A hand motion hotspot rapid positioning method and device

Abstract

The application provides a hand movement hotspot rapid positioning method and device, the method comprises the following steps: acquiring magnetic resonance image data and MEP signal data of an experimental subject, and preprocessing the magnetic resonance image data to obtain an electric field simulation result; then constructing a group hand movement hotspot atlas, dividing the experimental subject into positive samples and negative samples to train an outlier classification model; dividing the subject to be positioned into an outlier group and a non-outlier group through the outlier classification model; when it is the outlier group, performing correlation analysis on the electric field simulation result corresponding to the subject to be positioned and the MEP signal data to obtain a target hand movement hotspot; when it is the non-outlier group, performing individual hand movement hotspot registration through the group hand movement hotspot atlas to obtain the target hand movement hotspot. Through the application, the defects that the hand movement hotspot positioning process is time-consuming and laborious and cannot guarantee the accuracy of positioning in the prior art are overcome, and the low clinical treatment efficiency is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of transcranial magnetic stimulation, and particularly to a method and device for quickly positioning a hand motor hotspot. BACKGROUND

[0002] Transcranial magnetic stimulation (TMS) is a non-invasive neural modulation technique, which is used to study human neurophysiology and treat nervous system diseases. A hand motor hotspot (hMHS) refers to a brain cortex that is most likely to induce a motor evoked potential (MEP) under TMS, and is used to determine the resting motor threshold (MT) of a subject. The stimulation intensity for inducing MEP is often used as a reference value for determining the individual-specific stimulation intensity. Therefore, determining the hand motor hotspot is a common operation in TMS treatment.

[0003] The existing clinical hand motor hotspot positioning method needs to collect MEP signal data at multiple positions around the motor area of the patient's brain multiple times, and then perform surface fitting on the collected MEP signal data to determine the position of the maximum MEP signal data on the surface as the hand motor hotspot. However, the entire hand motor hotspot positioning process is time-consuming and labor-intensive, and cannot guarantee the accuracy of positioning, resulting in low treatment efficiency. SUMMARY

[0004] The present application provides a method and device for quickly positioning a hand motor hotspot to solve the technical problem of low clinical treatment efficiency caused by the time-consuming and labor-intensive hand motor hotspot positioning process in the prior art and the inability to guarantee the accuracy of positioning.

[0005] The present application provides a method for quickly positioning a hand motor hotspot, comprising the following steps:

[0006] Obtaining magnetic resonance image data of an experimental subject and MEP signal data corresponding to stimulation of different positions of the brain cortex, and pre-processing the magnetic resonance image data to obtain an electric field simulation result;

[0007] According to the MEP signal data and the electric field simulation result, a group hand motor hotspot atlas is constructed, and the experimental subject is divided into a positive sample and a negative sample through the group hand motor hotspot atlas;

[0008] A outlier classification model is trained according to the positive sample and the negative sample;

[0009] For the subjects to be located, dividing the subjects to be located into an outlier group and a non-outlier group by using the outlier classification model;

[0010] When the subject to be located is an outlier, correlation analysis is performed on the electric field simulation results corresponding to the subject to be located and the MEP signal data to obtain the target hand movement hotspot;

[0011] When the subject to be located is a non-outlier in the group, individual hand motion hotspot registration is performed using the group hand motion hotspot map to obtain a target hand motion hotspot.

[0012] In some embodiments, constructing a group hand motion heat map based on the MEP signal data and the electric field simulation results includes:

[0013] Performing correlation analysis on the electric field simulation results and the MEP signal data to obtain individual hand movement hotspots of the experimental subjects;

[0014] Based on the individual hand movement hotspots, a Gaussian window function is used to construct a corresponding sample probability map;

[0015] Each sample probability map is accumulated to construct a group hand movement hotspot map.

[0016] In some embodiments, performing correlation analysis on the electric field simulation results and the MEP signal data to obtain individual hand motion hotspots of the experimental subject includes:

[0017] Determining the vertices corresponding to the stimulation positions of the cerebral cortex of the experimental subject, and determining the electric field values ​​of each vertex at different stimulation positions based on the electric field simulation results;

[0018] For each vertex, determining a positive correlation value between the electric field value and the MEP signal data;

[0019] An individual hand motion hotspot probability map is determined according to the positive correlation value, and a vertex with the highest probability in the individual hand motion hotspot probability map is determined as the individual hand motion hotspot of the experimental subject.

