Neuromodulation method, apparatus, device and storage medium based on electrical stimulation

Abstract

The application discloses a nerve regulation method and device based on electric stimulation, equipment and storage medium, and the method comprises the steps of obtaining metabolic image data, functional image data and anatomical image data of a subject; based on the metabolic image data and the functional image data, the standardized uptake value ratio of each brain region of the subject is calculated, and the functional connection strength between each brain region and all other brain regions is calculated; based on the standardized uptake value ratio of each brain region of the subject and the functional connection strength between each brain region and all other brain regions, the brain abnormal characteristics of the subject and the position data of the target point are determined; based on the position data of the target point, the brain abnormal characteristics of the subject and the anatomical image data, the time-domain interference electric stimulation parameters are set. The application can combine and analyze PET image data and rs-fMRI image data, more comprehensively evaluate the metabolic and functional state of the brain of the subject, and perform corresponding nerve regulation based on the time-domain interference electric stimulation parameters.

Description

Technical Field

[0001] This application relates to the field of medical data processing technology, specifically to a neuromodulation method, device, equipment, and storage medium based on electrical stimulation. Background Technology

[0002] Positron emission tomography (PET) is a nuclear medicine imaging technique that displays metabolic processes within a subject's body. PET imaging is based on the use of positron-emitting radionuclides (also known as radiopharmaceuticals or tracers), which are labeled onto compounds involved in blood flow or metabolic processes in human tissues. By injecting these positron-labeled radionuclides into the subject's body, the PET system can sensitively capture gamma-ray radiation within the body and use software to triangulate the emission sources, creating a three-dimensional computed tomographic image of the tracer concentration within the body. PET imaging can be used to study human physiology, biochemistry, neurotransmitters, receptors, and even genetic alterations, showing unique advantages, particularly in diagnosing and guiding the treatment of tumors, coronary heart disease, and brain diseases.

[0003] Resting-state functional magnetic resonance imaging (rs-fMRI) is a method of functional magnetic resonance imaging of the brain. In this technique, the subject is in a resting state, and brain activity is mapped through blood oxygenation level-dependent brain functional imaging. rs-fMRI can observe that a regular functional activity network still exists in the normal human brain in the resting state, and that the functional activity network in the brain under pathological conditions differs from that in the normal human brain and shows remodeling. This technique does not require complex task design, is highly operable, and can avoid the incomparability of experimental results caused by different task designs and differences in subject performance in task-based studies.

[0004] Both PET and rs-fMRI techniques can acquire brain information from the subject, which can characterize whether the brain regions are functioning normally. However, single-modality imaging data often has limitations and cannot simultaneously and comprehensively assess the subject's brain metabolism and functional status.

[0005] In the field of neuromodulation, electrical stimulation techniques, such as transcranial direct current stimulation (tDCS) and transcranial alternating current stimulation (tACS), have been widely used. However, these existing electrical stimulation techniques typically use fixed stimulation parameters, lacking precise control based on the individual characteristics of the subject, resulting in significant individual differences in the modulatory effects and a lack of specificity. Temporal interference stimulation (TIS), as an emerging neuromodulation technique, utilizes the interference effect of currents at different frequencies to achieve precise stimulation of deep brain regions, exhibiting significant neuromodulation effects. Compared to traditional electrical stimulation techniques, TIS can focus on deep brain regions without damaging the cortex, making it applicable to the field of neuromodulation. However, current TIS applications lack precise guidance based on individualized imaging data, limiting its scope and effectiveness.

[0006] Therefore, how to combine PET imaging data and rs-fMRI imaging data for analysis to more comprehensively assess the metabolic and functional status of the subject's brain, and how to perform corresponding neural modulation based on time-domain interference electrical stimulation parameters, are urgent problems to be solved.

[0007] It should be noted that the above statements are only used to provide background information related to this application and do not necessarily constitute prior art. Summary of the Invention

[0008] In view of the above problems, embodiments of this application provide a method, device, electronic device and storage medium for neuromodulation based on electrical stimulation, which can combine and analyze PET image data and rs-fMRI image data, thereby enabling a more comprehensive assessment of the metabolic and functional state of the subject's brain, and performing corresponding neuromodulation based on determined time-domain interference electrical stimulation parameters.

[0009] In a first aspect, embodiments of this application provide a neural modulation method based on electrical stimulation, the method comprising:

[0010] Metabolic imaging data, functional imaging data, and anatomical imaging data of the subjects were acquired; the metabolic imaging data was used to reflect the brain glucose metabolism level, the functional imaging data was used to reflect the brain functional connectivity strength, and the anatomical imaging data was used to reflect the brain internal structure.

[0011] Based on the metabolic imaging data and the functional imaging data, the standardized uptake ratio of each brain region of the subject and the functional connectivity strength between each brain region and all other brain regions are calculated respectively.

[0012] Based on the standardized uptake ratio of each brain region of the subject and the functional connectivity strength between each brain region and all other brain regions, the abnormal characteristics of the subject's brain and the location data of the target points are determined.

[0013] Based on the abnormal brain characteristics of the subject, the location data of the target point, and the anatomical imaging data, time-domain interference electrical stimulation parameters are set.

