A single-sample network method and system for fMRI brain functional connectivity analysis

Abstract

The application provides a single-sample network method and system for fMRI brain function connection analysis, and belongs to the field of fMRI data community division algorithms, and comprises the following steps: preprocessing an initial fMRI data set; dividing brain regions of the preprocessed fMRI data set; obtaining a brain region average correlation matrix of a healthy control group, calculating a difference correlation matrix of each sample in a disease group relative to the healthy control group sample, and then obtaining a binary single-sample correlation matrix of each sample in the disease group to construct a single-sample network of each sample in the disease group; performing community division on the single-sample network to obtain a brain region co-community probability matrix of the disease group sample; performing significance test on the brain region co-community probability matrix to retain brain region pairs with a co-community probability greater than random allocation; performing functional enrichment on the retained brain region pairs to extract significant change brain region connections related to the disease. The application can reduce the influence of individual differences, retain component differences, and accurately extract significant change brain region connections related to the disease.

Description

Technical Field

[0001] The present invention belongs to the field of fMRI data community partitioning algorithms, and specifically relates to a single-sample network method and system for fMRI brain functional connectivity analysis. Background Art

[0002] The human brain is a complex structure composed of distinct regions. Each region, or brain area, has its own mission and function. When studying the relationships between brain regions, the biological connections between them are known as structural connectivity. Functional magnetic resonance imaging (fMRI) is a type of magnetic resonance imaging (MRI) based on the blood oxygen level-dependent (BOLD) signal. As early as the 1990s, researchers discovered that brain activation could be detected based on changes in the BOLD signal. With the study of BOLD signal correlations between different brain regions, the degree of temporal correlation generated by the time series of BOLD signals in different brain regions has been termed "functional connectivity," which is distinct from structural connectivity. Functional connectivity is defined as the temporal dependence of neuronal activation patterns in anatomically separate brain regions. It attempts to establish a link between two spatial regions of interest using linear temporal correlation. fMRI is an effective method for mapping functional brain regions in vivo, integrating functional, imaging, and anatomical techniques. It offers numerous advantages, including being non-invasive, non-radioactive, with high temporal and spatial resolution, and the ability to perform multiple repetitive procedures. Therefore, in recent years, it has been widely used in the study of functional connections between brain regions and in revealing functional connectivity changes related to the development of brain diseases and the diagnosis of brain degenerative diseases.

[0003] In neuroscience, graph theory is applied to mathematically model the complex functional networks within the human brain. These networks are interconnected and connected across brain regions and subregions, and the dynamic connections between these networks form a larger single network. Graph theory methods primarily study the relationships between nodes and edges. Calculating correlation coefficients involves calculating the correlation between BOLD signals between brain regions, transforming resting-state fMRI data into a functional network of nodes and edges. This allows for the application of graph theory to analyze brain functional networks. Calculating correlation coefficients can reveal interactions between brain regions. Furthermore, the magnitude and changes in the correlation coefficient can be used to characterize changes in functional connectivity between regions, making it a crucial research topic in fMRI data analysis. Functional connectivity between regions within functional brain networks is believed to underlie higher cognitive functions and neurodegenerative diseases. Therefore, calculating correlation coefficients not only accurately reflects functional connections between brain regions but also plays a crucial role in brain disease research.

[0004] Although the correlation coefficient method provides an effective statistical tool for analyzing correlations between two brain regions, it is not specifically designed for fMRI data. Directly acquired fMRI image data exhibits individual variability. During data collection, even under the same experimental conditions, subjects react differently to the stimulus used for data collection. Furthermore, differences in patient constitutions can lead to individual variations in the collected data. This results in low stability and accuracy when directly applying the correlation coefficient method to fMRI data, making it incapable of measuring changes in functional connectivity across brain regions. Therefore, a new method is needed that can mitigate the influence of individual differences, preserve intergroup differences, and accurately extract disease-related functional connectivity changes and related functional modules. Summary of the Invention

[0005] The purpose of this invention is to propose a single-sample network method and system for fMRI brain functional connectivity analysis, which can reduce the influence of individual differences, retain component differences, and accurately extract brain region connections with significant changes related to diseases.

