Brain region localization method and device for disease mapping of depression-anxiety comorbidity

Abstract

The present application discloses a method and device for locating brain regions for disease mapping of depression-anxiety comorbidity, which relates to the field of medical signal processing technology, and includes: reading magnetic resonance data and identity information data of a target individual, and determining the gray matter volume corresponding to the brain of the target individual based on the magnetic resonance data and the identity information data; partitioning the brain to obtain multiple brain regions, and determining the corresponding brain region depression vectors and brain region anxiety vectors according to the gray matter volume and the identity information data; classifying the multiple brain regions based on the brain region depression vectors and the brain region anxiety vectors to determine the depression-significant brain regions and anxiety-significant brain regions included in the multiple brain regions; generating significant brain region labels corresponding to each of the multiple brain regions according to the depression-significant brain regions and the anxiety-significant brain regions, and generating network topology labels corresponding to each of the multiple brain regions according to the identity information data and the magnetic resonance data; and determining the disease type of the target individual based on the significant brain region labels and the network topology labels.

Description

Technical Field

[0001] The present application relates to the field of medical signal processing technology, and in particular to a method and device for locating brain regions for disease mapping of depression-anxiety comorbidity. Background Art

[0002] With the continuous development of medical signal technology, various medical signals are increasingly used in detecting whether the target individual has depression and related symptoms.

[0003] In related technologies, technicians usually use the method of capturing the high-identification brain areas of the target individual to determine whether the target individual has depression.

[0004] However, due to significant biological differences between different individuals, the brain regions related to depression in different target individuals vary to a certain extent in terms of location, range, neural connection pattern, and functional activity intensity. Especially when the target individual has anxiety-depression comorbidity, it is difficult to comprehensively and accurately detect and evaluate the complex symptom manifestations of the target individual because the specific brain regions in the target individual that are closely related to anxiety symptoms cannot be identified through high-identification brain regions. Summary of the invention

[0005] The main purpose of this application is to provide a method for mapping brain regions for depression-anxiety comorbidity, aiming to solve the technical problem in related technologies that specific brain regions in the target individual's brain that are closely related to anxiety symptoms cannot be identified.

[0006] To achieve the above objectives, the present application proposes a method for mapping brain regions for depression-anxiety comorbidity, including:

[0007] Reading magnetic resonance data and identity information data of a target individual, and determining a gray matter volume corresponding to a brain of the target individual based on the magnetic resonance data and the identity information data;

[0008] Partitioning the brain to obtain a plurality of brain regions, and determining a brain region depression vector and a brain region anxiety vector corresponding to the brain according to the gray matter volume and the identity information data;

[0009] Classifying the plurality of brain regions based on the brain region depression vector and the brain region anxiety vector to determine a depression-significant brain region and an anxiety-significant brain region included in the plurality of brain regions;

[0010] Generating a plurality of significant brain region labels corresponding to the respective brain regions according to the significant depression brain regions and the significant anxiety brain regions, and generating a plurality of network topology labels corresponding to the respective brain regions according to the identity information data and the magnetic resonance data;

[0011] The disease type of the target individual is determined based on the significant brain region labels and the network topology labels, wherein the disease type includes first-time disease and non-first-time disease.

[0012] In one embodiment, the identity information data includes age, education level, gender, total intracranial volume, clinical score of depression and clinical score of anxiety, and the step of determining the gray matter volume corresponding to the brain of the target individual based on the magnetic resonance data and the identity information data comprises:

[0013] The magnetic resonance data are preprocessed, and the preprocessed magnetic resonance data, age, education level, gender, total intracranial volume, depression clinical score, and anxiety clinical score are combined for multivariate regression processing to determine the mapping relationship between the gray matter volume corresponding to the brain of the target individual and the magnetic resonance data, age, education level, gender, total intracranial volume, depression clinical score, and anxiety clinical score:

[0014] , where GMV is the gray matter volume, For gender, For age, For educational level, Clinical score for depression. is the clinical score of anxiety, TIV is the total intracranial volume, is the residual;

[0015] Based on the mapping relationship, the weight information corresponding to the magnetic resonance data, age, education level, gender, total intracranial volume, clinical score of depression, and clinical score of anxiety is determined, wherein the weight information is , , , , , , .

[0016] In one embodiment, the step of determining the depression vector and the anxiety vector of the brain region corresponding to the brain according to the gray matter volume and the identity information data comprises:

[0017] Obtaining depression score weight information matched by the depression clinical score in the gray matter volume;

[0018] Calculating depression weights of multiple brain regions corresponding to the depression score weight information in the brain, and determining a depression vector of the brain region corresponding to the brain according to each of the depression weights of the brain region;

[0019] Acquiring anxiety score weight information matching the anxiety clinical score in the gray matter volume;

[0020] The anxiety weights of multiple brain regions corresponding to the anxiety score weight information in the brain are calculated, and the anxiety vector of the brain region corresponding to the brain is determined according to each of the anxiety weights of the brain region.

[0021] In one embodiment, the step of classifying the plurality of brain regions based on the brain region depression vector and the brain region anxiety vector to determine depression-significant brain regions and anxiety-significant brain regions included in the plurality of brain regions comprises:

[0022] Reading each first signal time series contained in the magnetic resonance data;

[0023] Calculating the brain region correlation between any two brain regions according to each of the first signal time series, and determining the functional connection matrix corresponding to a plurality of the brain regions according to each of the brain region correlations;

[0024] Calculating various depression-related parameters based on the brain region depression vector and the functional connectivity matrix, and calculating various anxiety-related parameters based on the brain region anxiety vector and the functional connectivity matrix;

[0025] The plurality of brain regions are classified according to each of the depression-related parameters and each of the anxiety-related parameters to determine depression-significant brain regions and anxiety-significant brain regions included in the plurality of brain regions.

[0026] In one embodiment, the step of classifying the plurality of brain regions according to the depression-related parameters and the anxiety-related parameters to determine depression-significant brain regions and anxiety-significant brain regions included in the plurality of brain regions further includes:

[0027] Obtaining a preset depression correlation coefficient significance level threshold, and comparing each of the depression correlation parameters with the depression correlation coefficient significance level threshold to obtain a first comparison result;

[0028] Determine a target first comparison result in each of the first comparison results, and determine the brain region corresponding to the target first comparison result as a depression-significant brain region, wherein the target first comparison result is a depression-related parameter that is less than a depression-related coefficient significance level threshold;

[0029] Obtaining a preset anxiety correlation coefficient significance level threshold, and comparing each of the anxiety correlation parameters with the anxiety correlation coefficient significance level threshold to obtain a second comparison result;

[0030] A target second comparison result is determined in each of the second comparison results, and the brain region corresponding to the target second comparison result is determined as an anxiety-significant brain region, wherein the target second comparison result is that the anxiety-related parameter is less than the anxiety-related coefficient significance level threshold.

[0031] In one embodiment, the target individuals include a plurality of healthy persons and a plurality of patients, and the step of determining the disease type of the target individuals based on the significant brain region labels and the network topology labels comprises:

[0032] Determine the average gray matter volume and gray matter volume standard deviation corresponding to multiple brain regions of multiple healthy subjects;

[0033] The W scores of the multiple patients are calculated according to the gray matter volume parameters of the multiple brain regions of the multiple patients, the average gray matter volume of the multiple healthy persons and the gray matter volume standard deviation, and the node risk parameters and spatial risk parameters corresponding to the multiple brain regions are determined based on the W scores, wherein the W scores are: , is a gray matter volume parameter of multiple brain regions of multiple patients, is the average gray matter volume, is the standard deviation of the gray matter volume;

[0034] The node risk parameters, the spatial risk parameters, the significant brain region labels and the network topology labels corresponding to the multiple brain regions are integrated to obtain each brain feature vector, and each brain feature vector is classified and predicted to determine the disease type of the target individual.

