Individualized insomnia intervention target spot determination method and device, medium and product
By preprocessing and functional connection analysis of resting fMR images of insomnia patients, the clustering algorithm is used to determine the insomnia intervention targets, which solves the problem of the lack of individualized targets for insomnia treatment with TMS and improves the treatment effect.
Patent Information
- Application Number
- CN202510179661.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-18
- Publication Date
- 2025-06-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing TMS treatment insomnia lacks precise individualized intervention targets, resulting in poor treatment results.
By obtaining resting state fMRI images of insomnia patients, preprocessing and functional connection analysis were performed, and insomnia intervention targets were determined based on standard 26 voxel domain criteria.
The precise determination of individualized intervention targets for insomnia patients has been achieved, and the application effect of TMS technology in the treatment of insomnia has been improved.
Smart Images
Figure CN120093266A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of individualized intervention target selection, and in particular to an individualized insomnia intervention target determination method, device, medium and product. Background Art
[0002] Insomnia, as a common sleep disorder, can seriously affect the health of patients. Its symptoms mainly include difficulty falling asleep, inability to maintain sleep, and easy waking up. While it has a serious impact on the patient's daily life, it is also related to a variety of neurocognitive diseases. At present, drug treatment is the main way for insomnia patients to receive treatment, but due to the side effects of drug treatment and the potential dependence that may be generated, it is of great significance to explore effective non-drug treatment methods for insomnia. Transcranial Magnetic Stimulation (TMS) technology can affect the human nervous system with a pulsed magnetic field, and induce induced currents in cortical nerve cells, thereby affecting neural electrical activity and achieving the effect of intervening in neural responses. This technology is currently considered to be a clinical treatment and rehabilitation method with great potential due to its safety, controllability, and non-invasiveness. However, the existing TMS treatment programs for insomnia lack precise individualized intervention targets, which hinders the application of TMS technology in the treatment of insomnia.
[0003] Existing studies have shown that insomnia often manifests as excessive arousal of the cerebral cortex, which prevents insomniacs from falling asleep. Repetitive Transcranial Magnetic Stimulation (rTMS) technology can improve dysfunctional networks by regulating brain functional connections. However, the therapeutic effect of rTMS is closely related to the selection of stimulation targets. Therefore, finding precise and effective individualized insomnia intervention targets and inhibiting excessive arousal of the cerebral cortex are of great significance for the treatment of insomnia.
[0004] The current target of rTMS treatment for insomnia is mainly the dorsolateral prefrontal cortex (DLPFC). The traditional positioning method is used to determine the location of the DLPFC, that is, the stimulation point is located 5 cm in front of the site that can produce the maximum motor response in the abductor pollicis brevis. Some experimental plans also choose the parietal lobe as the stimulation target.
[0005] Although many existing studies have used traditional methods to locate rTMS targets for insomnia treatment, the biggest disadvantage of this method is that it ignores individual differences. Since the brain anatomical structure of different individuals is often different, the location of the same brain region can produce huge differences between individuals, and the network structure of the same brain region can also vary between individuals. The targets located using traditional methods are often not of practical significance. And for rTMS technology, the farther away from the stimulation site, the worse the stimulation effect. Therefore, it is difficult to obtain an accurate and effective intervention target through traditional positioning methods to give full play to the greatest advantage of rTMS technology in treating insomnia. In addition, the occurrence of the disease is related to the corresponding changes in the brain circuits, and rTMS stimulation also affects the brain network related to the stimulation target. The traditional method does not consider brain functional connectivity as an important factor in locating rTMS targets for insomnia treatment. Summary of the invention
[0006] The purpose of this application is to provide a method, device, medium and product for determining individualized insomnia intervention targets to accurately determine insomnia intervention targets.
