Nervous system image analysis method and device

Abstract

The invention discloses a nervous system image analysis method and a nervous system image analysis device, and relates to the technical field of nervous system disease diagnosis and treatment. Fusing and collecting multi-modal data: collecting nervous system image data of functional magnetic resonance imaging (fMRI), magnetic resonance spectrum imaging (MRS), diffusion tensor imaging (DTI) and positron emission tomography (PET) modals of a patient through an internal system of a hospital; according to the method, multi-modal data of functional magnetic resonance imaging, magnetic resonance spectrum imaging, diffusion tensor imaging and positron emission tomography are integrated, quality evaluation and integration processes are executed in the central data processing unit, the accuracy and reliability of the data are remarkably enhanced, meanwhile, a space-time joint feature analysis model is introduced, and the accuracy and reliability of the data are improved. The time and space dimension information in the image data is linked, the change rule and internal correlation of the data in the time and space dimensions are mined, and the diagnosis accuracy of nervous system diseases is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of diagnosis and treatment of nervous system diseases, and in particular to a method and device for analyzing nervous system images. Background Art

[0002] With the continuous advancement of medical technology, neurological imaging analysis plays an increasingly important role in the diagnosis, treatment and research of neurological diseases. In recent years, multimodal imaging technologies, such as functional magnetic resonance imaging (fMRI), magnetic resonance spectroscopy (MRS), diffusion tensor imaging (DTI) and positron emission tomography (PET), have been increasingly used in the diagnosis of neurological diseases. These technologies can reveal the structural and functional changes of the nervous system from different angles, providing doctors with rich diagnostic information. At the same time, with the rapid development of big data, artificial intelligence and machine learning technologies, data processing and analysis capabilities have been significantly improved, providing new means and methods for neurological imaging analysis.

[0003] Although traditional nervous system imaging analysis technology has achieved certain results, it still has some shortcomings. First, traditional methods only rely on single-modality imaging data for analysis, which limits the comprehensiveness and accuracy of diagnostic information. Imaging data of different modalities reflect information from different aspects of the nervous system. Single-modality analysis tends to ignore other important information, thus affecting the accuracy of the diagnosis. Secondly, when processing and analyzing imaging data, traditional methods often ignore the changing patterns and correlations of data in the temporal and spatial dimensions, resulting in insufficient sensitivity and specificity of the diagnostic results. In addition, traditional methods lack personalized treatment recommendations and cannot meet the specific needs of different patients, affecting the treatment effect and the quality of life of patients.

[0004] Therefore, the development of a method and device for analyzing nervous system images is expected to not only address the limitations of traditional technologies, but also provide more effective, safe, and personalized treatment services for patients with neurological diseases. Summary of the invention

[0005] The purpose of the present invention is to make up for the shortcomings of the existing technology and provide a method and device for analyzing nervous system images. By fusing multimodal image data and utilizing spatiotemporal joint feature analysis technology, the diagnostic accuracy of nervous system diseases is improved. At the same time, it is combined with a treatment effect prediction model to recommend personalized treatment plans based on the patient's specific situation, thereby achieving the goal of precision medicine.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: On the one hand, a method for analyzing nervous system images, the specific steps of the analysis method are: S100, multimodal data fusion acquisition: collect patients' functional magnetic resonance imaging (fMRI), magnetic resonance spectroscopy (MRS), diffusion tensor imaging (DTI), and positron emission tomography (PET) multimodal neurological imaging data through the hospital's internal system, and transmit the collected raw data to the central data processing unit in real time, conduct quality assessment on the integrated multimodal data, repair data with problems, and integrate the data after repair through the multimodal data fusion formula; S200, spatiotemporal joint feature analysis: preprocess the fused dynamic nervous system image data, remove artifacts and noise, perform spatiotemporal segmentation, extract temporal and spatial features, and fuse the temporal feature vector and the spatial feature vector to construct the spatiotemporal feature vector. ,Use the spatiotemporal correlation formula to mine the correlation between the spatiotemporal feature vector and the surrounding neighborhood in the spatiotemporal dimension; S300, construction of multi-disease joint diagnosis model: Combine the clinical information data with the data from the spatiotemporal joint feature analysis step, and divide them into a test set and a validation set. Use the disease discrimination formula to build a diagnosis model. The formula is: ,in Indicates the type of disease, is the number of disease-related characteristic patterns, , and are model parameters, is the time characteristic function, is the normalization constant, and the model is trained using the training set to determine the parameters in the model and , and then evaluate the model performance through the test set, and optimize and adjust the model according to the evaluation results; S400, treatment effect prediction: extract features related to treatment effect from multimodal imaging data and clinical information, construct feature vectors, build prediction models through treatment effect prediction formulas, use grid search to tune the model's hyperparameters, and after independent data verification, input the corresponding features of new patients into the model to obtain treatment effect prediction results for different treatment methods; S500, personalized treatment plan recommendation: construct a knowledge graph for the treatment of neurological diseases, integrate diagnosis, prediction results and patient clinical information to form a personalized treatment information network, use intelligent decision-making algorithms to generate preliminary personalized treatment plans based on the network, continuously collect feedback information to update the network during the treatment process, and update the network and optimize the treatment plan based on the treatment feedback information.