[0006] The present invention is achieved through the following technical solutions:

[0007] A single-sample network method for fMRI brain functional connectivity analysis includes the following steps:

[0008] Step S1, preprocessing the initial fMRI dataset to obtain a noise-reduced and spatially normalized fMRI dataset, wherein the preprocessed fMRI dataset includes samples from a healthy control group and samples from a disease group;

[0009] Step S2: dividing the preprocessed fMRI dataset into brain regions according to the standardized brain region atlas to obtain multiple brain regions and the BOLD signal of each brain region;

[0010] Step S3: obtaining the average correlation matrix of the brain regions of the healthy control group based on the BOLD signals of each brain region corresponding to the samples of the healthy control group, and using the obtained average correlation matrix of the brain regions of the healthy control group to calculate the difference correlation matrix of each sample in the disease group relative to the healthy control group, thereby obtaining the binary single-sample correlation matrix of each sample in the disease group, and constructing a single-sample network for each sample in the disease group using each brain region as a node and the binary single-sample correlation matrix as an adjacency matrix;

[0011] Step S4: performing community division on the single sample network and calculating the brain region common community probability matrix of the disease group samples;

[0012] Step S5: Perform a significance test on the brain region common community probability matrix, and retain brain region pairs with common community probabilities significantly greater than those obtained by random assignment;

[0013] Step S6: Perform functional enrichment on the brain region pairs retained in step S5 to extract brain region connections with significant changes related to the disease.

[0014] Furthermore, in step S1, the preprocessing of the initial fMRI dataset includes temporal layer correction, head motion correction, image registration, segmentation, standard space mapping and denoising.

[0015] Furthermore, in step S2, the fetch_atlas_aal function in the datasets package of Python script is used to divide the preprocessed fMRI dataset into brain regions. The number of brain regions divided for each sample in the preprocessed fMRI dataset is N indivual, N is an integer.

[0016] Furthermore, the step S3 specifically includes the following steps:

[0017] Step S31: According to the formula Obtain healthy control group H The average correlation matrix of brain regions of samples ,in, for Elements, The healthy control group h The BOLD signals of any two brain regions in the sample and The Pearson correlation coefficient between H is the sample size of the healthy control group, ;

[0018] Step S32: According to the formula Get the calculated disease group k The difference correlation matrix of samples relative to the healthy control group ,in, Indicates disease group k The BOLD signals of any two brain regions in the sample and The Pearson correlation coefficient between for Elements of

[0019] Step S33: According to the formula Pair difference correlation matrix conduct z Transformation, to obtain the disease group k The weight matrix of samples, and then according to the formula Calculate disease group kThe binary single sample correlation matrix of samples, where T is a given threshold;

[0020] Step S34: construct the disease group first by taking each brain region as a node and the binary single sample association matrix as an adjacency matrix. k Single-sample network ,in, Disease group k The brain region node set of samples, Disease group k The brain region association edge set of samples.

[0021] Furthermore, the step S4 specifically includes the following steps:

[0022] Step S41, according to the disease group k Single-sample network G Calculate the single sample network for each independent community in G The initial modularity of the single-sample network is calculated separately. G The combined modularity of any community in and the communities connected to it, where the initial modularity and the combined modularity are calculated according to the formula calculate, Representing the community C i The sum of the weights of the edges in Representation and Community C i The sum of the weights of all edges connecting the nodes in Represents a single-sample network G The number of middle edges, C represents the set of communities participating in the computation;

[0023] Step S42: Calculate the changes between the initial modularity and each merged modularity, and select the community with the largest modularity change as the C j With the community C i Merge into a new community and update the single sample network G ;

[0024] Step S43: Repeat steps S41 to S42 to continuously divide and merge communities until all brain region nodes are The community to which the user belongs no longer changes;

[0025] Step S44: According to the formula Calculate disease group k Any two brain region nodes of a sample and The co-community probability matrix ,in, f Divide the number of times for the community, p The total number of communities.

