Brain region morphological feature data processing method and device, equipment and storage medium

Abstract

This application relates to a method, apparatus, device, and storage medium for processing brain region morphological feature data. The method includes: acquiring brain magnetic resonance imaging (MRI) data corresponding to at least two target subjects; obtaining a brain morphological feature difference map based on the brain MRI data; acquiring gene transcription activity level values ​​for each brain region and establishing a first correlation between morphological feature change values ​​and gene transcription activity level values ​​for each brain region; acquiring somatic CAG repeat length data of a first subject and establishing a second correlation between somatic CAG repeat length data and gene transcription activity level values ​​for each brain region; and outputting correlation analysis results of preset brain state labels based on the first and second correlations, thereby enabling precise analysis of the correlation between brain region morphological changes, gene transcription dysregulation, and somatic CAG amplification.

Description

Technical Field

[0001] This application relates to the field of medical image processing technology, and in particular to a method, apparatus, computer device, computer-readable storage medium, and computer program product for processing brain region morphological feature data. Background Technology

[0002] Huntington's disease (HD) is an autosomal dominant neurodegenerative disorder caused by the amplification of the CAG trinucleotide repeat in the HTT gene. The pathology begins with striatal degeneration and progresses to widespread neuronal loss throughout the cerebral cortex, resulting in a complex triad of motor, cognitive, and psychiatric disorders.

[0003] However, the relevant technologies cannot accurately analyze the association between CAG trinucleotide repeat amplification and brain regions, which limits our understanding of the pathogenesis of Huntington's disease. Summary of the Invention

[0004] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for processing brain region morphological feature data that can accurately analyze the relationship between brain region morphological changes, gene transcription disorders, and somatic CAG amplification, in order to address the above-mentioned technical problems.

[0005] Firstly, this application provides a method for processing morphological feature data of brain regions, the method comprising:

[0006] Acquire brain MRI data corresponding to at least two target objects; the at least two target objects include a first object and a second object; the first object is an object associated with a preset brain state label; the second object is an object not associated with a preset brain state label;

[0007] Based on brain MRI data, a brain morphology feature difference map was obtained; the brain morphology feature difference map includes the morphological feature changes of each brain region of the first subject relative to the second subject.

[0008] The gene transcription activity level values ​​of each brain region were obtained, and the first correlation between the morphological feature change values ​​of each brain region and the gene transcription activity level values ​​of each brain region was established.

[0009] Obtain somatic CAG repeat length data of the first subject and establish a second association between somatic CAG repeat length data and gene transcription activity level values ​​of each brain region;

[0010] Based on the first and second association relationships, the association analysis results of preset brain state labels are output; the association analysis results include the association relationships among brain region morphological changes, gene transcriptional disorders, and somatic CAG amplification.

[0011] In one embodiment, establishing a first association between morphological feature change values ​​of each brain region and gene transcription activity levels of each brain region includes:

[0012] The first principal component of each brain region was extracted from the gene transcription activity level values ​​of each brain region; the first principal component is a linear combination of the gene transcription activity level values.

[0013] Establish a linear regression equation between the morphological feature changes of each brain region and the first principal component of each brain region;

[0014] Based on the linear regression equation and the first principal component, the first association between the morphological feature changes of each brain region and the gene transcription activity level of each brain region was established.

[0015] In one embodiment, establishing a second association between somatic CAG repeat length data and gene transcription activity levels in various brain regions includes:

[0016] The contribution of gene transcriptional activity levels of each gene in each brain region to the first principal component of each brain region was obtained.

[0017] Genes whose contribution to each brain region is greater than or equal to a preset threshold are identified as target genes;

[0018] A second association was established between somatic CAG repeat length data and gene transcription activity levels of target genes in each brain region.

[0019] In one embodiment, the contribution of gene transcriptional activity levels of each gene in each brain region to the first principal component of each brain region is obtained, including:

[0020] Obtain gene weight vectors for several samples; each sample includes gene transcription activity level values ​​for each gene in each brain region and the first principal component of each brain region. The gene weight vector is used to characterize the linear combination of gene transcription activity level values.

[0021] Calculate the standard deviation of the weight vector for each gene;

[0022] The z-score of each gene is calculated based on its weight and standard deviation.

[0023] The z-score is used as the contribution of the gene transcriptional activity level of each gene in each brain region to the first principal component of each brain region.