[0007] Furthermore, in the S100, in the multimodal data fusion acquisition, data integration is performed using a multimodal data fusion formula, assuming that the t-th mode in the multimodal image data is at a spatial position and the signal strength at time t is , the formula is: ,in is the number of modes, , , and is the fusion coefficient, is the variable in the time integral, The integral variable is .

[0008] Furthermore, in S100, signal strength in multimodal data fusion acquisition Calculation: The calculation of the functional magnetic resonance imaging signal intensity is based on the spatial position and time The signal strength at , whose expression is ,in represents the physical quantity related to magnetic resonance, represents the function related to the BOLD effect; The calculation of the magnetic resonance spectroscopy imaging signal intensity is as follows: The spatial position of MRS and time Signal strength at ,in is the concentration of a specific metabolite, is a function related to the MRS acquisition parameters; The calculation of the diffusion tensor imaging signal intensity is as follows: The spatial position of DTI and time Signal strength at ,in is a coefficient related to the tissue intrinsic signal intensity and other imaging parameters, is the diffusion weighting factor, is the diffusion tensor matrix, whose elements Describe the diffusion characteristics of water molecules in different directions; The calculation of the positron emission tomography signal intensity is based on The spatial position of PET and time Signal strength at ,in is a coefficient related to detector efficiency and photon attenuation factors, The radioactive tracer is located in space and time The concentration at It means that the photon is emitted from the point To the detection point is a function of the physical processes of attenuation and scattering.

[0009] Furthermore, in S200, temporal feature extraction in spatiotemporal joint feature analysis, for each ROI time window subsequence , discrete wavelet transform is used to extract time features, and the wavelet function is ( is the wavelet scale), then the wavelet coefficient , construct the time feature vector ,in is the number of wavelet scales selected.

[0010] Furthermore, in the S200, spatial feature extraction in the spatiotemporal joint feature analysis, the Geary's C index is used to calculate the spatial correlation feature between the voxels in each ROI. and voxels The characteristic value of and , the calculation formula is: ,in is the number of voxels in the ROI, is the spatial weight matrix, when voxel and Adjacent time ,otherwise , The dynamic time warping algorithm is used to calculate the functional connectivity features between different ROIs. The time series features of the two ROIs are and , then the calculation formula of DTW distance is: ,in Matching paths for time series, As the feature distance metric function, construct the spatial feature vector .

[0011] Furthermore, in the S200, the spatiotemporal joint feature analysis utilizes the spatiotemporal correlation formula to mine the correlation between the spatiotemporal feature vector and the surrounding neighborhood in the spatiotemporal dimension, and the formula is: ,in: Indicates spatial location The spatiotemporal correlation eigenvalue at is the spatial location Neighborhood of It is The area of ​​interest is Spatial position in the time window The spatiotemporal characteristic values ​​at It is ROI in spatial location The mean of the spatiotemporal characteristics at is calculated as: .

