i is a node on the graph; D i A on node i ij and; D j A on node j ij and; B i represents the number of shortest distance connections between two nodes through node i, B j represents the number of shortest distance connections between two nodes through node j; if B i =B j , then δ(B i ,B j ) is 1, otherwise it is 0; B average represents the mean betweenness of all nodes;

[0026] Step S3.4: Early diagnosis of the disease is performed by comparing the differences in the above characteristic values ​​between healthy people and patients with neurodegenerative diseases.

[0027] In a second aspect, a brain network construction system based on mechanical parameters is provided, the system comprising:

[0028] Module M1: Acquire brain structure images and mechanical parameter distribution images using magnetic resonance elastography. Regulate the brain structure images and mechanical parameter distribution images and segment them using a standard spatial atlas to extract the mechanical parameter values ​​of each pixel in each brain region.

[0029] Module M2: Calculate the probability distribution function of each brain region and use KL divergence to estimate the similarity of the probability distribution functions of each brain region;

[0030] Module M3: Use the calculated KL divergence values ​​as the connections between different brain regions, construct a mechanical network and perform graph theory analysis to compare the graph theory indicators of healthy people and patients with neurodegenerative diseases.

[0031] Preferably, the module M1 includes:

[0032] Module M1.1: registering the brain structure image with the mechanical parameter distribution image, and registering the mechanical parameter distribution image to the standard space;

[0033] Use the antsRegistrationSyN command in the ANTs software to register the brain structure image T1WI to the MNI152 standard space, and at the same time register the mechanical parameter distribution image to the T1WI. Then use the antsApplyTransforms command to combine the rigid body transformation and non-rigid body transformation deformation field conversion matrix generated in the first two steps to register the mechanical parameter distribution image to the MNI152 standard space.

[0034] Module M1.2: Use brain structural images in the MNI152 standard space to segment the mechanical parameter distribution image and extract the mechanical parameter value of each pixel in each brain region.

[0035] Preferably, the module M2 includes:

[0036] Module M2.1: Using Gaussian Kernel Function Where xc is the center of the kernel function and σ is the width parameter of the function to perform kernel density estimation and calculate the probability distribution function PDF of the mechanical parameters of each brain region;

[0037] Module M2.2: Calculate the KL divergence between each pair of brain regions:

[0038]

[0039] Where P and Q are the probability distribution functions PDF of two pairs of target brain regions, e is the natural base, and m is the number of sampling points. Here, n=2 is selected. 8 , KLDs range from 0 to 1, where 0 represents completely different PDFs and 1 represents completely identical PDFs.

[0040] Preferably, the module M3 includes:

[0041] Module M3.1: Use the KLDs values ​​obtained in module M2 as the mechanical network connection strength values ​​of two pairs of brain regions to construct a mechanical parameter brain network;

[0042] Module M3.2: Use graph theory to analyze the constructed mechanical parameter brain network. The mechanical parameter brain network is represented as an undirected graph G, consisting of N nodes and K edges. Nodes represent each brain region, and edges represent KLDs. The mechanical parameter brain network is binarized at different sparsities to obtain a binary undirected graph.

[0043] Module M3.3: Compute the features of binary undirected graphs, including the normalized clustering coefficient NormalizedC p , normalized shortest path length NormalizedL p , Normalized local efficiency NormalizedE glob , normalized global efficiency NormalizedE loc , Normalized modularity NormalizedQ, node degree value K i , node betweenness value B i and node efficiency E i :

[0044]

[0045] Among them, C i is the clustering coefficient of node i, representing the number of nodes connected to node i, N is the total number of nodes in the undirected graph G; L ijmin is the shortest path length required to connect node i and node j. If node i and node j are directly connected, then A ij or a ij is 1, otherwise it is 0; G i is an undirected graph representing the mechanical parameter brain network (containing i nodes), G represents a graph, i is a node on the graph; D i A on node i ij and; D j A on node j ij and; B i represents the number of shortest distance connections between two nodes through node i, B j represents the number of shortest distance connections between two nodes through node j; if B i =B j , then δ(B i ,B j ) is 1, otherwise it is 0; B average represents the mean betweenness of all nodes;

[0046] Module M3.4: Early diagnosis of diseases by comparing the differences in the above characteristic values ​​between healthy people and patients with neurodegenerative diseases.

[0047] In a third aspect, a computer-readable storage medium storing a computer program is provided, and when the computer program is executed by a processor, the steps in the brain network construction method based on mechanical parameters are implemented.

[0048] In a fourth aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps in the method for constructing a brain network based on mechanical parameters.