[0026] Furthermore, in step S1, the disease group samples are classified according to the severity of the disease, and for each severity, they are grouped according to age to obtain multiple sample groups.

[0027] Furthermore, in step S5, according to the formula A significance test was performed on the common community probability matrix, and the brain region pairs with common community probabilities significantly greater than those randomly assigned were retained, among which, t It indicates the probability of the observed sample statistic or a more extreme value occurring when no significant change occurs. and The same pair of brain regions in the sample group with two different severity levels of the disease in the same age group e ij The set of co-community probability values, and Respectively and The mean of express and The variance of the joint estimate, and Respectively and The variance of n 1 and n 2 respectively represent and The number of samples.

[0028] Furthermore, in step S6, Fisher's exact test is performed on the brain region pairs retained in step S5 to extract brain region connections with significant changes related to the disease.

[0029] The present invention is also achieved through the following technical solutions:

[0030] A single-sample network system for fMRI brain functional connectivity analysis, comprising:

[0031] Preprocessing module: used to preprocess the initial fMRI dataset to obtain a noise-reduced and spatially normalized fMRI dataset. The preprocessed fMRI dataset contains samples from the healthy control group and the disease group.

[0032] BOLD signal analysis module: used to divide the pre-processed fMRI dataset into brain regions according to the standardized brain region atlas, and obtain multiple brain regions and the BOLD signal of each brain region;

[0033] Single-sample network acquisition module: used to obtain the average correlation matrix of the healthy control group brain regions based on the BOLD signals of each brain region corresponding to the healthy control group samples, and use the obtained average correlation matrix of the healthy control group brain regions to calculate the difference correlation matrix of each sample in the disease group relative to the healthy control group samples, and then obtain the binary single-sample correlation matrix of each sample in the disease group. Each brain region is used as a node and the binary single-sample correlation matrix is ​​used as the adjacency matrix to construct the single-sample network of each sample in the disease group;

[0034] Common community probability matrix acquisition module: used to divide the single sample network into communities and calculate the brain region common community probability matrix of disease group samples;

[0035] Data verification module: used to perform significance testing on the brain region co-community probability matrix, and retain brain region pairs with co-community probabilities significantly greater than random assignment;

[0036] Functional connectivity analysis module: used to perform functional enrichment on the brain region pairs retained in step S5 and extract brain region connections with significant changes related to the disease.

[0037] The present invention has the following beneficial effects:

[0038] The application firstly pre-processes an initial fMRI data set to obtain a pre-processed fMRI data set containing healthy control group samples and disease group samples, and divides the brain regions of the pre-processed fMRI data set according to a standardized brain region map to obtain a plurality of brain regions and BOLD signals of each brain region. Next, the average correlation matrix of the brain regions corresponding to the healthy control group samples is obtained according to the BOLD signals of each brain region of the healthy control group samples, and the difference correlation matrix of each sample in the disease group relative to the healthy control group samples is calculated by using the obtained average correlation matrix of the brain regions of the healthy control group, and then the binary single-sample correlation matrix of each sample in the disease group is obtained. Each brain region is taken as a node, and the binary single-sample correlation matrix is taken as an adjacency matrix to construct a single-sample network of each sample in the disease group. Then, the single-sample network is community divided to calculate the brain region co-community probability matrix of the disease group samples, and the brain region co-community probability matrix is subjected to significance test to retain brain region pairs with significantly greater co-community probability than random allocation. Finally, the function enrichment of the retained brain region pairs is performed to extract the significantly changed brain region connections related to the disease. In the process, the difference between the disease samples and the healthy control group in the fMRI data is defined as a constraint term, and a weight matrix is established through mathematical transformation, and the healthy control group is taken as a reference. This method fully reduces the influence of individual differences and retains the differences between groups. This single-sample network calculation method improves the stability of the sample brain network, making the subsequent community division processing result more reliable. In the application, the co-community probability parameter is used instead of the traditional correlation coefficient to measure the brain region functional connection, which improves the accuracy of analyzing the changes in brain region functional connection, so that the subsequent significance test and function enrichment of the co-community probability matrix can fully extract the significantly changed brain region connections related to the disease and the related functional modules. BRIEF DESCRIPTION OF DRAWINGS

[0039] The application will be further described in detail below with reference to the accompanying drawings.

