A brain function activity nonlinear modeling method, system and storage medium

Abstract

The application provides a brain function activity nonlinear modeling method, system and storage medium, relates to the functional magnetic resonance imaging data analysis technical field, and the method comprises the following steps: the BOLD signal of the brain cortex in a task cycle is divided into multiple task sections and is respectively mapped to a group level unit spherical flow form and an individual level unit spherical flow form; the distance matrix between the BOLD signals is obtained according to the group level unit spherical flow form; the group level unit spherical flow form is processed in dimension reduction according to the distance matrix, and a functional neighborhood is assigned to each brain cortex vertex according to the low-dimensional embedding flow form obtained by processing in dimension reduction; the local synchronism measure of the brain cortex vertex is determined according to the average signal corresponding to the functional neighborhood, and the related function activation atlas of the brain cortex is obtained according to the local synchronism measure. The application enhances the capturing ability of the nonlinear characteristics of brain function activity by carrying out distance calculation and flow form learning on the group level unit spherical flow form, and improves the modeling precision of brain function activity.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of functional magnetic resonance imaging data analysis, in particular to a brain function activity nonlinear modeling method, system and storage medium. BACKGROUND

[0002] As an important tool for studying brain function, functional magnetic resonance imaging technology needs to collect and continuously acquire blood oxygen level dependent signals (BOLD signals) at tens of thousands of brain region sites for hundreds of time points to indirectly reflect neuron activity by measuring blood oxygen level dependent signals. On this basis, a general linear model is generally used to simplify the relationship between task stimulation and blood oxygen level dependent signals as a linear convolution process to achieve linear modeling of brain function activity.

[0003] In related technologies, since nonlinear response characteristics such as task dependence, context regulation and cross-brain region asynchronous cooperation exist in brain neural activity, modeling based on linear modeling cannot effectively represent these nonlinear response characteristics. In addition, blood oxygen level dependent signals have characteristics such as high dimension, high coupling and low signal-to-noise ratio, and linear models are difficult to fully reveal the potential low-dimensional geometric structure thereof, which comprehensively leads to the lack of ability of existing linear models to accurately model brain function activity. SUMMARY

[0004] The problem solved by the present application is how to improve the accuracy of modeling brain function activity.

[0005] To solve the above problems, the present application provides a brain function activity nonlinear modeling method, system and storage medium.

[0006] In a first aspect, a brain function activity nonlinear modeling method of the present application comprises:

[0007] acquiring fMRI data of a brain cortex in a task cycle, the fMRI data comprising BOLD signals of each time frame in the task cycle for each brain cortex vertex in the brain cortex;

[0008] dividing the BOLD signals into a plurality of task segments, and mapping the BOLD signals corresponding to each task segment into a group-level unit spherical manifold and an individual-level unit spherical manifold, respectively;

[0009] performing distance calculation according to the group-level unit spherical manifold to obtain a distance matrix between each BOLD signal and other BOLD signals;

[0010] According to the distance matrix, manifold learning dimension reduction processing is performed on the group level unit spherical manifold to obtain a low-dimensional embedded manifold, and a functional neighborhood is assigned to each brain cortex vertex according to the low-dimensional embedded manifold;

[0011] According to the functional neighborhood of each brain cortex vertex, an average signal corresponding to the functional neighborhood is determined from the individual level unit spherical manifold;

[0012] According to the average signal, a local synchrony measure of each brain cortex vertex is determined;

[0013] According to the local synchrony measure of all brain cortex vertices, a relevant functional activation map of the brain cortex during the task cycle is obtained.

[0014] Optionally, the BOLD signal is divided into a plurality of task segments, and the BOLD signal corresponding to each task segment is respectively mapped into a group level unit spherical manifold and an individual level unit spherical manifold, comprising:

[0015] According to a predetermined task design, all tasks included in the task cycle are determined, and each task corresponds to a task segment;

[0016] The BOLD signal is preprocessed to obtain a group level BOLD signal and an individual level BOLD signal;

[0017] The time series of each brain cortex vertex in each task segment is extracted from the group level and individual level BOLD signals to obtain original vectors of each task segment at the group level and individual level;

[0018] The original vectors corresponding to the group level and individual level are normalized to obtain unit spherical vectors corresponding to the group level and individual level, and the group level unit spherical manifold and the individual level unit spherical manifold are obtained according to the unit spherical vectors corresponding to all task segments at the group level and individual level.

[0019] Optionally, the distance matrix between each BOLD signal and other BOLD signals is obtained by calculating the distance according to the group level unit spherical manifold, comprising:

[0020] According to the unit spherical vectors in the group level unit spherical manifold, a point set of the group level unit spherical manifold is obtained, wherein each unit spherical vector corresponds to a point of the point set;

[0021] By measuring the distance, the unit spherical vectors corresponding to any two points in the point set are calculated to obtain the spherical distance between the two points.

[0022] arranging the spherical distances between each point in the point set and other points to obtain the distance matrix.

[0023] Optionally, the manifold learning dimension reduction processing of the group-level unit sphere manifold according to the distance matrix to obtain a low-dimensional embedding manifold comprises:

[0024] constructing an adjacency graph of the point set according to the distance matrix through a manifold learning algorithm;

[0025] obtaining a fuzzy topological structure of the group-level unit sphere manifold according to the adjacency graph;

[0026] performing low-dimensional coordinate optimization according to the fuzzy topological structure to determine the Euclidean distance distribution of the point set in a target low-dimensional space;

[0027] generating the low-dimensional embedding manifold with a dimension lower than the group-level unit sphere manifold according to the Euclidean distance distribution.

[0028] Optionally, the assigning of a functional neighborhood for each brain cortex vertex according to the low-dimensional embedding manifold comprises:

[0029] determining a low-dimensional coordinate corresponding to each brain cortex vertex according to the group-level low-dimensional embedding manifold;

[0030] determining a plurality of other brain cortex vertices closest to the brain cortex vertex in the individual-level unit sphere manifold through a K-nearest neighbor algorithm with the low-dimensional coordinate corresponding to each brain cortex vertex as the center;

[0031] obtaining a vertex set of the functional neighborhood according to a plurality of other brain cortex vertices;

[0032] mapping the vertex set back to the individual-level unit sphere manifold to obtain the functional neighborhood of each brain cortex vertex.

[0033] Optionally, the determining of an average signal corresponding to the functional neighborhood from the individual-level unit sphere manifold according to the functional neighborhood of each brain cortex vertex comprises:

[0034] extracting the functional neighborhood of each brain cortex vertex to obtain a unit sphere vector set corresponding to the functional neighborhood;

[0035] iteratively solving all unit sphere vectors in the unit sphere vector set through a Riemann center calculation rule to obtain a Karcher average signal of the functional neighborhood;

[0036] Converging iteratively according to the Karcher mean signal of the functional neighborhood to obtain the mean signal corresponding to the functional neighborhood.

[0037] Optionally, the determining of the local synchronism metric of each of the brain cortex vertices according to the mean signal comprises:

[0038] Performing geodesic line calculation on each point in the individual-level unit sphere manifold to obtain a geodesic distance between the unit sphere vector corresponding to each point and the mean signal corresponding to the unit sphere vector;

[0039] Constructing a geodesic line distance synchronism index according to the geodesic distance, wherein the geodesic line distance synchronism index comprises the activation direction and the local synchronism strength of the brain cortex vertex and other brain cortex vertices in the functional neighborhood corresponding to the brain cortex vertex in the time dimension;

[0040] Taking the geodesic line distance synchronism index as the local synchronism metric of the brain cortex vertex.