[0049] Compared with the prior art, the present invention has the following beneficial effects:

[0050] By designing a brain network based on mechanical parameters and simultaneously extracting network features, the accuracy of early diagnosis of neurodegenerative diseases can be improved, early detection and early treatment can be achieved, thereby improving the treatment effect of neurodegenerative diseases.

[0051] Other beneficial effects of the present invention will be explained through the introduction of specific technical features and technical solutions in the specific implementation methods. Those skilled in the art should be able to understand the beneficial technical effects brought about by the introduction of these technical features and technical solutions. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Other features, objects and advantages of the present invention will become more apparent upon reading the detailed description of non-limiting embodiments with reference to the following drawings:

[0053] Figure 1 It is the overall flow chart of the present invention. DETAILED DESCRIPTION

[0054] The present invention will be described in detail below with reference to specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but are not intended to limit the present invention in any form. It should be noted that, for those skilled in the art, several changes and improvements can be made without departing from the scope of the present invention. These all fall within the scope of protection of the present invention.

[0055] The present invention provides a method for constructing a brain network based on mechanical parameters, which can be used for early intervention of neurodegenerative diseases. The method mainly includes data preprocessing, similarity estimation of mechanical parameters of each brain region based on KL divergence (Kullback-Leibler divergence), brain network construction, and graph theory analysis. Figure 1 As shown, the method specifically includes the following contents:

[0056] Step S1: Acquire brain structure images (T1-Weighted Image) and mechanical parameter distribution images using magnetic resonance elastography. The brain structure images and mechanical parameter distribution images are registered and segmented using a standard spatial atlas to extract the mechanical parameter values ​​of each pixel in each brain region.

[0057] Specifically, step S1 includes:

[0058] Step S1.1: Register the brain structure image with the mechanical parameter distribution image, and register the mechanical parameter distribution image to the standard space.

[0059] Use the antsRegistrationSyN command in the ANTs software to register the brain structure image T1WI to the MNI152 standard space, and at the same time register the mechanical parameter distribution image to T1WI. Then use the antsApplyTransforms command to combine the rigid body transformation and non-rigid body transformation deformation field conversion matrix generated in the first two steps to register the mechanical parameter distribution image to the MNI152 standard space.

[0060] Step S1.2: Use the brain structure image in the MNI152 standard space to perform mask extraction on the mechanical parameter distribution image to obtain the mechanical parameter value of each pixel in each brain region.

[0061] Step S2: Calculate the probability distribution function (PDF) of each brain region and use KL divergence to estimate the similarity of the PDFs of each brain region.

[0062] Specifically, step S2 includes:

[0063] Step S2.1: Use Gaussian kernel function Where xc is the center of the kernel function and σ is the width parameter of the function to perform kernel density estimation and calculate the probability distribution function PDF of the mechanical parameters of each brain region;

[0064] Step S2.2: Calculate the KL divergence between each pair of brain regions:

[0065]

[0066] Where P and Q are the probability distribution functions PDF of two pairs of target brain regions, e is the natural base, and n is the number of sampling points. Here, n = 2 8 , KLDs range from 0 to 1, where 0 represents completely different PDFs and 1 represents completely identical PDFs.

[0067] Step S3: Using the calculated KL divergence values ​​as the connections between different brain regions, a mechanical network is constructed and graph theory analysis is performed. The graph theory indicators of healthy people and patients with neurodegenerative diseases are compared, thereby enabling early detection and intervention of neurodegenerative diseases.

[0068] Specifically, step S3 includes:

[0069] Step S3.1: Use the KLDs values ​​obtained in step S2 as the mechanical network connection strength values ​​of two pairs of brain regions to construct a mechanical parameter brain network.

[0070] Step S3.2: Use graph theory to analyze the constructed mechanical parameter brain network. The mechanical parameter brain network is represented as an undirected graph G, which contains N nodes and K edges. The nodes represent each brain region, and the edges represent the values ​​of KLDs. The mechanical parameter brain network is binarized at different sparsities (0.05-0.5, step size 0.01) to obtain a binary undirected graph.