[0040] Figure 1 The flowchart of the application.

[0041] Figure 2 The modularity change of the single-sample network of the application compared with the correlation coefficient network.

[0042] Figure 3 The participation coefficient change of the single-sample network of the application compared with the correlation coefficient network.

[0043] Figure 4 The co-community probability matrix of the disease at different stages of different age groups obtained by the application.

[0044] Figure 5 The distribution of the connection edges with significantly reduced co-community probability in different functional regions of the disease group under different age groups as the disease deepens (EMCI-LMCI-AD). DETAILED DESCRIPTION

[0045] like Figure 1 As shown in Figure 2, the single-sample network method for fMRI brain functional connectivity analysis includes the following steps:

[0046] Step S1, preprocessing the initial fMRI dataset to obtain a noise-reduced and spatially normalized fMRI dataset, wherein the preprocessed fMRI dataset includes samples from a healthy control group and samples from a disease group;

[0047] Specifically, this example uses Alzheimer's disease (AD) as a research case, and the initial fMRI dataset is derived from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database. To investigate changes in brain functional connectivity across age groups, from early mild cognitive impairment (EMCI) to late mild cognitive impairment (LMCI) to Alzheimer's disease (AD), a total of 182 fMRI data samples were selected: 20 healthy control samples (CN) and 162 disease samples. The disease samples were categorized by severity, namely 57 EMCI samples, 55 LMCI samples, and 50 AD samples. For each severity level, the samples were grouped by age: 60-69 years old, 70-79 years old, and 80-89 years old, resulting in multiple sample groups.

[0048] In this embodiment, the initial fMRI dataset is preprocessed using the Matlab toolbox SPM12, specifically including:

[0049] Step S11, time layer correction, eliminating files with distorted imaging, resetting the origin of each retained fMRI image, and using top-down slice time correction to correct the inconsistency of slice imaging time;

[0050] Step S12: head motion correction, correcting motion artifacts caused by the sample participant's head movement during image acquisition in six directions: up and down, left and right, and front and back;

[0051] Step S13: image registration, aligning the weighted structural image and the functional image, wherein the alignment process is conventional;

[0052] Step S14: Segmentation: Segmenting the structural image registered with the functional image into gray matter, white matter, cerebrospinal fluid, bone, and others;

[0053] Step S15: standard space mapping, using affine transformation to map the weighted structural image and functional image to the MNI standard space;

[0054] Step S16: Denoising, using a Gaussian kernel for spatial smoothing to increase the signal-to-noise ratio.

[0055] In this embodiment, the final pre-processed fMRI sample data matrix X is obtained. 91×109×91×140 In this embodiment, the fMRI data is collected by collecting a whole-brain fMRI image every 3 seconds. Therefore, 140 represents the number of time points for data collection, and 91×109×91 represents the size and position of the scanned brain volume.

[0056] Step S2: dividing the preprocessed fMRI dataset into brain regions according to the standardized brain region atlas to obtain multiple brain regions and the BOLD signal of each brain region;

[0057] In this embodiment, the fetch_atlas_aal function in the datasets package of Python script is used to fetch the preprocessed fMRI sample data matrix X 91×109×91×140 Perform brain region division and obtain the BOLD signal time series matrix T 90×140 The number of brain regions divided by each sample in the preprocessed fMRI dataset is N = 90, the BOLD signal of each brain region is obtained by scanning within 140 time points, and the time series matrix T 90×140 Each row represents the BOLD signal of a brain region.

