Functional connectivity weight-based TMS target positioning method and system

Abstract

Provided in the present application are a functional connectivity weight-based TMS target positioning method and system. The method comprises: preprocessing structural magnetic resonance image data and functional magnetic resonance image data of multiple subjects; acquiring, from the preprocessed structural magnetic resonance image data, a region of interest corresponding to a TMS stimulation target for each of the subjects to obtain multiple regions of interest; acquiring a first functional connectivity matrix between the multiple regions of interest and a whole-brain region in the preprocessed functional magnetic resonance image data; acquiring a functional connectivity weight matrix between depression scale score data and the functional connectivity matrix; mapping the functional connectivity weight matrix to a second functional connectivity matrix to obtain an estimated efficacy map of the whole-brain region; and clustering voxels of a left DLPFC region in the estimated efficacy map, and determining a cluster center as a TMS treatment target. By means of the method, the problem of TMS lacking individualized and precise stimulation targets in the related art is solved.

Description

Transcranial magnetic stimulation target positioning method and system based on functional connection weight

[0001] Cross-reference to Related Applications

[0002] This application claims priority to Chinese Patent Application No. 202411344321.3, filed September 25, 2024, entitled "Transcranial magnetic stimulation target positioning method and system based on functional connection weight", which is incorporated by reference herein in its entirety. TECHNICAL FIELD

[0003] The present application relates to the technical field of transcranial magnetic stimulation target positioning, and in particular to a transcranial magnetic stimulation target positioning method and system based on functional connection weight. BACKGROUND

[0004] Transcranial magnetic stimulation (TMS) is a non-invasive neural modulation technique used to study human neurophysiology and treat neurological disorders. TMS mainly stimulates the left dorsal lateral prefrontal cortex (DLPFC). Related studies have shown that TMS can change the functional connectivity between the DLPFC and the distal subcortical region, thereby improving depression. However, the TMS technology used in related technologies lacks individualized precise stimulation targets.

[0005] SUMMARY

[0006] The present application provides a transcranial magnetic stimulation target positioning method and system based on functional connection weight to solve the problem of lack of individualized precise stimulation targets in TMS used in related technologies.

[0007] The present application provides a transcranial magnetic stimulation target positioning method based on functional connection weight, comprising:

[0008] Obtaining depression scale score data, structural magnetic resonance imaging data, and functional magnetic resonance imaging data of a plurality of subjects; preprocessing the structural magnetic resonance imaging data and the functional magnetic resonance imaging data to obtain preprocessed structural magnetic resonance imaging data and preprocessed functional magnetic resonance imaging data;

[0009] In the preprocessed structural magnetic resonance imaging data, obtaining a region of interest corresponding to a TMS stimulation target of each subject to obtain a plurality of regions of interest;

[0010] Obtaining a first functional connection matrix between a plurality of regions of interest and brain regions in the preprocessed functional magnetic resonance imaging data;

[0011] obtain a functional connection weight matrix between the depression scale score data and the first functional connection matrix, the functional connection weight matrix being used to represent a degree of correlation between the functional connection matrix and the depression scale score data;

[0012] map the functional connection weight matrix into the second functional connection matrix to obtain an estimated efficacy map of the whole brain region; and cluster voxels in a left DLPFC region in the estimated efficacy map, and determine a cluster center as a TMS treatment target point.

[0013] According to the TMS target point positioning method based on the functional connection weight provided in the present application, the TMS stimulation target point corresponding to the region of interest of each subject is obtained in the preprocessed structural magnetic resonance imaging data, and a plurality of regions of interest are obtained, including:

[0014] obtain the coil position and the coil posture of each subject when the TMS treatment is performed;

[0015] perform electric field simulation in the cerebral cortex of the preprocessed structural magnetic resonance imaging data according to the coil position and the coil posture, and obtain a simulated electric field;

[0016] obtain a point with the maximum simulated electric field value in the simulated electric field as the TMS stimulation target point;

[0017] obtain the region of interest corresponding to the TMS stimulation target point of each subject in the cerebral cortex, and obtain a plurality of regions of interest.

[0018] According to the TMS target point positioning method based on the functional connection weight provided in the present application, the functional connection matrix between the plurality of regions of interest and the whole brain region in the preprocessed functional magnetic resonance imaging data is obtained, including:

[0019] extract blood oxygen level dependent signals of the plurality of regions of interest, the whole brain region and the whole brain voxels to obtain time series matrices of the plurality of regions of interest, the whole brain region and the whole brain voxels;

[0020] obtain a Pearson correlation coefficient between the time series matrices of the plurality of regions of interest and the time series matrices of the whole brain region to obtain a first functional connection matrix;

[0021] obtain a Pearson correlation coefficient between the time series matrices of the whole brain region and the time series matrices of the whole brain voxels to obtain a second functional connection matrix;

[0022] determine the functional connection weight matrix according to the first functional connection matrix and the second functional connection matrix.

[0023] According to the TMS target positioning method based on functional connection weight provided in the application, the functional connection weight matrix between the depression scale score data and the first functional connection matrix is obtained, including:

[0024] The functional connection weight matrix between the depression scale score data and the first functional connection matrix is obtained based on a partial least squares regression model.