[0041] Optionally, the obtaining of the relevant functional activation atlas of the brain cortex in the task cycle according to the local synchronism metric of all the brain cortex vertices comprises:

[0042] Mapping the local synchronism metric of each of the brain cortex vertices to the brain cortex spatial coordinate corresponding to the brain cortex vertex;

[0043] Generating a vertex-level synchronism value field of the brain cortex according to the brain cortex spatial coordinate of all the brain cortex vertices;

[0044] Performing encoding processing on the vertex-level synchronism value field to obtain a visualization layer of the brain cortex;

[0045] Superimposing the visualization layer to a preset standard brain cortex template to obtain the relevant functional activation atlas of the brain cortex in the task cycle.

[0046] In a second aspect, a brain function activity nonlinear modeling system is provided, comprising:

[0047] A data acquisition module is configured to acquire fMRI data of a brain cortex in a task cycle, wherein the fMRI data comprises a BOLD signal of each brain cortex vertex in the brain cortex in each time frame in the task cycle;

[0048] A task segmentation and mapping module is configured to divide the BOLD signal into a plurality of task segments, and map the BOLD signal corresponding to each of the task segments into a group-level unit sphere manifold and an individual-level unit sphere manifold, respectively;

[0049] a distance calculation module configured to calculate distances between the BOLD signals based on the set of horizontal unit sphere manifolds, to obtain a distance matrix;

[0050] a manifold dimension reduction and neighborhood assignment module configured to perform manifold learning dimension reduction on the set of horizontal unit sphere manifolds based on the distance matrix, to obtain a low-dimensional embedded manifold, and to assign a functional neighborhood to each of the brain cortex vertices based on the low-dimensional embedded manifold;

[0051] an average signal calculation module configured to determine an average signal corresponding to the functional neighborhood of each of the brain cortex vertices from the individual horizontal unit sphere manifold based on the functional neighborhood;

[0052] a local synchrony measure module configured to determine a local synchrony measure of each of the brain cortex vertices based on the average signal;

[0053] a map generation module configured to obtain a relevant functional activation map of the brain cortex during the task cycle based on the local synchrony measures of all the brain cortex vertices.

[0054] In a third aspect, a computer readable storage medium having a computer program stored thereon is provided. The computer program, when executed by a processor, implements the method for nonlinear modeling of brain function activity.

[0055] The brain function activity nonlinear modeling method, system and storage medium of the application first acquire fMRI data of the brain cortex in a task cycle, which contains the BOLD signal of each time frame of each brain cortex vertex in the task cycle. By task segment division on the BOLD signal and mapping the BOLD signal corresponding to each task segment to the group level unit spherical manifold and the individual level unit spherical manifold respectively, the time sequence characteristics of the BOLD signal are effectively utilized, the data integrity and accuracy are ensured, and the dynamic changes of the brain function activity are facilitated to be captured. The distance calculation is performed in the group level unit spherical manifold to obtain the distance matrix between each BOLD signal and other BOLD signals, and the nonlinear relationship between the brain regions is quantified from the geometric angle. The generation of the low-dimensional embedded manifold enables the subsequent analysis to be performed in a lower-dimensional space, improves the calculation efficiency and reduces the influence of data noise. The average signal corresponding to the functional neighborhood of the functional neighborhood of each brain cortex vertex is determined from the individual level unit spherical manifold to further refine the analysis of the brain function activity. In combination with the geodesic distance synchrony index, the local synchrony measure of each brain cortex vertex is determined according to the average signal, the task-induced activation region is identified, including the region showing an atypical activation mode, and the adaptability and explanatory power of the model under complex tasks and disease states are enhanced. Finally, the local synchrony measure of all brain cortex vertices is integrated to generate the related functional activation atlas of the brain cortex in the task cycle, so that the atlas not only contains the traditional activation region, but also can reveal the region with nonlinear and asymmetric response, and more comprehensively reflects the real functional response of the brain. It is ensured that each step from data preprocessing to functional activation atlas generation can effectively capture and reflect the complexity of the brain function activity. In summary, the application significantly enhances the ability to capture the nonlinear characteristics of the brain function activity by performing distance calculation and manifold learning on the group level unit spherical manifold. At the same time, through geometric perception dimension reduction and local characteristic analysis, a more comprehensive and detailed understanding of the brain function activity is provided, so that the model can more accurately reveal the functional mechanism of the brain under different task states, and the modeling accuracy of the brain function activity is improved. BRIEF DESCRIPTION OF DRAWINGS

[0056] Figure 1 The flowchart of the brain function activity nonlinear modeling method of the embodiment of the application is shown in the figure.

[0057] Figure 2 The flowchart of the brain function activity nonlinear modeling method of the embodiment of the application is shown in the figure.

[0058] Figure 3 The structure diagram of the brain function activity nonlinear modeling system of the embodiment of the application is shown in the figure. DETAILED DESCRIPTION

[0059] In order to make the above objectives, characteristics and advantages of the present application more apparent, concrete embodiments of the present application will be described in detail below with reference to the drawings. Although some embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms, and should not be interpreted as being limited to the embodiments set forth herein, but rather, these embodiments are provided so as to more completely and thoroughly understand the present application. It should be understood that the drawings and embodiments of the present application are merely for exemplary purposes, and are not intended to limit the scope of protection of the present application.

[0060] It should be understood that each of the steps described in the method embodiments of the present application can be performed in different orders, and / or in parallel. In addition, the method embodiments can include additional steps and / or omit the steps shown. The scope of the present application is not limited in this respect.

[0061] The term "comprising" and variations thereof as used herein are open-ended, that is "including, but not limited to"; the term "based on" is "based, at least in part, on"; the term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments"; the term "optional" means "optional in at least some embodiments". Related definitions are given throughout the description. It should be noted that the concepts mentioned in the present application are merely for distinguishing different devices, modules or units, and are not intended to limit the functions of these devices, modules or units.

[0062] It should be noted that the modification of "one" or "multiple" mentioned in the present application is illustrative rather than limiting, and those skilled in the art should understand that, unless otherwise explicitly indicated in the context, it should be understood as "one or more".

[0063] To solve the problems in the related art described above, the embodiment provides an intelligent site selection system and method based on multi-source terrain fusion and a storage medium.

[0064] In combination Figure 1 As shown in the figure, the brain function activity nonlinear modeling method provided by the embodiment of the present application comprises:

[0065] The fMRI data of the brain cortex in a task cycle is acquired, and the fMRI data comprises the BOLD signal of each time frame of each brain cortex vertex in the brain cortex in the task cycle.

[0066] Specifically, the fMRI data comprises the time series BOLD signal of each brain cortex vertex in the task cycle, which serves as the basis of the modeling method. In the embodiment of the present application, in combination Figure 2As shown, firstly, fMRI data of multiple subjects for tasks of brain cortex, such as subject-1 and subject-2, and the like, are required, and the fMRI data is preprocessed, wherein the preprocessing includes spatial alignment, time denoising, signal standardization, and the like, of the original data, so as to ensure the consistency of the fMRI data of different subjects in space and time. The pre-acquired fMRI data can be stored in a database or a storage medium, and the fMRI data is directly acquired from the database or the storage medium for processing in the embodiment, that is, the embodiment mainly relates to the processing process of the fMRI data, and does not relate to the improvement of the acquisition of the fMRI data from the human body.