[0024] In one embodiment, establishing a second association between somatic CAG repeat length data and gene transcription activity levels of target genes in each brain region includes:

[0025] The target gene is assigned to the corresponding cell type;

[0026] Extract the target CAG repeat length from the somatic CAG repeat length data of each cell type; the target CAG repeat length is the CAG repeat length that is greater than or equal to the length of the genetic mutation allele of each cell type;

[0027] A second association was established between the target CAG repeat length in each cell type and the gene transcription activity level of the target gene in each cell type.

[0028] In one embodiment, a brain morphological feature difference map is obtained based on brain MRI data, including:

[0029] Preprocessing of brain MRI data to obtain cortical surface data;

[0030] The cortical surface was divided into several brain regions; morphological feature data of each brain region were extracted from the brain MRI data of each brain region.

[0031] Calculate the Pearson correlation coefficient of morphological feature data between any two brain regions; for each brain region, perform a weighted summation of the Pearson correlation coefficients between the brain region and the remaining brain regions to obtain the morphological feature value of the brain region;

[0032] The morphological feature values ​​of each brain region of the first subject are subtracted from the morphological feature values ​​of each brain region of the second subject to obtain a brain morphological feature difference map.

[0033] In one embodiment, the brain MRI data are T1-weighted images; the brain MRI data are preprocessed to obtain the cortical surface, including:

[0034] Remove the skull from the T1-weighted image, segment the brain tissue, separate the hemispheres and subcortical structures, and obtain the gray matter interface and white matter interface;

[0035] The cortical surface is reconstructed based on the gray and white matter interfaces.

[0036] Secondly, this application also provides a brain region morphological feature data processing device, the device comprising:

[0037] The brain magnetic resonance imaging (MRI) data acquisition module is used to acquire brain MRI data corresponding to at least two target objects; the at least two target objects include a first object and a second object; the first object is an object associated with a preset brain state label; the second object is an object not associated with a preset brain state label;

[0038] The brain morphological feature difference map acquisition module is used to obtain a brain morphological feature difference map based on brain MRI data; the brain morphological feature difference map includes the morphological feature change values ​​of each brain region of the first object relative to the second object.

[0039] The first association establishment module is used to obtain the gene transcription activity level value of each brain region and establish the first association between the morphological feature change value of each brain region and the gene transcription activity level value of each brain region.

[0040] The second association establishment module is used to obtain the somatic CAG repeat length data of the first object and establish a second association between the somatic CAG repeat length data and the gene transcription activity level values ​​of each brain region;

[0041] The association analysis results output module is used to output the association analysis results of preset brain state labels based on the first association and the second association; the association analysis results include the association between brain region morphological changes, gene transcription disorders and somatic CAG amplification.

[0042] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method steps of the first aspect.

[0043] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method steps of the first aspect.

[0044] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the method steps of the first aspect.

[0045] The aforementioned brain region morphological feature data processing method, apparatus, computer equipment, computer-readable storage medium, and computer program product acquire brain MRI data corresponding to at least two target objects; the at least two target objects include a first object and a second object; the first object is an object associated with a preset brain state label; the second object is an object not associated with a preset brain state label; based on the brain MRI data, a brain morphological feature difference map is obtained; the brain morphological feature difference map includes morphological feature change values ​​of each brain region of the first object relative to the second object; gene transcription activity level values ​​of each brain region are acquired, and a first correlation relationship is established between the morphological feature change values ​​of each brain region and the gene transcription activity level values ​​of each brain region; somatic CAG repeat length data of the first object are acquired, and a second correlation relationship is established between the somatic CAG repeat length data and the gene transcription activity level values ​​of each brain region; based on the first and second correlation relationships, the correlation analysis results of the preset brain state label are output; the correlation analysis results include the correlation relationship between brain region morphological changes, gene transcriptional dysregulation, and somatic CAG amplification. As can be seen from the above, this application establishes a first correlation between the morphological feature change values ​​of each brain region and the gene transcription activity level values ​​of each brain region, and a second correlation between somatic CAG repeat length data and the gene transcription activity level values ​​of each brain region, to obtain the correlation analysis results of preset brain state labels. This allows for precise analysis of the correlation between brain region morphological changes, gene transcription disorders, and somatic CAG amplification, which helps to deepen the understanding of the pathogenesis of Huntington's disease. Attached Figure Description

[0046] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is a diagram illustrating the application environment of a brain region morphological feature data processing method in one embodiment.