[0014] In some optional embodiments, the step of calculating the standardized uptake ratio of each brain region of the subject, and the functional connectivity strength between each brain region and all other brain regions, based on the metabolic imaging data and the functional imaging data, includes:

[0015] The metabolic imaging data and the functional imaging data are subjected to standardized preprocessing and multimodal registration.

[0016] Based on the metabolic imaging data and functional imaging data after standardized preprocessing and multimodal registration, the standardized uptake ratio of each brain region of the subject and the functional connectivity strength between each brain region of the subject and all other brain regions are calculated.

[0017] In some optional embodiments, the standardization preprocessing and multimodal registration of the metabolic imaging data, the functional imaging data, and the anatomical imaging data to generate multimodal fused imaging data includes:

[0018] Motion correction is performed on the metabolic imaging data, the corrected metabolic imaging data is registered to the anatomical imaging data, and normalized to the MNI space;

[0019] The functional imaging data is time-corrected, the corrected metabolic imaging data is registered to the anatomical imaging data, and normalized to the MNI space.

[0020] In some optional embodiments, the step of calculating the standardized uptake ratio of each brain region of the subject, and the functional connectivity strength between each brain region of the subject and all other brain regions, based on the metabolic imaging data and the functional imaging data after standardized preprocessing and multimodal registration, includes:

[0021] Based on the metabolic imaging data after standardized preprocessing and multimodal registration, and the preset brain region template, the standardized uptake ratio of each brain region of the subject is calculated.

[0022] Based on the standardized preprocessed and multimodal registered functional image data, and the preset brain region template, the functional connectivity strength between each brain region of the subject and all other brain regions is calculated.

[0023] In some optional embodiments, determining the abnormal brain characteristics and target location data of the subject based on the standardized uptake ratios of each brain region and the functional connectivity strength between each brain region and all other brain regions includes:

[0024] Based on the standardized uptake ratios within each brain region and the mean and standard deviation of the standardized uptake ratios in the standard data of the healthy control group, metabolic abnormality index data for each brain region of the subject were calculated.

[0025] Based on the functional characteristic data within each brain region and the functional connectivity strength between each brain region and all other brain regions in the standard data of the healthy control group, the functional abnormality index data of each brain region of the subject were calculated.

[0026] Based on the metabolic abnormality index data and the functional abnormality index data of each brain region of the subject, the risk index data of each brain region of the subject are determined according to the preset risk assessment model.

[0027] Based on the metabolic abnormality index data and functional abnormality index data of each brain region of the subject, as well as the risk index data, the location data of the target point is determined.

[0028] In some optional embodiments, the step of determining the risk indicator data for each brain region of the subject based on metabolic abnormality indicator data for each brain region and functional abnormality indicator data between each pair of brain regions of the subject, according to a preset risk assessment model, includes:

[0029] Based on the metabolic abnormality index data of each brain region of the subject and the functional abnormality index data between each pair of brain regions of the subject, the risk index data of each brain region of the subject are determined according to the following formula:

[0030] S(i)=ω1·Z SUVR (i)+ω2·Z FC (i)

[0031] Among them, Z SUVR (i) represents the standardized metabolic abnormality index data, Z FC (i) represents the standardized functional abnormality index data, where ω1 and ω2 are the weighting coefficients of metabolic level and functional connectivity, respectively, reflecting the relative importance of metabolic level and functional connectivity characteristics.

[0032] In some optional embodiments, setting the temporal interferometric electrical stimulation parameters based on the abnormal brain characteristics of the subject, the location data of the target point, and the anatomical imaging data includes:

[0033] Based on the location data of the target point and the abnormal brain characteristics and physiological features of the subject, the frequency, intensity, time and period of the temporal interference electrical stimulation are set.

[0034] An individualized head model is constructed based on the anatomical imaging data of the subject, and electrode positions are preset based on the constructed head model.

[0035] Secondly, embodiments of this application provide an electrical stimulation-based neuromodulation device, the electrical stimulation-based neuromodulation device comprising:

[0036] The imaging data acquisition module is used to acquire metabolic imaging data, functional imaging data and anatomical imaging data of the subject; the metabolic imaging data is used to reflect the brain glucose metabolism level, the functional imaging data is used to reflect the brain functional connectivity strength, and the anatomical imaging data is used to reflect the brain internal structure.

[0037] The image data processing module is used to calculate the standardized uptake ratio of each brain region of the subject, as well as the functional connectivity strength between each brain region and all other brain regions, based on the metabolic image data and the functional image data.

[0038] The joint risk identification module is used to determine the abnormal brain characteristics and target location data of the subject based on the standardized uptake ratio of each brain region and the functional connectivity strength between each brain region and all other brain regions.

[0039] The stimulation parameter setting module is used to set time-domain interference electrical stimulation parameters based on the abnormal brain characteristics of the subject, the location data of the target point, and the anatomical imaging data.

[0040] Thirdly, embodiments of this application provide an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor, the processor running the computer program to implement the method as described in the first aspect.

[0041] Fourthly, embodiments of this application provide a computer-readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the method described in the first aspect.