[0035] In one embodiment, the step of determining the node risk parameters and spatial risk parameters corresponding to the plurality of brain regions based on the W score comprises:

[0036] Determining connection weights corresponding to each of the plurality of brain regions, wherein the connection weights are connection weights between the target brain region and other brain regions;

[0037] Determine five brain regions with the largest weights corresponding to the target brain region according to each of the connection weights, and determine a node risk parameter corresponding to the target brain region based on the five brain regions with the largest weights and the W score:

[0038] ,in, is the connection strength between brain region node N and other brain regions, is the node risk parameter.

[0039] In one embodiment, the step of determining the node risk parameters and spatial risk parameters corresponding to the plurality of brain regions based on the W score further includes:

[0040] Determine the Euclidean distance between each of the plurality of brain regions and other brain regions, and determine five brain regions with the closest Euclidean distances corresponding to the target brain region according to each of the Euclidean distances;

[0041] The spatial risk parameter of the target brain region is determined based on the five brain regions closest to the Euclidean distance and the W score:

[0042] ,in, is the spatial risk parameter.

[0043] In one embodiment, the step of determining the disease type of the target individual based on the significant brain region labels and the network topology labels further includes:

[0044] The spatial risk parameters, the node risk parameters, the network topology labels and the significant brain region labels corresponding to the significant depression brain regions and the significant anxiety brain regions are combined to generate brain feature vectors;

[0045] Classification prediction is performed on each of the brain feature vectors to determine the disease type of the target individual.

[0046] The embodiment of the present application provides a method for mapping brain regions for depression-anxiety comorbidity, which reads the magnetic resonance data and identity information data of a target individual, and determines the gray matter volume corresponding to the brain of the target individual based on the magnetic resonance data and the identity information data; partitions the brain to obtain multiple brain regions, and determines the brain region depression vector and the brain region anxiety vector corresponding to the brain according to the gray matter volume and the identity information data; classifies the multiple brain regions based on the brain region depression vector and the brain region anxiety vector to determine the depression-significant brain regions and the anxiety-significant brain regions included in the multiple brain regions; generates multiple significant brain region labels corresponding to each of the brain regions according to the depression-significant brain regions and the anxiety-significant brain regions, and generates multiple network topology labels corresponding to each of the brain regions according to the identity information data and the magnetic resonance data; determines the onset type of the target individual based on the significant brain region labels and the network topology labels, wherein the onset type includes first onset and non-first onset.

[0047] In this way, the present application solves the technical problem in the related art that the specific brain area in the target individual's brain that is closely related to anxiety symptoms cannot be identified. That is, the present application processes the magnetic resonance data and identity information data of the target individual so that the electronic device can obtain the gray matter volume representing the correlation between the magnetic resonance data and the identity information data, and determine the brain area depression vector and the brain area anxiety vector corresponding to the individual's brain based on the anxiety clinical score and the depression clinical score contained in the gray matter volume and the identity information data, so as to identify the anxiety-significant brain area and the depression-significant brain area contained in the multiple brain areas obtained by partitioning based on the brain area depression vector and the brain area anxiety vector, thereby identifying the disease type of the target individual based on the anxiety-significant brain area and the depression-significant brain area, thereby achieving the technical effect of enabling the electronic device to accurately identify the specific brain area in the target individual's brain that is closely related to anxiety symptoms and the specific brain area that is closely related to depressive symptoms, and identify the disease type of the target individual. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0049] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0050] Figure 1 A flowchart diagram of the first embodiment of the method for mapping brain regions for depression-anxiety comorbidity in the present application;

[0051] Figure 2 A detailed flowchart of the first embodiment of the method for mapping brain regions for depression-anxiety comorbidity in this application;

[0052] Figure 3 A schematic diagram of brain region classification results involved in the first embodiment of the method for mapping brain regions for depression-anxiety comorbidity in the present application;

[0053] Figure 4 A schematic diagram of the graph convolutional neural network structure involved in the first embodiment of the method for locating brain regions for symptom mapping of depression-anxiety comorbidity in this application;

[0054] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the method for locating brain regions for symptom mapping of depression-anxiety comorbidity in an embodiment of the present application.

[0055] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0056] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0057] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0058] In this embodiment, for ease of description, the following description is made with the electronic device, or a mobile terminal, a data storage control terminal, a PC or other terminal connected to an electronic control unit of the electronic device as the execution subject.

[0059] Based on the above-mentioned electronic device, the overall concept of the brain region localization method for disease mapping of depression-anxiety comorbidity in this application is proposed here.

[0060] With the continuous development of medical signal technology, various medical signals are increasingly used in detecting whether the target individual has depression and related symptoms. In related technologies, technicians usually use the method of capturing the high-identification brain areas of the target individual to determine whether the target individual has depression. However, due to the significant biological differences between different individuals, the brain areas related to depression in different target individuals have certain differences in location, range, neural connection pattern, and functional activity intensity. Especially when the target individual has anxiety-depression comorbidity, it is difficult to comprehensively and accurately detect and evaluate the complex symptom manifestations of the target individual because the high-identification brain areas cannot identify the specific brain areas in the target individual's brain that are closely related to anxiety symptoms.

[0061] In view of the above phenomenon, the present application provides a method for mapping brain regions for depression-anxiety comorbidity, including: reading magnetic resonance data and identity information data of a target individual, and determining the gray matter volume corresponding to the brain of the target individual based on the magnetic resonance data and the identity information data; partitioning the brain to obtain multiple brain regions, and determining the brain region depression vector and the brain region anxiety vector corresponding to the brain according to the gray matter volume and the identity information data; classifying the multiple brain regions based on the brain region depression vector and the brain region anxiety vector to determine the depression-significant brain regions and the anxiety-significant brain regions included in the multiple brain regions; generating multiple significant brain region labels corresponding to each of the brain regions according to the depression-significant brain regions and the anxiety-significant brain regions, and generating multiple network topology labels corresponding to each of the brain regions according to the identity information data and the magnetic resonance data; determining the onset type of the target individual based on the significant brain region labels and the network topology labels, wherein the onset type includes first onset and non-first onset.

[0062] In this way, the present application solves the technical problem in the related art that the specific brain area in the target individual's brain that is closely related to anxiety symptoms cannot be identified. That is, the present application processes the magnetic resonance data and identity information data of the target individual so that the electronic device can obtain the gray matter volume representing the correlation between the magnetic resonance data and the identity information data, and determine the brain area depression vector and the brain area anxiety vector corresponding to the individual's brain based on the anxiety clinical score and the depression clinical score contained in the gray matter volume and the identity information data, so as to identify the anxiety-significant brain area and the depression-significant brain area contained in the multiple brain areas obtained by partitioning based on the brain area depression vector and the brain area anxiety vector, thereby identifying the disease type of the target individual based on the anxiety-significant brain area and the depression-significant brain area, thereby achieving the technical effect of enabling the electronic device to accurately identify the specific brain area in the target individual's brain that is closely related to anxiety symptoms and the specific brain area that is closely related to depressive symptoms, and identify the disease type of the target individual.