[0020] In some embodiments, dividing the experimental subjects into positive samples and negative samples using the group hand movement heat map includes:

[0021] From the group hand motion hotspot map, determine the vertex corresponding to the maximum probability as the group hand motion hotspot;

[0022] Determining the cortical distance between each experimental subject's individual hand movement hotspot and the group hand movement hotspot;

[0023] When the cortical distance is greater than the distance threshold, the experimental subject is determined to be a negative sample;

[0024] When the cortical distance is less than or equal to the distance threshold, the experimental subject is determined to be a positive sample.

[0025] In some embodiments, the training of the outlier classification model based on the positive samples and the negative samples includes:

[0026] From the group hand motion hotspot map, determine the vertex corresponding to the maximum probability as the group hand motion hotspot;

[0027] Determining a region of interest from the cerebral cortex of the training samples with the group hand movement hotspot as the center, wherein the training samples include the positive samples and the negative samples;

[0028] Extracting cerebral cortical structural information within the region of interest from the magnetic resonance imaging data corresponding to the training sample, wherein the cerebral cortical structural information includes cortical thickness, cortical curvature, and cortical sulcus index;

[0029] The cerebral cortex structural information is used as training data to train an initial logistic regression model to obtain an outlier classification model.

[0030] In some embodiments, performing individual hand motion hotspot registration using the group hand motion hotspot map to obtain a target hand motion hotspot includes:

[0031] Determining, from the group hand motion hotspot map, a vertex corresponding to the maximum probability as the group hand motion hotspot;

[0032] Determine the registration mapping relationship from group to individual;

[0033] According to the registration mapping relationship, the group hand motion hotspots are mapped to the target hand motion hotspots of the subject to be located.

[0034] The present invention also provides a device for quickly locating a hand motion hotspot, which includes the following modules:

[0035] A preprocessing module is used to obtain magnetic resonance imaging data of the experimental subjects and MEP signal data corresponding to different locations of the brain motor area stimulated, and preprocess the magnetic resonance imaging data to obtain electric field simulation results;

[0036] A construction module, configured to construct a group hand motion hotspot map based on the MEP signal data and the electric field simulation results, and divide the experimental subjects into positive samples and negative samples based on the group hand motion hotspot map;

[0037] a training module configured to train an outlier classification model according to the positive sample and the negative sample;

[0038] a division module configured to divide the to-be-positioned subject into an outlier group and a non-outlier group by the outlier classification model;

[0039] an analysis module configured to perform correlation analysis on the electric field simulation result corresponding to the to-be-positioned subject and the MEP signal data when the to-be-positioned subject belongs to the outlier group, to obtain a target hand movement hotspot;

[0040] a registration module configured to perform individual hand movement hotspot registration on the to-be-positioned subject by the group hand movement hotspot atlas when the to-be-positioned subject belongs to the non-outlier group, to obtain the target hand movement hotspot.

[0041] 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 hand movement hotspot positioning method when executing the computer program.

[0042] The application further provides a non-transitory computer readable storage medium, which stores a computer program executable by a processor to implement the hand movement hotspot positioning method.

[0043] The application further provides a computer program product, which includes a computer program executable by a processor to implement the hand movement hotspot positioning method.

[0044] The hand movement hotspot positioning method and device provided by the application first collect magnetic resonance image data and MEP signal data of experimental subjects to construct a group hand movement hotspot atlas, and divide the experimental subjects into a negative sample and a positive sample to train an outlier classification model, so as to classify the outlier of a to-be-positioned subject. When the to-be-positioned subject belongs to an outlier, the target hand movement hotspot is determined by MEP signal data, and when the to-be-positioned subject belongs to a non-outlier, the target hand movement hotspot is determined by registration of the group hand movement hotspot atlas. Thus, the to-be-positioned subject is positioned by the combination of the outlier classification model and the group hand movement hotspot atlas, which not only realizes fast positioning of the hand movement hotspot, but also effectively guarantees the accuracy of the hand movement hotspot and improves the clinical treatment efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced one by one below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0046] Figure 1 It is a flow chart of the method for quickly locating hand motion hotspots provided by the present invention.