[0025] According to the TMS target positioning method based on functional connection weight provided in the application, the structural magnetic resonance image data and the functional magnetic resonance image data are preprocessed to obtain preprocessed structural magnetic resonance image data and preprocessed functional magnetic resonance image data, including:

[0026] Obtaining brain tissue image data in the structural magnetic resonance image data;

[0027] Obtaining the functional magnetic resonance image data after time correction and head motion correction to obtain corrected functional magnetic resonance image data;

[0028] Registering the brain tissue image data and the corrected functional magnetic resonance image data to the same standard template to obtain the preprocessed structural magnetic resonance image data and the preprocessed functional magnetic resonance image data, respectively.

[0029] According to the TMS target positioning method based on functional connection weight provided in the application, further comprising:

[0030] The extracted blood oxygen level dependent signal is smoothed by a band-pass filter.

[0031] The application also provides a TMS target positioning system based on functional connection weight, comprising:

[0032] An image acquisition module is configured to acquire depression scale score data, structural magnetic resonance image data and functional magnetic resonance image data of a plurality of subjects; and pre-process the structural magnetic resonance image data and the functional magnetic resonance image data to obtain preprocessed structural magnetic resonance image data and preprocessed functional magnetic resonance image data;

[0033] A region acquisition module is configured to acquire, in the preprocessed structural magnetic resonance image data, a region of interest corresponding to a TMS stimulation target point of each subject to obtain a plurality of regions of interest;

[0034] A first matrix acquisition module is configured to acquire a first functional connection matrix between a plurality of regions of interest and whole brain regions in the preprocessed functional magnetic resonance image data;

[0035] a second matrix obtaining module, configured to obtain a functional connection weight matrix between the depression scale score data and the first functional connection matrix, the functional connection weight matrix being used to represent a correlation degree between the functional connection matrix and the depression scale score data;

[0036] a target point obtaining module, configured to map the functional connection weight matrix to the second functional connection matrix to obtain an estimated efficacy map of brain regions of the whole brain; and perform clustering on voxels in a left DLPFC region in the estimated efficacy map, and determine a clustering center as a TMS treatment target point.

[0037] The application further provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the functional connection weight-based TMS target point positioning method according to any one of the above when executing the program.

[0038] The application further provides a non-transitory computer-readable storage medium, which stores a computer program, and the computer program is executable on a processor to implement the functional connection weight-based TMS target point positioning method according to any one of the above.

[0039] The application further provides a computer program product, which includes a computer program, and the computer program is executable on a processor to implement the functional connection weight-based TMS target point positioning method according to any one of the above.

[0040] The functional connection weight-based TMS target point positioning method and system provided by the application, by using the functional connection data between the actual TMS stimulation target point before treatment and the brain regions of the whole brain, and the efficacy improvement after TMS treatment, a functional connection weight matrix representing the correlation degree between the functional connection matrix and the depression scale score data is constructed. And the functional connection weight atlas is used to predict the potential effective treatment target point, and a precise and individualized TMS treatment depression target point positioning method is realized. BRIEF DESCRIPTION OF DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0042] Fig. 1 is a flowchart of the functional connection weight-based TMS target point positioning method provided by the application.

[0043] Fig. 2 is a schematic diagram of the principle of structural magnetic resonance imaging and functional magnetic resonance imaging provided by the application.

[0044] Fig. 3 is a flowchart of a method for locating a TMS target point based on functional connection weight according to the present application.

[0045] Fig. 4 is a diagram of a predicted efficacy of a method for locating a TMS target point based on functional connection weight according to the present application.

[0046] Fig. 5 is a diagram of a principle of a leave-one-out cross-validation method according to the present application.

[0047] Fig. 6 is a diagram of a result of a linear regression prediction based on PLSR score according to the present application.

[0048] Fig. 7 is a diagram of a comparison of efficacy of a method for locating a TMS target point according to the present application and a related art method for locating a TMS target point.

[0049] Fig. 8 is a diagram of a structure of a system for locating a TMS target point based on functional connection weight according to the present application.

[0050] Fig. 9 is a diagram of a structure of an electronic device according to the present application. DETAILED DESCRIPTION

[0051] In order to make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of the present application.

[0052] The terms "first", "second", and the like in the description and in the claims of the present application and the above drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the description used in this way can be interchanged under appropriate circumstances, so that the embodiments can be implemented in an order other than that illustrated or described in the present application. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or modules does not have to be limited to those steps or modules clearly listed, but can include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. The naming or numbering of the steps appearing in the present application does not mean that the steps in the method flow must be performed in the time / logical order indicated by the naming or numbering, and the flow steps that have been named or numbered can change the order of execution according to the technical purpose to be achieved, as long as the same or similar technical effects can be achieved. The division of modules appearing in the present application is a logical division, and in actual application, there can be another division method, for example, a plurality of modules can be combined or integrated in another system, or some features can be ignored or not executed, in addition, the coupling or direct coupling or communication connection between the modules shown or discussed can be through some interface, the indirect coupling or communication connection between the units can be electrical or other similar forms, which are not limited in the present application. In addition, the modules or sub-modules described as separate components can or can not be physically separated, and can or can not be physical units, or can be distributed to a plurality of circuit units, and some or all units can be selected according to actual needs to achieve the purpose of the present application.