[0042] In this application, after obtaining metabolic, functional, and anatomical imaging data of the subject, the standardized uptake ratio of each brain region and the functional connectivity strength between each brain region and all other brain regions are calculated based on the metabolic and functional imaging data. Based on these standardized uptake ratios and functional connectivity strengths, the location data of the target site and abnormal brain characteristics are determined. Then, based on the determined target site location data, the subject's abnormal brain characteristics, and the subject's anatomical imaging data, temporal interference electrical stimulation parameters are set. By combining and analyzing PET and rs-fMRI imaging data, the target site and temporal interference electrical stimulation parameters are further determined, thus revealing a more comprehensive understanding of the pathological mechanisms of Alzheimer's disease (AD). Based on the calculated temporal interference electrical stimulation parameters, corresponding neuromodulation is performed, providing more accurate data support for subsequent disease analysis and medical treatment.

[0043] The above description is merely an overview of the technical solutions of the embodiments of this application. In order to better understand the technical means of this application and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of the embodiments of this application more obvious and understandable, the following are specific embodiments of this application. Attached Figure Description

[0044] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiments below. The accompanying drawings are for illustrative purposes only and are not intended to limit the scope of this application. Furthermore, the same reference numerals denote the same parts throughout the drawings. In the drawings:

[0045] Figure 1 A flowchart illustrating a neuromodulation method based on electrical stimulation provided for some embodiments of this application;

[0046] Figure 2 This is a detailed flowchart illustrating step S2 provided in some embodiments of this application;

[0047] Figure 3 This is a schematic flowchart illustrating step S3 as provided in some embodiments of this application;

[0048] Figure 4 This application provides schematic diagrams illustrating the framework of an electrically stimulated neuromodulation device according to some embodiments.

[0049] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of this application is shown. Detailed Implementation

[0050] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0051] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which embodiments of this application pertain; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the embodiments of this application; the terms “comprising” and “having”, and any variations thereof, in the specification, claims, and foregoing description of the drawings of this application are intended to cover non-exclusive inclusion.

[0052] In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0053] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0054] In the description of the embodiments in this application, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0055] While PET and rs-fMRI technologies can acquire brain information that can characterize the normality of brain region function, single-modality imaging data often has limitations and cannot simultaneously and comprehensively assess the metabolic and functional status of the brain.

[0056] For the reasons mentioned above, this application proposes a neuromodulation method based on electrical stimulation. This method combines and analyzes PET and rs-fMRI image data to further determine the pathological mechanism of Alzheimer's disease (AD) more comprehensively, providing more accurate data support for subsequent disease analysis and medical treatment.

[0057] The following detailed description, with reference to the accompanying drawings, illustrates the neuromodulation method based on electrical stimulation provided in the embodiments of this application. Please refer to... Figure 1 , Figure 1This is a flowchart illustrating the neuromodulation method based on electrical stimulation provided in an embodiment of this application, as shown below. Figure 1 As shown, this electrical stimulation-based neuromodulation method may include the following steps:

[0058] Step S1: Obtain metabolic imaging data, functional imaging data, and anatomical imaging data of the subject;

[0059] Step S2: Based on metabolic imaging data and functional imaging data, calculate the standardized uptake ratio of each brain region of the subject, as well as the functional connectivity strength between each brain region and all other brain regions.

[0060] Step S3: Based on the standardized uptake ratio of each brain region of the subject and the functional connectivity strength between each brain region and all other brain regions, determine the abnormal characteristics of the subject's brain and the location data of the target points.

[0061] Step S4: Based on the abnormal characteristics of the subject's brain, the location data of the target point, and the anatomical imaging data, set the time-domain interference electrical stimulation parameters.

[0062] Metabolic imaging data reflects brain glucose metabolism levels, functional imaging data reflects the strength of brain functional connectivity, and anatomical imaging data reflects internal brain structure. Temporal-domain electrical stimulation (TIS), as an emerging neuromodulation technique, utilizes the interference effect of currents at different frequencies to achieve precise stimulation of deep brain regions, exhibiting significant neuromodulation effects. By adjusting the parameters of TIS, effective intervention in abnormal brain regions can be ensured while minimizing interference with normal brain regions.

[0063] In step S1 above, a standardized image acquisition protocol can be used to acquire multimodal image data of the subject, including FDG PET (deoxyglucose positron emission tomography) metabolic images, rs-fMRI (resting-state functional magnetic resonance imaging) functional images, and T1 MRI (referring to T1-weighted imaging in magnetic resonance imaging technology) anatomical images.

[0064] During FDG PET metabolic imaging, 18F-FDG (fluorodeoxyglucose) tracer is injected, and positron emission tomography (PET) technology is used to accurately identify the brain metabolic levels in various brain regions of the subject. Subjects must fast for at least 6 hours before the injection of the radiopharmaceutical to ensure adequate blood glucose levels, thereby reducing potential interference with the metabolic imaging results. During rs-fMRI data acquisition, subjects are instructed to remain awake with their eyes closed and complete at least 5 minutes of resting-state scanning to obtain information on functional connectivity between brain regions. For T1 MRI imaging, high-resolution T1-weighted imaging technology is used to capture subtle features of brain structures, providing a basis for subsequent anatomical registration and brain region segmentation, and assisting in the construction of accurate individualized head anatomical models.

[0065] All the collected data can be stored in DICOM format and transmitted to subsequent modules in an encrypted manner to ensure data security and integrity and prevent data loss or leakage.