[0071] Step S3.3: Calculate the characteristics of the binary undirected graph, including the normalized clustering coefficient NormalizedC p , normalized shortest path length NormalizedL p , Normalized local efficiency NormalizedE glob , normalized global efficiency NormalizedE loc , Normalized modularity NormalizedQ, node degree value K i , node betweenness value B i and node efficiency E i :

[0072]

[0073]

[0074] Among them, C i is the clustering coefficient of node i, representing the number of nodes connected to node i, N is the total number of nodes in the undirected graph G; L ijmin is the shortest path length required to connect node i and node j. If node i and node j are directly connected, then A ij or a ij is 1, otherwise it is 0; G i is an undirected graph representing the mechanical parameter brain network (containing i nodes), G represents a graph, i is a node on the graph; D i A on node i ij and; D j A on node j ij and; B irepresents the number of shortest distance connections between two nodes through node i, B j represents the number of shortest distance connections between two nodes through node j; if B i =B j , then δ(B i ,B j ) is 1, otherwise it is 0; B average represents the mean betweenness of all nodes;

[0075] Step S3.4: Early diagnosis of the disease is performed by comparing the differences in the above characteristic values ​​between healthy people and patients with neurodegenerative diseases.

[0076] The present invention also provides a brain network construction system based on mechanical parameters. The brain network construction system based on mechanical parameters can be implemented by executing the process steps of the brain network construction method based on mechanical parameters. That is, those skilled in the art can understand the brain network construction method based on mechanical parameters as a preferred embodiment of the brain network construction system based on mechanical parameters. The system specifically includes:

[0077] Module M1: Acquire brain structure images (T1-Weighted Image) and mechanical parameter distribution images using magnetic resonance elastography. The brain structure images and mechanical parameter distribution images are registered and segmented using a standard spatial atlas to extract the mechanical parameter values ​​of each pixel in each brain region.

[0078] Specifically, the module M1 includes:

[0079] Module M1.1: Register brain structure images with mechanical parameter distribution images, and register the mechanical parameter distribution images to the standard space.

[0080] Use the antsRegistrationSyN command in the ANTs software to register the brain structure image T1WI to the MNI152 standard space, and at the same time register the mechanical parameter distribution image to T1WI. Then use the antsApplyTransforms command combined with the transformation matrix of the first two steps to register the mechanical parameter distribution image to the MNI152 standard space.

[0081] Module M1.2: Use brain structural images in the MNI152 standard space to segment the mechanical parameter distribution image and extract the mechanical parameter value of each pixel in each brain region.

[0082] Module M2: Calculate the probability distribution function (PDF) of each brain region and use KL divergence to estimate the similarity of the PDFs of each brain region.

[0083] Specifically, module M2 includes:

[0084] Module M2.1: Using Gaussian Kernel Function Where xc is the center of the kernel function and σ is the width parameter of the function to perform kernel density estimation and calculate the probability distribution function PDF of the mechanical parameters of each brain region;

[0085] Module M2.2: Calculate the KL divergence between each pair of brain regions:

[0086]

[0087] Where P and Q are the probability distribution functions PDF of two pairs of target brain regions, e is the natural base, and n is the number of sampling points. Here, n = 2 8 , KLDs range from 0 to 1, where 0 represents completely different PDFs and 1 represents completely identical PDFs.

[0088] Module M3: Use the calculated KL divergence values ​​as the connections between different brain regions, construct a mechanical network and perform graph theory analysis, and compare the graph theory indicators of healthy people and patients with neurodegenerative diseases, so as to enable early detection and intervention of neurodegenerative diseases.

[0089] Specifically, module M3 includes:

[0090] Module M3.1: Use the KLDs values ​​obtained in module M2 as the mechanical network connection strength values ​​of two pairs of brain regions to construct a mechanical parameter brain network.

[0091] Module M3.2: Use graph theory to analyze the constructed mechanical parameter brain network. The mechanical parameter brain network is represented as an undirected graph G, which contains N nodes and K edges. The nodes represent each brain region, and the edges represent the values ​​of KLDs. The mechanical parameter brain network is binarized at different sparsities (0.05-0.5, step size 0.01) to obtain a binary undirected graph.

[0092] Module M3.3: Compute the features of binary undirected graphs, including the normalized clustering coefficient NormalizedC p , normalized shortest path length NormalizedL p , Normalized local efficiency NormalizedE glob , normalized global efficiency NormalizedE loc , Normalized modularity NormalizedQ, node degree value K i , node betweenness value B i and node efficiency E i :

[0093]

[0094] Among them, C i is the clustering coefficient of node i, representing the number of nodes connected to node i, N is the total number of nodes in the undirected graph G; L ijmin is the shortest path length required to connect node i and node j. If node i and node j are directly connected, then A ij or a ij is 1, otherwise it is 0; G i is an undirected graph representing the mechanical parameter brain network (containing i nodes), G represents a graph, i is a node on the graph; D i A on node i ij and; D j A on node j ij and; B i represents the number of shortest distance connections between two nodes through node i, B j represents the number of shortest distance connections between two nodes through node j; if B i =B j , then δ(B i ,B j ) is 1, otherwise it is 0; B average represents the mean betweenness of all nodes;

[0095] Module M3.4: Early diagnosis of diseases by comparing the differences in the above characteristic values ​​between healthy people and patients with neurodegenerative diseases.