[0067] The BOLD signals are divided into multiple task segments, and the BOLD signals corresponding to each of the task segments are respectively mapped into group-level unit spherical manifolds and individual-level unit spherical manifolds.

[0068] Specifically, the BOLD signals are divided into multiple task segments and are respectively mapped into group-level unit spherical manifolds and individual-level unit spherical manifolds. Specifically, a task period is divided into multiple non-overlapping task segments, and each task segment corresponds to a specific experimental condition. For the BOLD signal of each brain cortex vertex in each task segment, a time sequence is extracted to obtain an original vector, and then the original vector is mapped onto a unit spherical manifold through a normalization operation. At the group level, the data of all subjects are integrated for unified processing; and at the individual level, the data of each subject is processed respectively. In the embodiment of the present application, the group-level unit spherical manifold is calculated by combining the data of all subjects, and the individual-level unit spherical manifold is calculated by combining the data of each subject. Figure 2 As shown, the division of the task segments is based on the task start time in the experimental design. After the time sequence of the BOLD signal of each brain cortex vertex in each task segment is extracted to obtain an original vector, the norm of the vector is calculated, and the original vector is divided by the norm to realize the normalization processing of the vector, so as to be mapped into a unit spherical manifold. In combination with Figure 2 As shown, subject-1, subject-2, and subject-n jointly constitute a preset task design, and respectively correspond to a task segment, and the tasks are divided into task1 and task2 according to time periods, and the task period is divided into multiple continuous task segments, each of which corresponds to a specific task, and the blue and orange respectively represent task1 and task2, so as to reveal the spatial distribution and time dynamics of the brain function.

[0069] According to the group-level unit spherical manifold, distance calculation is performed to obtain a distance matrix between each of the BOLD signals and other BOLD signals.

[0070] Specifically, the normalized BOLD signals of all the brain cortex vertices in each task segment are regarded as a set of points on the group-level unit sphere manifold. For any two points in the set of points, the spherical distance between the two points is calculated by using the geodesic distance metric. In an embodiment of the present application, a distance matrix is generated by calculating the geodesic distance between each pair of points on the group-level unit sphere manifold and arranging the distance values in matrix form. Figure 2 The distance matrix comprehensively reflects the nonlinear relationship between the brain cortex vertices and provides a key quantitative basis for subsequent manifold learning dimension reduction.

[0071] According to the distance matrix, manifold learning dimension reduction processing is performed on the group-level unit sphere manifold to obtain a low-dimensional embedded manifold, and a functional neighborhood is assigned to each brain cortex vertex according to the low-dimensional embedded manifold.

[0072] Specifically, first, at the group level, a manifold learning algorithm is selected, the distance matrix is taken as the input, an adjacency graph of the set of points is constructed, and a fuzzy topological structure of the group-level unit sphere manifold is further obtained. In an embodiment of the present application, the UMAP algorithm can be used for manifold learning dimension reduction processing. The UMAP algorithm constructs an adjacency graph between data points at the group level according to the spherical distance in the distance matrix, estimates the local topological structure, and optimizes the embedded coordinates in the low-dimensional space, so that the distance between points in the low-dimensional embedded manifold is consistent with the topological structure of the original manifold, thereby realizing dimension reduction. The low-dimensional embedded manifold after dimension reduction not only reduces the complexity of the data, but also retains the key structural information of the data, which is convenient for subsequent analysis and processing. Secondly, at the individual level, the functional neighborhood is assigned. In a preferred embodiment of the present application, the assignment operation is performed by the K-nearest neighbor algorithm.

[0073] According to the functional neighborhood of each brain cortex vertex, the average signal corresponding to the functional neighborhood is determined from the individual-level unit sphere manifold.

[0074] Specifically, at the individual level, after obtaining the functional neighborhood corresponding to each brain cortex vertex, a set of unit sphere vectors corresponding to the functional neighborhood is extracted from the individual-level unit sphere manifold. Karcher average signal calculation is performed on the unit sphere vectors to obtain the average signal of the functional neighborhood. In an embodiment of the present application, as shown in Figure 2 For the functional neighborhood of each brain cortex vertex, first, all the unit sphere vectors in the neighborhood are determined, and then the Karcher average signal algorithm in Riemannian geometry is used to iteratively solve the average value of the vectors, thereby obtaining the average signal of the functional neighborhood. The average signal can represent the signal characteristics in the functional neighborhood and provide a basis for subsequent synchrony analysis.

[0075] determine a local synchrony measure for each of the cortical vertices based on the average signals.

[0076] Specifically, a geodesic distance synchrony index is calculated between each cortical vertex and other vertices based on the average signals of the functional neighborhood of each cortical vertex. The geodesic distance synchrony index comprehensively considers the activation direction and local synchrony strength of the cortical vertex and other vertices in the functional neighborhood in the time dimension. In embodiments of the present application, the geodesic distance synchrony index is constructed by calculating the geodesic distance between the unit spherical vector of each cortical vertex and the Karcher mean signal of the functional neighborhood, and the index can quantify the synchrony between vertices. According to this index, a local synchrony measure is determined for each cortical vertex.

[0077] According to the local synchrony measures of all the cortical vertices, a functional activation map of the cerebral cortex during the task cycle is obtained.

[0078] Specifically, the local synchrony measures of all the cortical vertices are integrated and mapped to the surface of the cerebral cortex to generate a task-related functional activation map. The map presents the functional activity pattern of the cerebral cortex during the task cycle in a visual manner. In embodiments of the present application, the local synchrony measure of each cortical vertex can be mapped to a standard brain template by a visualization tool to generate an intuitive color-coded or intensity-coded layer, and finally output the functional activation map of the cerebral cortex during the task cycle. This helps researchers to deeply understand the functional mechanism of the brain in different task states.

[0079] The brain function activity nonlinear modeling method, system and storage medium of the application first acquire fMRI data of the brain cortex in a task cycle, which contains the BOLD signal of each brain cortex vertex in each time frame in the task cycle. By dividing the BOLD signal into task segments and mapping the BOLD signal corresponding to each task segment to the group level unit spherical manifold and the individual level unit spherical manifold respectively, the time sequence characteristics of the BOLD signal are effectively utilized, the data integrity and accuracy are ensured, and the dynamic changes of brain function activity are facilitated to be captured. The distance calculation is performed in the group level unit spherical manifold to obtain the distance matrix between each BOLD signal and other BOLD signals, and the nonlinear relationship between brain regions is quantified from the geometric angle. The generation of the low-dimensional embedded manifold enables the subsequent analysis to be performed in a lower-dimensional space, improves the calculation efficiency, and reduces the influence of data noise. By determining the average signal corresponding to the functional neighborhood of each brain cortex vertex from the individual level unit spherical manifold, the analysis of brain function activity is further refined. Combined with the geodesic distance synchrony index, the local synchrony measure of each brain cortex vertex is determined according to the average signal, which can identify the activation regions induced by the task, including the regions showing atypical activation patterns, and enhances the adaptability and explanatory power of the model under complex tasks and disease states. Finally, the local synchrony measures of all brain cortex vertices are integrated to generate the related functional activation atlas of the brain cortex in the task cycle, so that the atlas not only contains the traditional activation regions, but also reveals the regions with nonlinear and asymmetric responses, and more comprehensively reflects the real functional response of the brain. It is ensured that each step from data preprocessing to functional activation atlas generation can effectively capture and reflect the complexity of brain function activity. In summary, the application significantly enhances the ability to capture the nonlinear characteristics of brain function activity by performing distance calculation and manifold learning on the group level unit spherical manifold. At the same time, through geometric perception dimension reduction and local characteristic analysis, a more comprehensive and detailed understanding of brain function activity is provided, so that the model can more accurately reveal the functional mechanism of the brain under different task states, and the modeling accuracy of brain function activity is improved.