[0058] Step S3: obtaining the average correlation matrix of the brain regions of the healthy control group based on the BOLD signals of each brain region corresponding to the samples of the healthy control group, and using the obtained average correlation matrix of the brain regions of the healthy control group to calculate the difference correlation matrix of each sample in the disease group relative to the healthy control group, thereby obtaining the binary single-sample correlation matrix of each sample in the disease group, and constructing a single-sample network for each sample in the disease group using each brain region as a node and the binary single-sample correlation matrix as an adjacency matrix;

[0059] The specific steps include:

[0060] Step S31: According to the formula Obtain healthy control group H The average correlation matrix of brain regions of samples ,in, for Elements, The healthy control group h In the samples, the BOLD signals of any two brain regions and The Pearson correlation coefficient between H is the sample size of the healthy control group, ;

[0061] Step S32: According to the formula Get the calculated disease group k The difference correlation matrix of samples relative to the healthy control group ,in, Indicates the disease group k In the samples, the BOLD signals of any two brain regions and The Pearson correlation coefficient between for Elements, ;

[0062] Step S33: According to the formula Pair difference correlation matrix conduct z Transformation, to obtain the disease group k The weight matrix of samples, and then according to the formula Calculate disease group k Binarized single sample correlation matrix of samples ,in, T is a given threshold;

[0063] Step S34: construct the disease group first by taking each brain region as a node and the binary single sample association matrix as an adjacency matrix. k Single-sample network ,in, Disease group k The brain region node set of samples, each element is called a node of the graph, Disease group k The brain region association edge set of samples, each element For the sample association network G An internal line from arrive edge.

[0064] Step S4: performing community division on the single sample network and calculating the brain region common community probability matrix of the disease group samples;

[0065] The specific steps include:

[0066] Step S41, according to the disease group k Single-sample network G Calculate the single sample network for each independent community in G The initial modularity of the single-sample network is calculated separately. G Any community in C i and with the community C iThe combined modularity of the connected communities after merging, where the initial modularity and the combined modularity are calculated according to the formula calculate, Representing the community C i The sum of the weights of the edges in Representation and Community C i The sum of the weights of all edges connecting the nodes in Represents a single-sample network G The number of edges, that is, the binary single sample association matrix The number of non-zero elements in , C represents the set of communities participating in the computation;

[0067] Step S42: Calculate the changes between the initial modularity and each merged modularity, and select the community with the largest modularity change as the C j With the community C i Merge into a new community and update the single sample network G ;

[0068] Step S43: Repeat steps S41 to S42 to continuously divide and merge communities until all brain region nodes are The community to which the commu- nity belongs no longer changes, thus G Find the more closely connected sub-networks;

[0069] More specifically, when calculating the initial modularity for the first time, the disease group k Single-sample network G Divided into 90 communities C i , C i correspond V A node in , at this time according to 90 communities C i Calculate the initial modularity, for any community C i , merge all communities connected to this community with this community, and then calculate the corresponding merge modularity of each merge; perform a merged single sample network G It can be divided into 89 communities, and the initial modularity is calculated again based on the 89 communities, and this cycle is repeated until all brain region nodes are The community to which the community belongs no longer changes, that is, all communities are merged into a new community;

[0070] When calculating the initial modularity, the community C iRefers to each community that has not been merged. When calculating the merged modularity, C i Connecting communities C i The community formed after the merger is also called community C i express;

[0071] Step S44: According to the formula Calculate disease group k Any two brain region nodes of a sample and The co-community probability matrix ,in, f Divide the number of times for the community, p For the total number of communities, .