[0066] In some alternative embodiments, such as Figure 2 As shown, step S2 above may include the following specific steps: step S21, performing standardized preprocessing and multimodal registration on metabolic imaging data and functional imaging data; step S22, based on the standardized preprocessing and multimodal registration of metabolic imaging data and functional imaging data, calculating the standardized uptake ratio of each brain region of the subject, and the functional connectivity strength between each brain region of the subject and all other brain regions.

[0067] In this embodiment, metabolic imaging data and functional imaging data can be preprocessed in a unified manner and fused in the same space and coordinate system to form multimodal fused imaging data. Based on this multimodal fused imaging data, data quality and cross-individual consistency can be ensured, thereby providing a solid data foundation for subsequent analysis and processing.

[0068] Specifically, step S21 may include the following processing: performing motion correction on the metabolic imaging data, registering the corrected metabolic imaging data to the anatomical imaging data, and standardizing it to the MNI space; performing time correction on the functional imaging data, registering the corrected metabolic imaging data to the anatomical imaging data, and standardizing it to the MNI space.

[0069] In this embodiment, when performing standardized preprocessing and multimodal registration on metabolic imaging data, functional imaging data, and anatomical imaging data, firstly, motion correction is performed on FDG PET images, which are then registered to T1 MRI images and standardized to the MNI space, with Gaussian smoothing applied to reduce noise. For rs-fMRI images, time correction is performed first, followed by motion correction, then registration to T1 MRI and MNI spaces, and finally spatial smoothing is applied to improve the signal-to-noise ratio.

[0070] Furthermore, various brain tissue structure data can be obtained based on anatomical imaging data, and these data can be standardized to the MNI space. Specifically, after head dissection, T1 MRI images are used to identify and separate 11 types of brain tissue, including gray matter, white matter, cerebrospinal fluid, and muscle tissue, using brain tissue segmentation algorithms, and then standardized to the MNI space, providing a reliable basis for subsequent electrical stimulation simulations. Finally, by fusing metabolic, functional, and anatomical information, high-quality multimodal fused images are generated based on registered FDG PET, rs-fMRI, and T1 MRI images, providing a solid data foundation for subsequent analysis and processing.

[0071] Furthermore, step S22 may include the following processing: calculating the standardized uptake ratio of each brain region of the subject based on the metabolic imaging data after standardized preprocessing and multimodal registration, and the preset brain region template; calculating the functional connectivity strength between each brain region of the subject and all other brain regions based on the functional imaging data after standardized preprocessing and multimodal registration, and the preset brain region template.

[0072] In this embodiment, after multimodal image preprocessing, the Schaefer 400 brain region segmentation template is further introduced to accurately assess metabolic and functional abnormalities in brain regions. Based on functional connectivity maps, the Schaefer 400 template divides the whole brain into 400 regions of interest (ROIs) with good anatomical and functional consistency. Specifically, FDG PET, rs-fMRI, and T1 MRI data normalized to MNI space are first spatially aligned with the Schaefer 400 template to ensure accurate mapping between the template segmentation and individual image data. Subsequently, the template is used to segment the image data into brain regions, facilitating the extraction of metabolic indicators and functional characteristics within each ROI. Based on the extracted metabolic indicators and functional characteristics, the normalized uptake ratio of each brain region and the functional connectivity strength between each brain region and all other brain regions can be accurately calculated. This Schaefer 400 template-based segmentation method provides both refined metabolic and functional assessment and ensures consistency and comparability across individual analyses, providing a reliable basis for subsequent disease analysis and medical treatment.

[0073] The Standardized Uptake Ratio (SUVR) is a method for quantifying metabolic activity in PET data. It works by calculating the ratio of the average radioactivity value of the target region to the average value of a reference region (cerebellar cortex or whole brain white matter) to eliminate the influence of individual dose and body weight differences.

[0074] Based on rs-fMRI data, a whole-brain functional connectivity matrix based on Regions of Interest (ROIs) was constructed. For each ROI pair, the correlation between brain regions over time was measured by calculating the Pearson correlation coefficient, and the functional connectivity strength (FC) between brain region i and every other brain region j was calculated. patients (i, j).

[0075] After calculating the SUVR value for each brain region of the subject, their metabolic abnormality score S was calculated. SUVR (i) is used to quantify the degree of decline in the metabolic level of this brain region relative to a healthy baseline, and is calculated using the following formula:

[0076]

[0077] Where, μ HC (i) and σ HC (i) represents the mean and standard deviation of the SUVR value in brain region i of the healthy control group, respectively. patient (i) represents the actual SUVR value of brain region i in the subject, S SUVR (i)>0 indicates a decrease in metabolic level, suggesting possible pathological changes; negative values ​​indicate that the metabolic level is close to or higher than the healthy baseline.

[0078] To ensure the comparability and consistency of the scores, all metabolic abnormality scores were further standardized using Z-scores to obtain the Z-score. SUVR (i) To unify the dimensions and provide a unified standard for the calculation of subsequent joint risk scores.