[0080] Optionally, the BOLD signal is divided into a plurality of task segments, and the BOLD signal corresponding to each task segment is mapped to a group level unit spherical manifold and an individual level unit spherical manifold, respectively, comprising:

[0081] According to the preset task design, all tasks included in the task cycle are determined, and each task corresponds to a task segment;

[0082] The BOLD signal is preprocessed to obtain a group level BOLD signal and an individual level BOLD signal;

[0083] extracting the time series of the BOLD signal of each of the brain cortex vertices in each of the task segments at the group level and the individual level, to obtain the original vector of each of the task segments at the group level and the individual level;

[0084] normalizing the original vectors corresponding to the group level and the individual level respectively to obtain the unit spherical vectors corresponding to the group level and the individual level respectively, and obtaining the group level unit spherical manifold and the individual level unit spherical manifold according to the unit spherical vectors corresponding to all the task segments at the group level and the individual level.

[0085] Specifically, first, all tasks included in the task period are determined according to a preset task design, and each of the tasks corresponds to a task segment. Then, the BOLD signal is preprocessed to obtain the BOLD signal at the group level and the BOLD signal at the individual level. The preprocessing step ensures the consistency of the data in space and time, laying a foundation for subsequent analysis. Next, the time series of the BOLD signal of each of the brain cortex vertices in each of the task segments at the group level and the individual level is extracted, to obtain the original vector of each of the task segments at the group level and the individual level. Finally, the original vectors corresponding to the group level and the individual level respectively are normalized to obtain the unit spherical vectors corresponding to the group level and the individual level respectively, and the group level unit spherical manifold and the individual level unit spherical manifold are obtained according to the unit spherical vectors corresponding to all the task segments at the group level and the individual level. Among them, the group level BOLD signal is the average BOLD signal, so after normalizing the average BOLD signal at the group level, the obtained unit spherical vector is the average unit spherical vector, that is, Figure 2 Figure 2 , , until . The BOLD signal at the individual level is the BOLD signal at the individual level during the task, that is, Figure 2 q1, q2, q3,..., q v。

[0086] In the preferred embodiment of the present application, as shown in Figure 2 According to the task information marked in the task graph of the preset task design at each time point, the entire fMRI scanning sequence can be divided into multiple segments corresponding to each task. In the task-state fMRI analysis, the fMRI segment corresponding to the jth task contains T j frames and V vertices. Let f i represent the real value vector of the BOLD time series of the i th vertex of the cerebral cortex during the j th task. If T j ​​= n + 1, then the BOLD signal f i belongs to the n-dimensional Euclidean space. Since in practical applications, the number of frames f in one fMRI scan is usually in the hundreds to thousands, and the number of voxels V can reach the order of 104 to 105. Therefore, the brain function research based on fMRI faces the complexity challenge brought by the high dimensionality and high coupling of data. In task-induced fMRI research, the mainstream method (such as the general linear model) mainly focuses on the relationship between the change of BOLD signal in the time dimension and the task structure, rather than the absolute signal strength, because the latter is difficult to accurately define physiologically and has limited analytical significance.

[0087] Based on this assumption, in addition to spatial smoothing, the present application also performs normalization preprocessing on the input fMRI time series to eliminate features related to signal amplitude. The normalized BOLD signal is denoted as:

[0088] ;

[0089] where, denotes the vector 2 norm. This processing makes the norm of all equal to 1, meaning that is a point on the unit sphere in n-dimensional space. The unit n-dimensional sphere refers to the set of all points in Euclidean space with a distance of 1 from the origin. Thus, the set of normalized BOLD signals of all vertices of the cerebral cortex is a subset of the n-dimensional unit sphere . Based on the geometric interpretation, it is possible to apply differential geometry tools in a non-Euclidean framework to analyze the statistical structure of the normalized BOLD signal time series. In addition, the unit sphere is a compact, smooth, and boundaryless Riemannian manifold equipped with a standard metric induced by its embedding in Euclidean space.

[0090] In embodiments of the present application, by mapping the BOLD signal to the unit sphere manifold, the difference in signal strength is eliminated, allowing subsequent analysis to focus on the pattern and dynamic changes of the signal. The normalized unit sphere vector set constitutes the unit sphere manifold, providing a mathematical basis for subsequent distance calculation and manifold learning, improving the accuracy and reliability of modeling, and ensuring accurate capture and analysis of brain function activities.

[0091] Optionally, the distance calculation according to the group-level unit sphere manifold to obtain the distance matrix between each BOLD signal and other BOLD signals includes:

[0092] According to the unit spherical vectors in the group-level unit spherical manifold, a point set of the group-level unit spherical manifold is obtained, wherein each unit spherical vector corresponds to a point in the point set;

[0093] A spherical distance between any two points in the point set is calculated by measuring the geodesic distance of the unit spherical vectors corresponding to the two points respectively.

[0094] The distance matrix is obtained by arranging the spherical distances between each point and other points in the point set.

[0095] Specifically, the fMRI data is composed of BOLD signals, which is time-series data with high spatial and temporal resolution. This high-resolution characteristic provides rich information and accurate analysis capability for brain function research, but also brings significant data high-dimensional challenges. In most natural task states, the physiological activity of the brain is triggered by limited specific stimulus conditions, which means that complex brain function dynamics can be described by a set of low-dimensional latent variables. To better represent the cross-subject cortical functional structure, first, according to the unit spherical vectors in the group-level unit spherical manifold, a point set of the group-level unit spherical manifold is obtained, wherein each unit spherical vector corresponds to a point in the point set, and the complex high-dimensional data is simplified into a set of points, which provides a basis for subsequent distance calculation. Next, by measuring the geodesic distance of the unit spherical vectors corresponding to any two points in the point set respectively, the spherical distance between the two points is obtained. Geodesic distance measurement is a geometric calculation method based on the unit sphere, which can accurately reflect the actual distance between two points on the sphere. Finally, the spherical distances between each point and other points in the point set are arranged to obtain the distance matrix. The distance matrix comprehensively quantifies the nonlinear relationship between brain regions, providing a key quantitative basis for subsequent manifold learning dimension reduction and functional neighborhood assignment.

[0096] In the embodiment of the present application, the geodesic distance measurement accurately captures the nonlinear relationship between BOLD signals, ensuring the accuracy and reliability of the distance matrix, not only reflecting the similarity between the brain cortex vertices, but also providing a quantitative basis for subsequent functional neighborhood assignment and average signal calculation, thereby improving the accuracy and efficiency of the entire modeling method.