[0053] In the embodiments of the present application, each subject is a person who has received iTBS treatment for a period of time. iTBS treatment, i.e. Stanford therapy, is a brain neuromodulation technique that adjusts the activity of brain neurons through transcranial magnetic stimulation (TMS) or other means. Current research shows that Stanford therapy (iTBS) can have certain diagnosis and treatment effects on some mental and psychological diseases. In the embodiments of the present application, the subjects can be people who have certain symptoms of depression.

[0054] It should be noted that depression is only an exemplary description of a mental and psychological disease in the embodiments of the present application, and based on the concept of the present application, the TMS target positioning method based on functional connection weight can also be applied to a TMS target positioning system for other mental and psychological diseases.

[0055] The specific content of the present application will be described below in conjunction with FIGS. 1-9.

[0056] The TMS target positioning method based on functional connection weight provided in the application can be applied to a TMS target positioning system.

[0057] FIG. 1 is a flowchart of a TMS target positioning method based on functional connection weight provided in the application, including steps S101-S105.

[0058] In step S101, the depression scale score data, structural magnetic resonance imaging data and functional magnetic resonance imaging data of a plurality of subjects are obtained; the structural magnetic resonance imaging data and the functional magnetic resonance imaging data are preprocessed to obtain preprocessed structural magnetic resonance imaging data and preprocessed functional magnetic resonance imaging data.

[0059] In the embodiment of the application, the structural magnetic resonance imaging data and the functional magnetic resonance imaging data of a plurality of subjects before TMS treatment are obtained; the position and posture of the stimulation coil during actual TMS treatment are obtained; and the depression scale score data before treatment, one week after treatment and two weeks after treatment are obtained.

[0060] In step S102, the TMS stimulation target point corresponding to the region of interest of each subject is obtained in the preprocessed structural magnetic resonance imaging data to obtain a plurality of regions of interest.

[0061] Specifically, the TMS stimulation target point is the target position of the subject during previous TMS treatment. The region of interest is located in the preprocessed structural magnetic resonance imaging data and is composed of a region within a preset range around the TMS stimulation target point.

[0062] In step S103, the first functional connection matrix between the plurality of regions of interest and the whole brain regions in the preprocessed functional magnetic resonance imaging data is obtained.

[0063] In the embodiment of the application, the first functional connection matrix is used to represent the functional connection relationship between the plurality of regions of interest in the preprocessed structural magnetic resonance imaging data and the whole brain regions in the preprocessed functional magnetic resonance imaging data.

[0064] In step S104, the functional connection weight matrix between the depression scale score data and the first functional connection matrix is obtained, and the functional connection weight matrix is used to represent the correlation degree between the functional connection matrix and the depression scale score data.

[0065] In step S105, the functional connection weight matrix is mapped to the second functional connection matrix to obtain an estimated efficacy map of the whole brain regions; the voxels in the left DLPFC region of the estimated efficacy map are clustered, and the cluster center is determined as the TMS treatment target point.

[0066] In a possible implementation, the step S101 of preprocessing the structural magnetic resonance imaging data and the functional magnetic resonance imaging data to obtain the preprocessed structural magnetic resonance imaging data and the preprocessed functional magnetic resonance imaging data comprises steps S101A-S101C.

[0067] The step S101A is to acquire brain tissue image data in the structural magnetic resonance imaging data.

[0068] Specifically, the preprocessing of the acquired structural magnetic resonance imaging data comprises brain tissue image data extraction. For example, the BET brain extraction algorithm is used to remove the skull and other non-brain tissues in the structural magnetic resonance imaging, thereby extracting the brain tissue image data.

[0069] The step S101B is to acquire the functional magnetic resonance imaging data after time correction and head motion correction.

[0070] Specifically, the head motion correction: since the acquisition time of the functional magnetic resonance imaging usually lasts for a long time, the head motion of the subject during the acquisition process can easily cause the image to deviate, and therefore a head motion correction algorithm is needed to correct the functional magnetic resonance imaging at each time point, by estimating the motion parameters at each scanning time point, and then repositioning all the functional magnetic resonance imaging to the same time reference point. The time correction: since the functional magnetic resonance imaging is scanned layer by layer, the time of each layer is different, but in subsequent analysis, it is generally considered that all layers are acquired at the same time, and therefore time correction is needed. After the above-mentioned time correction and head motion correction, the corrected functional magnetic resonance imaging is obtained.

[0071] As shown in FIG. 2, it is a principle diagram of the structural magnetic resonance imaging and the functional magnetic resonance imaging provided by the embodiment of the present application. In FIG. 2, the upper half is the functional magnetic resonance imaging acquired at multiple time points. For example, the number of time points in the embodiment of the present application is set to 180.

[0072] The step S101C is to register the brain tissue image data and the corrected functional magnetic resonance imaging data to the same standard template, to obtain the preprocessed structural magnetic resonance imaging data and the preprocessed functional magnetic resonance imaging data respectively.

[0073] Specifically, in the registration process of the brain tissue image data, the brain tissue image data is registered to the standard template or other template. The registration process generally uses linear registration and nonlinear registration.