[0072] Step S5: Perform a significance test on the brain region common community probability matrix, and retain brain region pairs with common community probabilities significantly greater than those obtained by random assignment;

[0073] Specifically, according to the formula A significance test was performed on the common community probability matrix, and the brain region pairs with common community probabilities significantly greater than those randomly assigned (i.e., brain region pairs with t < 0.05) were retained. t It indicates the probability of the observed sample statistic or a more extreme value occurring when no significant change occurs (i.e., it is set to true). A lower t-value means that the observed result is very different from the expected result under the null hypothesis. Usually, if the t-value is lower than the predetermined significance level (such as 0.05), the null hypothesis (i.e., a significant change has occurred) will be rejected. and The same pair of brain regions in the sample group with two different severity levels of the disease in the same age group e ij The set of co-community probability values, and Respectively and The mean of express and The variance of the joint estimate, and Respectively and The variance of n 1 and n 2 respectively represent and The number of samples.

[0074] In this embodiment, all samples are divided into 9 different sample groups, and the inter-group significance test is performed on the co-community probability matrix calculated from the samples of different diseases in the same age group , and the co-community probability significantly reduced brain region pair matrix in 3 age groups is obtained P 60 、 P 70 、 P 80 .

[0075] Step S6, function enrichment is performed on the brain region pairs reserved in step S5, and the significantly changed brain region connection related to the disease is extracted;

[0076] Fisher's exact test is performed on the brain region pairs reserved in step S5 to extract the significantly changed brain region connection related to the disease, and the co-community probability significantly reduced brain region pair matrix in this embodiment P 60 、 P 70 、 P 80 is subjected to function enrichment, and the enrichment is performed into seven functional connection networks of the brain, namely, visual network, motor sensory network, dorsal attention network, ventral attention network, edge network, frontal-parietal network, and default mode network. The functional regions with p≤0.05 are reserved as the enrichment results.

[0077] Correspondingly, the single-sample network system for fMRI brain function connection analysis comprises:

[0078] A preprocessing module: used for preprocessing the initial fMRI data set to obtain a denoised and spatially standardized fMRI data set, wherein the fMRI data set after preprocessing comprises healthy control group samples and disease group samples;

[0079] A BOLD signal analysis module: used for dividing the fMRI data set after preprocessing into brain regions according to a standardized brain region map to obtain a plurality of brain regions and BOLD signals of each brain region;

[0080] A single-sample network acquisition module: used for acquiring a healthy control group brain region average correlation matrix according to the BOLD signals of each brain region corresponding to the healthy control group samples, and calculating a difference correlation matrix of each sample in the disease group relative to the healthy control group samples by using the healthy control group brain region average correlation matrix, and then obtaining a binary single-sample correlation matrix of each sample in the disease group, taking each brain region as a node and the binary single-sample correlation matrix as an adjacency matrix, and constructing a single-sample network of each sample in the disease group;

[0081] A co-community probability matrix acquisition module: used for community division of the single-sample network to calculate a brain region co-community probability matrix of the disease group samples;

[0082] Data verification module: used to perform significance testing on the brain region co-community probability matrix, and retain brain region pairs with co-community probabilities significantly greater than random assignment;

[0083] Functional connectivity analysis module: used to perform functional enrichment on the brain region pairs retained in step S5 and extract brain region connections with significant changes related to the disease.

[0084] Figure 2 and Figure 3 It shows that compared with the traditional calculation method of correlation coefficient (Pearson Brain Network), the average modularity (Modularity Q) of the single sample network (Individual Metabolic Brain Network) after community division is improved by about 70%, and the average participation coefficient (Participation Coefficient P) is significantly reduced by 50%, showing obvious performance superiority. Figure 4 and Figure 5 The results of the single-sample network after the subsequent calculation of the co-community probability matrix, the significance test and functional enrichment are shown. Figure 4 It can be seen that there are differences in the distribution of strong functional connections between different age groups and different disease severity. Figure 5 As can be seen from the t-test, within the same age group, different disease groups (EMCI-LMCI-AD) showed different connectivity patterns across seven functional networks with significantly decreased common community probability (p ≤ 0.05) as disease severity increased. Enrichment enabled rapid localization of functional networks affected by disease across age groups. In the 60-year-old group, significantly decreased functional connectivity was concentrated in the sensory-motor network (SMN) and the frontal-parietal network (FN); in the 70-year-old group, significantly decreased functional connectivity was concentrated in the dorsal attention network (DAN); and in the 80-year-old group, significantly decreased functional connectivity was concentrated in the visual network (VIS) and the limbic network (LN). Based on these analysis results, by focusing on enrichment in different functional areas across age groups, patients' disease states can be accurately identified and Alzheimer's disease diagnosed.