[0079] The functional connectivity strength FC between brain regions i and j was calculated. patients After (i, j), the functional connectivity abnormality score S for each brain region can be calculated. FC (i) is used to measure the degree of deviation of the functional connectivity of brain region i from the healthy baseline, and is calculated as follows:

[0080]

[0081] in, and , i and j represent the functional connectivity strengths of brain regions i and j in the subjects and healthy controls, respectively, where N is the total number of brain regions connected to brain region i. To reduce noise interference, the functional connectivity is defined using a globally uniform threshold determined by the functional connectivity distribution of the healthy control group data (e.g., retaining the top 10% of strong connections). This ensures that the functional connectivity matrices of all subjects are consistent and comparable.

[0082] Building upon this foundation, to further reduce noise interference and avoid the loss of key connections due to sparse networks, regularization methods (such as Lasso or graph regularization) are introduced to balance network sparsity with the preservation of key information. This method effectively removes interference from low-strength connections while ensuring the biological reliability of strong connections, thus providing a more robust functional connectivity matrix for subsequent analysis. After calculation, all functional connectivity anomaly scores are Z-score standardized to obtain Z0. FC (i).

[0083] In some other alternative embodiments, such as Figure 3 As shown, step S3 above may include the following specific steps: Step S31, calculating metabolic abnormality index data for each brain region of the subject based on the standardized uptake ratio within each brain region and the mean and standard deviation of the standardized uptake ratio in the standard data of the healthy control group; Step S32, calculating functional abnormality index data between each brain region of the subject and all other brain regions based on the functional characteristic data within each brain region and the functional connectivity strength of each brain region in the standard data of the healthy control group; Step S33, determining risk index data for each brain region of the subject according to a preset risk assessment model based on the metabolic abnormality index data for each brain region of the subject and the functional abnormality index data between each two brain regions of the subject; Step S34, determining the location data of the target point based on the metabolic abnormality index data for each brain region of the subject, the functional abnormality index data for each brain region, and the risk index data.

[0084] Specifically, step S33 above may include the following processing: based on metabolic abnormality index data of each brain region of the subject and functional abnormality index data between each pair of brain regions of the subject, determine the risk index data of each brain region of the subject according to the following formula:

[0085] S(i)=ω1·Z SUVR (i)+ω2·Z FC (i)

[0086] Among them, Z SUVR (i) represents the standardized metabolic abnormality index data, Z FC (i) represents the standardized functional abnormality index data, where ω1 and ω2 are the weighting coefficients of metabolic level and functional connectivity, respectively, reflecting the relative importance of metabolic level and functional connectivity characteristics.

[0087] In this embodiment, after calculating the standardized metabolic abnormality score Z... SUVR (i) and functional connectivity anomaly score Z FC Following (i), to comprehensively assess the risk level of each brain region and accurately identify high-risk lesions, providing key targets for subsequent personalized treatment, this module proposes the aforementioned risk assessment index data, namely the functional-metabolic joint risk score S(i). To ensure the scientific validity of the score calculation and the optimal performance of the model, the weights ω1 and ω2 will be determined on the publicly available ADNI dataset using the following method:

[0088] 1. Initial weight setting:

[0089] The initial weights were set using characteristic statistics from the healthy control group, specifically using variance contributions based on metabolic and functional connectivity scores. In particular, the larger the variance of a feature, the more significant its distributional differences at the healthy baseline, and the higher its sensitivity to abnormal features, thus assigning it a higher weight. The initial weight setting formula is as follows:

[0090]

[0091] Where, σ k The standard deviation of feature k (metabolic activity function connectivity score) is represented.

[0092] 2. Bayesian optimization process:

[0093] Bayesian optimization approximates the distribution of the objective function by constructing a probabilistic model (such as a Gaussian process, GP), gradually narrowing the search range and improving optimization efficiency. First, the search range of weight parameters ω1 and ω2 is set (e.g., [0,1]), and the constraint ω1+ω2=1 is applied to ensure the rationality of weight allocation. GP, as a surrogate model for the objective function, fits the distribution of the objective function based on the evaluated weight combinations and their corresponding classification performance indicators (such as AUC, sensitivity, and specificity), while providing predictions of the objective function value and its uncertainty. Based on this, a collection function (such as the desired improvement in EI or the upper confidence limit UCB) is used to select the next set of weight combinations for evaluation, balancing exploration and utilization, and prioritizing the most promising combinations. The new evaluation results are added to the dataset, and the surrogate model is updated, gradually improving its prediction accuracy and fitting ability to the distribution of the objective function. When the improvement of the collection function is lower than a preset threshold or the maximum number of iterations is reached, the optimization process stops and the optimal weight combination is output. and

[0094] Before setting the time-domain interferometric electrical stimulation parameters, candidate high-risk targets can be determined by setting a screening threshold T based on the joint risk score S(i). The threshold T is determined as follows: 1. Initially set the screening threshold THC :

[0095] The preliminary screening threshold is calculated based on the joint score distribution of healthy control groups in the ADNI dataset, using the following formula:

[0096] T HC =μ HC +k·σ HC

[0097] Where, μ HC and σ HC The mean and standard deviation of the combined scores of the healthy control group were used as the basis for calculation. The initial k=1.96 (corresponding to the 95th percentile) was set to ensure that the selected brain regions deviated significantly from those of the healthy control group.