[0074] Specifically, in the configuration process of the whole brain region image data, the sizes and shapes of the head and brain tissues of the subjects are different. In order to facilitate subsequent statistical analysis between subjects, the whole brain region image data of all subjects need to be registered to a standard template. Here, the registration process file in the configuration process of the brain tissue image data is directly used to register the whole brain region image data to the standard template.

[0075] In a possible implementation, in step S102, the TMS stimulation target point corresponding region of interest of each subject is obtained in the preprocessed structural magnetic resonance image data, and a plurality of regions of interest are obtained, including: obtaining the coil position and coil posture of each subject when the TMS treatment is performed; performing electric field simulation in the cerebral cortex of the preprocessed structural magnetic resonance image data according to the coil position and the coil posture, to obtain a simulated electric field; obtaining a point with the maximum simulated electric field value in the simulated electric field as the TMS stimulation target point; obtaining the TMS stimulation target point corresponding region of interest of each subject in the cerebral cortex, to obtain a plurality of regions of interest.

[0076] Specifically, the electric field simulation is performed according to the coil position and the coil posture of each subject when the actual TMS treatment is performed.

[0077] Specifically, the electric field simulation is performed according to the coil position and the coil posture of each subject when the actual TMS treatment is performed.

[0078] In a possible implementation, in step S103, the first functional connection matrix between the whole brain regions in the preprocessed functional magnetic resonance image data and the plurality of regions of interest are obtained, as shown in FIG. 3, including steps S301-S304.

[0079] Step S301, extract blood-oxygen-level-dependent signals of a plurality of regions of interest, brain regions of the whole brain and voxels of the whole brain to obtain time series matrices of the plurality of regions of interest, the brain regions of the whole brain and the voxels of the whole brain.

[0080] For example, blood-oxygen-level-dependent (BOLD) signals are extracted from a plurality of regions of interest (a sphere with a radius of 10 mm centered on a TMS stimulation target), brain regions (brain regions defined by a brain network group atlas) and voxels of the whole brain (all voxels under an MNI template).

[0081] In the embodiments of the present application, the number of subjects N is 35, the number of brain regions of the whole brain is 246, the number of voxels of the whole brain is 235375 when the size is 2 mm, and the functional magnetic resonance image is scanned for 180 time points. Therefore, the sizes of the time series matrices of the plurality of regions of interest, the brain regions of the whole brain and the voxels of the whole brain are 35x180, 246x180 and 235375x180 respectively.

[0082] In a possible implementation, step S103 further includes: smoothing filtering the extracted blood-oxygen-level-dependent signals by a band-pass filter.

[0083] In the embodiments of the present application, since the activity frequency of the brain is generally around 0.01 Hz-0.1 Hz, a band-pass filter is used to smooth filter the BOLD signals during the extraction of the BOLD signals, the low-pass filtering frequency of which is 0.01 Hz, the high-pass filtering frequency of which is 0.1 Hz, and the time interval of which is 2 s. Meanwhile, spatial smoothing with a full width at half maximum of 6 mm is also performed to reduce spatial noise and increase signal-to-noise ratio.

[0084] Step S302, obtain the Pearson correlation coefficients between the time series matrices of the plurality of regions of interest and the time series matrices of the brain regions of the whole brain to obtain a first functional connection matrix.

[0085] Step S303, obtain the Pearson correlation coefficients between the time series matrices of the brain regions of the whole brain and the time series matrices of the voxels of the whole brain to obtain a second functional connection matrix.

[0086] Step S304, determine a functional connection weight matrix according to the first functional connection matrix and the second functional connection matrix.

[0087] In steps S303 and S304, the Pearson correlation coefficients between the time series matrix of a plurality of regions of interest and the time series matrix of the whole brain brain region are calculated to obtain a first functional connection matrix with a size of 35*246. The Pearson correlation coefficients between the time series matrix of the whole brain brain region and the time series matrix of the whole brain voxel are calculated to obtain a second functional connection matrix with a size of 246*235375.

[0088] In the embodiments of the present application, in order to make the functional connection matrix more visualized, the Fisher-z transformation is performed on the Pearson correlation coefficients in the functional connection matrix to obtain a functional connection image.

[0089] In a possible implementation, in step S104, the functional connection weight matrix between the depression scale score data and the first functional connection matrix is obtained based on a partial least squares regression model.

[0090] Based on the partial least squares regression model, i.e., the PLSR model, the correlation between the TMS stimulation target and the functional connection improvement is mined to obtain the weight of each brain region in the correlation analysis in the brain network group atlas, i.e., the functional connection weight matrix. The functional connection improvement is represented by the functional connection matrix.

[0091] The PLSR model can be represented by the following two formulas:

[0092] Wherein, the X and Y matrices represent the first and second functional connection matrices respectively, and are the partial least squares estimates of the X and Y matrices, and E and F are the corresponding residual matrices. X and Y are obtained by multiplying a score matrix (T and U) and a loading matrix (P and Q), and T and U can be considered as the representation of X and Y in the low-dimensional space after projection. Wherein, the subscript k represents the number of effective components of the matrix X, i.e., rank(X)=k.