[0085] In summary, the present invention improves the traditional method of calculating correlation coefficients. The results show that compared with the traditional method of calculating correlation coefficients, the embodiments of the present invention fully reduce the impact of individual differences on fMRI data, retain inter-group differences, and improve the stability of the sample brain network, making the subsequent community division processing results more reliable. The present invention also provides a new method for defining functional correlations between brain regions through common community probability, replacing the traditional correlation coefficient to measure correlation, improving the accuracy of analyzing changes in functional connectivity between brain regions, so that subsequent significance tests and differential function enrichment can fully extract brain region connections with significant changes related to the disease. Further promote the application of fMRI data in brain neurodegenerative diseases.

[0086] It is worth mentioning that the present invention is not only applicable to the analysis of Alzheimer's disease patient data, but also applicable to other disease patient data, such as Parkinson's disease, etc., which is not limited in this embodiment.

[0087] The above description is merely a preferred embodiment of the present invention and therefore cannot be used to limit the scope of the present invention. In other words, equivalent changes and modifications made according to the scope of the patent application and the contents of the specification should still fall within the scope of the patent of the present invention.

Claims

1. A single-sample network method for fMRI brain functional connectivity analysis, characterized by: The steps include: Step S1, preprocessing the initial fMRI dataset to obtain a noise-reduced and spatially normalized fMRI dataset, wherein the preprocessed fMRI dataset includes samples from a healthy control group and samples from a disease group; Step S2: dividing the preprocessed fMRI dataset into brain regions according to the standardized brain region atlas to obtain multiple brain regions and the BOLD signal of each brain region; Step S3: obtaining the average correlation matrix of the brain regions of the healthy control group based on the BOLD signals of each brain region corresponding to the samples of the healthy control group, and using the obtained average correlation matrix of the brain regions of the healthy control group to calculate the difference correlation matrix of each sample in the disease group relative to the healthy control group, thereby obtaining the binary single-sample correlation matrix of each sample in the disease group, and constructing a single-sample network for each sample in the disease group using each brain region as a node and the binary single-sample correlation matrix as an adjacency matrix; Step S4: performing community division on the single sample network and calculating the brain region common community probability matrix of the disease group samples; Step S5: Perform a significance test on the brain region common community probability matrix, and retain brain region pairs with common community probabilities significantly greater than those obtained by random assignment; Step S6: Perform functional enrichment on the brain region pairs retained in step S5 to extract brain region connections with significant changes related to the disease; The step S3 specifically includes the following steps: Step S31: According to the formula Obtain healthy control group H The average correlation matrix of brain regions of samples ,in, for Elements, The healthy control group h The BOLD signals of any two brain regions in the sample and The Pearson correlation coefficient between H is the sample size of the healthy control group, The number of brain regions divided by each sample in the preprocessed fMRI dataset is N indivual, N is an integer; Step S32: According to the formula Get the calculated disease group k The difference correlation matrix of samples relative to the healthy control group ,in, Indicates disease group k The BOLD signals of any two brain regions in the sample and The Pearson correlation coefficient between for Elements of Step S33: According to the formula Pair difference correlation matrix conduct z Transformation, to obtain the disease group k The weight matrix of samples, and then according to the formula Calculate disease group k The binary single sample correlation matrix of samples, where T is a given threshold; Step S34: construct the disease group first by taking each brain region as a node and the binary single sample association matrix as an adjacency matrix. k Single-sample network ,in, Disease group k The brain region node set of samples, Disease group k The brain region association edge set of samples; The step S4 specifically includes the following steps: Step S41, according to the disease group k Single-sample network G Calculate the single sample network for each independent community in G The initial modularity of the single-sample network is calculated separately. G The combined modularity of any community in and the communities connected to it, where the initial modularity and the combined modularity are calculated according to the formula calculate, Representing the community C i The sum of the weights of the edges in Representation and Community C i The sum of the weights of all edges connecting the nodes in Represents a single-sample network G The number of edges, C represents the set of communities participating in the computation; Step S42: Calculate the changes between the initial modularity and each merged modularity, and select the community with the largest modularity change as the C j With the community C i Merge into a new community and update the single sample network G ; Step S43: Repeat steps S41 to S42 to continuously divide and merge communities until all brain region nodes are The community to which the user belongs no longer changes; Step S44: According to the formula Calculate disease group k Any two brain region nodes of a sample and The co-community probability matrix ,in, f Divide the number of times for the community, p The total number of communities.