[0047] Figure 2 This is a visualization of the cerebral cortex search grid provided by the present invention.

[0048] Figure 3 This is the MEP signal distribution diagram of 25 stimulation points provided by the present invention.

[0049] Figure 4 This is a visualization diagram of the visualized simulated electric field results of 25 stimulation points provided by the present invention.

[0050] Figure 5 It is a visualization diagram of the cortical structural information provided by the present invention.

[0051] Figure 6 It is a positive correlation diagram between the electric field value and the MEP signal data provided by the present invention.

[0052] Figure 7 It is a visualization of the hand motion hotspot probability map provided by the present invention.

[0053] Figure 8 Schematic diagram of the region of interest of the cerebral cortex provided by the present invention.

[0054] Figure 9 It is a structural schematic diagram of the hand movement hotspot rapid positioning device provided by the present invention.

[0055] Figure 10 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0056] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0057] The following combination Figures 1-8 The present invention describes a method for quickly locating hand motion hotspots.Figure 1 FIG. 1 is a flow chart of a method for quickly locating a hand motion hotspot provided by the present invention. Figure 1 As shown, the method includes the following steps 101 to 106.

[0058] Step 101: Acquire magnetic resonance imaging data of an experimental subject and MEP signal data corresponding to stimulation of different locations of the cerebral cortex, and pre-process the magnetic resonance imaging data to obtain electric field simulation results.

[0059] The embodiment of the present invention takes into account the different situations of each subject to be located. The hand motion hotspots of some groups of people are relatively similar and can be summarized and determined as a group hand motion hotspot. The hand motion hotspots of another group of people are relatively special, and their hand motion hotspots are outliers. Therefore, when the embodiment of the present invention locates the hand motion hotspots, it is necessary to construct a group hand motion hotspot map as prior knowledge, which can not only divide the samples to train the outlier classification model, but also quickly locate the hand motion hotspots of the subjects to be located.

[0060] Therefore, before locating the hand movement hotspot of the subject to be positioned, it is necessary to obtain the MRI data of the experimental subject and the MEP signal data corresponding to different locations of the cerebral cortex (motor area) stimulated. Here, in the process of collecting MEP signal data, such as Figure 2 As shown, the TMS coil can be firmly fixed by a neuroregulatory robot, and the predefined search grid corresponding to the cerebral cortex of the experimental subject can be traversed in a random order, and a single pulse stimulation is applied at a certain intensity to record the corresponding MEP signal. The search grid is a 5×5 square matrix with a spacing of 1 cm between each stimulation point. There are 25 stimulation points in total, and the center of the matrix falls on the central stimulation point. In the process of searching for hand movement hotspots, the TMS coil will traverse the 25 stimulation points in a random order. Each stimulation point is stimulated using a single pulse transcranial magnetic stimulation (spTMS) method with an interval of 5s. Each stimulation point is stimulated 3 times, and the corresponding MEP signal is collected. From the 3 collected MEP signals, the maximum value of the MEP signal is selected as the MEP signal data induced by the TMS stimulation at that point. Among them, the MEP signal distribution of the 25 stimulation points of the experimental subject can be shown as follows. Figure 3 shown.

[0061] Magnetic resonance imaging data (MRI data) can be extracted from experimental subjects through relevant magnetic resonance instruments and equipment, which will not be described in detail here. After the data acquisition is completed, the magnetic resonance imaging data is preprocessed to obtain electric field simulation results. Here, the collected MRI data undergoes a series of preprocessing processes such as cortical reconstruction, electric field simulation, and calculation of cortical structure information. For example, the brain of the experimental subject is first extracted, the brain tissue is segmented, and the T1w image of the individual space of the experimental subject is aligned with the MNI standard template. The cerebral cortex is also segmented and reconstructed to accurately divide the brain sulcus and gyrus structure. Then, electric field simulation is performed at the corresponding stimulation points on the cerebral cortex and cortical structure information is extracted. In an embodiment of the present invention, the visual simulation electric field results of 25 stimulation points are as follows. Figure 4 As shown, the visualization results of the extracted cortical structural information can be seen in Figure 5 As shown in the figure, the cortical structural information specifically includes cortical thickness, cortical curvature and cortical sulcus index.