[0093] Suppose t1 and u1 are the first principal component components of X and Y respectively, i.e., t1=Xw1, u1=Yc1. The CCA model focuses on the correlation between the independent variable and the dependent variable after projection, and its optimization goal is max(Corr(t1, u1)). The PCR focuses on the method explanation of the data before and after projection, and its optimization goal is max(Var(t1)), max(Var(u1)). The PLSR combines the two methods, optimizes the correlation between the independent variable and the dependent variable after projection, and also focuses on the data information before and after projection, and its optimization goal is

[0094] The optimization objective of PLSR can be expressed as:

[0095] maximize <Xw1, Yc1>

[0096] s.t.‖w1‖=1,‖c1‖=1

[0097] The w1 is solved as a symmetric matrix X T YY T The eigenvector corresponding to the largest eigenvalue of X, and c1 is a symmetric matrix Y T XX T The eigenvector corresponding to the largest eigenvalue of Y. After solving the first pair of principal components, the X and Y are respectively regressed on their principal components to obtain:

[0098] And according to the correlation of t1 and u1, the regression model of X and Y is established:

[0099] Then the least square method is used to solve three equations to obtain the load factor corresponding to the principal component score, and the following is obtained:

[0100] After that, the residual E and F that cannot be explained by this pair of principal components in the regression process are taken as new X and Y, and then the new principal components and load factors are solved by continuing the regression until the residual F reaches a certain accuracy requirement or the number of principal components reaches the effective component number k.

[0101] After solving all k principal components, X and Y can be expressed as:

[0102] Thus, the regression equation of Y with respect to X is obtained, as well as the principal components of X and Y in the projection space.

[0103] The principal components of X and Y in the projection space are determined as the functional connection weight matrix between the depression scale score data and the first functional connection matrix.

[0104] The dimension k of the data dimension reduction by PLSR, i.e. the number of principal components, is an important parameter that determines the prediction performance of the model. In order to select the optimal component number, 1000 times of repeated training are performed on PLSR models with different component numbers, and the regression indicators are calculated to obtain the component number corresponding to the model with the best regression performance. In order to prevent overfitting of the PLSR model on the training data, the model is also subjected to permutation test.

[0105] Step S105, map the functional connection weight matrix to the second functional connection matrix to obtain the estimated efficacy map of the whole brain region; cluster the voxels in the left DLPFC region of the estimated efficacy map, and determine the cluster center as the TMS treatment target.

[0106] In step S105, the mapping relationship of the functional connection weight matrix is applied to the second functional connection matrix, the 246x235375 matrix is reduced in dimension, a 1x235375 vector is obtained, and then a linear regression model is used to predict the potential efficacy of each voxel. Finally, the one-dimensional vector is restored to a three-dimensional brain image to obtain the estimated efficacy map shown in FIG. 4. By clustering the voxels belonging to the left DLPFC region in the efficacy map, the cluster center is determined as the individualized optimal treatment target, i.e., the TMS treatment target.

[0107] In the embodiments of the present application, for step S105, the estimated efficacy map of the whole brain region is obtained according to the functional connection weight matrix. It is necessary to first verify the predictability of the PLSR model for the efficacy of depression, and based on the PLSR scores after dimension reduction, a linear regression model is used to predict the efficacy after treatment.

[0108] For each model evaluation of PLSR and linear regression, leave-one-out cross-validation method is used for evaluation (as shown in FIG. 5). Each time, one subject is selected and not used for training, and the remaining N-1 (N is 35) subjects are used to train the linear regression model, and then the trained model is used to predict the subject not used for training. For each subject, such training and prediction is performed to obtain the prediction results of all subjects. Then, the R2 score of the prediction results of all subjects and the true results of all subjects is calculated as the model evaluation result of leave-one-out validation.

[0109] The correlation between the actual stimulation target and the functional connection of the brain network group atlas region and the efficacy of depression is mined by the PLSR model, and the corresponding principal component weight W, i.e., the functional connection weight matrix, is obtained. The matrix represents the contribution degree of each brain region in the brain network group atlas to predict the potential efficacy of depression. The closer the weight is to 1, the stronger the functional connection between the target stimulation target and the brain region, and the better the corresponding efficacy. Through the functional connection weight matrix, the functional connection matrix between the brain regions and the voxels of the brain regions of N subjects can be reduced in dimension, i.e., the 35 second functional connection matrices of 246x235375 are mapped into 35 vectors of 1x235375, and then combined into a training data of 35x235375. Linear regression is performed on the corresponding 35 subjects' depression evaluation efficacy to obtain a linear regression model. The specific regression process can be represented as:

[0110] y ni =m i x ni +b i ,i=1…235375

[0111] For each voxel, through N(x niy ni ), find the best parameters and Then for the new known x i But y i Unknown data, can directly predict its y i Possible values

[0112] The following describes the linear regression prediction results based on PLSR scores in the embodiments of the application.