[0096] The embodiments of the present invention provide a method, system, medium and device for constructing a brain network based on mechanical parameters. By designing a brain network based on mechanical parameters and simultaneously extracting network features, the problem of limited early diagnosis methods for neurodegenerative diseases is solved.

[0097] Those skilled in the art will appreciate that, in addition to implementing the system and its various devices, modules, and units provided by the present invention in purely computer-readable program code, it is entirely possible to implement the same functions of the system and its various devices, modules, and units provided by the present invention in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered a hardware component, and the devices, modules, and units included therein for implementing various functions can also be considered as structures within the hardware component; the devices, modules, and units for implementing various functions can also be considered as both software modules implementing the method and structures within the hardware component.

[0098] The above describes specific embodiments of the present invention. It should be understood that the present invention is not limited to the specific embodiments described above, and those skilled in the art may make various changes or modifications within the scope of the claims, which do not affect the essence of the present invention. The embodiments of this application and the features in the embodiments may be combined with each other in any manner unless there is a conflict.

Claims

1. A method for constructing a brain network based on mechanical parameters, characterized in that: include: Step S1: Acquire brain structure images and mechanical parameter distribution images using magnetic resonance elastography, register the brain structure images and mechanical parameter distribution images, segment them using a standard spatial atlas, and extract the mechanical parameter values ​​of each pixel in each brain region; Step S2: Calculate the probability distribution function of the mechanical parameters of each brain region and use KL divergence to estimate the similarity of the probability distribution functions of each brain region; Step S3: Using the calculated KL divergence values ​​as the connections between different brain regions, a mechanical network is constructed and graph theory analysis is performed to compare the graph theory indicators of healthy people and patients with neurodegenerative diseases.

2. The method for constructing a brain network based on mechanical parameters according to claim 1, characterized in that: The step S1 comprises: Step S1.1: registering the brain structure image with the mechanical parameter distribution image, and registering the mechanical parameter distribution image to a standard space; Use the antsRegistrationSyN command in the ANTs software to register the brain structure image T1WI to the MNI152 standard space, and at the same time register the mechanical parameter distribution image to the T1WI. Then use the antsApplyTransforms command to combine the rigid body transformation and non-rigid body transformation deformation field conversion matrix generated in the first two steps to register the mechanical parameter distribution image to the MNI152 standard space. Step S1.2: Use the brain structure image in the MNI152 standard space to perform mask extraction on the mechanical parameter distribution image to obtain the mechanical parameter value of each pixel in each brain region.

3. The method for constructing a brain network based on mechanical parameters according to claim 1, characterized in that: The step S2 comprises: Step S2.1: Use Gaussian kernel function Where xc is the center of the kernel function and σ is the width parameter of the function to perform kernel density estimation and calculate the probability distribution function PDF of the mechanical parameters of each brain region; Step S2.2: Calculate the KL divergence between each pair of brain regions: Where P and Q are the probability distribution functions PDF of two pairs of target brain regions, e is the natural base, and n is the number of sampling points. Here, n = 2 8 , KLDs range from 0 to 1, where 0 represents completely different PDFs and 1 represents exactly the same PDFs.

4. The method for constructing a brain network based on mechanical parameters according to claim 3, characterized in that: The step S3 comprises: Step S3.1: Use the KLDs values ​​obtained in step S2 as the mechanical network connection strength values ​​of two pairs of brain regions to construct a mechanical parameter brain network; Step S3.2: Analyze the constructed mechanical parameter brain network using graph theory. The mechanical parameter brain network is represented as an undirected graph G, consisting of N nodes and K edges. Nodes represent each brain region, and edges represent KLDs. Binarize the mechanical parameter brain network at different sparsities to obtain a binary undirected graph. Step S3.3: Calculate the characteristics of the binary undirected graph, including the normalized clustering coefficient NormalizedC p , normalized shortest path length NormalizedL p , Normalized local efficiency NormalizedE glob , normalized global efficiency NormalizedE loc , Normalized modularity NormalizedQ, node degree value K i , node betweenness value B i and node efficiency E i : Among them, C i is the clustering coefficient of node i, representing the number of nodes connected to node i, N is the total number of nodes in the undirected graph G; L ijmin is the shortest path length required to connect node i and node j. If node i and node j are directly connected, then A ij or a ij is 1, otherwise it is 0; G i is an undirected graph representing the mechanical parameter brain network (containing i nodes), G represents a graph, i is a node on the graph; D i A on node i ij and; D j A on node j ij and; B i represents the number of shortest distance connections between two nodes through node i, B j represents the number of shortest distance connections between two nodes through node j; if B i =B j , then δ(B i ,B j ) is 1, otherwise it is 0; B average represents the mean betweenness of all nodes; Step S3.4: Early diagnosis of the disease is performed by comparing the differences in the above characteristic values ​​between healthy people and patients with neurodegenerative diseases.