[0048] Figure 2 This is a flowchart illustrating a method for processing morphological feature data of brain regions in one embodiment;

[0049] Figure 3 This is a flowchart illustrating the process of establishing the first association in one embodiment;

[0050] Figure 4 This is a structural block diagram of a brain region morphological feature data processing device in one embodiment;

[0051] Figure 5 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0053] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0054] The brain region morphological feature data processing method provided in this application embodiment can be applied to, for example... Figure 1In the application environment shown, terminal 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104, or it can be located in the cloud or on another network server. Terminal 102 acquires brain MRI data corresponding to at least two target objects; the at least two target objects include a first object and a second object; the first object is an object associated with a preset brain state label; the second object is an object not associated with a preset brain state label; based on the brain MRI data, a brain morphological feature difference map is obtained; the brain morphological feature difference map includes the morphological feature change values ​​of each brain region of the first object relative to the second object; the gene transcription activity level value of each brain region is acquired, and a first correlation relationship is established between the morphological feature change value of each brain region and the gene transcription activity level value of each brain region; the somatic CAG repeat length data of the first object is acquired, and a second correlation relationship is established between the somatic CAG repeat length data and the gene transcription activity level value of each brain region; based on the first correlation relationship and the second correlation relationship, the correlation analysis results of the preset brain state label are output; the correlation analysis results include the correlation relationship between brain region morphological changes, gene transcription dysregulation, and somatic CAG amplification. Terminal 102 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, drones, low-altitude aircraft, IoT devices, and portable wearable devices. IoT devices can include smart speakers, smart TVs, smart air conditioners, smart in-vehicle devices, and projection equipment. Portable wearable devices can include smartwatches, smart bracelets, and head-mounted displays. Head-mounted displays can be virtual reality (VR) devices, augmented reality (AR) devices, and smart glasses. Server 104 can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services.

[0055] In one embodiment, such as Figure 2 As shown, a method for processing morphological feature data of brain regions is provided. This embodiment applies this method to... Figure 1 Taking terminal 102 as an example, the method includes the following steps:

[0056] Step S210: Obtain brain MRI data corresponding to at least two target objects; the at least two target objects include a first object and a second object; the first object is an object associated with a preset brain state label; the second object is an object not associated with a preset brain state label.

[0057] The pre-defined brain state labels represent the clinical features of Huntington's disease. Specifically, the pre-defined brain state labels can be at least one of striatal atrophy, caudate nucleus atrophy, or putamen atrophy.

[0058] The first subject can be a Huntington's disease patient, and the second subject can be a healthy human being.

[0059] In this embodiment of the application, MRI (Nuclear Magnetic Resonance Imaging) scans are performed on each target object to obtain corresponding brain MRI data for each target object. The brain MRI data can be brain MRI images or T1-weighted images of brain MRI images after processing.

[0060] Step S220: Obtain a brain morphological feature difference map based on brain MRI data; the brain morphological feature difference map includes the morphological feature change values ​​of each brain region of the first object relative to the second object.

[0061] The morphological characteristics of brain regions include at least one of the following: surface area, cortical thickness, gray matter volume, Gaussian curvature, mean curvature, folding index, and curvature index.

[0062] In this embodiment of the application, morphological features of each brain region of the first object and the second object are extracted from brain magnetic resonance imaging data, and the morphological feature changes of each brain region of the first object relative to the second object are determined.

[0063] Step S230: Obtain the gene transcription activity level values ​​of each brain region and establish the first correlation between the morphological feature change values ​​of each brain region and the gene transcription activity level values ​​of each brain region.

[0064] Among them, the gene transcription activity level value refers to the number or concentration of RNA molecules produced by a gene during transcription.

[0065] In this embodiment of the application, linear regression analysis can be used to establish a first association between the morphological feature changes of each brain region and the gene transcription activity level of each brain region. The linear regression analysis method includes, but is not limited to, least squares regression and partial least squares regression.

[0066] Step S240: Obtain somatic CAG repeat length data of the first subject and establish a second association between somatic CAG repeat length data and gene transcription activity level values ​​of each brain region.

[0067] Among them, the somatic CAG repeat length data refers to the number of times the CAG trinucleotide sequence is repeated in the HTT gene in somatic cells.

[0068] In this embodiment, a second association between somatic CAG repeat length data and gene transcription activity levels in various brain regions is established using correlation analysis. The correlation analysis methods include, but are not limited to, Pearson correlation analysis, Spearman correlation analysis, and Kendall correlation analysis.

[0069] Step S250: Based on the first association relationship and the second association relationship, output the association relationship analysis results of the preset brain state labels; the association relationship analysis results include the association relationship between brain region morphological changes, gene transcriptional disorders and somatic cell CAG amplification.