[0113] The linear regression prediction results based on PLSR scores are shown in FIG. 6, and the evaluation process uses the leave-one-out method. The left of FIG. 6 is the prediction result of the linear regression model trained using the depression scale score reduction rate after one week of treatment as the label data, and the right of FIG. 6 is the prediction result of the linear regression model trained using the depression scale score reduction rate after two weeks of treatment as the label data. It is found that the model trained using the depression scale score reduction rate after two weeks of treatment has a significantly positive correlation (two weeks: r = 0.474, p = 0.004*). The model trained using the depression scale score reduction rate after one week of treatment has a high p value and a low statistical effect size (one week: r = 0.292, p = 0.089).

[0114] The correlation between the distance between the optimal treatment target and the actual stimulation target and the depression scale score reduction rate is used to evaluate the effectiveness of the TMS target positioning method proposed in the application. The evaluation results are shown in FIG. 7, where the horizontal axis is the Euclidean distance between the optimal treatment target and the actual stimulation target, and the vertical axis is the TMS efficacy. After two weeks of treatment, there is a significant negative correlation between the distance between the targets and the depression scale score reduction rate (r = -0.343, p = 0.044, FIG. 7, bottom right), indicating that when the actual stimulation target is closer to the optimal treatment target, the corresponding efficacy will be better, verifying the effectiveness of the treatment target positioned by the method in the application. However, the depression scale score reduction rate after one week of treatment (r = -0.234, p = 0.176) did not find a significant negative correlation, which is consistent with the result that the PLSR score has weak prediction performance on the depression scale score reduction rate after one week of treatment. In addition, by comparing with the traditional positioning method based on the functional connectivity of the sgACC brain region. The results in FIG. 7 show that the treatment target positioning method based on the functional connectivity of the sgACC brain region does not show a significant negative correlation.

[0115] The results show that the TMS target positioning method based on functional connectivity weights proposed in the application is superior to the positioning method based on the functional connectivity of the sgACC brain region in the related art.

[0116] The application can achieve at least one of the following beneficial effects: by using the above method, the functional connection weight matrix representing the correlation degree between the first functional connection matrix and the depression scale score data is constructed based on the functional connection data of the TMS stimulation target point and the whole brain region before treatment, and the improvement of the curative effect after TMS treatment. And using the functional connection weight atlas to predict the potential effective treatment target, a precise and individualized TMS treatment depression target positioning method is realized.

[0117] The functional connection weight-based TMS target positioning system provided by the application is described below, and the functional connection weight-based TMS target positioning system described below can be mutually corresponding to the functional connection weight-based TMS target positioning method described above.

[0118] As shown in FIG. 8, the application also provides a functional connection weight-based TMS target positioning system, which comprises:

[0119] The image acquisition module 810 is configured to acquire depression scale score data, structural magnetic resonance image data and functional magnetic resonance image data of a plurality of subjects; and pre-process the structural magnetic resonance image data and the functional magnetic resonance image data to obtain pre-processed structural magnetic resonance image data and pre-processed functional magnetic resonance image data.

[0120] The region acquisition module 820 is configured to acquire, in the pre-processed structural magnetic resonance image data, a region of interest corresponding to a TMS stimulation target point of each subject to obtain a plurality of regions of interest.

[0121] The first matrix acquisition module 830 is configured to acquire a first functional connection matrix between the plurality of regions of interest and the whole brain region in the pre-processed functional magnetic resonance image data.

[0122] The second matrix acquisition module 840 is configured to acquire a functional connection weight matrix between the depression scale score data and the first functional connection matrix, the functional connection weight matrix being used to represent the correlation degree between the first functional connection matrix and the depression scale score data.

[0123] The target acquisition module 850 is configured to map the functional connection weight matrix to the second functional connection matrix to obtain an estimated curative effect map of the whole brain region; and cluster voxels in a left DLPFC region in the estimated curative effect map, and determine a cluster center as a TMS treatment target point.

[0124] In a possible implementation, the region acquisition module 820 is specifically configured to:

[0125] acquire the coil position and the coil posture of each subject when the TMS treatment is performed; perform electric field simulation in the cerebral cortex of the preprocessed structural magnetic resonance image data according to the coil position and the coil posture, to obtain a simulated electric field; acquire a point with the maximum simulated electric field value in the simulated electric field as a TMS stimulation target point; acquire a region of interest corresponding to the TMS stimulation target point of each subject in the cerebral cortex, to obtain a plurality of regions of interest.

[0126] In a possible implementation, the first matrix acquisition module 830 is specifically configured to:

[0127] extract blood oxygen level dependent signals of the plurality of regions of interest, the whole brain brain regions and the whole brain voxels, to obtain time sequence matrices of the plurality of regions of interest, the whole brain brain regions and the whole brain voxels;

[0128] acquire a Pearson correlation coefficient between the time sequence matrices of the plurality of regions of interest and the time sequence matrices of the whole brain brain regions, to obtain a first functional connection matrix;

[0129] acquire a Pearson correlation coefficient between the time sequence matrices of the whole brain brain regions and the time sequence matrices of the whole brain voxels, to obtain a second functional connection matrix;

[0130] determine a functional connection weight matrix according to the first functional connection matrix and the second functional connection matrix.

[0131] In a possible implementation, the second matrix acquisition module 840 is configured to acquire a functional connection weight matrix between the depression scale score data and the functional connection matrix based on a partial least squares regression model.