[0097] Optionally, the manifold learning dimension reduction processing of the group-level unit spherical manifold according to the distance matrix to obtain a low-dimensional embedded manifold comprises:

[0098] An adjacency graph of the point set is constructed according to the distance matrix by a manifold learning algorithm.

[0099] According to the adjacency graph, obtain the fuzzy topological structure of the set of horizontal unit sphere manifolds;

[0100] According to the fuzzy topological structure, perform low-dimensional coordinate optimization to determine the Euclidean distance distribution of the point set in the target low-dimensional space;

[0101] According to the Euclidean distance distribution, generate the low-dimensional embedded manifold with a dimension lower than the set of horizontal unit sphere manifolds.

[0102] Specifically, first, an adjacency graph of the point set is constructed according to the distance matrix through a manifold learning algorithm. The construction of the adjacency graph is based on the similarity between each point in the point set, reflecting the local topological structure of the data. Next, according to the adjacency graph, the fuzzy topological structure of the set of horizontal unit sphere manifolds is obtained, which further characterizes the overall topological features of the data and provides a basis for low-dimensional embedding. Then, according to the fuzzy topological structure, low-dimensional coordinate optimization is performed to determine the Euclidean distance distribution of the point set in the target low-dimensional space. The goal of low-dimensional coordinate optimization is to make the distance between points in the low-dimensional embedded manifold as close as possible to the topological structure in the original high-dimensional space. Finally, according to the Euclidean distance distribution, the low-dimensional embedded manifold with a dimension lower than the set of horizontal unit sphere manifolds is generated. The low-dimensional embedded manifold not only reduces the dimension of the data, but also retains the key structural information of the data, making subsequent analysis more efficient and accurate. This step is performed at the group level, meaning it is cross-subject, reflecting the integrated results of multiple subject data.

[0103] In a preferred embodiment of the present application, the present application averages and time-normalizes the task-evoked BOLD signals of multiple subjects at each cortical vertex, and then applies a manifold learning method (Uniform Manifold Approximation and Projection-UMAP) to the set to discover the underlying low-dimensional structure in the normalized activation patterns. It should be noted that, due to Located in the curvature space, operations such as interpolation, averaging and statistical modeling must respect the properties of spherical geometry. If linear Euclidean operations are directly applied on the manifold, the results may deviate from the manifold and cannot accurately characterize the intrinsic structure of the normalized BOLD signal space. Therefore, UMAP uses the pair-wise distance matrix calculated from the geodesic distance on the set of horizontal unit sphere manifolds to perform dimensionality reduction analysis, thereby ensuring that the angular relationships between normalized BOLD signals are faithfully preserved. UMAP constructs a nearest neighbor-based manifold that is based on the number of neighbors (hyperparameter n rThe algorithm constructs an adjacency graph of the brain cortex and estimates a fuzzy topology reflecting the local relationship between vertices. Then, the algorithm optimizes a low-dimensional embedding space using the geodesic distance metric on the sphere, so that the point relationship in the space can best maintain the above topology. The final embedding point set forms a point cloud structure in the three-dimensional Euclidean space, reflecting the manifold structure of the whole brain cortex BOLD signal. The learned manifold not only maintains the structural adjacency between adjacent vertices of the cortex, but also reveals the functional proximity between distant brain regions, thereby jointly modeling the local and non-local functional relationships in a way with geometric perception ability.

[0104] In the embodiments of the present application, by constructing the adjacency graph and the fuzzy topology, this step can accurately capture the local and global features of the data, providing a solid foundation for subsequent functional neighborhood allocation and average signal calculation. The generation of low-dimensional embedding manifold not only improves the computational efficiency, but also enhances the interpretability and robustness of the model, making the subsequent analysis more efficient and accurate.

[0105] Optionally, the functional neighborhood is allocated to each brain cortex vertex according to the low-dimensional embedding manifold, comprising:

[0106] According to the low-dimensional embedding manifold at the group level, a low-dimensional coordinate corresponding to each brain cortex vertex is determined;

[0107] A plurality of other brain cortex vertices closest to the brain cortex vertex in the individual level unit sphere manifold are determined by K-nearest neighbor algorithm with the low-dimensional coordinate corresponding to each brain cortex vertex as the center;

[0108] According to a plurality of other brain cortex vertices, a vertex set of the functional neighborhood is obtained;

[0109] The vertex set is mapped back to the individual level unit sphere manifold to obtain the functional neighborhood of each brain cortex vertex.

[0110] Specifically, first, in the individual level, a low-dimensional coordinate corresponding to each of the brain cortex vertices is determined according to the low-dimensional embedding manifold. The low-dimensional embedding manifold is obtained through manifold learning dimension reduction processing, which retains the key structure and topological information of the data. Then, taking the low-dimensional coordinate corresponding to each of the brain cortex vertices as the center, a plurality of other brain cortex vertices closest to the brain cortex vertex are determined through the K-Nearest Neighbor algorithm. The K-Nearest Neighbor algorithm is a distance-based clustering method, which can effectively identify local features in the data. Then, according to the plurality of other brain cortex vertices closest to the current vertex, a vertex set of the functional neighborhood is formed. The vertex set represents the brain cortex vertices with similar features to the current vertex in the low-dimensional embedding manifold. Finally, the vertex set is mapped back to the individual level unit sphere manifold to obtain the functional neighborhood, which not only ensures that the determination of the functional neighborhood is based on the reduced data, but also reflects the geometric structure in the original data.

[0111] In the preferred embodiment of the present application, it is assumed that the coordinate of the currently processed brain cortex vertex A in the low-dimensional embedding manifold is and all other brain cortex vertices also have their own coordinates in this low-dimensional space. The K-Nearest Neighbor algorithm calculates the Euclidean distance between vertex A and each other vertex, for example, the coordinate of vertex B is and the distance between the two is:

[0112] ;

[0113] The algorithm selects the k vertices closest to vertex A according to these distance values, and these k vertices constitute the neighborhood set of the functional neighborhood of vertex A. For example, if k=5 is selected, the five vertices closest to vertex A will be identified as the neighborhood vertices with strong functional association with A. In this way, the K-Nearest Neighbor algorithm accurately locates the other vertices in the functional neighborhood of each brain cortex vertex, thereby supporting subsequent synchronization measurement analysis and ensuring that the analysis results accurately reflect the functional connection patterns between brain regions. In actual operation, the selection of k value needs to consider the local sensitivity and topological stability, for example, small k value is beneficial to capture local features but may be affected by noise, and large k value provides global stability but may blur local details.

[0114] In the embodiment of the present application, the plurality of other brain cortex vertices determined by the K-Nearest Neighbor algorithm can reflect the similarity and correlation between the brain cortex vertices. Mapping the vertex set back to the individual level unit sphere manifold further ensures that the determination of the functional neighborhood is consistent with the geometric structure of the original data.

[0115] Optionally, the determination of the average signal corresponding to the functional neighborhood from the individual level unit sphere manifold according to the functional neighborhood of each of the brain cortex vertices comprises:

[0116] extracting the functional neighborhood of each of the brain cortex vertices to obtain a unit sphere vector set corresponding to the functional neighborhood;

[0117] iteratively solving all the unit sphere vectors in the unit sphere vector set by a Riemann center of mass rule to obtain a Karcher mean signal of the functional neighborhood;

[0118] iteratively converging according to the Karcher mean signal of the functional neighborhood to obtain the mean signal corresponding to the functional neighborhood.