2. A single-sample network method for fMRI brain functional connectivity analysis according to claim 1, characterized in that: In step S1, the preprocessing of the initial fMRI dataset includes temporal layer correction, head motion correction, image registration, segmentation, standard space mapping and denoising.

3. The single-sample network method for fMRI brain functional connectivity analysis according to claim 1, characterized in that: In step S2, the fetch_atlas_aal function in the datasets package of Python script is used to perform brain region division on the pre-processed fMRI dataset.

4. A single-sample network method for fMRI brain functional connectivity analysis according to claim 1, 2 or 3, characterized in that: In step S1, the disease group samples are classified according to the severity of the symptoms, and for each severity, they are grouped according to age to obtain multiple sample groups.

5. A single-sample network method for fMRI brain functional connectivity analysis according to claim 1, 2 or 3, characterized in that: In step S5, according to the formula A significance test was performed on the common community probability matrix, and the brain region pairs with common community probabilities significantly greater than those randomly assigned were retained, among which, t It indicates the probability of the observed sample statistic or a more extreme value occurring when no significant change occurs. and The same pair of brain regions in the sample group with two different severity levels of the disease in the same age group e ij The set of co-community probability values, and Respectively and The mean of express and The variance of the joint estimate, and Respectively and The variance of n 1 and n 2 respectively represent and The number of samples.

6. A single-sample network method for fMRI brain functional connectivity analysis according to claim 1, 2 or 3, characterized in that: In step S6, Fisher's exact test is performed on the brain region pairs retained in step S5 to extract brain region connections with significant changes related to the disease.

7. A single-sample network system for fMRI brain functional connectivity analysis, for implementing the single-sample network method for fMRI brain functional connectivity analysis according to any one of claims 1 to 6, characterized in that: include: Preprocessing module: used to preprocess the initial fMRI dataset to obtain a noise-reduced and spatially normalized fMRI dataset. The preprocessed fMRI dataset contains samples from the healthy control group and the disease group. BOLD signal analysis module: used to divide the pre-processed fMRI dataset into brain regions according to the standardized brain region atlas, and obtain multiple brain regions and the BOLD signal of each brain region; Single-sample network acquisition module: used to obtain the average correlation matrix of the healthy control group brain regions based on the BOLD signals of each brain region corresponding to the healthy control group samples, and use the obtained average correlation matrix of the healthy control group brain regions to calculate the difference correlation matrix of each sample in the disease group relative to the healthy control group samples, and then obtain the binary single-sample correlation matrix of each sample in the disease group. Each brain region is used as a node and the binary single-sample correlation matrix is ​​used as the adjacency matrix to construct the single-sample network of each sample in the disease group; Common community probability matrix acquisition module: used to divide the single sample network into communities and calculate the brain region common community probability matrix of disease group samples; Data verification module: used to perform significance testing on the brain region co-community probability matrix, and retain brain region pairs with co-community probabilities significantly greater than random assignment; Functional connectivity analysis module: used to perform functional enrichment on the brain region pairs retained in step S5 and extract brain region connections with significant changes related to the disease.

Images