[0063] Based on the overall concept of the present invention for the method of locating brain regions for symptom mapping of depression-anxiety comorbidity, the present invention provides a method of locating brain regions for symptom mapping of depression-anxiety comorbidity, referring to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the method for locating brain regions for symptom mapping of depression-anxiety comorbidity in this application. In this embodiment, the method for locating brain regions for symptom mapping of depression-anxiety comorbidity includes steps S10 to S50:

[0064] Step S10: reading magnetic resonance data and identity information data of the target individual, and determining the gray matter volume corresponding to the brain of the target individual based on the magnetic resonance data and the identity information data;

[0065] It should be noted that the magnetic resonance data specifically includes functional magnetic resonance imaging data and structural magnetic resonance imaging data of the target individual, wherein the functional magnetic resonance imaging data indirectly reflects the functional activity of the tissue by detecting the hemodynamic changes in the brain or other tissues. For example, when a certain area of ​​the brain is active and performs a specific cognitive task, the neuronal activity in the area will increase. Correspondingly, in order to meet metabolic needs, the local blood flow will also increase. In this way, the functional magnetic resonance imaging data can sensitively capture the subtle changes in blood flow, and then infer the functional state of different brain regions. Similarly, the structural magnetic resonance imaging data is to place the human body in a strong magnetic field environment, use radio frequency pulses to excite the hydrogen nuclei that are widely present in the human body, so that they resonate and release detectable radio frequency signals, and then detect the morphology of each lobe in the brain of the target individual, the distribution range of gray matter and white matter, the size and shape of the ventricles, etc.

[0066] In addition, the identity information data may specifically include the target individual's corresponding gender, age, education level, total intracranial volume, depression clinical score, and anxiety clinical score. It is understandable that there are many ways to obtain the magnetic resonance data and identity information data, and this application does not limit this.

[0067] In this embodiment, during operation, the electronic device first reads a preset database to obtain magnetic resonance data and identity information data corresponding to the target individual stored in the database. The electronic device then processes the magnetic resonance data and identity information data to determine the gray matter volume that indicates the mapping relationship between the target individual's age, gender, years of education, total cranial volume, clinical depression score, clinical anxiety score, and the magnetic resonance data.

[0068] For example, see Figure 2 , Figure 2 This is a detailed flow chart of the first embodiment of the method for mapping brain regions for depression-anxiety comorbidity in this application. Figure 2As shown, during operation, the electronic device first reads a preset database to obtain functional magnetic resonance imaging data and structural magnetic resonance imaging data of target individuals with depression-anxiety comorbidity, and identity information data corresponding to each target individual including gender, age, education level, total intracranial volume, depression clinical score, and anxiety clinical score. The electronic device then processes the functional magnetic resonance imaging data of one of the target individuals through a preset DPARSF toolbox, and calculates the GMV (gray matter volume) parameter used to indicate the mapping relationship between the functional magnetic resonance imaging data and gender, age, education level, total intracranial volume, depression clinical score, and anxiety clinical score based on the processed functional magnetic resonance imaging data:

[0069] .

[0070] It is understandable that in the GMV parameter, is the gender of the target individual. Similarly, is the age of the target individual, is the educational level of the target individual. Similarly, For the above-mentioned clinical score of depression, similarly, is the above-mentioned clinical score of anxiety. Similarly, TIV is the above-mentioned total intracranial volume.

[0071] In a feasible implementation manner, the step of “determining the gray matter volume corresponding to the brain of the target individual based on the magnetic resonance data and the identity information data” in the above step S10 may specifically include steps S101 to S102:

[0072] Step S101: Preprocessing the magnetic resonance data, and performing multiple regression processing on the preprocessed magnetic resonance data, age, education level, gender, total intracranial volume, depression clinical score, and anxiety clinical score to determine the mapping relationship between the gray matter volume corresponding to the brain of the target individual and the magnetic resonance data, age, education level, gender, total intracranial volume, depression clinical score, and anxiety clinical score:

[0073] , where GMV is the gray matter volume, For gender, For age, For educational level, Clinical score for depression. is the clinical score of anxiety, TIV is the total intracranial volume, is the residual;

[0074] Step S102: Based on the mapping relationship, determine the weight information corresponding to the magnetic resonance data, age, education level, gender, total intracranial volume, depression clinical score, and anxiety clinical score, wherein the weight information is , , , , , , .

[0075] For example, for example, Figure 2 As shown, after acquiring the functional magnetic resonance imaging data and structural magnetic resonance imaging data of the target individual, and acquiring the gender, age, education level, total intracranial volume, depression clinical score, and anxiety clinical score of the target individual, the electronic device calls the preset DPARSF toolbox to process the functional magnetic resonance imaging data, so as to convert the functional magnetic resonance imaging data in DICOM format into functional magnetic resonance imaging data in NIFTI format, and delete the functional magnetic resonance imaging data at the initial multiple time points. At the same time, the electronic device uses the DPARSF toolbox to process the functional magnetic resonance imaging data in NIFTI format remaining after the deletion. The image data is processed with time layer correction, head motion correction, spatial registration, segmentation, spatial standardization, spatial smoothing, and linear drift removal. After that, the electronic device calls the preset general linear model to perform multivariate regression on multiple voxels contained in the processed functional magnetic resonance imaging data to regress out the effects of gender, age, education level, total cranial volume, clinical depression score, and clinical anxiety score on the voxels, thereby obtaining the GMV parameters corresponding to the target individual, which can reflect the mapping relationship between each voxel in the functional magnetic resonance imaging data and gender, age, education level, total cranial volume, clinical depression score, and clinical anxiety score:

[0076] .

[0077] The electronic device then determines the weight information corresponding to the gender based on the GMV parameter , weight information corresponding to age , weight information corresponding to education level , weight information corresponding to the total intracranial volume , weight information corresponding to the clinical score of depression , weight information corresponding to the anxiety clinical score .

[0078] It should be noted that the above-mentioned DICOM format is a commonly used format for medical images corresponding to functional magnetic resonance imaging data. It is understandable that the DICOM format is usually not suitable for the analysis of functional magnetic resonance imaging data, while the NIFIT format usually has only two files for each 3D or 4D image. Therefore, the NIFTI file is easy to manage and process, and is therefore more suitable for data analysis than the DICOM format.

[0079] Similarly, since the magnetic field of the MRI machine is unstable when it is started, the functional MRI data acquired at the first few time points may be affected by the unstable magnetic field, resulting in low accuracy. Therefore, by deleting the functional MRI data at the initial multiple time points, the accuracy of the test results can be further improved.

[0080] Similarly, since functional MRI data are collected layer by layer, and the collection time of different layers is different, this may cause temporal artifacts in the functional MRI data. By adjusting the collection time of each time layer through the time layer correction operation, the data of all layers can be aligned in time, further increasing the accuracy of the detection results.

[0081] Similarly, during the head motion correction process, the image at each time point is aligned by using rigid body transformation (translation and rotation) so that the image is aligned with the image at the previous time point or the first time point, thereby reducing the impact of the target individual's head movement on the data during the scanning process, thereby further improving the accuracy of the detection results.

[0082] Similarly, in the spatial registration operation, by mapping the functional magnetic resonance imaging data of the target individual to a standard space such as under the MNI template, the differences in brain morphology between different target individuals and the inconsistency in spatial position during scanning can be resolved, thereby further improving the accuracy of the detection results.