[0062] Step 102: construct a group hand motion hotspot map based on the MEP signal data and the electric field simulation results, and divide the experimental subjects into positive samples and negative samples through the group hand motion hotspot map.

[0063] After obtaining the MEP signal data and electric field simulation results of the experimental subjects, we can then construct a group hand movement hotspot map based on the MEP signal data and electric field simulation results.

[0064] First, it is necessary to determine the individual hand motion hotspots of each experimental subject. In this embodiment of the present invention, the electric field simulation results of the experimental subject are correlated with the MEP signal data to obtain the individual hand motion hotspots. The specific process of the correlation analysis is described below.

[0065] First, the vertices corresponding to different positions of the experimental subjects' cerebral cortex (motor area) are determined (for example, the 25 stimulation points described above), and the electric field values ​​of each vertex at different stimulation positions are determined from the electric field simulation results.

[0066] Then, for each vertex, the positive correlation value between the electric field value and the MEP signal data is determined. Figure 6 As shown, Figure 6 The positive correlation between the electric field value (E Filed) and the MEP signal data is shown in Figure 1. Based on this positive correlation, the corresponding positive correlation value can be calculated. The positive correlation value can be mapped to the corresponding hand movement hotspot probability. The higher the positive correlation value, the higher the positive correlation between the electric field value and the MEP signal, and the higher the hand movement hotspot probability. By combining the hand movement hotspot probabilities of each vertex, a hand movement hotspot probability map is formed. Figure 7 As shown, Figure 7The visualization results of the hand motion hotspot probability map for some vertices are shown in Figure 2. In the hand motion hotspot probability map, the vertex corresponding to the maximum probability is determined as the individual hand motion hotspot.

[0067] After determining the individual hand motion hotspot based on the electric field simulation results and the MEP signal data, each experimental subject can determine the corresponding individual hand motion hotspot. Then, based on the individual hand motion hotspot, the corresponding sample probability map is constructed using the Gaussian window function. Here, the corresponding sample probability map g(x) is constructed based on the true value of the individual hand motion hotspot (i.e., the coordinates of the individual hand motion hotspot on the cerebral cortex (motor area)). For each true value of the individual hand motion hotspot, the Gaussian window function is used to construct the corresponding sample probability model, which is expressed as the following formula (1):

[0068] (1)

[0069] In the above formula (1), represents the true value of any individual hand movement hotspot, x represents any vertex on the cerebral cortex (motor area), is a hyperparameter representing the effective stimulation range of TMS, generally determined by the intervals between the 25 stimulation points. By performing the calculation process of formula (1) on any vertex in the cerebral cortex (motor area), the corresponding probability of the vertex can be obtained. This can generate multiple different probabilities, thus forming a sample probability map.

[0070] Finally, the sample probability maps of each experimental subject are accumulated to construct the group hand movement hotspot map. Here, the sample probability maps corresponding to each individual hand movement hotspot are uniformly accumulated to obtain the group hand movement hotspot map p(x) corresponding to the population. The accumulation process is to add the Gaussian window function corresponding to each hand movement hotspot, which is expressed as the following formula (2):

[0071] (2)

[0072] In the above formula (2), represents the sample probability map corresponding to the individual hand movement hotspot of the i-th experimental subject. The meanings of the remaining parameters are the same as those in formula (1) and can be referenced to each other, so they will not be repeated here.

[0073] Next, the experimental subjects were divided into positive samples and negative samples through the group hand movement hotspot map. The division process was as follows: first, the vertex corresponding to the maximum probability was determined as the group hand movement hotspot from the group hand movement hotspot map, and then the cortical distance between the individual hand movement hotspot of each experimental subject and the group hand movement hotspot was determined. This distance was generally obtained by coordinate calculation of the true value of the individual hand movement hotspot (coordinates on the cerebral cortex (motor area)) and the true value of the group hand movement hotspot.

[0074] When the cortical distance is greater than the distance threshold, it indicates that the experimental subject's individual hand movement hotspot is far away from the group hand movement hotspot, and the subject belongs to the outlier group. In this case, the experimental subject in the outlier group is determined to be a negative sample. When the cortical distance is less than or equal to the distance threshold, it indicates that the experimental subject's individual hand movement hotspot is close to the group hand movement hotspot, and the subject belongs to the non-outlier group. In this case, the experimental subject in the non-outlier group is determined to be a positive sample.