[0012] Furthermore, in the S300, the training of the diagnostic model in the construction of the multi-disease joint diagnostic model, the training set data is input into the constructed model, and the model is trained using the back propagation algorithm. Suppose the training set data is , For the The characteristic data of samples, is the corresponding disease type label, and the model prediction output is , calculate the cross entropy loss function, the formula is: , calculate the loss function for The gradient of is: , the specific gradient expression is obtained by gradually expanding the calculation through the chain rule, and the model parameters are updated by stochastic gradient descent. The formula is: , is the learning rate, and the number of training rounds is set to ,After each round of training, the model performance is evaluated on the validation set.

[0013] Furthermore, in the S400, a prediction model is constructed by using a treatment effect prediction formula in the treatment effect prediction, and the formula is: ,in: Representation based on image features and disease type Predicted treatment outcome indicators The probability value of , , is a coefficient determined through clinical data training, Treatment outcome index Adjustment factor related to its own characteristics.

[0014] Furthermore, in the above S500, the intelligent decision-making algorithm is used to generate a preliminary personalized treatment plan based on this network in the personalized treatment plan recommendation, and the formula is: ,in: Indicates a preliminary personalized treatment plan, is the number of treatment options in the knowledge graph that are related to the current patient's disease and meet the screening criteria, It is The initial weight of each treatment plan in the knowledge graph, is an adjustment factor based on disease matching, calculated as: ,in is the patient's disease feature vector, It is a treatment plan The feature vector of the applicable disease, is the adjustment parameter, is an adjustment factor based on individual patient characteristics, is an adjustment factor based on the prediction of treatment effect, calculated as: ,in is the adjustment parameter, Predicted value of treatment effect, It is the first A treatment plan.

[0015] On the other hand, a nervous system image analysis device includes: a multimodal data fusion acquisition module, a spatiotemporal joint feature analysis module, a multi-disease joint diagnosis model construction module, a treatment effect prediction module, and a personalized treatment plan recommendation module The multimodal data fusion acquisition module collects the patient's fMRI, MRS, DTI, and PET modal neurological imaging data through the hospital's internal system, transmits them to the central data processing unit in real time, repairs the problematic data, and integrates the data using the data fusion formula; The spatiotemporal joint feature analysis module pre-processes the fused dynamic nervous system image data to remove artifacts and noise, extracts the temporal and spatial features of the data, fuses and constructs a spatiotemporal feature vector, and uses the spatiotemporal correlation formula to mine its correlation with the surrounding neighborhood; The multi-disease joint diagnosis model construction module collects clinical information data and spatiotemporal joint feature analysis data, divides them into a test set and a validation set, constructs a model through a disease discrimination formula, trains the model using a back propagation algorithm using the training set, and evaluates the model performance using a validation set; The treatment effect prediction module: extracts treatment effect related features from multimodal imaging data and clinical information to construct a vector, builds a model based on the treatment effect prediction formula, adjusts hyperparameters using grid search, verifies through independent data, and inputs new patient features to obtain the effect prediction results of different treatment methods; The personalized treatment plan recommendation module constructs a knowledge graph for the treatment of neurological diseases, integrates diagnosis, prediction results and patient clinical information to form a personalized treatment information network, uses an intelligent decision-making algorithm to generate a preliminary plan, and continuously collects feedback during treatment to update the network optimization plan.

[0016] Compared with the prior art, this method and device for analyzing nervous system images have the following beneficial effects: 1. The present invention integrates multi-modal data of functional magnetic resonance imaging, magnetic resonance spectroscopy imaging, diffusion tensor imaging and positron emission tomography, and executes quality assessment and integration processes in the central data processing unit, thereby significantly enhancing the accuracy and reliability of the data. At the same time, a spatiotemporal joint feature analysis model is introduced to connect the time and space dimension information in the imaging data, and to mine the changing laws and intrinsic correlations of the data in the spatiotemporal dual dimensions, thereby improving the diagnostic accuracy of neurological diseases. This not only breaks through the limitations of traditional neurological imaging analysis, but also provides a basis for early diagnosis and personalized precision treatment of neurological diseases, and effectively promotes technological progress and clinical application expansion in this field.