[0007] To achieve the above objectives, this application provides the following solutions:
[0008] In a first aspect, the present application provides a method for determining individualized insomnia intervention targets, comprising:
[0009] Acquire resting-state functional magnetic resonance images of insomnia patients;
[0010] Preprocessing the resting-state functional magnetic resonance image to obtain a resting-state functional magnetic resonance image in the MNI standard space; the preprocessing includes image format conversion, removal of unstable time points, time layer correction, magnetic field deformation correction, head motion correction, noise signal removal, structural image registration, filtering, spatial standardization and spatial smoothing;
[0011] Extracting a time series of a region of interest of a resting-state functional magnetic resonance image in the MNI standard space; the region of interest is a mask of an insomnia functional atlas; the insomnia functional atlas is constructed based on experimental results; the experimental results include the MNI standard space coordinates of the dorsolateral prefrontal lobe stimulation site and the improvement of insomnia symptoms in insomnia patients before and after treatment;
[0012] Determine the functional connection between the time series signals of the region of interest and the time series signals of each voxel in the dorsolateral prefrontal brain region of the insomnia patient;
[0013] According to the functional connection, a clustering algorithm is used to determine the insomnia intervention target of the insomnia patient based on the standard 26-voxel field criterion; the insomnia intervention target is the center of gravity of the largest cluster.
[0014] Optionally, the process of constructing the insomnia functional map specifically includes:
[0015] The actual stimulation site was located according to the MNI standard spatial coordinates of the dorsolateral prefrontal stimulation site in insomnia patients;
[0016] Determine a repetitive transcranial magnetic stimulation modulation area; the repetitive transcranial magnetic stimulation modulation area is a spherical area centered on the actual stimulation site; the radius of the spherical area is a set radius;
[0017] Constructing a resting-state functional connectivity database; the resting-state functional connectivity database includes a functional connectivity regional network of resting-state functional magnetic resonance images of several normal persons;
[0018] Determining the functional connection area network activated by the repetitive transcranial magnetic stimulation modulation area of the insomnia patient according to the resting state functional connection database;
[0019] Determine the correlation between each voxel in the functional connection area network activated by the repetitive transcranial magnetic stimulation modulation area of the insomnia patient and the improvement of the insomnia symptoms of the corresponding insomnia patient before and after treatment, and obtain the correlation value corresponding to each voxel;
[0020] Determine the functional connectivity of the dorsolateral prefrontal region in the insomnia group and the dorsolateral prefrontal region in the normal group, and determine the difference map between the groups;
[0021] According to the correlation values corresponding to all voxels and the inter-group difference map, an insomnia functional map is constructed.
[0022] Optionally, extracting a time series of a region of interest of a resting-state functional magnetic resonance image in the MNI standard space specifically includes:
[0023] Extract the time series signals of voxels in the region of interest of the resting-state functional magnetic resonance image in the MNI standard space;
[0024] The weighted average of the time series signals of the voxels in the region of interest was calculated to obtain the time series of the region of interest of the resting-state functional magnetic resonance image in the MNI standard space.
[0025] Optionally, the functional connection is the Pearson correlation coefficient between the time series of the region of interest of the insomnia patient and the time series signal of each voxel in the dorsolateral prefrontal region.
[0026] Optionally, according to the functional connectivity, a clustering algorithm is used to determine the insomnia intervention target of the insomnia patient based on the standard 26-voxel field criterion, specifically including:
[0027] According to the functional connectivity, using a clustering algorithm, a continuous cluster of voxels with the strongest negative functional connectivity is identified; the strongest negative functional connectivity is when the functional connectivity strength value of the corresponding voxel is in the top 0.5% of all voxels in the dorsolateral prefrontal brain region;
[0028] The continuous clusters are clustered based on the standard 26-voxel neighborhood criterion, and the center of gravity of the largest cluster is determined as the insomnia intervention target for the insomnia patient.
[0029] In a second aspect, the present application provides a computer device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any of the above-described individualized insomnia intervention target determination methods.
[0030] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-described individualized insomnia intervention target determination methods.
[0031] In a fourth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned individualized insomnia intervention target determination methods.