[0132] In a possible implementation, the image acquisition module 810 is specifically configured to:

[0133] acquire brain tissue image data in the structural magnetic resonance image data;

[0134] acquire functional magnetic resonance image data after time correction and head motion correction, to obtain whole brain brain region image data;

[0135] register the brain tissue image data and the whole brain brain region image data to the same standard template, to obtain preprocessed structural magnetic resonance image data and preprocessed functional magnetic resonance image data respectively.

[0136] In a possible implementation, the image acquisition module 810 is further configured to perform smooth filtering on the extracted blood oxygen level dependent signals by using a band-pass filter.

[0137] FIG. 9 shows a schematic diagram of an electronic device, as shown in FIG. 9, the electronic device can include: a processor 910, a communications interface 920, a memory 930 and a communications bus 940, wherein the processor 910, the communications interface 920, the memory 930 complete the communication among each other through the communications bus 940. The processor 910 can call the logical instructions in the memory 930 to execute a TMS target positioning method based on functional connection weight, the method comprising:

[0138] Obtain depression scale score data, structural magnetic resonance imaging data and functional magnetic resonance imaging data of a plurality of subjects; preprocess the structural magnetic resonance imaging data and the functional magnetic resonance imaging data to obtain preprocessed structural magnetic resonance imaging data and preprocessed functional magnetic resonance imaging data;

[0139] In the preprocessed structural magnetic resonance imaging data, obtain the target region corresponding to the TMS stimulation target point of each subject to obtain a plurality of target regions;

[0140] Obtain a first functional connection matrix between a plurality of target regions and whole brain regions in the preprocessed functional magnetic resonance imaging data;

[0141] Obtain a functional connection weight matrix between the depression scale score data and the first functional connection matrix, the functional connection weight matrix being used to represent the correlation degree between the functional connection matrix and the depression scale score data;

[0142] Map the functional connection weight matrix to a second functional connection matrix to obtain an estimated efficacy map of the whole brain region; cluster the voxels in the left DLPFC region of the estimated efficacy map, and determine the cluster center as the TMS treatment target point.

[0143] Further, the logic instructions in the memory 930 described above can be implemented by a software functional unit and sold or used as an independent product, which can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or partly or parts of the technical solutions can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for making a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, and various media that can store program codes.

[0144] In another aspect, the present application also provides a computer program product, which comprises a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and the computer program is executed by a processor, so that the computer can execute a TMS target point positioning method based on functional connection weight provided by the above-mentioned method, the method comprises:

[0145] Obtain depression scale score data, structural magnetic resonance image data and functional magnetic resonance image data of a plurality of subjects; preprocess the structural magnetic resonance image data and the functional magnetic resonance image data to obtain preprocessed structural magnetic resonance image data and preprocessed functional magnetic resonance image data;

[0146] In the preprocessed structural magnetic resonance image data, obtain the target region corresponding to the TMS stimulation target point of each subject to obtain a plurality of target regions;

[0147] Obtain a first functional connection matrix between the plurality of target regions and the whole brain regions in the preprocessed functional magnetic resonance image data;

[0148] Obtain a functional connection weight matrix between the depression scale score data and the functional connection matrix, the functional connection weight matrix being used to represent the correlation degree between the functional connection matrix and the depression scale score data;

[0149] Map the functional connection weight matrix to the second functional connection matrix to obtain an estimated efficacy map of the whole brain regions; cluster the voxels in the left DLPFC region of the estimated efficacy map, and determine the cluster center as the TMS treatment target point.

[0150] In yet another aspect, the present application also provides a non-transitory computer-readable storage medium having stored thereon a computer program, which, when executed by a processor, implements a TMS target positioning method based on functional connection weight, the method comprising:

[0151] obtaining depression scale score data, structural magnetic resonance imaging data and functional magnetic resonance imaging data of a plurality of subjects; preprocessing the structural magnetic resonance imaging data and the functional magnetic resonance imaging data to obtain preprocessed structural magnetic resonance imaging data and preprocessed functional magnetic resonance imaging data;

[0152] in the preprocessed structural magnetic resonance imaging data, obtaining a region of interest corresponding to a TMS stimulation target point of each subject to obtain a plurality of regions of interest;

[0153] obtaining a first functional connection matrix between a plurality of regions of interest and brain regions in the preprocessed functional magnetic resonance imaging data;

[0154] obtaining a functional connection weight matrix between the depression scale score data and the functional connection matrix, the functional connection weight matrix being used to represent a degree of correlation between the functional connection matrix and the depression scale score data;

[0155] mapping the functional connection weight matrix to the second functional connection matrix to obtain an estimated efficacy map of the whole brain regions; clustering voxels in a left DLPFC region in the estimated efficacy map, and determining a cluster center as a TMS treatment target point.

[0156] The device embodiments described above are only schematic, wherein the units illustrated as separate components can or can not be physically separate, and the components illustrated as units can or can not be physical units, i.e., can be located in one place, or can be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the present embodiment. Those skilled in the art can understand and implement without creative labor.