[0083] Similarly, by performing segmentation operations, different brain tissues such as gray matter, white matter, and cerebrospinal fluid contained in functional magnetic resonance imaging data can be identified to further improve the accuracy of the detection results.

[0084] Similarly, through spatial standardization operations, the magnetic resonance data corresponding to the target individual can be mapped to the standard brain template space and resampled to facilitate cross-individual comparison, thereby further improving the accuracy of the test results.

[0085] Similarly, spatial smoothing operations can reduce the noise contained in functional magnetic resonance imaging data and improve the signal-to-noise ratio in functional magnetic resonance imaging data, thereby more clearly observing the functional activation areas in statistical analysis and further improving the accuracy of the detection results.

[0086] Similarly, through the removal of linear drift operations, the linear trend caused by machine heating or subject fatigue in the functional magnetic resonance imaging data can be removed, making the functional magnetic resonance imaging data more accurate and further improving the accuracy of the test results.

[0087] Step S20: partitioning the brain to obtain a plurality of brain regions, and determining a depression vector and an anxiety vector of the brain region corresponding to the brain according to the gray matter volume and the identity information data;

[0088] In this embodiment, after calculating the gray matter volume, the electronic device further divides the target individual's brain into regions according to a preset partition template to obtain multiple brain regions. At the same time, the electronic device extracts depression score weight information corresponding to the clinical score of depression in the gray matter volume, and extracts anxiety score weight information corresponding to the clinical score of anxiety in the gray matter volume. The electronic device calculates the brain region depression vector and the brain region anxiety vector corresponding to the brain of the target individual based on the depression score weight information and the anxiety score weight information.

[0089] For example, for example, Figure 2 As shown, after calculating the GMV parameters, the electronic device first divides the brain of the target individual according to the AAL116 template, thereby dividing 116 ROI brain regions. At the same time, the electronic device extracts the depression score weight information that matches the depression clinical score in the GMV parameters , and extract the anxiety score weight information in the GMV parameters that matches the anxiety clinical score , electronic devices based on depression score weight information Calculate the depression vector of the brain region that matches the individual brain vector, and at the same time, the electronic device is based on the weight information of each anxiety score Calculate the anxiety vector of the brain region that matches the individual brain .

[0090] In a feasible implementation manner, the step of "determining the depression vector and the anxiety vector of the brain region corresponding to the brain according to the gray matter volume and the identity information data" in the above step S20 may specifically include steps S201 to S204:

[0091] Step S201: Obtain depression score weight information matched by the depression clinical score in the gray matter volume;

[0092] Step S202: calculating depression weights of multiple brain regions corresponding to the depression score weight information in the brain, and determining a depression vector of the brain region corresponding to the brain according to the depression weights of each brain region;

[0093] Step S203: Obtaining anxiety score weight information matched by the anxiety clinical score in the gray matter volume;

[0094] Step S204: Calculating anxiety weights of multiple brain regions corresponding to the anxiety score weight information in the brain, and determining a brain region anxiety vector corresponding to the brain according to each of the brain region anxiety weights.

[0095] In this embodiment, after the electronic device divides the target individual's brain into regions to obtain multiple brain regions, it first obtains the depression clinical score, determines the depression score weight information in the gray matter volume that matches the depression clinical score, calculates the brain region depression weights corresponding to the depression score weight information in all brain regions, and calculates the depression weight of each brain region to obtain the brain region depression vector corresponding to all brain regions; at the same time, the electronic device extracts the anxiety clinical score contained in the identity information data, determines the anxiety score weight information in the gray matter volume that matches the anxiety clinical score, calculates the brain region anxiety weights corresponding to the anxiety score weight information in all brain regions, and calculates the anxiety weight of each brain region to obtain the brain region anxiety vector corresponding to all brain regions.

[0096] For example, for example, Figure 2 As shown, after the electronic device divides the target individual's brain into 116 ROI brain regions, it first extracts the depression clinical score contained in the identity information data, and then screens out the depression score weight information that matches the depression clinical score in the GMV parameter according to the depression clinical score. , after which the electronic device calculates the depression score weight information The corresponding brain region depression ROI weights in the 116 ROI brain regions are calculated to determine the average brain region depression ROI weight. The electronic device determines the average brain region depression ROI weight as and identifies the brain region depression vectors in which each brain region in the target individual's brain has depression-related symptoms. At the same time, the electronic device extracts the anxiety clinical score contained in the identity information data, and screens out the anxiety score weight information in the GMV parameter that matches the anxiety clinical score according to the anxiety clinical score. , then the electronic device calculates the anxiety score weight information The anxiety ROI weights of the corresponding brain regions in the 116 ROI brain regions are calculated to determine the average anxiety ROI weight of the brain region. The electronic device determines the average anxiety ROI weight of the brain region as the anxiety vector of the brain region in which the anxiety-related symptoms exist in each brain region of the target individual's brain. .

[0097] Step S30: Classifying the plurality of brain regions based on the brain region depression vector and the brain region anxiety vector to determine depression-significant brain regions and anxiety-significant brain regions included in the plurality of brain regions.

[0098] Please note that, please refer to Figure 3 , Figure 3 This is a schematic diagram of the brain region classification results involved in the first embodiment of the method for mapping brain regions for depression-anxiety comorbidity in this application, as shown in FIG. Figure 3 As shown, the anxiety-significant brain region is a brain region indicating the presence of anxiety-related symptoms, and similarly, the depression-significant brain region is a brain region indicating the presence of depression-related symptoms. In addition, if a certain brain region of the target individual is both an anxiety-significant brain region and a depression-significant brain region, it indicates that the target individual has anxiety-depression combined symptoms.

[0099] In this embodiment, after obtaining the brain region depression vector and the brain region anxiety vector, the electronic device classifies each brain region according to the brain region depression vector and the brain region anxiety vector to determine anxiety-significant brain regions with anxiety symptoms in each brain region, and determine depression-significant brain regions with depressive symptoms in each brain region.

[0100] For example, for example, Figure 2 As shown, the electronic device calculates the depression vector of the brain region and brain area anxiety vector Then, according to the depression vector of the brain region and brain area anxiety vector 116 ROI brain regions were screened to identify anxiety-significant brain regions that are correlated with the target individual's anxiety symptoms, and depression-significant brain regions that are correlated with the target individual's depressive symptoms.

[0101] In a feasible implementation manner, the above step S30 may specifically include steps S301 to S304:

[0102] Step S301: reading each first signal time series contained in the magnetic resonance data;

[0103] Step S302: calculating the brain region correlation between any two brain regions according to each of the first signal time series, and determining the functional connection matrix corresponding to a plurality of the brain regions according to each of the brain region correlations;

[0104] Step S303: Calculating various depression-related parameters based on the brain region depression vector and the functional connectivity matrix, and calculating various anxiety-related parameters based on the brain region anxiety vector and the functional connectivity matrix;

[0105] Step S304: classifying the plurality of brain regions according to the depression-related parameters and the anxiety-related parameters to determine depression-significant brain regions and anxiety-significant brain regions included in the plurality of brain regions.

[0106] In this embodiment, after calculating the brain region depression vector and the brain region anxiety vector, the electronic device first reads each first signal time series contained in the magnetic resonance data, and then determines the brain region correlation between any two brain regions according to each first signal time series. The electronic device then determines the functional connection matrix formed between the brain regions according to the brain region correlation. Then, the electronic device performs a correlation analysis on the brain region depression vector and the functional connection matrix to obtain the depression correlation parameters corresponding to each brain region. At the same time, the electronic device performs a correlation analysis on the brain region anxiety vector and the functional connection matrix to obtain the anxiety correlation parameters corresponding to each brain region. Finally, the electronic device classifies each brain region based on each depression correlation parameter and each anxiety correlation parameter to determine the depression-significant brain region and anxiety-significant brain region in each brain region.