[0119] Specifically, unlike the traditional general linear model which models the BOLD signal as the convolution of the task event and the fixed HRF function, the present application describes the functional synchrony through the consistency of the BOLD signal trajectory in the neighborhood at the individual level. When a vertex is activated under task stimulation, its BOLD signal should show higher synchrony with the signals of other vertices in its spatial neighborhood, while the non-activated region lacks such consistency. On the learned low-dimensional embedding manifold, the BOLD signal usually shows spatial clustering due to functional partitioning and structural connectivity. In order to extract this local synchrony, first, the functional neighborhood of each of the brain cortex vertices is extracted to obtain a unit sphere vector set corresponding to the functional neighborhood, which ensures that the subsequent calculation is based on the correct data set; Next, all the unit sphere vectors in the unit sphere vector set are iteratively solved by the Riemann center of mass rule to obtain the Karcher mean signal of the functional neighborhood. Karcher mean signal is a method for calculating the average value on the Riemann manifold, which can effectively reflect the central tendency of the signals in the functional neighborhood; Finally, according to the Karcher mean signal of the functional neighborhood, the mean signal corresponding to the functional neighborhood is obtained by iterative convergence, which represents the common activation pattern of the brain regions in the functional neighborhood and provides a basis for the subsequent synchrony measurement.

[0120] In the embodiments of the present application, the average signal of the functional neighborhood is calculated to provide a key quantitative indicator for modeling brain function activity. The introduction of the Karcher mean signal enables accurate calculation of the average signal in non-Euclidean space, which is more suitable for processing vector data on the sphere than the traditional Euclidean average. This step not only improves the accuracy of modeling, but also enhances the ability of the model to capture the complexity of brain function activity. Through the iterative convergence process, the stability and reliability of the average signal are ensured, which lays a solid foundation for the subsequent synchrony measurement and generation of functional activation atlas.

[0121] Optionally, the determination of the local synchrony measure of each of the brain cortex vertices according to the mean signal comprises:

[0122] Geodesic calculations are performed on each point in the individual horizontal unit spherical manifold to obtain the geodesic distance between the unit spherical vector corresponding to each point and the average signal corresponding to the unit spherical vector;

[0123] Based on the geodesic distance, a geodesic distance synchronization index is constructed, wherein the geodesic distance synchronization index includes the activation direction and local synchronization intensity of the cortical vertex and other cortical vertices in the functional neighborhood corresponding to the cortical vertex in the time dimension.

[0124] The geodesic distance synchronization index is used as the measure of local synchronization at the vertices of the cerebral cortex.

[0125] Specifically, by accurately calculating the geodesic distance between each unit spherical vector and the average signal, the degree of difference between them on the sphere can be quantified. Subsequently, based on the geodesic distance, a geodesic distance synchronicity index is constructed, which integrates the activation direction and local synchronization intensity information of cortical vertices and other vertices within their functional neighborhoods in the time dimension. Finally, the constructed geodesic distance synchronicity index is used as a measure of the local synchronicity of cortical vertices, providing crucial data support for the subsequent generation of functional activation maps, enabling the model to accurately capture and reflect the detailed features of brain functional activity. In a preferred embodiment of the invention, firstly, the neighborhood signal set of each vertex... Calculate the Karcher average signal This serves as the representative trajectory for that neighborhood. Subsequently, a geodesic distance-based synchronization metric (GDSM) is constructed, as follows:

[0126] ;

[0127] in, Represents a vector consisting entirely of 1s. For Riemannian manifold The geodesic distance defined above, The total activation direction of this trajectory is given by the set of signals from each vertex i and its neighborhood. Its GDSM value is denoted as k is the neighborhood index. This is the Karcher average signal.

[0128] The above calculation formula is divided into two parts:

[0129] The first part represents the local synchronicity strength, which is a reciprocal form of the average geodesic distance. It measures the "unity" among the neighborhood signals of vertex i. Neighborhood set : denotes the set of neighbors of vertex i (e.g. the 36 closest vertices to it). : denotes the normalized BOLD signal of vertex i. : denotes the set of neighbors of vertex i : denotes the Karcher mean signal of all BOLD signals in the set of neighbors : can be understood as the "central tendency" of the neighbor signals. : is the geodesic distance on the unit sphere : is used to measure the similarity between signals. If the neighbor signals are very consistent, then the distance mean is close, the denominator is small, and the GDSM is large, indicating strong synchrony.

[0130] : is the second part of the equation, representing the activation direction. : is the normalized BOLD signal of vertex i : is summed over all time points, and the sign function : determines whether the sum is positive or negative. If it is positive, the result is +1 (positive), indicating that the average signal in this region is "activating"; if it is negative, the result is -1 (negative), indicating an "inhibitory" response, such as a general decrease in signal or a trough. This term allows the synchrony index to distinguish between "activating synchrony" and "inhibitory synchrony", providing neuroscientific significance for subsequent interpretation.

[0131] : is the second part of the equation, representing the activation direction. : is the normalized BOLD signal of vertex i : is summed over all time points, and the sign function k : determines whether the sum is positive or negative. If it is positive, the result is +1 (positive), indicating that the average signal in this region is "activating"; if it is negative, the result is -1 (negative), indicating an "inhibitory" response, such as a general decrease in signal or a trough. This term allows the synchrony index to distinguish between "activating synchrony" and "inhibitory synchrony", providing neuroscientific significance for subsequent interpretation. : is the second part of the equation, representing the activation direction.

[0132] : is the normalized BOLD signal of vertex i : is summed over all time points, and the sign function : determines whether the sum is positive or negative. If it is positive, the result is +1 (positive), indicating that the average signal in this region is "activating"; if it is negative, the result is -1 (negative), indicating an "inhibitory" response, such as a general decrease in signal or a trough. This term allows the synchrony index to distinguish between "activating synchrony" and "inhibitory synchrony", providing neuroscientific significance for subsequent interpretation. : is the second part of the equation, representing the activation direction. : is the normalized BOLD signal of vertex i

[0133] : is summed over all time points, and the sign function : determines whether the sum is positive or negative. If it is positive, the result is +1 (positive), indicating that the average signal in this region is "activating"; if it is negative, the result is -1 (negative), indicating an "inhibitory" response, such as a general decrease in signal or a trough. This term allows the synchrony index to distinguish between "activating synchrony" and "inhibitory synchrony", providing neuroscientific significance for subsequent interpretation. : is the second part of the equation, representing the activation direction. : is the normalized BOLD signal of vertex i : is summed over all time points, and the sign function : determines whether the sum is positive or negative. If it is positive, the result is +1 (positive), indicating that the average signal in this region is "activating"; if it is negative, the result is -1 (negative), indicating an "inhibitory" response, such as a general decrease in signal or a trough. This term allows the synchrony index to distinguish between "activating synchrony" and "inhibitory synchrony", providing neuroscientific significance for subsequent interpretation. : is the second part of the equation, representing the activation direction. : is the normalized BOLD signal of vertex i

[0134] : is summed over all time points, and the sign function : determines whether the sum is positive or negative. If it is positive, the result is +1 (positive), indicating that the average signal in this region is "activating"; if it is negative, the result is -1 (negative), indicating an "inhibitory" response, such as a general decrease in signal or a trough. This term allows the synchrony index to distinguish between "activating synchrony" and "inhibitory synchrony", providing neuroscientific significance for subsequent interpretation. : is the second part of the equation, representing the activation direction. : is the normalized BOLD signal of vertex i : is summed over all time points, and the sign function

[0135] : determines whether the sum is positive or negative. If it is positive, the result is +1 (positive), indicating that the average signal in this region is "activating"; if it is negative, the result is -1 (negative), indicating an "inhibitory" response, such as a general decrease in signal or a trough. This term allows the synchrony index to distinguish between "activating synchrony" and "inhibitory synchrony", providing neuroscientific significance for subsequent interpretation.Fourthly, the normalized BOLD signal of the vertex i left-multiply the transposed all-1 vector 1 T The result will be a scalar value, and then take the sign of this scalar value, that is This term represents the activation or inhibition discriminant sign of the signal, and then multiplied by the result obtained in the third step, that is, the final GDSM value of the i-th vertex.