[0032] According to the specific embodiments provided in this application, this application has the following technical effects:
[0033] The present application provides a method, device, medium and product for determining individualized insomnia intervention targets, obtaining resting-state functional magnetic resonance images of insomnia patients; preprocessing the resting-state functional magnetic resonance images to obtain resting-state functional magnetic resonance images in the MNI standard space; extracting the time series of the region of interest of the resting-state functional magnetic resonance images in the MNI standard space; the region of interest is a mask of the insomnia functional map; the insomnia functional map is constructed based on experimental results; the experimental results include the MNI standard space coordinates of the dorsolateral prefrontal stimulation site and the improvement of insomnia symptoms before and after treatment of insomnia patients; determining the functional connection of the time series of the region of interest of the insomnia patient and the time series signal of each voxel in the dorsolateral prefrontal brain region; according to the functional connection, using a clustering algorithm, based on the standard 26-voxel field criterion, determining the insomnia intervention target of the insomnia patient; the insomnia intervention target is the center of gravity of the largest cluster. The present application determines accurate and stable individualized intervention targets for insomnia patients by integrating group-level information and individual-level information in the insomnia functional map. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0035] Figure 1 A schematic diagram of a process for determining a target for individualized insomnia intervention provided in one embodiment of the present application;
[0036] Figure 2 A flowchart of the actual application of the method for determining individualized insomnia intervention targets provided in one embodiment of the present application;
[0037] Figure 3 Schematic diagram of the process for constructing a functional map of insomnia;
[0038] Figure 4 This is a schematic diagram of the calculation of the functional connection between the insomnia functional map and each voxel in the DLPFC brain area;
[0039] Figure 5 Schematic diagram of clustering method;
[0040] Figure 6 A schematic diagram of the structure of a computer device provided in one embodiment of the present application. DETAILED DESCRIPTION
[0041] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.
[0042] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below with reference to the accompanying drawings and specific implementation methods.
[0043] This application proposes a method for selecting individualized insomnia intervention targets. This method constructs an insomnia functional map, comprehensively considers the functional connectivity closely related to the improvement of insomnia symptoms and the intergroup differences between insomnia patients and normal people, makes full use of the functional connectivity information at the group level and individual level of insomnia patients, and combines the cluster analysis method to calculate accurate and effective individualized insomnia intervention targets.
[0044] In an exemplary embodiment, Figure 1 and Figure 2As shown, a method for determining individualized insomnia intervention targets is provided, comprising the following steps:
[0045] S1: Obtain resting-state functional magnetic resonance images of insomnia patients.
[0046] S2: Preprocessing the resting-state functional magnetic resonance image to obtain a resting-state functional magnetic resonance image in the MNI standard space; the preprocessing includes image format conversion, removal of unstable time points, time layer correction, magnetic field deformation correction, head motion correction, noise signal removal, structural image registration, filtering, spatial standardization and spatial smoothing.
[0047] In practical applications, the resting-state functional magnetic resonance imaging (fMRI) data of insomnia patients are preprocessed, including image format conversion, removal of unstable time points, time layer correction, magnetic field deformation correction, head motion correction, removal of noise signals such as white matter and cerebrospinal fluid, structural image registration, filtering, spatial standardization, spatial smoothing, etc., to obtain fMRI of insomnia patients registered to the MNI standard space.
[0048] S3: Extracting the time series of the region of interest of the resting-state functional magnetic resonance image in the MNI standard space; the region of interest is a mask of the insomnia functional map; the insomnia functional map is constructed based on the experimental results; the experimental results include the MNI standard space coordinates of the dorsolateral prefrontal lobe stimulation site and the improvement of insomnia symptoms in insomnia patients before and after treatment.