[0107] For example, for example, Figure 2 As shown, the electronic device calculates the depression vector of the brain region and brain area anxiety vector Afterwards, each first BOLD signal time series contained in the functional magnetic resonance imaging data is first read, and then the electronic device calculates the brain region correlation between any two brain regions according to each first BOLD signal time series. :

[0108] ;

[0109] Electronic devices thus correlate various brain regions The 116 ROI brain regions were processed to obtain a functional connection matrix with a vector dimension of 1×116. After that, the electronic device processed the depression vector of the brain region. Pearson correlation coefficient analysis was performed on each row of the functional connectivity matrix to determine the depression vector of the brain region The significance level of the depression correlation coefficient generated between each row of the functional connection matrix, and the effect of electronic devices on the anxiety vector of the brain region Pearson correlation coefficient analysis was performed on each row of the functional connectivity matrix to determine the anxiety vector of the brain region and the significance level of the anxiety correlation coefficient generated between each row of the functional connectivity matrix. Finally, the electronic device classifies the 116 ROI brain regions according to the significance level of each depression correlation coefficient and the significance level of each anxiety correlation coefficient to determine the depression-significant brain regions and anxiety-significant brain regions contained in the 116 ROI brain regions.

[0110] It should be noted that the correlation between brain regions middle, is the Pearson correlation coefficient between brain area A and brain area B, is the covariance of the BOLD signal time series corresponding to brain area A and brain area B, is the standard deviation of the BOLD signal time series corresponding to brain area A and brain area B respectively.

[0111] In a feasible implementation manner, the above step S304 may further include steps S3041 to S3044:

[0112] Step S3041: obtaining a preset depression correlation coefficient significance level threshold, and comparing each of the depression correlation parameters with the depression correlation coefficient significance level threshold to obtain a first comparison result;

[0113] Step S3042: determining a target first comparison result in each of the first comparison results, and determining the brain region corresponding to the target first comparison result as a depression-significant brain region, wherein the target first comparison result is a depression-related parameter that is less than a depression-related coefficient significance level threshold;

[0114] Step S3043: obtaining a preset anxiety correlation coefficient significance level threshold, and comparing each of the anxiety correlation parameters with the anxiety correlation coefficient significance level threshold to obtain a second comparison result;

[0115] Step S3044: Determine a target second comparison result in each of the second comparison results, and determine the brain area corresponding to the target second comparison result as an anxiety-significant brain area, wherein the target second comparison result is an anxiety-related parameter that is less than a significance level threshold of the anxiety-related coefficient.

[0116] In this embodiment, after obtaining each depression-related parameter and each anxiety-related parameter, the electronic device first reads the storage module configured by itself to obtain a preset depression-related coefficient significance level threshold, and the electronic device compares each depression-related parameter with the depression-related coefficient significance level threshold to obtain multiple first comparison results. Afterwards, the electronic device determines in the multiple first comparison results that the comparison result is a target first comparison result in which the depression-related parameter is less than the depression-related coefficient significance level threshold, and determines the brain area corresponding to the target first comparison result as a depression-significant brain area; similarly, the electronic device reads the storage module to obtain a preset anxiety-related coefficient significance level threshold, and the electronic device compares each anxiety-related parameter with the anxiety-related coefficient significance level threshold to obtain multiple second comparison results. Afterwards, the electronic device determines in the multiple second comparison results that the comparison result is a target second comparison result in which the anxiety-related parameter is less than the anxiety-related coefficient significance level threshold, and determines the brain area corresponding to the target second comparison result as an anxiety-significant brain area.

[0117] Exemplarily, for example, after obtaining the significance level of each depression-related coefficient and the significance level of each anxiety-related coefficient, the electronic device first reads the storage module configured by itself to obtain a preset depression-related coefficient significance level threshold of 0.0003125, and the electronic device compares the significance level of each depression-related coefficient with the depression-related coefficient significance level threshold to obtain multiple first comparison results. After that, the electronic device reads the multiple first comparison results to mark the ROI brain area with a significance level of the depression-related coefficient less than 0.0003125 as 1 based on the multiple first comparison results, and marks the ROI brain area with a significance level of the depression-related coefficient greater than 0.0003125 as 0, and the electronic device further determines the ROI brain area marked as 1 as A significant depression brain region that is correlated with the depressive symptoms of the target individual; similarly, the electronic device reads the storage module to obtain a preset anxiety-related coefficient significance level threshold of 0.0003125, and the electronic device compares the significance level of each anxiety-related coefficient with the anxiety-related coefficient significance level threshold to obtain a plurality of second comparison results. Thereafter, the electronic device reads the plurality of second comparison results, and based on the plurality of second comparison results, marks the ROI brain region whose significance level of the anxiety-related coefficient is less than 0.0003125 as 1, and marks the ROI brain region whose significance level of the anxiety-related coefficient is greater than 0.0003125 as 0, and the electronic device further determines the ROI brain region marked as 1 as a significant anxiety brain region that is correlated with the anxiety symptoms of the target individual.

[0118] Step S40: generating a plurality of significant brain region labels corresponding to the respective brain regions according to the significant depression brain regions and the significant anxiety brain regions, and generating a plurality of network topology labels corresponding to the respective brain regions according to the identity information data and the magnetic resonance data;

[0119] In this embodiment, after screening out the anxiety-significant brain areas and depression-significant brain areas of the target individual, the electronic device generates significant brain area labels indicating whether the brain area is a depression-significant brain area and an anxiety-significant brain area based on the above-mentioned depression-significant brain areas and anxiety-significant brain areas. At the same time, the electronic device generates network topology labels corresponding to multiple brain areas based on the identity information data and the above-mentioned magnetic resonance data, including clustering coefficient, node connection strength, node betweenness center number, node local efficiency, node regional efficiency, modularity center Z score, node risk coefficient, and spatial risk coefficient.

[0120] Exemplarily, for example, after screening out the anxiety-significant brain regions and depression-significant brain regions of the target individual, the electronic device can also generate a brain region significance label indicating whether the brain region is an anxiety-significant brain region or a depression-significant brain region based on the anxiety-significant brain region and the depression-significant brain region. At the same time, the electronic device reads the functional connection matrix generated based on each first BOLD signal time series, and calculates the clustering coefficient corresponding to each ROI brain region according to the functional connection matrix. , Node connection strength , node betweenness, centrality , node local efficiency , Node Area Efficiency , Modularity Center Z Score and other network topology indicators, and determine the node risk parameters corresponding to each brain region :

[0121] ;

[0122] And, determine the spatial risk parameters corresponding to each brain region :

[0123] .

[0124] It should be noted that the above clustering coefficient The extraction process is:

[0125] ;in, is the number of edges between brain region node i and its adjacent brain region nodes, is the number of edges connecting the surrounding brain region nodes and brain region node i;

[0126] In addition, the above node connection strength The extraction process is:

[0127] ;in, is the number of common neighbors of brain region node x and brain region node y, is the smaller strength of the node in brain region node x and brain region node y, is the weight of the edge between brain region node x and brain region node y;

[0128] In addition, the above node betweenness center number The extraction process is:

[0129] ,in, is the number of all shortest paths from brain region node s to brain region node t, is the number of paths passing through the brain region node v in the shortest path, and s and t are two different brain region nodes in the network.