[0098] 2. Dynamically adjust the filtering threshold:

[0099] At the initial screening threshold T HC Based on this, and combined with the data from the subject group, the screening threshold T is dynamically adjusted to comprehensively consider both the healthy baseline and pathological characteristics, as shown in the following formula:

[0100] T = α·T HC +(1-α)·T Patient

[0101] Among them, T Patient The upper quartile of the joint score distribution of the subject group is α, which is the weighting coefficient that controls the influence ratio of the healthy control group and the subject group.

[0102] By adjusting α, the selection threshold T is optimized in the validation set to achieve the best classification performance (such as AUC value, sensitivity, and specificity), and the optimal threshold T is finally output. * As a global standard for target screening, it is used for subsequent screening and identification of targets in subjects.

[0103] For each brain region in the subject data, after calculating the joint risk score, regions satisfying S(i)>T are selected. * Brain regions with high scores were identified as high-risk candidate targets. For candidate targets, they were ranked from highest to lowest based on their combined score S(i), with high-scoring brain regions being prioritized for therapeutic intervention. If some targets showed significant abnormalities only in a single characteristic (e.g., metabolic abnormalities only or functional connectivity abnormalities only), they were marked as low-priority targets.

[0104] In some alternative embodiments, the individualized characteristics of the subject include the subject's physiological and anatomical features. The subject's physiological features may include parameters such as age, sex, and weight. The subject's anatomical features may include tissue segmentation features and brain region segmentation features. The subject's anatomy includes tissue segmentation and brain region segmentation.

[0105] Accordingly, step S4, which sets the temporal interference electrical stimulation parameters based on the subject's abnormal brain characteristics and the location data of the target point, may include the following specific processing: setting the frequency, intensity, time, and period of the temporal interference electrical stimulation based on the location data of the target point and the subject's abnormal brain characteristics and physiological features; constructing an individualized head model based on the subject's anatomical imaging data, and presetting electrode positions based on the constructed head model.

[0106] Specifically, the characteristics of the examinee include the examinee's multi-level individualized characteristics, mainly including: (1) Target characteristics: obtaining the specific location (anatomical coordinates) of high-risk targets and the degree of metabolic abnormality and functional connectivity abnormality (joint score S(i) and characteristic composition Z). SUVR (i), Z FC (i) ;(2) Anatomical and physiological characteristics of the subject (i.e., anatomical imaging data): including tissue segmentation and brain region segmentation, as well as parameters such as age, sex, and weight.

[0107] The stimulation parameters of TIS can be optimized in the following aspects: (1) Stimulation frequency setting: Two sets of high-frequency currents (such as 2kHz and 2.01kHz) interference waves are used to form a focused low-frequency (such as 10Hz) stimulation at the target point through phase interference; (2) Stimulation intensity calculation: Combine the joint score of the target point as the adjustment coefficient. The higher the degree of abnormality of the target point, the greater the stimulation intensity; (3) Electrode position optimization: Combine T1MRI data and brain tissue segmentation results, construct an individualized head model through MRI or CT navigation, and accurately preset the electrode position. Ensure that the electrode placement can effectively generate the interference focusing effect of two sets of high-frequency currents. Using the finite element method (FEM) or other bioelectric simulation technology, based on the brain tissue information obtained from the segmentation, simulate the current distribution and the focusing effect of the stimulation field to verify the effectiveness of the electrode placement. In this way, the accuracy and safety of electrode stimulation can be ensured, and the treatment effect can be further optimized; (4) Stimulation time and cycle setting: Optimize the stimulation time (such as 20 minutes per session) and cycle (such as 3 times a week for 4 weeks) according to the treatment tolerance of the subject to achieve the best therapeutic effect.

[0108] In addition, the treatment effect can be monitored in real time through imaging and behavioral assessment methods, such as: (1) metabolic monitoring: using PET imaging to monitor the metabolic activity level of the target and its surrounding brain regions, and assessing the metabolic recovery by quantifying changes in metabolic rate; (2) network function monitoring: combining EEG and fMRI data to assess the degree of enhancement of target neural activity and the synergy of the whole brain network; (3) behavioral function assessment: quantifying changes in the cognitive, emotional and motor functions of the examinee through neuropsychological tests (such as MMSE, WAIS) to provide an intuitive reference for the treatment effect.

[0109] In summary, the electrical stimulation-based neuromodulation method provided in this embodiment, after acquiring metabolic, functional, and anatomical imaging data of the subject, calculates the standardized uptake ratio of each brain region and the functional connectivity strength between each brain region and all other brain regions based on the metabolic and functional imaging data. Based on these data, the location data of the target site and abnormal brain characteristics are determined. Then, based on the determined target site location data, the subject's abnormal brain characteristics, and the subject's anatomical imaging data, temporal interference electrical stimulation parameters are set. By combining and analyzing PET and rs-fMRI imaging data, the target site and temporal interference electrical stimulation parameters are further determined, thus revealing a more comprehensive understanding of the pathological mechanisms of Alzheimer's disease (AD). Based on the calculated temporal interference electrical stimulation parameters, corresponding neuromodulation is performed, providing more accurate data support for subsequent disease analysis and medical treatment.