[0157] From the above description of the embodiments, those skilled in the art can clearly understand that the embodiments can be implemented by means of software plus necessary universal hardware platforms, and of course, can also be implemented by hardware. Based on such understanding, the above technical solutions, essentially or in other words, the part that contributes to the prior art can be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0158] It should be noted that the above examples are only used to illustrate the technical solutions of the present application, and are not intended to limit the same. Although the present application has been described in detail with reference to the foregoing examples, it should be understood by those skilled in the art that the technical solutions recorded in the foregoing examples can be modified, or some technical features can be replaced by equivalent features. Such modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A TMS target positioning method based on functional connection weight, comprising: obtaining depression scale score data, structural magnetic resonance image data and functional magnetic resonance image data of a plurality of subjects; preprocessing the structural magnetic resonance image data and the functional magnetic resonance image data to obtain preprocessed structural magnetic resonance image data and preprocessed functional magnetic resonance image data; in the preprocessed structural magnetic resonance image data, obtaining a region of interest corresponding to a TMS stimulation target point of each subject to obtain a plurality of regions of interest; obtaining a functional connection matrix between a plurality of regions of interest and brain regions in the preprocessed functional magnetic resonance image data; obtaining a functional connection weight matrix between the depression scale score data and the functional connection matrix, the functional connection weight matrix being used to represent the correlation degree between the functional connection matrix and the depression scale score data; mapping the functional connection weight matrix to the functional connection matrix to obtain an estimated efficacy map of the whole brain region; clustering voxels in the left DLPFC region of the estimated efficacy map, and determining the cluster center as a TMS treatment target.

2. The functional connectivity weight-based TMS target localization method of claim 1, wherein, The method further comprises: obtaining the coil position and the coil posture of each subject during TMS treatment; performing electric field simulation in the cerebral cortex of the preprocessed structural magnetic resonance image data according to the coil position and the coil posture to obtain a simulated electric field; obtaining a point with the maximum simulated electric field value in the simulated electric field as a TMS stimulation target point; obtaining the region of interest corresponding to the TMS stimulation target point of each subject in the cerebral cortex to obtain a plurality of regions of interest.

3. The functional connectivity weight-based TMS target localization method of claim 1, wherein, The method further comprises: extracting blood oxygen level dependent signals of the plurality of regions of interest, the whole brain regions and the whole brain voxels to obtain time series matrices of the plurality of regions of interest, the whole brain regions and the whole brain voxels; obtaining a Pearson correlation coefficient between the time series matrix of the plurality of regions of interest and the time series matrix of the whole brain regions to obtain a first functional connection matrix; obtaining a Pearson correlation coefficient between the time series matrix of the whole brain regions and the time series matrix of the whole brain voxels to obtain a second functional connection matrix; determining the functional connection weight matrix according to the first functional connection matrix and the second functional connection matrix. The method further comprises:

4. The functional connectivity weight-based TMS target localization method of claim 1, wherein, obtaining the functional connection weight matrix between the depression scale score data and the first functional connection matrix based on a partial least squares regression model. The method further comprises:

5. The functional connectivity weight-based TMS target localization method of claim 1, wherein, ​ acquire brain tissue image data in the structural magnetic resonance image data; acquire the functional magnetic resonance image data after time correction and head motion correction to obtain corrected functional magnetic resonance image data; register the brain tissue image data and the corrected functional magnetic resonance image data to the same standard template to obtain the preprocessed structural magnetic resonance image data and the preprocessed functional magnetic resonance image data respectively.

6. The functional connectivity weight-based TMS target localization method of claim 3, wherein, Further comprising: Smooth filtering the extracted blood oxygen level dependent signal through a band-pass filter.

7. A TMS target positioning system based on functional connection weight, comprising: An image acquisition module configured to acquire depression scale score data, structural magnetic resonance image data, and functional magnetic resonance image data of a plurality of subjects; Preprocess the structural magnetic resonance image data and the functional magnetic resonance image data to obtain preprocessed structural magnetic resonance image data and Preprocessed functional magnetic resonance image data; A region acquisition module configured to acquire, in the preprocessed structural magnetic resonance image data, a region of interest corresponding to a TMS stimulation target point of each subject to obtain a plurality of regions of interest; A first matrix acquisition module configured to acquire a first functional connection matrix between the plurality of regions of interest and brain regions in the preprocessed functional magnetic resonance image data; A second matrix acquisition module configured to acquire a functional connection weight matrix between the depression scale score data and the first functional connection matrix, the functional connection weight matrix being configured to represent a correlation degree between the first functional connection matrix and the depression scale score data; A target point acquisition module configured to map the functional connection weight matrix to a second functional connection matrix to obtain a predicted efficacy map of the brain regions; and cluster voxels in a left DLPFC region in the predicted efficacy map, and determine a cluster center as a TMS treatment target point.

8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein, The processor executes the computer program to realize the TMS target positioning method based on functional connection weight according to any one of claims 1 to 6.

9. A non-transitory computer readable storage medium having stored thereon a computer program, wherein, The computer program is executed by the processor to realize the TMS target positioning method based on functional connection weight according to any one of claims 1 to 6.

10. A computer program product comprising a computer program, wherein, The computer program is executed by the processor to realize the TMS target positioning method based on functional connection weight according to any one of claims 1 to 6.

Images