[0070] In this embodiment, by analyzing the second correlation, it can be determined that the abnormal gene transcription activity levels in each brain region of the first subject are caused by somatic CAG amplification. By analyzing the first correlation, it can be determined that the abnormal morphological characteristics of each brain region of the first subject are caused by abnormal gene transcription activity levels. Based on the first and second correlations, it can be determined that somatic CAG amplification drives gene transcriptional dysregulation, which in turn manifests as morphological changes in brain regions.

[0071] The aforementioned brain region morphological feature data processing method involves acquiring brain MRI data corresponding to at least two target objects; the at least two target objects include a first object and a second object; the first object is an object associated with a preset brain state label; the second object is an object not associated with a preset brain state label; based on the brain MRI data, a brain morphological feature difference map is obtained; the brain morphological feature difference map includes the morphological feature change values ​​of each brain region of the first object relative to the second object; the gene transcription activity level values ​​of each brain region are acquired, and a first correlation relationship is established between the morphological feature change values ​​of each brain region and the gene transcription activity level values ​​of each brain region; the somatic CAG repeat length data of the first object are acquired, and a second correlation relationship is established between the somatic CAG repeat length data and the gene transcription activity level values ​​of each brain region; based on the first and second correlation relationships, the correlation analysis results of the preset brain state label are output; the correlation analysis results include the correlation relationship between brain region morphological changes, gene transcriptional dysregulation, and somatic CAG amplification. As can be seen from the above, this application establishes a first correlation between the morphological feature change values ​​of each brain region and the gene transcription activity level values ​​of each brain region, and a second correlation between somatic CAG repeat length data and the gene transcription activity level values ​​of each brain region, to obtain the correlation analysis results of preset brain state labels. This allows for precise analysis of the correlation between brain region morphological changes, gene transcription disorders, and somatic CAG amplification, which helps to deepen the understanding of the pathogenesis of Huntington's disease.

[0072] In one embodiment, a brain morphological feature difference map is obtained based on brain MRI data, including:

[0073] Step S221: Preprocess the brain MRI data to obtain the cortical surface.

[0074] In this embodiment of the application, human brain MRI processing software (such as FreeSurfer) is used to preprocess brain MRI data in a surface-based space to reconstruct the cortical surface.

[0075] Step S222: Divide the cortical surface into several brain regions; extract the morphological feature data of each brain region from the brain MRI data of each brain region.

[0076] In this embodiment, the cortical surface is divided into multiple cortical regions (i.e., brain regions), and each cortical region is further divided into multiple spatially continuous regions. For example, the cortical surface is divided into 68 cortical regions, and each cortical region is further divided into 308 spatially continuous regions.

[0077] Brain MRI data from various brain regions are input into a morphological feature extraction model to extract morphological features from each brain region, thereby obtaining morphological feature data for each brain region. The morphological feature extraction model can be a pre-trained deep learning model.

[0078] Step S223: Calculate the Pearson correlation coefficient of morphological feature data of any two brain regions; for each brain region, perform a weighted summation of the Pearson correlation coefficients of the brain region and the remaining brain regions to obtain the morphological feature value of the brain region.

[0079] The Pearson correlation coefficient is used to measure the linear relationship between two variables, and its value is between -1 and 1.

[0080] In this embodiment, the mean and standard deviation of morphological feature data for each brain region are calculated. Based on the mean and standard deviation, the Pearson correlation coefficient of morphological feature data for any two brain regions is calculated. Using a preset weighting coefficient, the Pearson correlation coefficients of the i-th brain region and the j-th brain region are weighted and summed to obtain the morphological feature value of the i-th brain region. Here, j = 1, 2, ..., N, and j ≠ i. N is the total number of brain regions.

[0081] Step S224: Subtract the morphological feature values ​​of each brain region of the first subject from the morphological feature values ​​of each brain region of the second subject to obtain a brain morphological feature difference map.

[0082] In this embodiment, the calculation process of the morphological feature values ​​of each brain region of the second object is the same as that of the calculation process of the morphological feature values ​​of each brain region of the first object. Referring to the aforementioned steps S221 to S223, it will not be repeated here.

[0083] The morphological feature values ​​of each brain region in the first subject are subtracted from the morphological feature values ​​of the corresponding brain regions in the second subject to obtain a brain morphological feature difference map. Here, "corresponding brain regions" can refer to brain regions located in the same position.