5. A brain network construction system based on mechanical parameters, characterized in that: include: Module M1: Acquire brain structure images and mechanical parameter distribution images using magnetic resonance elastography. Regulate the brain structure images and mechanical parameter distribution images and segment them using a standard spatial atlas to extract the mechanical parameter values ​​of each pixel in each brain region. Module M2: Calculate the probability distribution function of the mechanical parameters of each brain region and use KL divergence to estimate the similarity of the probability distribution functions of each brain region; Module M3: Use the calculated KL divergence values ​​as the connections between different brain regions, construct a mechanical network and perform graph theory analysis to compare the graph theory indicators of healthy people and patients with neurodegenerative diseases.

6. The brain network construction system based on mechanical parameters according to claim 5, characterized in that: The module M1 includes: Module M1.1: registering the brain structure image with the mechanical parameter distribution image, and registering the mechanical parameter distribution image to the standard space; Use the antsRegistrationSyN command in the ANTs software to register the brain structure image T1WI to the MNI152 standard space, and at the same time register the mechanical parameter distribution image to the T1WI. Then use the antsApplyTransforms command to combine the rigid body transformation and non-rigid body transformation deformation field conversion matrix generated in the first two steps to register the mechanical parameter distribution image to the MNI152 standard space. Module M1.2: Use brain structural images in the MNI152 standard space to segment the mechanical parameter distribution image and extract the mechanical parameter value of each pixel in each brain region.

7. The brain network construction system based on mechanical parameters according to claim 5, characterized in that: The module M2 includes: Module M2.1: Using Gaussian Kernel Function Where xc is the center of the kernel function and σ is the width parameter of the function to perform kernel density estimation and calculate the probability distribution function PDF of the mechanical parameters of each brain region; Module M2.2: Calculate the KL divergence between each pair of brain regions: Where P and Q are the probability distribution functions PDF of two pairs of target brain regions, e is the natural base, and n is the number of sampling points. Here, n = 2 8 , KLDs range from 0 to 1, where 0 represents completely different PDFs and 1 represents exactly the same PDFs.

8. The brain network construction system based on mechanical parameters according to claim 7, characterized in that: The module M3 includes: Module M3.1: Use the KLDs values ​​obtained in module M2 as the mechanical network connection strength values ​​of two pairs of brain regions to construct a mechanical parameter brain network; Module M3.2: Use graph theory to analyze the constructed mechanical parameter brain network. The mechanical parameter brain network is represented as an undirected graph G, consisting of N nodes and K edges. Nodes represent each brain region, and edges represent KLDs. The mechanical parameter brain network is binarized at different sparsities to obtain a binary undirected graph. Module M3.3: Compute the features of binary undirected graphs, including the normalized clustering coefficient NormalizedC p , normalized shortest path length NormalizedL p , Normalized local efficiency NormalizedE glob , normalized global efficiency NormalizedE loc , Normalized modularity NormalizedQ, node degree value K i , node betweenness value B i and node efficiency E i : Among them, C i is the clustering coefficient of node i, representing the number of nodes connected to node i, N is the total number of nodes in the undirected graph G; L ijmin is the shortest path length required to connect node i and node j. If node i and node j are directly connected, then A ij or a ij is 1, otherwise it is 0; G i is an undirected graph representing the mechanical parameter brain network (containing i nodes), G represents a graph, i is a node on the graph; D i A on node i ij and; D j A on node j ij and; B i represents the number of shortest distance connections between two nodes through node i, B j represents the number of shortest distance connections between two nodes through node j; if B i =B j , then δ(B i ,B j ) is 1, otherwise it is 0; B average represents the mean betweenness of all nodes; Module M3.4: Early diagnosis of diseases by comparing the differences in the above characteristic values ​​between healthy people and patients with neurodegenerative diseases.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for constructing a brain network based on mechanical parameters according to any one of claims 1 to 4 are implemented.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the computer program is executed by a processor, the steps of the method for constructing a brain network based on mechanical parameters according to any one of claims 1 to 4 are implemented.

Images