[0130] In addition, the above node local efficiency The extraction process is:

[0131] ,in, is the number of brain region nodes in the subgraph formed by the adjacent brain region nodes of brain region node i, For brain region node j and brain region node k in the subgraph The shortest path length in ;

[0132] In addition, the above node area efficiency The extraction process is:

[0133] ,in, is the number of points within the radius R of brain region node i, For brain region node j and brain region node k in the subgraph The shortest path length in ;

[0134] In addition, the above modularity center Z score The extraction process is:

[0135] ,in, is the total number of edges between brain region node i and other brain region nodes in the module, is the average connectivity of brain region node i among all brain region nodes in module S, is the standard deviation of the connectivity of brain region node i among all brain region nodes in module S.

[0136] Step S50: determining the disease type of the target individual based on the significant brain region labels and the network topology labels, wherein the disease type includes first-time disease and non-first-time disease.

[0137] In this embodiment, after generating each significant brain region label and each network topology label, the electronic device integrates the significant brain region label and the network topology label corresponding to each brain region to generate a brain feature vector corresponding to each brain region. The electronic device inputs the brain feature vectors corresponding to all brain regions into a preset graph convolutional neural network, and the graph convolutional neural network determines whether the onset type of the target individual is the first onset or non-first onset based on each brain feature vector.

[0138] For example, when the electronic device determines to perform full image input, it selects the node risk parameters corresponding to 90 ROI brain regions in the brain area among the 116 ROI brain regions. , spatial risk parameters , network topology indicators, and significant brain area labels form a brain feature vector, and each brain feature vector is input into a preset graph convolutional neural network. The graph convolutional neural network identifies the disease status of the target individual based on each brain feature vector to determine whether the disease status of the target individual is the first onset or non-first onset.

[0139] In a feasible implementation manner, the target individuals include multiple healthy persons and multiple patients, and the above step S50 may specifically include steps S501 to S503:

[0140] Step S501: determining the average gray matter volume and gray matter volume standard deviation corresponding to multiple brain regions of multiple healthy subjects;

[0141] Step S502: Calculate the W scores of multiple patients according to the gray matter volume parameters of multiple brain regions of multiple patients, the average gray matter volume of multiple healthy people, and the gray matter volume standard deviation, and determine the node risk parameters and spatial risk parameters corresponding to the multiple brain regions based on the W scores, wherein the W scores are: , is a gray matter volume parameter of multiple brain regions of multiple patients, is the average gray matter volume, is the standard deviation of the gray matter volume;

[0142] Step S503: Integrate the node risk parameters, the spatial risk parameters, the significant brain region labels and the network topology labels corresponding to the multiple brain regions to obtain each brain feature vector, and classify and predict each brain feature vector to determine the disease type of the target individual.

[0143] For example, after generating each significant brain region label and each network topology label, the electronic device first determines the gray matter volume of each of the 116 ROI brain regions. , and based on the gray matter volume corresponding to each of the 116 ROI brain regions The average gray matter volume corresponding to 116 ROI brain regions was calculated and gray matter volume standard deviation , the electronic device then based on the average gray matter volume and gray matter volume standard deviation The W scores corresponding to 116 ROI brain regions were calculated:

[0144] ;

[0145] Afterwards, the electronic device determines the node risk parameters corresponding to each brain region node based on the W score. and spatial risk parameters Finally, when the electronic device determines to execute the full image input, it selects the node risk parameters corresponding to 90 ROI brain areas in the brain area among the 116 ROI brain areas. , spatial risk parameters , network topology indicators, and significant brain area labels form a brain feature vector, and each brain feature vector is input into the above-mentioned graph convolutional neural network, which identifies the disease status of the target individual based on each brain feature vector to determine whether the disease status of the target individual is the first onset or non-first onset.

[0146] In this way, after determining the anxiety-significant brain areas and depression-significant brain areas of the target individual, the electronic device can further detect the individual's disease type based on the anxiety-significant brain areas and depression-significant brain areas.

[0147] It should be noted that, in another embodiment, in addition to directly identifying the individual's disease type through the graph convolutional neural network, a sample data set can be formed based on the extracted brain feature vectors. The sample data set is randomly shuffled and the first 80% is selected as a training set, and the remaining 20% ​​is used as a test set. The model is built according to the model framework diagram shown in Table 1, and the data is input for training:

[0148]

[0149] Table 1

[0150] Please note that, please refer to Figure 4 , Figure 4 This is a schematic diagram of the graph convolutional neural network structure involved in the first embodiment of the method for locating brain regions for symptoms mapping of depression-anxiety comorbidity in this application, as shown in Figure 4As shown, the convolution type of each layer of the graph convolutional neural network base model can be GCNConv, GINConv, GATConv, etc. The hidden_channel of each layer defaults to 128. The optuna framework can be used to perform optimal parameterized grid search of hidden layer dimension and learning rate to find the optimal parameters for each task for different data sets. It can be understood that the specific process of training the graph convolutional neural network base is a prior art, so it will not be repeated here.

[0151] In a feasible implementation manner, the step of “determining the node risk parameters and the spatial risk parameters corresponding to the plurality of brain regions based on the W score” in the above step S502 may specifically include steps S5021 to S5022:

[0152] Step S5021: determining the connection weights corresponding to each of the plurality of brain regions, wherein the connection weights are connection weights between the target brain region and other brain regions;

[0153] Step S5022: determining five brain regions with the largest weights corresponding to the target brain region according to each of the connection weights, and determining a node risk parameter corresponding to the target brain region based on the five brain regions with the largest weights and the W score:

[0154] ,in, is the connection strength between brain region node N and other brain regions, is the node risk parameter.

[0155] For example, after determining the W score corresponding to each brain region, the electronic device first determines the connection weights generated between the brain region node N and other brain regions, and then determines the five brain regions with the largest weights N1, N2, N3, N4, and N5 corresponding to the brain region node N according to the connection weights, and the electronic device calculates the connection strength between each of the brain regions with the largest weights N1, N2, N3, N4, and N5 and the brain region node N. , and sum the results of multiplying them with the W score to obtain the node risk parameter corresponding to the brain region node N :

[0156] .

[0157] In a feasible implementation manner, the step of “determining the node risk parameters and the spatial risk parameters corresponding to the plurality of brain regions based on the W score” in the above step S502 may further include steps S5023-S5024:

[0158] Step S5023: determining the Euclidean distance between each of the plurality of brain regions and other brain regions, and determining five brain regions with the closest Euclidean distances to the target brain region according to each of the Euclidean distances;

[0159] Step S5024: Determine the spatial risk parameter of the target brain region based on the five brain regions closest to the Euclidean distance and the W score:

[0160] ,in, is the spatial risk parameter.

[0161] Exemplarily, for example, after determining the W score corresponding to each brain region, the electronic device can also determine the Euclidean distance between the brain region node N and other brain regions, and determine the five Euclidean distances closest to the brain region node N, M1, M2, M3, M4, M5, and the electronic device calculates the connection strength between the brain regions M1, M2, M3, M4, M5 with the Euclidean distance and the brain region node N. , and sum the results of multiplying them with the W score to obtain the spatial risk parameter corresponding to the brain area node N :

[0162] .