[0017] 2. The present invention realizes accurate diagnosis of neurological diseases and personalized treatment plan recommendation by constructing a multi-disease joint diagnosis model and a knowledge graph for the treatment of neurological diseases. The multi-disease joint diagnosis model can comprehensively consider the patient's clinical information and the results of spatiotemporal joint feature analysis to perform differential diagnosis on a variety of neurological diseases. The knowledge graph for the treatment of neurological diseases integrates diagnosis, prediction results and patient clinical information, and can generate personalized treatment plans using intelligent decision-making algorithms. This not only improves the diagnostic accuracy of the disease, but also provides patients with personalized treatment plans, which helps to improve the treatment effect and the patient's quality of life.

[0018] Other advantages, objectives and features of the present invention will be set forth in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0020] Figure 1 It is a flowchart of a method for analyzing nervous system images; Figure 2 The figure is a schematic diagram of the structure of a nervous system image analysis device. DETAILED DESCRIPTION

[0021] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation mode, structure, characteristics and effects of the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments.

[0022] Embodiment 1 Alzheimer's disease diagnosis and treatment recommendations Multimodal data fusion acquisition. Patient A went to the hospital for treatment due to symptoms of memory loss and cognitive decline. The hospital's internal system collected functional magnetic resonance imaging (fMRI), magnetic resonance spectroscopy (MRS), diffusion tensor imaging (DTI), and positron emission tomography (PET) neurological imaging data for patient A within a week. Suppose the first The mode is located in space and time The signal strength at , the collected raw data is integrated through the multimodal data fusion formula, the formula is: ,in is the number of modes, , , For the fusion coefficient, the integrated raw data is transmitted to the central data processing unit in real time, and the quality of the integrated multimodal data is evaluated, and data repair is performed for any problems.

[0023] Spatiotemporal joint feature analysis: preprocessing the fused dynamic nervous system image data, removing artifacts and noise, and performing spatiotemporal segmentation. For temporal feature extraction, for each ROI time window subsequence , discrete wavelet transform is used to extract time features, and the wavelet function is ( is the wavelet scale), then the wavelet coefficients are: , construct the time feature vector ,in is the number of wavelet scales selected. In terms of spatial feature extraction, Geary's C index is used to calculate the spatial correlation characteristics between voxels in each ROI. and voxels The characteristic value of and , the calculation formula is: ,in is the number of voxels in the ROI, is the spatial weight matrix, when voxel and Adjacent time ,otherwise , The dynamic time warping algorithm is used to calculate the functional connectivity features between different ROIs. The time series features of the two ROIs are and , then the calculation formula of DTW distance is: ,in Matching paths for time series, As the feature distance metric function, construct the spatial feature vector Finally, the time feature vector and the space feature vector are fused to construct the space-time feature vector , and use the spatiotemporal correlation formula to mine its correlation with the surrounding neighborhood in the spatiotemporal dimension. The formula is: ,in Indicates spatial location The spatiotemporal correlation eigenvalue at is the spatial location Neighborhood of It is The area of ​​interest is Spatial position in the time window The space-time characteristic value at It is ROI in spatial location The mean of the spatiotemporal characteristics at .

[0024] To build a multi-disease joint diagnosis model, we collect clinical information data of patient A, such as age, family medical history, and living habits, and combine it with the data from the spatiotemporal joint feature analysis step. The data is divided into a test set and a validation set, and the model is built using the disease discrimination formula. The formula is: ,in Indicates the type of disease, is the number of disease-related characteristic patterns, , and are model parameters, is the time characteristic function, As the normalization constant, the training set data is input into the constructed model, and the model is trained using the back propagation algorithm. The training set data is assumed to be , For the The characteristic data of samples, is the corresponding disease type label, and the model prediction output is , calculate the cross entropy loss function: , calculate the loss function for Ladder: Degree , the specific gradient expression is obtained by gradually expanding the calculation through the chain rule, and the model parameters are updated by stochastic gradient descent: is the learning rate, and the number of training rounds is set to ,After each round of training, the model performance is evaluated on the ,validation set, and the model is optimized and adjusted according to the ,evaluation results.