[0084] In one embodiment, the brain MRI data are T1-weighted images; the brain MRI data are preprocessed to obtain the cortical surface, including:

[0085] Step S2211: Remove the skull from the T1-weighted image, segment the brain tissue, separate the hemispheres and subcortical structures to obtain the gray matter interface and white matter interface.

[0086] The gray matter interface is the boundary between gray matter and cerebrospinal fluid, while the white matter interface is the boundary between gray matter and white matter.

[0087] Step S2212: Reconstruct the cortical surface based on the gray and white matter interfaces.

[0088] Among them, the T1-weighted image is a type of contrast image generated in magnetic resonance imaging based on the difference in longitudinal relaxation time (T1 value) of tissues.

[0089] In this embodiment, the grayscale difference between brain tissue and skull in T1-weighted images (e.g., brain tissue is medium grayscale, skull is high grayscale) can be used to initially separate the skull and brain tissue by setting a threshold. The brain tissue is then segmented into left and right hemispheres, and subcortical structures (such as the basal ganglia, thalamus, and hippocampus) are separated. The gray matter interface and white matter interface are extracted from the segmented brain tissue.

[0090] The white and gray interfaces are registered to a spherical template (such as fsaverage), and cross-individual surface alignment is achieved through spherical harmonic functions to obtain the cortical surface.

[0091] In one embodiment, such as Figure 3 As shown, the first association between morphological feature changes in each brain region and gene transcription activity levels in each brain region was established, including:

[0092] Step S310: Extract the first principal component of each brain region from the gene transcription activity level values ​​of each brain region; the first principal component is a linear combination of the gene transcription activity level values.

[0093] In this embodiment, the gene transcription activity level of each brain region is used as the independent variable, and the morphological feature change value of each brain region is used as the dependent variable. The independent variable components are obtained by linearly combining the independent variables using a first weight vector. The dependent variable components are obtained by linearly combining the dependent variables using a second weight vector. The first weight vector is solved by maximizing the covariance between the independent and dependent variable components. The first principal components are obtained by linearly combining the independent variables using the solved first weight vector.

[0094] Step S320: Establish a linear regression equation between the morphological feature change values ​​of each brain region and the first principal component of each brain region.

[0095] In this embodiment of the application, the least squares method is used to perform linear regression on the morphological feature change values ​​of each brain region and the first principal component of each brain region to obtain the linear regression equation.

[0096] Step S330: Based on the linear regression equation and the first principal component, establish the first association between the morphological feature change values ​​of each brain region and the gene transcription activity level values ​​of each brain region.

[0097] In this embodiment of the application, after obtaining the linear regression equation, the first principal component in the linear regression equation is replaced by the transcriptional activity level value of each gene to obtain the first correlation between the morphological feature change value of each brain region and the transcriptional activity level value of each brain region.

[0098] In one embodiment, establishing a second association between somatic CAG repeat length data and gene transcriptional activity levels in various brain regions includes:

[0099] Step S241: Obtain the contribution of gene transcription activity level of each gene in each brain region to the first principal component of each brain region.

[0100] In this embodiment, since the first principal component is a linear combination of the transcriptional activity levels of each gene, the contribution of each gene's transcriptional activity level to each first principal component can be determined based on the linear combination coefficients. Specifically, a gene weight vector is constructed based on the linear combination coefficients. The contribution of each gene's transcriptional activity level to each first principal component is then determined based on the gene weight vector.

[0101] Step S242: Genes whose contribution in each brain region is greater than or equal to a preset threshold are identified as target genes.

[0102] The preset threshold can be set according to requirements.

[0103] Step S243: Establish a second association between somatic cell CAG repeat length data and gene transcription activity levels of target genes in each brain region.

[0104] In this embodiment of the application, Spearman correlation analysis is used to take somatic CAG repeat length data and gene transcription activity level of target genes in each brain region as two variables, calculate the correlation coefficient between the two variables, and obtain the second association between somatic CAG repeat length data and gene transcription activity level of target genes in each brain region based on the correlation coefficient.

[0105] In one embodiment, the contribution of gene transcriptional activity levels of each gene in each brain region to the first principal component of each brain region is obtained, including:

[0106] Step S2411: Obtain gene weight vectors for several samples; each sample includes gene transcription activity level values ​​of each gene in each brain region and the first principal component of each brain region. The gene weight vector is used to characterize the linear combination of gene transcription activity level values.

[0107] In the embodiments of this application, each sample includes at least two target objects, and the calculation process of the gene weight vector of each sample can refer to the aforementioned step S231, which will not be repeated here.