[0136] In the embodiment of the present application, by quantifying the synchrony between the brain cortex vertices, not only the understanding of the brain function activity mechanism is deepened, but also a solid and reliable data foundation for subsequent functional activation atlas generation is laid, which helps to reveal the functional characteristics and activity patterns of the brain in different task states more deeply.

[0137] Optionally, the obtaining of the relevant functional activation atlas of the brain cortex during the task cycle according to the local synchrony metrics of all the brain cortex vertices comprises:

[0138] mapping the local synchrony metric of each brain cortex vertex to the brain cortex spatial coordinate corresponding to the brain cortex vertex;

[0139] generating a vertex-level synchrony value field of the brain cortex according to the brain cortex spatial coordinates of all the brain cortex vertices;

[0140] encoding the vertex-level synchrony value field to obtain a visualization layer of the brain cortex;

[0141] superimposing the visualization layer to a preset standard brain cortex template to obtain the relevant functional activation atlas of the brain cortex during the task cycle.

[0142] Specifically, first, the local synchrony measure of each brain cortex vertex is mapped to the corresponding brain cortex spatial coordinate. This step ensures that the synchrony measure of each vertex is associated with its actual position on the brain cortex. Next, based on the spatial coordinates of all vertices and their corresponding synchrony measures, a vertex-level synchrony value field is generated. The vertex-level synchrony value field is a data structure that records the synchrony measure value of each position on the brain cortex. Subsequently, the vertex-level synchrony value field is encoded to generate a visualization layer. The visualization layer visually demonstrates the degree of synchrony in different regions of the brain cortex through color or intensity encoding. Finally, the visualization layer is superimposed on the preset standard brain cortex template to generate the final functional activation map. This map presents the functional activity pattern of the brain cortex during the task period in an intuitive way. In the preferred embodiment of the present application, the synchrony measure can be calculated for all vertices in the whole brain, forming a task-related functional activation map on the brain cortex. This map not only contains traditional activation regions, but also reveals regions with nonlinear and asymmetric responses, such as signal delay, adaptive weakening, down-regulation, etc., providing a more comprehensive reflection of the real functional response of the brain.

[0143] In the embodiment of the present application, by mapping the local synchrony measure to the brain cortex spatial coordinate and generating a visualization layer, the intuitive display of brain functional activity is achieved. This method not only captures the synchrony differences between brain cortex vertices, but also enhances the readability of the map through color coding. Superimposing the visualization layer on the standard brain template makes it possible to compare results between different studies, and also facilitates the combination with existing neuroanatomical knowledge.

[0144] In summary, in combination with Figure 2 As shown in FIG. 6, in the group-level process, first, the fMRI data of N subjects is preprocessed to obtain the preprocessed BOLD signal. These data include the time series BOLD signal of each brain cortex vertex during the task period. Next, according to the task design, the task period is divided into multiple task segments, such as task1 and task2, and the BOLD signal corresponding to each task segment is mapped to the group-level unit sphere manifold. The signal of each subject is averaged to obtain the group-level averaged BOLD signal, and then normalized to obtain the unit sphere vector q i . Subsequently, using these unit sphere vectors, the geodesic distance between any two points in the point set of the group-level unit sphere manifold is calculated to construct a distance matrix. Through manifold learning dimension reduction by UMAP algorithm, a low-dimensional embedded manifold I k(i), which is represented in a low-dimensional space R³. Finally, the local synchrony measure GDSM for each brain cortex vertex is calculated by finding the Karcher mean signal on the low-dimensional manifold embedding through the KNN algorithm. In the individual level procedure, the BOLD signals of each subject are preprocessed similarly, then divided into segments according to the task start and end time, and normalized. The individual level BOLD signals are mapped to the individual level unit sphere manifold to obtain the unit sphere vector q i Unlike the group level procedure, the individual level analysis focuses on the unique neural activity pattern of each subject. At the individual level, the individual level functional neighborhood is determined by calculating the Karcher mean of the BOLD signals within the neighborhood of each vertex. Then, the local synchrony measure GDSM is calculated based on the geodesic distance, which reflects the synchrony of neural activity of the individual in a specific task segment. Finally, the local synchrony measures of all subjects are integrated to generate the individual functional activation map, revealing the spatial distribution of brain function activity of the individual during the task period. The parameters involved in this procedure include the number of subjects N, the number of vertices V, the time frame T, the number of tasks J, and the normalized unit sphere vectors q i and q v , as well as the point coordinates z i (i) in the low-dimensional embedding manifold.

[0145] According to the embodiment shown in Figure 3 , a brain function activity nonlinear modeling system of the present application comprises:

[0146] A data acquisition module is configured to acquire fMRI data of the brain cortex during a task period, wherein the fMRI data includes BOLD signals of each brain cortex vertex in the brain cortex at each time frame during the task period.

[0147] A task segmentation and mapping module is configured to divide the BOLD signals into multiple task segments, and map the BOLD signals corresponding to each task segment to a group level unit sphere manifold and an individual level unit sphere manifold, respectively.

[0148] A distance calculation module is configured to calculate distances based on the group level unit sphere manifold to obtain a distance matrix between each BOLD signal and other BOLD signals.

[0149] A manifold dimension reduction and neighborhood assignment module is configured to perform manifold learning dimension reduction processing on the group level unit sphere manifold based on the distance matrix to obtain a low-dimensional embedding manifold, and assign a functional neighborhood to each brain cortex vertex based on the low-dimensional embedding manifold.

[0150] an average signal calculation module configured to determine an average signal corresponding to the functional neighborhood of each of the brain cortex vertices from the individual level unit sphere manifold according to the functional neighborhood of each of the brain cortex vertices;

[0151] a local synchrony measure module configured to determine a local synchrony measure of each of the brain cortex vertices according to the average signal;

[0152] a graph generation module configured to obtain a relevant functional activation graph of the brain cortex during the task cycle according to the local synchrony measure of all the brain cortex vertices.

[0153] The brain function activity nonlinear modeling system of the present application has the same advantages as the brain function activity nonlinear modeling method of the present application, which will not be repeated here.

[0154] The present application also provides a computer readable storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the brain function activity nonlinear modeling method is realized.

[0155] The computer readable storage medium of the present application has the same advantages as the brain function activity nonlinear modeling method of the present application, which will not be repeated here.