[0049] In practical applications, the experimental results of the intervention treatment of insomnia by locating rTMS stimulation sites based on traditional methods are used to construct a functional connection map related to insomnia, namely, an insomnia functional map. The experimental results include the coordinates of the Montreal Neurological Institute standardspace (MNI standard space) of the DLPFC stimulation site and the improvement of insomnia symptoms in insomnia patients before and after treatment. The improvement refers to the change in the Pittsburgh sleep quality index (PSQI) of insomnia patients before and after treatment. The higher the PSQI score, the worse the sleep quality. The specific calculation formula for the improvement is as follows:
[0050]
[0051] Among them, Delta-PSQI is the improvement of insomnia symptoms in insomnia patients before and after treatment.
[0052] like Figure 3As shown in the figure, the construction process of the insomnia functional map specifically includes:
[0053] (1) The actual stimulation site was located according to the MNI standard spatial coordinates of the dorsolateral prefrontal stimulation site in insomnia patients.
[0054] In practical applications, the actual stimulation site is located based on the coordinates in the MNI standard space. The specific positioning method is as follows: First, the patient's nuclear magnetic resonance image is registered to the MNI standard space. The registration process includes roughly aligning the image with the MNI standard template, using nonlinear registration to accurately match the MNI standard template, matching the resolution of the image and the template through interpolation and resampling, and applying the transformation matrix to achieve coordinate transformation; after the registration is completed, since the experimental results in S1 already contain the MNI standard space coordinates of the stimulation site, the actual stimulation site can be located in the MNI standard space according to the coordinates. Due to individual differences in traditional positioning methods, the actual stimulation sites of different patients are often located in different positions in the DLPFC brain region.
[0055] (2) Determine a repetitive transcranial magnetic stimulation modulation area; the repetitive transcranial magnetic stimulation modulation area is a spherical area centered on the actual stimulation site; the radius of the spherical area is a set radius.
[0056] In practical applications, a spherical area with a radius of 0.5 cm, centered on the actual stimulation site, is set as the actual rTMS modulation area, that is, the brain area actually affected by rTMS.
[0057] (3) Constructing a resting-state functional connectivity database; the resting-state functional connectivity database includes a functional connectivity area network of resting-state functional magnetic resonance images of several normal people.
[0058] In practical applications, based on a large sample data set of 1,000 normal people collected by ourselves, the functional connectivity of resting-state functional magnetic resonance imaging was calculated on the data set, and the functional connection area network corresponding to different parts of the brain was obtained, and a standardized resting-state functional connectivity database was constructed.
[0059] The calculation process of functional connectivity is as follows: first, extract the time series of the target voxel. If calculating the functional connectivity between different brain regions, it is necessary to extract the time series of the target brain region. The time series of a certain brain region is defined as the average of all the time series of voxels in the brain region. Calculate the Pearson correlation coefficient between the time series of the target voxel (or brain region) and the time series of other voxels (or brain regions) respectively, and use the calculated result as the functional connectivity strength value between voxels (or brain regions). The time series of n time points X = [x 1 ,x 2 ,...,x n ] and Y=[y 1 ,y 2 ,...,yn The calculation formula of the Pearson correlation coefficient r is as follows:
[0060]
[0061] (4) Determine the functional connection area network activated by the repetitive transcranial magnetic stimulation modulation area of the insomnia patient based on the resting-state functional connection database.
[0062] In practical applications, the functional connection area network activated by the actual rTMS stimulation modulation area of each insomnia patient is calculated based on the resting state functional connection database obtained in step (3). The specific calculation process is as follows: first determine the functional connection area network corresponding to each voxel in the rTMS stimulation modulation area in the resting state functional connection database; average all functional connection area networks to obtain the functional connection area network corresponding to the entire rTMS stimulation modulation area. The functional connection area network represents the brain area affected during the actual stimulation process.
[0063] (5) Determine the correlation between each voxel in the functional connection area network activated by the repetitive transcranial magnetic stimulation modulation area of the insomnia patient and the improvement of the insomnia symptoms of the corresponding insomnia patient before and after treatment, and obtain the correlation value corresponding to each voxel.