[0108] Step S2412: Calculate the standard deviation of the weight vector of each gene;

[0109] Step S2413: Obtain the z-score of each gene based on its weight and standard deviation; the weight of each gene is the linear combination coefficient of the gene transcription activity level values ​​of each gene in the first principal component.

[0110] Step S2414: The z-score is used as the contribution of the gene transcriptional activity level of each gene in each brain region to the first principal component of each brain region.

[0111] In this embodiment, for each brain region, the weight of each gene is divided by its standard deviation to obtain the z-score of each gene. The z-score of each gene is then used as the contribution of the gene transcriptional activity level to the first principal component.

[0112] In one embodiment, establishing a second association between somatic CAG repeat length data and gene transcriptional activity levels of target genes in each brain region includes:

[0113] Step S2431: Assign the target gene to the corresponding cell type.

[0114] The cell types include, but are not limited to, excitatory neurons (layers 2, 4, 5a, 6a, 6b, and region-specific Bates cells in layer 5), interneurons (expressing LAMP, PVALB, RELN, and VIP), and non-neuronal cells (astrocytes, microglia, oligodendrocytes, and OPCs).

[0115] In this embodiment, the gene set of each cell type is overlapped with the target gene. The statistical significance of the number of overlapping genes for each cell type is determined using a permutation test, and corrected by the false discovery rate (FDR) to classify the target gene into the cell type most relevant to its expression.

[0116] Step S2432: Extract the target CAG repeat length from the somatic CAG repeat length data of each cell type; the target CAG repeat length is the CAG repeat length that is greater than or equal to the length of the genetic mutation allele of each cell type.

[0117] The length of the genetic mutation allele is the number of times the CAG trinucleotide sequence is repeated in the normal allele. For example, 10-35 times.

[0118] Step S2433: Establish a second association between the target CAG repeat length of each cell type and the gene transcription activity level of the target gene in each cell type.

[0119] In this embodiment of the application, Spearman correlation analysis is used to take the target CAG repeat length of each cell type and the gene transcription activity level of the target gene of each cell type as two variables, calculate the correlation coefficient between the two variables, and obtain the second association between the target CAG repeat length of each cell type and the gene transcription activity level of the target gene of each cell type based on the correlation coefficient.

[0120] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0121] Based on the same inventive concept, this application also provides a brain region morphological feature data processing device for implementing the brain region morphological feature data processing method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more brain region morphological feature data processing device embodiments provided below can be found in the limitations of the large model inference request processing method described above, and will not be repeated here.

[0122] In one exemplary embodiment, such as Figure 4 As shown, a brain region morphological feature data processing device is provided, the device comprising:

[0123] The brain magnetic resonance imaging (MRI) data acquisition module 410 is used to acquire brain MRI data corresponding to at least two target objects; the at least two target objects include a first object and a second object; the first object is an object associated with a preset brain state label; the second object is an object not associated with a preset brain state label;

[0124] The brain morphological feature difference map acquisition module 420 is used to obtain a brain morphological feature difference map based on brain magnetic resonance data; the brain morphological feature difference map includes the morphological feature change values ​​of each brain region of the first object relative to the second object.

[0125] The first association establishment module 430 is used to obtain the gene transcription activity level value of each brain region and establish the first association between the morphological feature change value of each brain region and the gene transcription activity level value of each brain region.

[0126] The second association establishment module 440 is used to obtain the somatic CAG repeat length data of the first object and establish a second association between the somatic CAG repeat length data and the gene transcription activity level values ​​of each brain region;

[0127] The association analysis result output module 450 is used to output the association analysis results of preset brain state labels based on the first association and the second association; the association analysis results include the association between brain region morphological changes, gene transcription disorders and somatic cell CAG amplification.

[0128] In one embodiment, establishing a first association between morphological feature change values ​​of each brain region and gene transcription activity levels of each brain region includes:

[0129] The first principal component of each brain region was extracted from the gene transcription activity level values ​​of each brain region; the first principal component is a linear combination of the gene transcription activity level values.

[0130] Establish a linear regression equation between the morphological feature changes of each brain region and the first principal component of each brain region;

[0131] Based on the linear regression equation and the first principal component, the first association between the morphological feature changes of each brain region and the gene transcription activity level of each brain region was established.

[0132] In one embodiment, establishing a second association between somatic CAG repeat length data and gene transcription activity levels in various brain regions includes:

[0133] The contribution of gene transcriptional activity levels of each gene in each brain region to the first principal component of each brain region was obtained.