[0075] Step 103: Train the positive samples and the negative samples to obtain an outlier classification model.

[0076] After the experimental subjects are divided into positive samples and negative samples through the group hand movement hotspot map according to step 102, an outlier classification model can be obtained by training the positive samples and the negative samples.

[0077] When training an outlier classification model to distinguish outliers, negative samples and positive samples are mixed to obtain training samples for the outlier classification model. First, training data must be obtained from the training samples. Here, the vertex with the highest probability is first determined from the group hand motion hotspot map as the group hand motion hotspot. Because the probability corresponding to each vertex in the group hand motion hotspot map represents the possibility of being determined as a group hand motion hotspot, the vertex with the highest probability can be used as the group hand motion hotspot to represent the hand motion hotspot of this group of people.

[0078] Next, the region of interest (ROI) is determined from the cerebral cortex (motor area) of the training samples (including negative and positive samples) with the group hand movement hotspot as the center. Figure 8 As shown, a 20mm area can be defined in the cerebral cortex (motor area) with the group hand movement hotspot as the center ( Figure 8 The yellow area in the middle is used as the region of interest, and then the cerebral cortical structural information within the region of interest is extracted from the magnetic resonance imaging data of the training samples (i.e., the experimental subjects corresponding to the negative samples and the positive samples). The cerebral cortical structural information includes cortical thickness, cortical curvature, and cortical sulcus index.

[0079] Finally, the cerebral cortical structural information (i.e., cortical thickness, cortical curvature, and cortical sulcus index) is used as training data to train the initial logistic regression model and obtain an outlier classification model. During the training process, the information features can be extracted based on the cerebral cortical structural information, and the logistic regression model can be made to learn the differences in information features between negative samples and positive samples, so that the model can subsequently identify the information features of the subjects to be located, that is, identify yin or yang, and thus distinguish whether the hand movement hotspots of the subjects to be located are outliers. The logistic regression model can adopt a classification model in machine learning, such as a random forest, a decision tree, etc., which is not limited in the embodiments of the present application.

[0080] Step 104: For the subjects to be located, the subjects to be located are divided into an outlier group and a non-outlier group using an outlier classification model.

[0081] In some embodiments, after the outlier classification model is trained, it can be used to distinguish subjects to be located (i.e., new subjects). For the subjects to be located, magnetic resonance imaging data can be first acquired, and then cerebral cortical structural information can be extracted from it, and then the information features can be extracted. The outlier classification model can then identify the information features and predict whether the subjects to be located are outliers or non-outliers, thereby classifying the subjects to be located into outlier and non-outlier groups.

[0082] Step 105: When the subject to be located is out of the group, correlation analysis is performed between the electric field simulation result corresponding to the subject to be located and the MEP signal data to obtain the target hand movement hotspot.

[0083] When it is determined that the subject to be located is out of the group, it means that the hand movement hotspot of the subject to be located is far away from the group hand movement hotspot, and the target hand movement hotspot cannot be determined through the group hand movement hotspot map. Therefore, the correlation analysis method is used to locate the target hand movement hotspot. First, the magnetic resonance imaging data of the subject to be located and the MEP signal data corresponding to different locations of the cerebral cortex are obtained, and the magnetic resonance imaging data are preprocessed to obtain the electric field simulation results. Then, the vertex corresponding to the stimulation position of the cerebral cortex of the subject to be located is determined, and the electric field value of each vertex at different stimulation positions is determined from the electric field simulation results.

[0084] Next, for each vertex, a positive correlation value between the electric field value and the MEP signal data is determined. Based on this positive correlation value, an individual hand motion hotspot probability map is determined. The vertex with the highest probability in the individual hand motion hotspot probability map is determined as the target hand motion hotspot for the subject to be located. This correlation analysis process is similar to step 102, and the specific implementation details are not repeated here.

[0085] Step 106: When the subject to be located is not an outlier in the group, individual hand motion hotspots are registered using the group hand motion hotspot map to obtain the target hand motion hotspot.