[0064] In practical applications, the correlation between each voxel in the functional connection area network obtained in step (4) and the improvement of insomnia symptoms before and after treatment of insomnia patients is calculated to obtain the correlation value corresponding to each voxel, which indicates the importance of the functional connection change in the area for the improvement of insomnia. The specific calculation process is as follows: For each voxel in the functional connection area network of each insomnia patient, there is a corresponding functional connection strength value. The Pearson correlation coefficient between the functional connection strength value of a certain voxel of all insomnia patients and the improvement is calculated, and the result is used as the correlation value of the voxel; the same operation is performed on all voxels in the whole brain to obtain the correlation value corresponding to the voxels in the whole brain.
[0065] (6) Determine the functional connectivity of the dorsolateral prefrontal region in the insomnia patient group and the normal control group, and determine the difference map between the groups.
[0066] In practical applications, the functional connectivity between the DLPFC region and other brain regions of insomnia patients and normal subjects was calculated. A generalized linear model was used to evaluate the difference in DLPFC functional connectivity between insomnia patients and normal subjects. Cohen's f 2 To characterize the effect size of the difference between insomnia patients and normal people, based on this result, the intergroup difference map of DLPFC functional connectivity between insomnia patients and normal people was constructed. The generalized linear model involved is expressed by the following equation:
[0067] y=μ+Xβ+∈。
[0068] Where μ represents a constant term, y represents the functional connectivity value of DLPFC in insomnia patients or normal people, X represents the design matrix of independent variables (including diagnostic status, age, gender, education level, etc.), β is the regression coefficient corresponding to X, and ∈ is the normal distribution N(0,σ 2 ) The false discovery rate was used to correct for multiple comparisons, with a threshold of q < 0.05.
[0069] Cohen's f 2 The specific calculation process is as follows:
[0070] Two generalized linear models were constructed: a full model, i.e., a model including all variables; and a reduced model, i.e., a model including all variables except diagnostic status. Cohen's f 2 The calculation formula is as follows:
[0071]
[0072] in, is the R of the full model 2 , represents the proportion of total variance explained by all variables, To simplify the model R 2 , which represents the proportion of variance explained after removing the target variable.
[0073] (7) Constructing an insomnia functional map based on the correlation values corresponding to all voxels and the inter-group difference map.
[0074] In practical applications, the intergroup difference map determined in step (6) is used as the weight to weight the correlation values of the corresponding brain region voxels in the result of step (5). Finally, the weighted calculation results are normalized to the range of [-1, 1] and the threshold is set to 0.5. These voxel-based mapping results are used as insomnia functional maps.
[0075] Next, based on the insomnia functional map, individualized intervention targets are calculated for insomnia patients.
[0076] As an optional implementation, S3 specifically includes:
[0077] S31: Extract the time series signals of voxels within the region of interest of the resting-state functional magnetic resonance image in the MNI standard space.
[0078] S32: Calculate the weighted average of the time series signals of the voxels in the region of interest to obtain the time series of the region of interest of the resting-state functional magnetic resonance image in the MNI standard space.
[0079] In practical applications, in the MNI standard space, the insomnia functional map mask is used as the region of interest to extract the time series signals of the voxels in the fMRI region of interest of the insomnia patient in the MNI standard space. The value of the voxel corresponding to the insomnia functional map, that is, the importance of the functional change of the region for the improvement of insomnia, is used as the weight to calculate the weighted average of the time series signals of the voxels in the region of interest. The calculation result is used as the time series of the insomnia functional map of the insomnia patient, that is, the time series of the region of interest of the resting state functional magnetic resonance image in the MNI standard space.
[0080] S4: Determine the functional connection between the time series of the region of interest of the insomnia patient and the time series signals of each voxel in the dorsolateral prefrontal lobe brain region. The functional connection is the Pearson correlation coefficient between the time series of the region of interest of the insomnia patient and the time series signals of each voxel in the dorsolateral prefrontal lobe brain region.
[0081] In practical applications, such as Figure 4 As shown, for each insomnia patient, the Pearson correlation coefficient between the time series under the insomnia functional map and the time series of each voxel in the DLPFC brain region is calculated, that is, the functional connection between the insomnia functional map and each voxel in the DLPFC brain region is calculated.