[0025] Treatment effect prediction: extract features related to treatment effect from multimodal imaging data and clinical information, construct feature vectors, and build a prediction model through the treatment effect prediction formula. The formula is: ,in Representation based on image features and disease type Predicted treatment outcome indicators The probability value of , , is a coefficient determined through clinical data training, Treatment outcome index The adjustment coefficient related to the patient’s own characteristics is used, and the hyperparameters of the model are tuned using grid search. After independent data verification, the corresponding characteristics of patient A are input into the model to obtain the predicted results of the treatment effect of different treatment methods (such as drug therapy and cognitive training).

[0026] Personalized treatment plan recommendation, build a knowledge graph for the treatment of neurological diseases, integrate diagnosis, prediction results and clinical information of patient A to form a personalized treatment information network, and use intelligent decision-making algorithms to generate preliminary personalized treatment plans based on this network. The formula is: ,in Indicates a preliminary personalized treatment plan, is the number of treatment options in the knowledge graph that are related to the current patient's disease and meet the screening criteria, It is The initial weight of each treatment plan in the knowledge graph, is an adjustment factor based on disease matching, calculated as: ,in is the patient's disease feature vector, It is a treatment plan The feature vector of the applicable disease, is the adjustment parameter, is an adjustment factor based on individual patient characteristics, is an adjustment factor based on the prediction of treatment effect: ,in is the adjustment parameter, Predicted value of treatment effect, It is the first During the treatment process, the network is continuously updated based on the feedback information from the treatment to optimize the treatment plan.

[0027] In summary, this embodiment conducts a comprehensive diagnosis and treatment analysis on Alzheimer's patient A through multimodal data fusion acquisition, spatiotemporal joint feature analysis, multi-disease joint diagnosis model construction, treatment effect prediction and personalized treatment plan recommendation steps, obtains rich information from multiple imaging modalities, accurately assesses the condition and predicts the treatment effect through complex calculations and model construction, and finally provides patient A with a personalized treatment plan, which can be continuously optimized during treatment, demonstrating the effectiveness and practicality of this method in the diagnosis and treatment of neurological diseases.

[0028] Embodiment 2: Parkinson's disease diagnosis and treatment process Multimodal data fusion acquisition: Patient B had hand tremors and slow movements. The hospital collected neurological imaging data of fMRI, MRS, DTI, and PET modalities for him within one week. The mode is located in space and time The signal strength at , the original data is integrated through the multimodal data fusion formula, the formula is: , is the number of modes, , , is the fusion coefficient, and then the integrated raw data is transmitted to the central data processing unit in real time to perform quality assessment on the integrated multimodal data to ensure data quality.

[0029] Spatiotemporal joint feature analysis, preprocessing the fused dynamic nervous system image data, removing artifacts and noise, and performing spatiotemporal segmentation. When extracting temporal features, for each ROI time window subsequence , using discrete wavelet transform, assuming the wavelet function is ( is the wavelet scale), wavelet coefficients: , construct the time feature vector is the number of wavelet scales selected), the spatial feature extraction uses Geary's C index to calculate the spatial correlation characteristics between voxels in each ROI, assuming that the voxels in the ROI and voxels The characteristic value of and , the calculation formula is: , is the number of voxels in the ROI, is the spatial weight matrix, the adjacent voxels ,otherwise , The dynamic time warping algorithm is used to calculate the functional connectivity features between different ROIs. The time series features of the two ROIs are and , the DTW distance calculation formula is: , Matching paths for time series, As the feature distance metric function, construct the spatial feature vector , and then fuse the temporal feature vector and the spatial feature vector into the spatiotemporal feature vector , use the spatiotemporal correlation formula to mine its spatiotemporal correlation, the formula is: , Indicates spatial location The spatiotemporal correlation eigenvalue at is the spatial location Neighborhood of It is The area of ​​interest is Spatial position in the time window The space-time characteristic value at It is ROI in spatial location The mean of the spatiotemporal characteristics at .