[0086] If the subject being located is determined to be outside the group, it means that the subject's hand motion hotspot is close to the group's hand motion hotspot. The target hand motion hotspot can then be determined using the group hand motion hotspot map. The target hand motion hotspot is then obtained by registering the individual hand motion hotspots using the group hand motion hotspot map.

[0087] Specifically, from the group hand motion hotspot map, the vertex with the highest probability is determined as the group hand motion hotspot, and then the group-to-individual registration mapping relationship is determined. Here, the open source registration tool Advanced Normalization Tools (ANTs) can be used to first register the T1w image corresponding to the magnetic resonance imaging data of the subject to be located to the standard MNI152 image, and the mapping relationship obtained by the registration is used as the registration mapping relationship. Finally, based on the registration mapping relationship, the group hand motion hotspot is mapped to the individual to obtain the target hand motion hotspot of the subject to be located.

[0088] The method and device for quickly locating hand motion hotspots provided by the present invention first collect the magnetic resonance imaging data and MEP signal data of the experimental subjects to construct a group hand motion hotspot map, and divide the experimental subjects into negative samples and positive samples to train the outlier classification model. To classify the outlier nature of the subject to be located. When the subject to be located is an outlier, the target hand motion hotspot is determined by the MEP signal data. When the subject to be located is not an outlier, the group hand motion hotspot map is directly used for alignment to determine the target hand motion hotspot. In this way, the hand motion hotspot of the subject to be located is located by combining the outlier classification model and the group hand motion hotspot map, which not only achieves the rapid positioning of the hand motion hotspot, but also effectively ensures the accuracy of the hand motion hotspot, thereby improving the efficiency of clinical treatment.

[0089] The hand motion hotspot rapid positioning device provided by the present invention is described below. The hand motion hotspot rapid positioning device described below and the hand motion hotspot rapid positioning method described above can refer to each other.

[0090] See also Figure 9 , Figure 9 This is a schematic diagram of the structure of the hand motion hotspot rapid positioning device provided by the present invention. Figure 9As shown, the hand motion hotspot rapid positioning device includes a pre-processing module 901, a construction module 902, a training module 903, a division module 904, an analysis module 905, and a registration module 906. Among them, the pre-processing module 901 is used to obtain the magnetic resonance imaging data of the experimental subjects and the MEP signal data corresponding to different positions of the brain motor area, and pre-process the magnetic resonance imaging data to obtain electric field simulation results; the construction module 902 is used to construct a group hand motion hotspot map based on the MEP signal data and the electric field simulation results, and divide the experimental subjects into positive samples and negative samples through the group hand motion hotspot map; the training module 903 is used to train the positive samples and the negative samples to obtain outliers A classification model; a division module 904, for dividing the subject to be located into an outlier group and a non-outlier group by using the outlier classification model; an analysis module 905, for performing a correlation analysis between the electric field simulation results corresponding to the subject to be located and the MEP signal data when the subject to be located is an outlier group, so as to obtain a target hand motion hotspot; a registration module 906, for performing individual hand motion hotspot registration by using the group hand motion hotspot map when the subject to be located is a non-outlier group, so as to obtain a target hand motion hotspot.

[0091] It should be noted that the beneficial effects of the hand motion hotspot rapid positioning device here and the hand motion hotspot rapid positioning method mentioned above can correspond to each other, so the beneficial effects of the hand motion hotspot rapid positioning device will not be repeated here.

[0092] Figure 10 This is a schematic diagram of the physical structure of an electronic device provided by the present invention, such as Figure 10As shown, the electronic device may include: a processor 910 , a communication interface 920 , a memory 930 and a communication bus 940 , wherein the processor 910 , the communication interface 920 and the memory 930 communicate with each other via the communication bus 940 . The processor 910 can call the logic instructions in the memory 930 to execute a method for quickly locating hand motion hotspots, which includes: obtaining magnetic resonance imaging data of the experimental subjects and MEP signal data corresponding to stimulating different positions of the cerebral cortex, and preprocessing the magnetic resonance imaging data to obtain electric field simulation results; constructing a group hand motion hotspot map based on the MEP signal data and the electric field simulation results, and dividing the experimental subjects into positive samples and negative samples through the group hand motion hotspot map; training an outlier classification model based on the positive samples and the negative samples; for the subjects to be located, dividing the subjects to be located into outlier groups and non-outlier groups through the outlier classification model; when the subjects to be located are outliers, performing correlation analysis on the electric field simulation results corresponding to the subjects to be located and the MEP signal data to obtain target hand motion hotspots; when the subjects to be located are non-outliers, performing individual hand motion hotspot alignment through the group hand motion hotspot map to obtain target hand motion hotspots.