[0134] Genes whose contribution to each brain region is greater than or equal to a preset threshold are identified as target genes;

[0135] A second association was established between somatic CAG repeat length data and gene transcription activity levels of target genes in each brain region.

[0136] In one embodiment, the contribution of gene transcriptional activity levels of each gene in each brain region to the first principal component of each brain region is obtained, including:

[0137] Obtain gene weight vectors for several samples; each sample includes gene transcription activity level values ​​for each gene in each brain region and the first principal component of each brain region. The gene weight vector is used to characterize the linear combination of gene transcription activity level values.

[0138] Calculate the standard deviation of the weight vector for each gene;

[0139] The z-score of each gene is calculated based on its weight and standard deviation.

[0140] The z-score is used as the contribution of the gene transcriptional activity level of each gene in each brain region to the first principal component of each brain region.

[0141] In one embodiment, establishing a second association between somatic CAG repeat length data and gene transcription activity levels of target genes in each brain region includes:

[0142] The target gene is assigned to the corresponding cell type;

[0143] Extract the target CAG repeat length from the somatic CAG repeat length data of each cell type; the target CAG repeat length is the CAG repeat length that is greater than or equal to the length of the genetic mutation allele of each cell type;

[0144] A second association was established between the target CAG repeat length in each cell type and the gene transcription activity level of the target gene in each cell type.

[0145] In one embodiment, a brain morphological feature difference map is obtained based on brain MRI data, including:

[0146] Preprocessing of brain MRI data to obtain cortical surface data;

[0147] The cortical surface was divided into several brain regions; morphological feature data of each brain region were extracted from the brain MRI data of each brain region.

[0148] Calculate the Pearson correlation coefficient of morphological feature data between any two brain regions; for each brain region, perform a weighted summation of the Pearson correlation coefficients between the brain region and the remaining brain regions to obtain the morphological feature value of the brain region;

[0149] The morphological feature values ​​of each brain region of the first subject are subtracted from the morphological feature values ​​of each brain region of the second subject to obtain a brain morphological feature difference map.

[0150] In one embodiment, the brain MRI data are T1-weighted images; the brain MRI data are preprocessed to obtain the cortical surface, including:

[0151] Remove the skull from the T1-weighted image, segment the brain tissue, separate the hemispheres and subcortical structures, and obtain the gray matter interface and white matter interface;

[0152] The cortical surface is reconstructed based on the gray and white matter interfaces.

[0153] Each module in the aforementioned brain region morphological feature data processing device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0154] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows. Figure 5 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores brain region morphological feature data for processing. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network. When the computer program is executed by the processor, it implements a brain region morphological feature data processing method.

[0155] Those skilled in the art will understand that Figure 5 The structures shown are merely block diagrams of some structures related to the present application and do not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than shown in the figures, or combine certain components, or have different component arrangements. In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program, which, when executed by the processor, causes the processor to perform the steps of the aforementioned brain region morphological feature data processing method. The steps of the brain region morphological feature data processing method described here can be the steps of a brain region morphological feature data processing method from the various embodiments described above.

[0156] In one embodiment, a computer-readable storage medium is provided storing a computer program that, when executed by a processor, causes the processor to perform the steps of the brain region morphological feature data processing method described above. The steps of the brain region morphological feature data processing method described here can be steps from one of the brain region morphological feature data processing methods in the various embodiments described above.

[0157] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, causes the processor to perform the steps of the brain region morphological feature data processing method described above. The steps of the brain region morphological feature data processing method described here may be steps from one of the brain region morphological feature data processing methods in the various embodiments described above.

[0158] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0159] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0160] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0161] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for processing morphological feature data of brain regions, characterized in that, The method includes: Obtain brain MRI data corresponding to at least two target objects; the at least two target objects include a first object and a second object; the first object is an object associated with a preset brain state label; the second object is an object not associated with the preset brain state label; Based on the brain MRI data, a brain morphological feature difference map is obtained; the brain morphological feature difference map includes the morphological feature changes of each brain region of the first object relative to the second object; Obtain gene transcription activity level values ​​for each brain region and establish a first correlation between morphological feature change values ​​of each brain region and gene transcription activity level values ​​of each brain region. Obtain somatic CAG repeat length data of the first object, and establish a second correlation between the somatic CAG repeat length data and the gene transcription activity level values ​​of each brain region; Based on the first association and the second association, the association analysis results of the preset brain state labels are output; the association analysis results include the association between brain region morphological changes, gene transcriptional disorders, and somatic CAG amplification.