[0156] Although the present application is disclosed as above, the protection scope of the present application is not limited to this. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present application, and these changes and modifications will fall within the protection scope of the present application.

Claims

1. A method of nonlinear modeling of brain functional activity, characterized in that, The method comprises the following steps: acquiring fMRI data of brain cortex in a task cycle, the fMRI data comprising BOLD signals of each vertex of the brain cortex in each time frame in the task cycle; dividing the BOLD signals into a plurality of task segments, and mapping the BOLD signals corresponding to each task segment into a group-level unit spherical manifold and an individual-level unit spherical manifold, respectively; performing distance calculation according to the group-level unit spherical manifold to obtain a distance matrix between each BOLD signal and other BOLD signals; performing manifold learning dimension reduction processing on the group-level unit spherical manifold according to the distance matrix to obtain a low-dimensional embedded manifold, and assigning a functional neighborhood to each vertex of the brain cortex according to the low-dimensional embedded manifold; determining average signals corresponding to the functional neighborhood from the individual-level unit spherical manifold according to the functional neighborhood of each vertex of the brain cortex; determining a local synchrony metric of each vertex of the brain cortex according to the average signals; obtaining a relevant functional activation atlas of the brain cortex in the task cycle according to the local synchrony metrics of all vertices of the brain cortex.

2. The method of nonlinear modeling of brain functional activity according to claim 1, characterized in that, The method comprises the following steps: determining all tasks included in the task cycle according to a preset task design, each task corresponding to a task segment; preprocessing the BOLD signals to obtain group-level BOLD signals and individual-level BOLD signals; extracting time series of the BOLD signals of each vertex of the brain cortex in each task segment at the group level and the individual level to obtain original vectors of each task segment at the group level and the individual level; performing normalization processing on the original vectors corresponding to the group level and the individual level, respectively, to obtain unit spherical vectors corresponding to the group level and the individual level, respectively, and obtaining the group-level unit spherical manifold and the individual-level unit spherical manifold according to the unit spherical vectors corresponding to all task segments at the group level and the individual level.

3. The method of nonlinear modeling of brain functional activity according to claim 2, characterized in that, The method comprises the following steps: obtaining a point set of the group-level unit spherical manifold according to the unit spherical vectors in the group-level unit spherical manifold, wherein each unit spherical vector corresponds to a point of the point set; calculating the unit spherical vectors corresponding to any two points in the point set by measuring geodesic distance to obtain spherical distance between the two points; arranging the spherical distances between each point and other points in the point set to obtain the distance matrix.

4. The method of nonlinear modeling of brain functional activity according to claim 3, characterized in that, The method comprises the following steps: constructing an adjacency graph of the point set according to the distance matrix by a manifold learning algorithm; According to the adjacency graph, a fuzzy topological structure of the group-level unit sphere manifold is obtained; According to the fuzzy topological structure, low-dimensional coordinate optimization is performed to determine the Euclidean distance distribution of the point set in a target low-dimensional space; According to the Euclidean distance distribution, a low-dimensional embedded manifold with a dimension lower than the group-level unit sphere manifold is generated.

5. The method for nonlinear modeling of brain functional activities according to claim 1, wherein, The assigning of a functional neighborhood to each of the brain cortex vertices according to the low-dimensional embedded manifold of the group level comprises: According to the low-dimensional embedded manifold of the group level, a low-dimensional coordinate corresponding to each of the brain cortex vertices is determined; According to the low-dimensional coordinate corresponding to each of the brain cortex vertices, a plurality of other brain cortex vertices closest to the brain cortex vertex in the individual-level unit sphere manifold are determined by a K-nearest neighbor algorithm; According to the plurality of other brain cortex vertices, a vertex set of the functional neighborhood is obtained; The vertex set is mapped back to the individual-level unit sphere manifold to obtain the functional neighborhood of each of the brain cortex vertices.

6. The method of nonlinear modeling of brain functional activity according to claim 5, characterized in that, The determining of an average signal corresponding to the functional neighborhood from the individual-level unit sphere manifold according to the functional neighborhood of each of the brain cortex vertices comprises: The functional neighborhood of each of the brain cortex vertices is extracted to obtain a unit sphere vector set corresponding to the functional neighborhood; All unit sphere vectors in the unit sphere vector set are iteratively solved by a Riemann center calculation rule to obtain a Karcher average signal of the functional neighborhood; The average signal corresponding to the functional neighborhood is obtained by iterative convergence according to the Karcher average signal of the functional neighborhood.

7. The method of claim 3, wherein the step of nonlinear modeling of brain functional activities is characterized by, The determining of a local synchrony measure of each of the brain cortex vertices according to the average signal comprises: Geodesic line calculation is performed on each point in the individual-level unit sphere manifold to obtain a geodesic distance between a unit sphere vector corresponding to each point and the average signal corresponding to the unit sphere vector; A geodesic line distance synchrony index is constructed according to the geodesic distance, wherein the geodesic line distance synchrony index comprises an activation direction and a local synchrony strength of the brain cortex vertex and other brain cortex vertices in the functional neighborhood of the brain cortex vertex in a time dimension; The geodesic line distance synchrony index is taken as the local synchrony measure of the brain cortex vertex.

8. The method of nonlinear modeling of brain functional activity according to claim 7, characterized in that, The obtaining of a relevant functional activation atlas of the brain cortex in the task cycle according to the local synchrony measures of all the brain cortex vertices comprises: The local synchrony measure of each of the brain cortex vertices is mapped to a brain cortex spatial coordinate corresponding to the brain cortex vertex; A vertex-level synchrony value field of the brain cortex is generated according to the brain cortex spatial coordinates of all the brain cortex vertices; An encoding process is performed on the vertex-level synchrony value field to obtain a visualization layer of the brain cortex; The visualization layer is superimposed on a preset standard brain cortex template to obtain the relevant functional activation atlas of the brain cortex in the task cycle.

9. A system for nonlinear modeling of brain functional activity, characterized by The method comprises: a data acquisition module configured to acquire fMRI data of a brain cortex in a task period, the fMRI data comprising a BOLD signal of each vertex of the brain cortex in each time frame in the task period; a task segmentation and mapping module configured to divide the BOLD signal into a plurality of task segments, and map the BOLD signal corresponding to each of the task segments into a group-level unit sphere manifold and an individual-level unit sphere manifold, respectively; a distance calculation module configured to perform distance calculation according to the group-level unit sphere manifold, to obtain a distance matrix between each of the BOLD signal and other BOLD signals; a manifold dimension reduction and neighborhood assignment module configured to perform manifold learning dimension reduction processing on the group-level unit sphere manifold according to the distance matrix, to obtain a low-dimensional embedded manifold, and assign a functional neighborhood for each of the vertices of the brain cortex according to the low-dimensional embedded manifold; an average signal calculation module configured to determine an average signal corresponding to the functional neighborhood from the individual-level unit sphere manifold according to the functional neighborhood of each of the vertices of the brain cortex; a local synchrony measure module configured to determine a local synchrony measure of each of the vertices of the brain cortex according to the average signal; a map generation module configured to obtain a related functional activation map of the brain cortex in the task period according to the local synchrony measure of all of the vertices of the brain cortex.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by a processor to implement the brain function activity nonlinear modeling method in any one of claims 1-8.

Images