[0093] Furthermore, the logic instructions in the aforementioned memory 930 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product, stored in a storage medium, includes instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0094] On the other hand, the present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the hand motion hotspot rapid positioning method provided by the above methods, which includes: obtaining magnetic resonance imaging data of the experimental subject and MEP signal data corresponding to different positions of the cerebral cortex, and preprocessing the magnetic resonance imaging data to obtain electric field simulation results; constructing a group hand motion hotspot map based on the MEP signal data and the electric field simulation results, and The experimental subjects are divided into positive samples and negative samples through the group hand motion hotspot map; an outlier classification model is obtained according to the training of the positive samples and the negative samples; for the subjects to be located, the subjects to be located are divided into an outlier group and a non-outlier group through the outlier classification model; when the subjects to be located are outliers, the electric field simulation results corresponding to the subjects to be located are correlated with the MEP signal data to obtain target hand motion hotspots; when the subjects to be located are non-outliers, individual hand motion hotspots are aligned through the group hand motion hotspot map to obtain target hand motion hotspots.

[0095] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method for quickly locating hand motion hotspots provided by the above methods, the method comprising: obtaining magnetic resonance imaging data of an experimental subject and MEP signal data corresponding to different locations of the cerebral cortex being stimulated, and preprocessing the magnetic resonance imaging data to obtain an electric field simulation result; constructing a group hand motion hotspot map based on the MEP signal data and the electric field simulation result, and using the group hand motion hotspot map to locate the hand motion hotspots. Experimental subjects are divided into positive samples and negative samples; an outlier classification model is obtained by training the positive samples and the negative samples; for subjects to be located, the subjects to be located are divided into an outlier group and a non-outlier group through the outlier classification model; when the subjects to be located are in the outlier group, the electric field simulation results corresponding to the subjects to be located are correlated with the MEP signal data to obtain target hand motion hotspots; when the subjects to be located are in the non-outlier group, individual hand motion hotspots are aligned through the group hand motion hotspot map to obtain target hand motion hotspots.

[0096] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0097] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and the necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions 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 number 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.

[0098] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for quickly locating hand motion hotspots, characterized in that: The method comprises: Acquiring magnetic resonance imaging data of the experimental subject and MEP signal data corresponding to stimulating different locations of the cerebral cortex, and preprocessing the magnetic resonance imaging data to obtain electric field simulation results; constructing a group hand motion hotspot map based on the MEP signal data and the electric field simulation results, and dividing the experimental subjects into positive samples and negative samples based on the group hand motion hotspot map; An outlier classification model is obtained by training the positive samples and the negative samples; For the subjects to be located, dividing the subjects to be located into an outlier group and a non-outlier group by using the outlier classification model; When the subject to be located is an outlier, correlation analysis is performed on the electric field simulation results corresponding to the subject to be located and the MEP signal data to obtain the target hand movement hotspot; When the subject to be located is a non-outlier in the group, individual hand motion hotspot registration is performed using the group hand motion hotspot map to obtain a target hand motion hotspot; The method of dividing the experimental subjects into positive samples and negative samples by using the group hand movement heat map includes: From the group hand motion hotspot map, determine the vertex corresponding to the maximum probability as the group hand motion hotspot; Determining the cortical distance between each experimental subject's individual hand movement hotspot and the group hand movement hotspot; When the cortical distance is greater than the distance threshold, the experimental subject is determined to be a negative sample; When the cortical distance is less than or equal to the distance threshold, the experimental subject is determined to be a positive sample; The outlier classification model is obtained by training the positive samples and the negative samples, comprising: From the group hand motion hotspot map, determine the vertex corresponding to the maximum probability as the group hand motion hotspot; Determining a region of interest from the cerebral cortex of training samples with the group hand movement hotspot as the center, wherein the training samples include the positive samples and the negative samples; Extracting cerebral cortical structural information within the region of interest from the magnetic resonance imaging data corresponding to the training sample, wherein the cerebral cortical structural information includes cortical thickness, cortical curvature, and cortical sulcus index; The cerebral cortex structural information is used as training data to train an initial logistic regression model to obtain an outlier classification model.