[0082] S5: According to the functional connectivity, a clustering algorithm is used to determine the insomnia intervention target of the insomnia patient based on the standard 26-voxel field criterion; the insomnia intervention target is the center of gravity of the largest cluster.
[0083] As an optional implementation, S5 specifically includes:
[0084] S51: Based on the functional connectivity, a clustering algorithm is used to identify a continuous cluster of voxels with the strongest negative functional connectivity; the strongest negative functional connectivity is when the functional connectivity strength value of the corresponding voxel is in the top 0.5% of all voxels in the dorsolateral prefrontal brain region.
[0085] S52: Clustering the continuous clusters based on a standard 26-voxel neighborhood criterion, and determining the center of gravity of the largest cluster as the insomnia intervention target for the insomnia patient.
[0086] In practical applications, such as Figure 5 As shown in the figure, based on the functional connection between the insomnia functional map and each voxel in the DLPFC brain region, a clustering method is used to identify continuous clusters of voxels with the strongest negative functional connections. The strongest negative functional connection is defined as the functional connection strength value of the corresponding voxel is in the top 0.5% of all voxels in the DLPFC brain region. Too high a threshold will lead to a lower level of individualization. Clustering is based on the standard 26-voxel neighborhood criterion. The center of gravity of the largest cluster is calculated, and this position is defined as the individualized target for insomnia patients.
[0087] This application aims to solve the problem of lack of individualized targets for rTMS intervention treatment of insomnia patients, and proposes a method for selecting individualized insomnia intervention targets based on the functional connectivity strength of resting-state functional network connections. The group-level insomnia functional map and the individual-level functional connectivity map are combined to determine the individualized targets for insomnia. The insomnia functional map is constructed by combining the functional connectivity closely related to the improvement of insomnia symptoms and the intergroup differences between insomnia patients and normal people, which can more comprehensively reflect the functional connectivity changes of insomnia patients.
[0088] This application uses resting-state functional network connectivity to determine targets for insomnia patients. Different from traditional positioning methods, it combines brain functional network information and can provide relatively more accurate and effective therapeutic intervention targets for insomnia patients.
[0089] This application comprehensively considers the functional connections that are closely related to the improvement of insomnia symptoms and the inter-group differences between insomnia patients and normal people to construct an insomnia functional map, reflecting the functional connection changes of insomnia patients from a more comprehensive perspective.
[0090] This application comprehensively utilizes information at the group level and the individual level, rather than considering only one aspect of them. This makes the calculated individualized targets not only have strong individuality, but also retains the relevant characteristics of the group level, and the calculated targets are more stable.
[0091] This application uses a weighted average method combined with global information when calculating the time series of insomnia functional maps, effectively reducing the interference caused by noise. At the same time, a clustering method is used based on functional connectivity to determine the best target, making the calculation results more accurate and stable.
[0092] This application is a set of target selection methods specifically for individual patients, taking into account individual information such as the brain anatomical structure and functional connectivity of different patients. Each patient can ultimately calculate personalized potential treatment targets, which has obvious individual advantages.
[0093] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the above-mentioned individualized insomnia intervention target determination method is implemented.
[0094] In an exemplary embodiment, a computer-readable storage medium is provided, storing a computer program, which, when executed by a processor, implements the above-mentioned individualized insomnia intervention target determination method.
[0095] In an exemplary embodiment, a computer program product is provided, including a computer program, which implements the above-mentioned individualized insomnia intervention target determination method when executed by a processor.
[0096] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for determining an individualized insomnia intervention target is implemented.
[0097] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.
[0098] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.
[0099] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM may be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).
[0100] The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. The non-relational database may include a distributed database based on blockchain, etc., but is not limited thereto. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but is not limited thereto.
[0101] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0102] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.