2. The method according to claim 1, characterized in that, The establishment of a first association between the morphological feature change values ​​of each brain region and the gene transcription activity level values ​​of each brain region includes: The first principal component of each brain region is extracted from the gene transcription activity level values ​​of each brain region; the first principal component is a linear combination of the gene transcription activity level values ​​of each brain region. Establish a linear regression equation between the morphological feature change values ​​of each brain region and the first principal component of each brain region; Based on the linear regression equation and the first principal component, a first correlation is established between the morphological feature change values ​​of each brain region and the gene transcription activity level values ​​of each brain region.

3. The method according to claim 2, characterized in that, The establishment of a second association between the somatic CAG repeat length data and the gene transcription activity levels of each brain region includes: The contribution of gene transcriptional activity level values ​​of each gene in each brain region to the first principal component of each brain region is obtained. Genes whose contribution in each brain region is greater than or equal to a preset threshold are identified as target genes; A second association was established between the somatic CAG repeat length data and the gene transcription activity level of the target gene in each brain region.

4. The method according to claim 3, characterized in that, The step of obtaining the contribution of the gene transcription activity level of each gene in each brain region to the first principal component of each brain region includes: Obtain gene weight vectors for several samples; each sample includes gene transcription activity level values ​​of each gene in each brain region and the first principal component of each brain region, and the gene weight vectors are used to characterize linear combinations of the gene transcription activity level values; Calculate the standard deviation of each gene weight vector; The z-score of each gene is determined by its weight and standard deviation; the weight of each gene is the linear combination coefficient of the gene transcription activity level values ​​of each gene in the first principal component. The z-score is used as the contribution of the gene transcriptional activity level of each gene in each brain region to the first principal component of each brain region.

5. The method according to claim 3, characterized in that, The establishment of a second association between the somatic cell CAG repeat length data and the gene transcription activity level of the target gene in each brain region includes: The target gene is assigned to the corresponding cell type; The target CAG repeat length is extracted from the somatic CAG repeat length data of each cell type; the target CAG repeat length is a CAG repeat length that is greater than or equal to the length of the genetic mutation allele of each cell type. Establish a second association between the target CAG repeat length for each cell type and the gene transcriptional activity level of the target gene for each cell type.

6. The method according to any one of claims 1 to 5, characterized in that, The step of obtaining a brain morphological feature difference map based on the brain MRI data includes: The brain MRI data are preprocessed to obtain the cortical surface. The cortical surface is divided into several brain regions; morphological feature data of each brain region are extracted from the brain MRI data of each brain region; Calculate the Pearson correlation coefficient of morphological feature data of any two brain regions; for each brain region, perform a weighted summation of the Pearson correlation coefficients of the brain region and the remaining brain regions to obtain the morphological feature value of the brain region; The brain morphological feature difference map is obtained by subtracting the morphological feature values ​​of each brain region of the first object from the morphological feature values ​​of each brain region of the second object.

7. The method according to claim 6, characterized in that, The brain MRI data are T1-weighted images; the preprocessing of the brain MRI data to obtain the cortical surface includes: Remove the skull from the T1-weighted image, segment the brain tissue, separate the hemispheres and subcortical structures to obtain the gray matter interface and white matter interface; The cortical surface is reconstructed based on the gray matter interface and the white matter interface.

8. A brain region morphological feature data processing device, characterized in that, The device includes: A brain magnetic resonance imaging (MRI) data acquisition module is used to acquire brain MRI data corresponding to at least two target objects; the at least two target objects include a first object and a second object; the first object is an object associated with a preset brain state label; the second object is an object not associated with the preset brain state label; The brain morphological feature difference map acquisition module is used to obtain a brain morphological feature difference map based on the brain magnetic resonance data; the brain morphological feature difference map includes the morphological feature change values ​​of each brain region of the first object relative to the second object. The first association module is used to obtain the gene transcription activity level value of each brain region and establish a first association between the morphological feature change value of each brain region and the gene transcription activity level value of each brain region. The second association establishment module is used to obtain the somatic CAG repeat length data of the first object and establish a second association between the somatic CAG repeat length data and the gene transcription activity level values ​​of each brain region; The association analysis result output module is used to output the association analysis results of the preset brain state labels based on the first association and the second association; the association analysis results include the association between brain region morphological changes, gene transcription disorders, and somatic CAG amplification.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images