[0163] In a feasible implementation manner, the above step S50 may further include steps S504 to S505:

[0164] Step S504: combining the spatial risk parameters, the node risk parameters, the network topology labels and the significant brain region labels corresponding to the significant depression brain regions and the significant anxiety brain regions to generate brain feature vectors;

[0165] Step S505: classify and predict each of the brain feature vectors to determine the disease type of the target individual.

[0166] In this embodiment, after generating network topology labels corresponding to multiple brain regions, the electronic device can also integrate the network topology labels, significant brain region labels, node risk parameters and spatial risk parameters corresponding to the anxiety-significant brain regions and depression-significant brain regions to generate feature vectors for each brain. Finally, the electronic device inputs the generated feature vectors into the above-mentioned graph convolutional neural network, and the graph convolutional neural network determines whether the onset type of the target individual is the first onset or non-first onset based on the brain feature vectors.

[0167] For example, after the electronic device generates network topology labels corresponding to multiple brain regions, if the electronic device determines to execute the subgraph input, it will filter out the node risk parameters corresponding to the anxiety-significant brain region and the depression-significant brain region. , spatial risk parameters , network topology indicators, and significant brain area labels form a brain feature vector. After that, the electronic device inputs each brain feature vector into the above-mentioned graph convolutional neural network, and the graph convolutional neural network identifies the disease status of the target individual based on each brain feature vector to determine whether the disease status of the target individual is the first onset or not the first onset.

[0168] In this way, compared with the full-graph input method, sub-graph input can detect the individual's disease type with less data input, thereby further improving the detection efficiency.

[0169] In this embodiment, during operation, the electronic device first reads a preset database to obtain magnetic resonance data and identity information data corresponding to the target individual stored in the database, and then processes the magnetic resonance data and identity information data to determine the gray matter volume used to indicate the mapping relationship between the target individual's age, gender, years of education, total intracranial volume, clinical depression score, and clinical anxiety score and the magnetic resonance data. Afterwards, the electronic device divides the target individual's brain into regions according to a preset partitioning template to obtain a plurality of brain regions. At the same time, the electronic device extracts depression score weight information corresponding to the clinical depression score in the gray matter volume, and extracts anxiety score weight information corresponding to the clinical anxiety score in the gray matter volume. The electronic device calculates the brain region depression vector and the brain region anxiety vector corresponding to the target individual's brain based on the depression score weight information and the anxiety score weight information. Afterwards, the electronic device classifies each brain region based on the brain region depression vector and the brain region anxiety vector to determine the presence of depression in each brain region. In the anxiety-significant brain areas of anxiety symptoms, and the depression-significant brain areas where depressive symptoms are determined in each brain area, the electronic device then generates significant brain area labels indicating whether the brain area is a depression-significant brain area and an anxiety-significant brain area based on the above-mentioned depression-significant brain areas and anxiety-significant brain areas. At the same time, the electronic device generates network topology labels corresponding to multiple brain areas according to the identity information data and the above-mentioned magnetic resonance data, including clustering coefficient, node connection strength, node betweenness center number, node local efficiency, node regional efficiency, modularity center Z score, node risk coefficient, and spatial risk coefficient. Finally, the electronic device integrates the significant brain area labels and network topology labels corresponding to each brain area to generate a brain feature vector corresponding to each brain area. The electronic device inputs the brain feature vectors corresponding to all brain areas into a preset graph convolutional neural network, and the graph convolutional neural network determines whether the onset type of the target individual is the first onset or non-first onset based on each brain feature vector.

[0170] In this way, the present application solves the technical problem in the related art that the specific brain area in the target individual's brain that is closely related to anxiety symptoms cannot be identified. That is, the present application processes the magnetic resonance data and identity information data of the target individual so that the electronic device can obtain the gray matter volume representing the correlation between the magnetic resonance data and the identity information data, and determine the brain area depression vector and the brain area anxiety vector corresponding to the individual's brain based on the anxiety clinical score and the depression clinical score contained in the gray matter volume and the identity information data, so as to identify the anxiety-significant brain area and the depression-significant brain area contained in the multiple brain areas obtained by partitioning based on the brain area depression vector and the brain area anxiety vector, thereby identifying the disease type of the target individual based on the anxiety-significant brain area and the depression-significant brain area, thereby achieving the technical effect of enabling the electronic device to accurately identify the specific brain area in the target individual's brain that is closely related to anxiety symptoms and the specific brain area that is closely related to depressive symptoms, and identify the disease type of the target individual.

[0171] The present application provides an electronic device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the brain region localization method for symptom mapping for depression-anxiety comorbidity in the above-mentioned embodiment 1.

[0172] Reference below Figure 5 , which shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present application. The electronic device in the embodiments of the present application may include but is not limited to a mobile terminal, a data storage control terminal, a PC and other terminals connected to an electronic control unit supporting the electronic device. Figure 5 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0173] like Figure 5As shown, the electronic device may include a processing device 1001 (e.g., a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM: Read Only Memory) 1002 or a program loaded from a storage device 1003 to a random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the electronic device are also stored. The processing device 1001, ROM1002, and RAM1004 are connected to each other through a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Generally, the following systems can be connected to the I / O interface 1006: an input device 1007 including, for example, a touch screen, a touch pad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 1008 including, for example, a liquid crystal display (LCD: Liquid Crystal Display), a speaker, a vibrator, etc.; a storage device 1003 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 1009. The communication device 1009 can allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an electronic device with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems can be implemented or have alternatively.

[0174] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0175] The electronic device provided by the present application adopts the method for locating brain regions for symptom mapping for depression-anxiety comorbidity in the above-mentioned embodiment, which can solve the technical problem in the related art that the specific brain regions in the target individual's brain that are closely related to anxiety symptoms cannot be identified. Compared with the prior art, the beneficial effects of the electronic device provided by the present application are the same as the beneficial effects of the method for locating brain regions for symptom mapping for depression-anxiety comorbidity provided in the above-mentioned embodiment, and the other technical features in the electronic device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0176] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0177] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0178] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the brain region localization method for disease mapping for depression-anxiety comorbidity in the above-mentioned embodiment.

[0179] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0180] The computer-readable storage medium may be included in the electronic device, or may exist independently without being installed in the electronic device.

[0181] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by an electronic device, the electronic device: reads the magnetic resonance data and identity information data of the target individual, and determines the gray matter volume corresponding to the brain of the target individual based on the magnetic resonance data and the identity information data; partitions the brain to obtain multiple brain regions, and determines the brain region depression vector and the brain region anxiety vector corresponding to the brain according to the gray matter volume and the identity information data; classifies the multiple brain regions based on the brain region depression vector and the brain region anxiety vector to determine the depression-significant brain regions and the anxiety-significant brain regions included in the multiple brain regions; generates multiple significant brain region labels corresponding to each of the brain regions according to the depression-significant brain regions and the anxiety-significant brain regions, and generates multiple network topology labels corresponding to each of the brain regions according to the identity information data and the magnetic resonance data; determines the onset type of the target individual based on the significant brain region labels and the network topology labels, wherein the onset type includes the first onset and the non-first onset.

[0182] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0183] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0184] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0185] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned method for mapping brain regions for depression-anxiety comorbidity, and can solve the technical problem in the related art that the specific brain regions in the target individual's brain that are closely related to anxiety symptoms cannot be identified. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the method for mapping brain regions for depression-anxiety comorbidity provided in the above-mentioned embodiment, and will not be repeated here.

[0186] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for mapping brain regions for depression-anxiety comorbidity.