Claims
1. A method for determining individualized insomnia intervention targets, characterized in that: include: Acquire resting-state functional magnetic resonance images of insomnia patients; Preprocessing the resting-state functional magnetic resonance image to obtain a resting-state functional magnetic resonance image in the MNI standard space; the preprocessing includes image format conversion, removal of unstable time points, time layer correction, magnetic field deformation correction, head motion correction, noise signal removal, structural image registration, filtering, spatial standardization and spatial smoothing; Extracting a time series of a region of interest of a resting-state functional magnetic resonance image in the MNI standard space; the region of interest is a mask of an insomnia functional atlas; the insomnia functional atlas is constructed based on experimental results; the experimental results include the MNI standard space coordinates of the dorsolateral prefrontal lobe stimulation site and the improvement of insomnia symptoms in insomnia patients before and after treatment; Determine the functional connection between the time series signals of the region of interest and the time series signals of each voxel in the dorsolateral prefrontal brain region of the insomnia patient; According to the functional connection, a clustering algorithm is used to determine the insomnia intervention target of the insomnia patient based on the standard 26-voxel field criterion; the insomnia intervention target is the center of gravity of the largest cluster.
2. The method for determining individualized insomnia intervention targets according to claim 1, characterized in that: The construction process of the insomnia functional map includes: The actual stimulation site was located according to the MNI standard spatial coordinates of the dorsolateral prefrontal stimulation site in insomnia patients; Determine a repetitive transcranial magnetic stimulation modulation area; the repetitive transcranial magnetic stimulation modulation area is a spherical area centered on the actual stimulation site; the radius of the spherical area is a set radius; Constructing a resting-state functional connectivity database; the resting-state functional connectivity database includes a functional connectivity regional network of resting-state functional magnetic resonance images of several normal persons; Determining the functional connection area network activated by the repetitive transcranial magnetic stimulation modulation area of the insomnia patient according to the resting state functional connection database; Determine the correlation between each voxel in the functional connection area network activated by the repetitive transcranial magnetic stimulation modulation area of the insomnia patient and the improvement of the insomnia symptoms of the corresponding insomnia patient before and after treatment, and obtain the correlation value corresponding to each voxel; Determine the functional connectivity of the dorsolateral prefrontal region in the insomnia group and the dorsolateral prefrontal region in the normal group, and determine the difference map between the groups; According to the correlation values corresponding to all voxels and the inter-group difference map, an insomnia functional map is constructed.
3. The method for determining individualized insomnia intervention targets according to claim 1, characterized in that: Extract the time series of the region of interest of the resting-state functional magnetic resonance image in the MNI standard space, including: Extract the time series signals of voxels in the region of interest of the resting-state functional magnetic resonance image in the MNI standard space; The weighted average of the time series signals of the voxels in the region of interest was calculated to obtain the time series of the region of interest of the resting-state functional magnetic resonance image in the MNI standard space.
4. The method for determining individualized insomnia intervention targets according to claim 1, characterized in that: The functional connection is the Pearson correlation coefficient between the time series of the region of interest of the insomnia patient and the time series signal of each voxel in the dorsolateral prefrontal brain region.
5. The method for determining individualized insomnia intervention targets according to claim 1, characterized in that: According to the functional connectivity, a clustering algorithm is used to determine the insomnia intervention targets for the insomnia patient based on the standard 26-voxel field criteria, specifically including: According to the functional connectivity, using a clustering algorithm, a continuous cluster of voxels with the strongest negative functional connectivity is identified; the strongest negative functional connectivity is when the functional connectivity strength value of the corresponding voxel is in the top 0.5% of all voxels in the dorsolateral prefrontal brain region; The continuous clusters are clustered based on the standard 26-voxel neighborhood criterion, and the center of gravity of the largest cluster is determined as the insomnia intervention target for the insomnia patient.
6. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for determining individualized insomnia intervention targets according to any one of claims 1 to 5.
7. A 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 determining individualized insomnia intervention targets according to any one of claims 1 to 5 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 determining individualized insomnia intervention targets according to any one of claims 1 to 5 is implemented.