[0030] The multi-disease joint diagnosis model is constructed by combining the clinical information of patient B (such as onset time, whether there are other underlying diseases) with the data of the spatiotemporal joint feature analysis step, dividing it into a test set and a validation set, and using the disease discrimination formula to build the model. The formula is: , Indicates the type of disease, is the number of disease-related characteristic patterns, , and are model parameters, is the time characteristic function, is the normalization constant, and the training set data is the sample feature data, is the disease type label, and the model prediction output is ) Input the model, use the back propagation algorithm to train, and calculate the cross entropy loss function: , calculate the loss function for The gradient is: , calculate the gradient expression by chain rule, and update the model parameters by stochastic gradient descent , is the learning rate, and the number of training rounds is set to After each round of training, the model performance is evaluated and optimized on the validation set.

[0031] Prediction of treatment effect: extract features related to the treatment effect of Parkinson's disease, such as the imaging features of the substantia nigra and dopamine metabolism-related indicators to construct feature vectors, and construct a prediction model through the treatment effect prediction formula. The formula is: ,in Representation based on image features and disease type Predicted treatment outcome indicators The probability value of , , is a coefficient determined through clinical data training, Treatment outcome index The adjustment coefficient related to the patient’s own characteristics is used, and the hyperparameters are tuned using grid search. After independent data verification, the corresponding characteristics of patient B are input into the model to predict the effects of different treatment methods (such as drug therapy and surgical treatment).

[0032] Personalized treatment plan recommendation, build a knowledge graph for the treatment of neurological diseases, integrate diagnosis, prediction results and clinical information of patient B, form a personalized treatment information network, and use intelligent decision-making algorithms to generate preliminary personalized treatment plans based on this network. Suppose there is Treatment options related to Parkinson's disease that meet the screening criteria The value of is determined according to the number of eligible solutions in the actual knowledge graph), for each treatment solution , calculate its initial weight in the knowledge graph , calculate the adjustment factor based on disease matching: ,in is the disease feature vector of patient B, It is a treatment plan The feature vector of the applicable disease, is the adjustment parameter, which determines the adjustment factor based on the individual characteristics of the patient , calculate the adjustment factor based on the prediction of treatment effect: ,in is the adjustment parameter, It is the predicted value of the treatment effect of the treatment plan on patient B obtained in the treatment effect prediction step. Finally, the preliminary personalized treatment plan is calculated according to the formula , the formula is: For example, if there are three related treatment options in the knowledge graph, namely drug treatment options , surgical treatment options and rehabilitation training programs After the weights and adjustment factors of each plan are determined through the above calculations, the personalized treatment plan suitable for patient B is calculated to be drug treatment combined with a certain degree of rehabilitation training. During the treatment process, feedback information is continuously collected to update the network, such as the improvement of patient B's symptoms after a period of treatment and information on drug side effects. Based on this treatment feedback information, the treatment plan is further optimized, such as adjusting the drug dosage and increasing the intensity of rehabilitation training.

[0033] In summary, for Parkinson's disease patient B, this embodiment uses a series of processes, including collecting multimodal imaging data, analyzing spatiotemporal characteristics, building a diagnostic model, predicting treatment effects and generating personalized plans. In each link, data is processed according to relevant formulas and algorithms, and various factors are comprehensively considered to finally determine a treatment plan suitable for patient B. Continuous improvement is made through feedback, which reflects the scientificity and reliability of this method in the diagnosis and treatment of Parkinson's disease and provides strong support for clinical treatment.

[0034] The above description is only a preferred embodiment of the present invention and does not limit the present invention in any form. Although the present invention has been disclosed as a preferred embodiment as above, it is not used to limit the present invention. Any technical personnel in this field can make some changes or modify the technical contents disclosed above into equivalent embodiments without departing from the scope of the technical solution of the present invention. However, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention are still within the scope of the technical solution of the present invention.