[0110] Based on the same concept as the above-described electrical stimulation-based neuromodulation method, this application also provides an electrical stimulation-based neuromodulation device for implementing the above-described electrical stimulation-based neuromodulation method, such as... Figure 4 As shown, the electrical stimulation-based neuromodulation device includes:

[0111] The imaging data acquisition module is used to acquire metabolic imaging data, functional imaging data and anatomical imaging data of the subject; metabolic imaging data is used to reflect the brain glucose metabolism level, functional imaging data is used to reflect the strength of brain functional connectivity, and anatomical imaging data is used to reflect the internal structure of the brain.

[0112] The image data processing module is used to calculate the standardized uptake ratio of each brain region of the subject, as well as the functional connectivity strength between each brain region and all other brain regions, based on metabolic imaging data and functional imaging data.

[0113] The joint risk identification module is used to determine the abnormal characteristics of the subject's brain and the location data of the target points based on the standardized uptake ratio of each brain region and the functional connectivity between each brain region and all other brain regions.

[0114] The stimulation parameter setting module is used to set time-domain interference electrical stimulation parameters based on the abnormal characteristics of the subject's brain, the location data of the target point, and anatomical imaging data.

[0115] It is understood that the electrical stimulation-based neuromodulation device provided in this embodiment is used to execute the above-described electrical stimulation-based neuromodulation method, and therefore can at least achieve the beneficial effects that the above-described electrical stimulation-based neuromodulation method can achieve. Moreover, the various embodiments of the above-described electrical stimulation-based neuromodulation method are also applicable to this electrical stimulation-based neuromodulation device, and will not be described again here.

[0116] Based on the same concept as the above-described electrical stimulation-based neuromodulation method, this application also provides an electronic device for performing the above-described electrical stimulation-based neuromodulation method. Please refer to... Figure 5 This illustrates a schematic diagram of an electronic device provided by some embodiments of this application. For example... Figure 5 As shown, the electronic device 5 includes: a processor 501, a memory 502, a bus 503 and a communication interface 504. The processor 501, the communication interface 504 and the memory 502 are connected through the bus 503. The memory 502 stores a computer program that can run on the processor 501. When the processor 501 runs the computer program, it executes the neuromodulation method based on electrical stimulation provided in any of the foregoing embodiments of this application.

[0117] The memory 502 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this device network element and at least one other network element is achieved through at least one communication interface 504 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc.

[0118] Bus 503 can be an ISA bus, PCI bus, or EISA bus, etc. Buses can be divided into address buses, data buses, control buses, etc. Memory 502 is used to store programs. After receiving execution instructions, processor 501 executes the programs. The neuromodulation method based on electrical stimulation disclosed in any of the aforementioned embodiments of this application can be applied to processor 501, or implemented by processor 501.

[0119] Processor 501 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 501 or by instructions in software form. Processor 501 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application-Specific Integrated Circuit (ASIC), an Off-the-shelf Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 502. Processor 501 reads the information in memory 502 and, in conjunction with its hardware, completes the steps of the above method.

[0120] The electronic device provided in this application embodiment and the neuromodulation method based on electrical stimulation provided in this application embodiment are based on the same inventive concept and have the same beneficial effects as the methods they employ, operate or implement.

[0121] This application also provides a computer-readable storage medium corresponding to the electrical stimulation-based neuromodulation method provided in the foregoing embodiments, wherein a computer program (i.e., a program product) is stored thereon, and when the computer program is run by a processor, it executes the electrical stimulation-based neuromodulation method provided in any of the foregoing embodiments.

[0122] It should be noted that computer-readable storage media may include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory, optical disc or other optical and magnetic storage media, etc., which will not be elaborated here.

[0123] The computer-readable storage medium provided in this application embodiment and the electrical stimulation-based neuromodulation method provided in this application embodiment are based on the same inventive concept and have the same beneficial effects as the methods used, run or implemented by the application stored therein.

[0124] This application also provides a computer program product corresponding to the electrical stimulation-based neuromodulation method provided in the foregoing embodiments, including a computer program that is executed by a processor to implement the aforementioned electrical stimulation-based neuromodulation method.

[0125] The computer program product provided in this application embodiment is based on the same inventive concept as the electrical stimulation-based neuromodulation method provided in this application embodiment, and has the same beneficial effects as the method implemented by the computer program being executed by a processor.

[0126] It is understood that the description of the various embodiments above tends to emphasize the differences between the various embodiments, and the similarities or similarities can be referred to each other. For the sake of brevity, these will not be repeated here.

[0127] Those skilled in the art will understand that in the methods described above in specific embodiments, the order in which the steps are written does not imply a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined based on its function and possible internal logic.

[0128] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and not to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. These modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application, and they should all be covered within the scope of the claims and specification of this application. In particular, as long as there is no structural conflict, the various technical features mentioned in the embodiments can be combined in any way. This application is not limited to the specific embodiments disclosed herein, but includes all technical solutions falling within the scope of the claims.