2. The method for quickly locating hand motion hotspots according to claim 1, characterized in that: The constructing a group hand motion heat map according to the MEP signal data and the electric field simulation results includes: Performing correlation analysis on the electric field simulation results and the MEP signal data to obtain individual hand movement hotspots of the experimental subjects; Based on the individual hand movement hotspots, a Gaussian window function is used to construct a corresponding sample probability map; Each sample probability map is accumulated to construct a group hand movement hotspot map.

3. The method for quickly locating hand motion hotspots according to claim 2, characterized in that: The correlation analysis of the electric field simulation results and the MEP signal data to obtain the individual hand movement hotspots of the experimental subjects includes: Determining the vertices corresponding to the stimulation positions of the cerebral cortex of the experimental subject, and determining the electric field values ​​of each vertex at different stimulation positions based on the electric field simulation results; For each vertex, determining a positive correlation value between the electric field value and the MEP signal data; An individual hand motion hotspot probability map is determined according to the positive correlation value, and a vertex with the highest probability in the individual hand motion hotspot probability map is determined as the individual hand motion hotspot of the experimental subject.

4. The method for quickly locating hand motion hotspots according to claim 1, wherein: The registering of individual hand motion hotspots using the group hand motion hotspot map to obtain a target hand motion hotspot includes: Determining, from the group hand motion hotspot map, a vertex corresponding to the maximum probability as the group hand motion hotspot; Determine the registration mapping relationship from group to individual; According to the registration mapping relationship, the group hand motion hotspots are mapped to the target hand motion hotspots of the subject to be located.

5. A device for quickly locating hand movement hotspots, characterized in that: The device comprises: A preprocessing module is used to obtain magnetic resonance imaging data of the experimental subjects and MEP signal data corresponding to different locations of the brain motor area stimulated, and preprocess the magnetic resonance imaging data to obtain electric field simulation results; A construction module, configured to construct a group hand motion hotspot map based on the MEP signal data and the electric field simulation results, and divide the experimental subjects into positive samples and negative samples based on the group hand motion hotspot map; A training module, configured to obtain an outlier classification model by training the positive samples and the negative samples; a division module, configured to divide the subjects to be located into an outlier group and a non-outlier group by using the outlier classification model; an analysis module, configured to perform a correlation analysis between the electric field simulation results corresponding to the subject to be located and the MEP signal data to obtain a target hand motion hotspot when the subject to be located is out of the group; a registration module for performing individual hand motion hotspot registration using the group hand motion hotspot map to obtain a target hand motion hotspot when the subject to be located is a non-outlier group; The method of dividing the experimental subjects into positive samples and negative samples by using the group hand movement heat map includes: From the group hand motion hotspot map, determine the vertex corresponding to the maximum probability as the group hand motion hotspot; Determining the cortical distance between each experimental subject's individual hand movement hotspot and the group hand movement hotspot; When the cortical distance is greater than the distance threshold, the experimental subject is determined to be a negative sample; When the cortical distance is less than or equal to the distance threshold, the experimental subject is determined to be a positive sample; The outlier classification model is obtained by training the positive samples and the negative samples, comprising: From the group hand motion hotspot map, determine the vertex corresponding to the maximum probability as the group hand motion hotspot; Determining a region of interest from the cerebral cortex of training samples with the group hand movement hotspot as the center, wherein the training samples include the positive samples and the negative samples; Extracting cerebral cortical structural information within the region of interest from the magnetic resonance imaging data corresponding to the training sample, wherein the cerebral cortical structural information includes cortical thickness, cortical curvature, and cortical sulcus index; The cerebral cortex structural information is used as training data to train an initial logistic regression model to obtain an outlier classification model.

6. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method for quickly locating the hand motion hotspot according to any one of claims 1 to 4 is implemented.

7. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for quickly locating a hand motion hotspot as claimed in any one of claims 1 to 4 is implemented.

8. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for quickly locating a hand motion hotspot as claimed in any one of claims 1 to 4 is implemented.

Images