Claims

1. A method for analyzing nervous system images, characterized in that: The specific steps of this analysis method are: S100, multimodal data fusion acquisition: collect patients' functional magnetic resonance imaging (fMRI), magnetic resonance spectroscopy (MRS), diffusion tensor imaging (DTI), and positron emission tomography (PET) multimodal neurological imaging data through the hospital's internal system, and transmit the collected raw data to the central data processing unit in real time, conduct quality assessment on the integrated multimodal data, repair data with problems, and integrate the data after repair through the multimodal data fusion formula; S200, spatiotemporal joint feature analysis: preprocess the fused dynamic nervous system image data, remove artifacts and noise, perform spatiotemporal segmentation, extract temporal and spatial features, and fuse the temporal feature vector and the spatial feature vector to construct the spatiotemporal feature vector. ,Use the spatiotemporal correlation formula to mine the correlation between the spatiotemporal feature vector and the surrounding neighborhood in the spatiotemporal dimension; S300, construction of multi-disease joint diagnosis model: Combine the clinical information data with the data from the spatiotemporal joint feature analysis step, and divide them into a test set and a validation set. Use the disease discrimination formula to build a diagnosis model. The formula is: ,in Indicates the type of disease, is the number of disease-related characteristic patterns, , and are model parameters, is the time characteristic function, is the normalization constant, and the model is trained using the training set to determine the parameters in the model and , and then evaluate the model performance through the test set, and optimize and adjust the model according to the evaluation results; S400, treatment effect prediction: extract features related to treatment effect from multimodal imaging data and clinical information, construct feature vectors, build prediction models through treatment effect prediction formulas, use grid search to tune the model's hyperparameters, and after independent data verification, input the corresponding features of new patients into the model to obtain treatment effect prediction results for different treatment methods; S500, personalized treatment plan recommendation: construct a knowledge graph for the treatment of neurological diseases, integrate diagnosis, prediction results and patient clinical information to form a personalized treatment information network, use intelligent decision-making algorithms to generate preliminary personalized treatment plans based on the network, continuously collect feedback information to update the network during the treatment process, and update the network and optimize the treatment plan based on the treatment feedback information.

2. A method for analyzing nervous system images according to claim 1, characterized in that: In the S100, in the multimodal data fusion acquisition, data integration is performed using a multimodal data fusion formula. Suppose the t-th mode in the multimodal image data is at a spatial position and the signal strength at time t is , the formula is: ,in is the number of modes, , , and is the fusion coefficient, is the variable in the time integration, The integral variable is .

3. A method for analyzing nervous system images according to claim 1, characterized in that: S100, signal strength in multi-modal data fusion acquisition Calculation: The calculation of the functional magnetic resonance imaging signal intensity is based on the spatial position and time The signal strength at , whose expression is ,in represents the physical quantity related to magnetic resonance, represents the function related to the BOLD effect; The calculation of the magnetic resonance spectroscopy imaging signal intensity is as follows: The spatial position of MRS and time Signal strength at ,in is the concentration of a specific metabolite, is a function related to the MRS acquisition parameters; The calculation of the diffusion tensor imaging signal intensity is as follows: The spatial position of DTI and time Signal strength at ,in is a coefficient related to the tissue intrinsic signal intensity and other imaging parameters, is the diffusion weighting factor, is the diffusion tensor matrix, whose elements Describe the diffusion characteristics of water molecules in different directions; The calculation of the positron emission tomography signal intensity is based on The spatial position of PET and time Signal strength at ,in is a coefficient related to detector efficiency and photon attenuation factors, The radioactive tracer is located in space and time The concentration at It means that the photon is emitted from the point To the detection point is a function of the physical processes of attenuation and scattering.

4. A method for analyzing nervous system images according to claim 1, characterized in that: S200, temporal feature extraction in spatiotemporal joint feature analysis, for each ROI time window subsequence , discrete wavelet transform is used to extract time features, and the wavelet function is , is the wavelet scale, then the wavelet coefficient , construct the time feature vector ,in is the number of wavelet scales selected.

5. A method for analyzing nervous system images according to claim 1, characterized in that: In S200, spatial feature extraction in spatiotemporal joint feature analysis uses Geary's C index to calculate the spatial correlation characteristics between voxels in each ROI. and voxels The characteristic value of and , the calculation formula is: ,in is the number of voxels in the ROI, is the spatial weight matrix, when voxel and Adjacent time ,otherwise , The dynamic time warping algorithm is used to calculate the functional connectivity features between different ROIs. The time series features of the two ROIs are and , then the calculation formula of DTW distance is: ,in Matching paths for time series, As the feature distance metric function, construct the spatial feature vector .