[0187] The computer program product provided by the present application can solve the technical problem in the related art that the specific brain region in the target individual's brain that is closely related to anxiety symptoms cannot be identified. Compared with the prior art, the beneficial effects of the computer program product provided by the present application are the same as the beneficial effects of the brain region localization method for symptom mapping for depression-anxiety comorbidity provided in the above embodiment, and will not be repeated here.

[0188] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for mapping brain regions for depression-anxiety comorbidity, characterized in that: The method for mapping brain regions for depression-anxiety comorbidity includes: Reading magnetic resonance data and identity information data of a target individual, and determining a gray matter volume corresponding to a brain of the target individual based on the magnetic resonance data and the identity information data; Partitioning the brain to obtain a plurality of brain regions, and obtaining depression score weight information matching the depression clinical score in the gray matter volume; Calculating depression weights of multiple brain regions corresponding to the depression score weight information in the brain, and determining a depression vector of the brain region corresponding to the brain according to each of the depression weights of the brain region; Obtaining anxiety score weight information matched to the anxiety clinical score in the gray matter volume; Calculating anxiety weights of multiple brain regions corresponding to the anxiety score weight information in the brain, and determining an anxiety vector of the brain region corresponding to the brain according to each of the anxiety weights of the brain region; Classifying the plurality of brain regions based on the brain region depression vector and the brain region anxiety vector to determine a depression-significant brain region and an anxiety-significant brain region included in the plurality of brain regions; Generating a plurality of significant brain region labels corresponding to the respective brain regions according to the significant depression brain regions and the significant anxiety brain regions, and generating a plurality of network topology labels corresponding to the respective brain regions according to the identity information data and the magnetic resonance data; The disease type of the target individual is determined based on the significant brain region labels and the network topology labels, wherein the disease type includes first-time disease and non-first-time disease.

2. The method for locating brain regions for disease mapping of depression-anxiety comorbidity according to claim 1, characterized in that: The identity information data includes age, education level, gender, total intracranial volume, clinical score of depression and clinical score of anxiety. The step of determining the gray matter volume corresponding to the brain of the target individual based on the magnetic resonance data and the identity information data includes: The magnetic resonance data are preprocessed, and the preprocessed magnetic resonance data, age, education level, gender, total intracranial volume, depression clinical score, and anxiety clinical score are combined for multivariate regression processing to determine the mapping relationship between the gray matter volume corresponding to the brain of the target individual and the magnetic resonance data, age, education level, gender, total intracranial volume, depression clinical score, and anxiety clinical score: , where GMV is the gray matter volume, For gender, For age, For educational level, Clinical score for depression. is the clinical score of anxiety, TIV is the total intracranial volume, is the residual; Based on the mapping relationship, the weight information corresponding to the magnetic resonance data, age, education level, gender, total intracranial volume, clinical score of depression, and clinical score of anxiety is determined, wherein the weight information is , , , , , , .

3. The method for mapping brain regions for depression-anxiety comorbidity according to claim 1, characterized in that: The step of classifying the plurality of brain regions based on the brain region depression vector and the brain region anxiety vector to determine depression-significant brain regions and anxiety-significant brain regions included in the plurality of brain regions comprises: Reading each first signal time series contained in the magnetic resonance data; Calculating the brain region correlation between any two brain regions according to each of the first signal time series, and determining the functional connection matrix corresponding to a plurality of the brain regions according to each of the brain region correlations; Calculating various depression-related parameters based on the brain region depression vector and the functional connectivity matrix, and calculating various anxiety-related parameters based on the brain region anxiety vector and the functional connectivity matrix; The plurality of brain regions are classified according to each of the depression-related parameters and each of the anxiety-related parameters to determine depression-significant brain regions and anxiety-significant brain regions included in the plurality of brain regions.

4. The method for locating brain regions for disease mapping of depression-anxiety comorbidity according to claim 3, characterized in that: The step of classifying the plurality of brain regions according to the depression-related parameters and the anxiety-related parameters to determine depression-significant brain regions and anxiety-significant brain regions included in the plurality of brain regions further includes: Obtaining a preset depression correlation coefficient significance level threshold, and comparing each of the depression correlation parameters with the depression correlation coefficient significance level threshold to obtain a first comparison result; Determine a target first comparison result in each of the first comparison results, and determine the brain region corresponding to the target first comparison result as a depression-significant brain region, wherein the target first comparison result is a depression-related parameter that is less than a depression-related coefficient significance level threshold; Obtaining a preset anxiety correlation coefficient significance level threshold, and comparing each of the anxiety correlation parameters with the anxiety correlation coefficient significance level threshold to obtain a second comparison result; A target second comparison result is determined in each of the second comparison results, and the brain region corresponding to the target second comparison result is determined as an anxiety-significant brain region, wherein the target second comparison result is that the anxiety-related parameter is less than the anxiety-related coefficient significance level threshold.

5. The method for locating brain regions for disease mapping of depression-anxiety comorbidity according to claim 4, characterized in that: The target individuals include multiple healthy people and multiple patients, and the step of determining the disease type of the target individuals based on the significant brain region labels and the network topology labels includes: Determine the average gray matter volume and gray matter volume standard deviation corresponding to multiple brain regions of multiple healthy subjects; The W scores of the multiple patients are calculated according to the gray matter volume parameters of the multiple brain regions of the multiple patients, the average gray matter volume of the multiple healthy persons and the gray matter volume standard deviation, and the node risk parameters and spatial risk parameters corresponding to the multiple brain regions are determined based on the W scores, wherein the W scores are: , is a gray matter volume parameter of multiple brain regions of multiple patients, is the average gray matter volume, is the standard deviation of the gray matter volume; The node risk parameters, the spatial risk parameters, the significant brain region labels and the network topology labels corresponding to the multiple brain regions are integrated to obtain each brain feature vector, and each brain feature vector is classified and predicted to determine the disease type of the target individual.

6. The method for locating brain regions for disease mapping of depression-anxiety comorbidity according to claim 5, characterized in that: The step of determining the node risk parameters and spatial risk parameters corresponding to the plurality of brain regions based on the W score comprises: Determining connection weights corresponding to each of the plurality of brain regions, wherein the connection weights are connection weights between the target brain region and other brain regions; Determine five brain regions with the largest weights corresponding to the target brain region according to each of the connection weights, and determine a node risk parameter corresponding to the target brain region based on the five brain regions with the largest weights and the W score: ,in, is the connection strength between brain region node N and other brain regions, is the node risk parameter.

7. The method for locating brain regions for disease mapping of depression-anxiety comorbidity according to claim 6, characterized in that: The step of determining the node risk parameters and spatial risk parameters corresponding to the plurality of brain regions based on the W score further includes: Determine the Euclidean distance between each of the plurality of brain regions and other brain regions, and determine five brain regions with the closest Euclidean distances corresponding to the target brain region according to each of the Euclidean distances; The spatial risk parameter of the target brain region is determined based on the five brain regions closest to the Euclidean distance and the W score: ,in, is the spatial risk parameter.

8. The method for mapping brain regions for depression-anxiety comorbidity according to claim 7, characterized in that: The step of determining the disease type of the target individual based on the significant brain region labels and the network topology labels further includes: The spatial risk parameters, the node risk parameters, the network topology labels and the significant brain region labels corresponding to the significant depression brain regions and the significant anxiety brain regions are combined to generate brain feature vectors; Classification prediction is performed on each of the brain feature vectors to determine the disease type of the target individual.

9. An electronic device, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for mapping brain regions for depression-anxiety comorbidity according to any one of claims 1 to 8.

Images