Claims

1. A method of neuromodulation based on electrical stimulation, characterized in that, The method comprises: acquiring metabolic image data, functional image data and anatomical image data of a subject; the metabolic image data is used to reflect brain glucose metabolism level, the functional image data is used to reflect brain functional connection strength, and the anatomical image data is used to reflect brain internal structure; based on the metabolic image data and the functional image data, respectively calculating the standardized uptake value ratio of each brain region of the subject and the functional connection strength between each brain region and all other brain regions; based on the standardized uptake value ratio of each brain region of the subject and the functional connection strength between each brain region and all other brain regions, determining the brain abnormality characteristics and the location data of the target point of the subject; including: based on the standardized uptake value ratio in each brain region and the mean and standard deviation of the standardized uptake value ratio in the health control group standard data, calculating the metabolic abnormality index data of each brain region of the subject; based on the functional feature data in each brain region and the functional connection strength between each brain region and all other brain regions in the health control group standard data, calculating the functional abnormality index data of each brain region of the subject; based on the metabolic abnormality index data of each brain region of the subject and the functional abnormality index data of each brain region of the subject, determining the risk index data of each brain region of the subject according to a preset risk assessment model; based on the metabolic abnormality index data of each brain region of the subject and the functional abnormality index data of each brain region, and the risk index data, determining the location data of the target point; based on the brain abnormality characteristics of the subject, the location data of the target point and the anatomical image data, setting time domain interference electric stimulation parameters.

2. The method of claim 1, wherein, The method comprises: acquiring metabolic image data, functional image data and anatomical image data of a subject; the metabolic image data is used to reflect brain glucose metabolism level, the functional image data is used to reflect brain functional connection strength, and the anatomical image data is used to reflect brain internal structure; based on the metabolic image data and the functional image data, respectively calculating the standardized uptake value ratio of each brain region of the subject and the functional connection strength between each brain region and all other brain regions; 3. The method of claim 2, wherein, based on the metabolic image data and the functional image data, respectively calculating the standardized uptake value ratio of each brain region of the subject and the functional connection strength between each brain region and all other brain regions; The method comprises: motion correction is performed on the metabolic image data, the corrected metabolic image data is registered to the anatomical image data, and is standardized to MNI space; 4. The method of claim 2, wherein, time correction is performed on the functional image data, the corrected metabolic image data is registered to the anatomical image data, and is standardized to MNI space. The method comprises: motion correction is performed on the metabolic image data, the corrected metabolic image data is registered to the anatomical image data, and is standardized to MNI space; time correction is performed on the functional image data, the corrected metabolic image data is registered to the anatomical image data, and is standardized to MNI space. calculate, based on the standardized pre-processing and multi-modal registration of the metabolic image data and a preset brain partition template, a standardized uptake value ratio of each brain region of the subject; calculate, based on the standardized pre-processing and multi-modal registration of the functional image data and the preset brain partition template, a functional connection strength between each brain region and all other brain regions of the subject.

5. The method of claim 1, wherein, The risk index data of each brain region of the subject is determined according to a preset risk assessment model based on the metabolic abnormality index data of each brain region of the subject and the functional abnormality index data between each two brain regions of the subject, including: The risk index data of each brain region of the subject is determined according to the following formula based on the metabolic abnormality index data of each brain region of the subject and the functional abnormality index data between each two brain regions of the subject: wherein, denotes the standardized metabolic abnormality index data, denotes the standardized functional abnormality index data, and ω1 and ω2 are weight coefficients of the metabolic level and the functional connection, respectively, reflecting the relative importance of the metabolic level and the functional connection characteristics.

6. The method according to any one of claims 1 to 5, wherein, The time-domain interference electric stimulation parameters are set based on the brain abnormality characteristics of the subject, the position data of the target point and the anatomical image data, including: The frequency, intensity, time and period of the time-domain interference electric stimulation are set based on the position data of the target point and the brain abnormality characteristics and physiological characteristics of the subject; An individualized head model is constructed based on the anatomical image data of the subject, and an electrode position is preset based on the constructed head model.

7. An electric stimulation based neuromodulation device, characterized by The neural regulation device based on electric stimulation includes: An image data acquisition module is configured to acquire metabolic image data, functional image data and anatomical image data of a subject; the metabolic image data is used to reflect the brain glucose metabolism level, the functional image data is used to reflect the brain functional connection strength, and the anatomical image data is used to reflect the brain internal structure; An image data processing module is configured to calculate, based on the metabolic image data and the functional image data, a standardized uptake value ratio of each brain region of the subject and a functional connection strength between each brain region and all other brain regions; A joint risk identification module is configured to determine brain abnormality characteristics and position data of a target point of a subject based on a standardized uptake value ratio of each brain region of the subject and a functional connection strength between each brain region and all other brain regions; including: calculating metabolic abnormality index data of each brain region of the subject based on the standardized uptake value ratio in the brain region and a mean value and a standard deviation of the standardized uptake value ratio in the health control group standard data; calculating functional abnormality index data of each brain region of the subject based on functional feature data in the brain region and a functional connection strength between each brain region and all other brain regions in the health control group standard data; determining risk index data of each brain region of the subject according to a preset risk assessment model based on the metabolic abnormality index data of each brain region of the subject and the functional abnormality index data of each brain region of the subject; and determining the position data of the target point based on the metabolic abnormality index data of each brain region of the subject, the functional abnormality index data of each brain region and the risk index data. A stimulation parameter setting module is configured to set time-domain electrical stimulation parameters based on the brain abnormality characteristics of the subject, the position data of the target site, and the anatomical image data.

8. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor executes the computer program to implement the method of any one of claims 1-6.

9. A computer readable storage medium having stored thereon a computer program, characterized in that, The program is executed by the processor to implement the method of any one of claims 1-6.

Images