6. A method for analyzing nervous system images according to claim 1, characterized in that: In the S200, the spatiotemporal joint feature analysis uses the spatiotemporal correlation formula to mine the correlation between the spatiotemporal feature vector and the surrounding neighborhood in the spatiotemporal dimension, and the formula is: ,in: Indicates spatial location The spatiotemporal correlation eigenvalue at is the spatial location Neighborhood of It is The area of ​​interest is Spatial position in the time window The spatiotemporal characteristic values ​​at It is ROI in spatial location The mean of the spatiotemporal characteristics at is calculated as follows: .

7. A method for analyzing nervous system images according to claim 1, characterized in that: In the S300, the diagnostic model training in the construction of the multi-disease joint diagnostic model is input into the constructed model, and the model training is performed using the back propagation algorithm. The training set data is assumed to be , For the The characteristic data of samples, is the corresponding disease type label, and the model prediction output is , calculate the cross entropy loss function, the formula is: , calculate the loss function for The gradient of is: , the specific gradient expression is obtained by gradually expanding the calculation through the chain rule, and the model parameters are updated by stochastic gradient descent. The formula is: , is the learning rate, and the number of training rounds is set to ,After each round of training, the model performance is evaluated on the validation set.

8. A method for analyzing nervous system images according to claim 1, characterized in that: In the S400, a prediction model is constructed by using a prediction formula for treatment effect in the prediction of treatment effect, and the formula is: ,in: Representation based on image features and disease type Predicted treatment outcome indicators The probability value of , , is a coefficient determined through clinical data training, Treatment outcome index Adjustment factor related to its own characteristics.

9. A method for analyzing nervous system images according to claim 1, characterized in that: In the above S500, the intelligent decision-making algorithm is used to generate a preliminary personalized treatment plan based on the network in the personalized treatment plan recommendation, and the formula is: ,in: Indicates a preliminary personalized treatment plan, is the number of treatment options in the knowledge graph that are related to the current patient's disease and meet the screening criteria, It is The initial weight of each treatment plan in the knowledge graph, is an adjustment factor based on disease matching, calculated as: ,in is the patient's disease feature vector, It is a treatment plan The feature vector of the applicable disease, is the adjustment parameter, is an adjustment factor based on individual patient characteristics, is an adjustment factor based on the prediction of treatment effect, calculated as: ,in is the adjustment parameter, Predicted value of treatment effect, It is the first A treatment plan.

10. A nervous system image analysis device, characterized in that: The system includes: multimodal data fusion acquisition module, spatiotemporal joint feature analysis module, multi-disease joint diagnosis model construction module, treatment effect prediction module and personalized treatment plan recommendation module The multimodal data fusion acquisition module collects the patient's fMRI, MRS, DTI, and PET modal neurological imaging data through the hospital's internal system, transmits them to the central data processing unit in real time, repairs the problematic data, and integrates the data using the data fusion formula; The spatiotemporal joint feature analysis module pre-processes the fused dynamic nervous system image data to remove artifacts and noise, extracts the temporal and spatial features of the data, fuses and constructs a spatiotemporal feature vector, and uses the spatiotemporal correlation formula to mine its correlation with the surrounding neighborhood; The multi-disease joint diagnosis model construction module collects clinical information data and spatiotemporal joint feature analysis data, divides them into a test set and a validation set, constructs a model through a disease discrimination formula, trains the model using a back propagation algorithm using the training set, and evaluates the model performance using a validation set; The treatment effect prediction module: extracts treatment effect related features from multimodal imaging data and clinical information to construct a vector, builds a model based on the treatment effect prediction formula, adjusts hyperparameters using grid search, verifies through independent data, and inputs new patient features to obtain the effect prediction results of different treatment methods; The personalized treatment plan recommendation module constructs a knowledge graph for the treatment of neurological diseases, integrates diagnosis, prediction results and patient clinical information to form a personalized treatment information network, uses an intelligent decision-making algorithm to generate a preliminary plan, and continuously collects feedback during treatment to update the network optimization plan.

Images