Electrode positioning system based on personalized brain segmentation

Abstract

The present invention relates to the technical field of brain electrode positioning programs. Specifically disclosed is an electrode positioning system based on personalized brain segmentation, comprising an image data processing unit, an electrode parameter acquisition unit, a target coordinate selection unit, an electrode target analysis unit, a brain region analysis processing unit, an electrode positioning analysis module and a display module. The present invention provides a set of complete system and software which are used for carrying out a whole process from tracing optimization to electric field visualization from data obtained when a personalized magnetic resonance image of a subject is segmented and supporting stimulation modes such as time interference stimulation, transcranial electric stimulation and high-precision transcranial electric stimulation, and also provides a personalized brain tissue and brain region segmentation mode in which personalized segmentation data is used in subsequent tracing optimization calculation, and the influence of personality difference during electrode positioning is emphasized.

Description

An Electrode Localization System Based on Personalized Brain Segmentation Technical Field

[0001] This invention relates to the field of brain electrode localization technology, specifically to an electrode localization system based on personalized brain segmentation. Background Technology

[0002] In recent years, the incidence of neurological diseases has been increasing. Doctors often use drugs to combat neurological diseases or alleviate their symptoms. However, this approach may cause adverse reactions in patients and may interact with other drugs, thus increasing the risk of side effects. In addition, some subjects may be tolerant to the drugs. The limitations of drug treatment further increase the cost of treatment and the need to develop new technologies.

[0003] Deep brain stimulation (DBS) is a neurosurgical procedure that involves implanting electrodes into specific areas of the brain and stimulating the target area with a constant or intermittent electrical current from an implanted battery. However, subjects often have strong resistance to the surgery, and the procedure also carries certain risks of bleeding and infection, so DBS is not the first choice.

[0004] Transcranial electric stimulation (tES) is a non-invasive brain stimulation (NIBS) that modulates the excitability of the central nervous system by applying direct current or alternating current to electrodes placed on the scalp, producing a sustained neuroplastic effect and thereby regulating the function of the central nervous system.

[0005] However, determining the optimal location of electrodes in the brain and the appropriate current level to effectively activate the target brain region is crucial. Previously, doctors could only rely on experience to determine approximate locations, lacking the precise ability to select personalized electrode channels and current levels corresponding to specific target points on the subject. This patent enables personalized electrode localization (brain region navigation) and visualization of the corresponding electric field.

[0006] Existing similar products have the following problems and defects:

[0007] (1) A standardized brain model is usually used, while individual differences are ignored;

[0008] (2) It usually cannot support multiple electrode positioning methods, especially the currently superior time-interference electrical stimulation method;

[0009] (3) The calculation time is usually long. For electrode localization of time-interference electrical stimulation, the calculation time is generally 10 hours or more.

[0010] (4) It usually cannot output multiple results, thus offering fewer options for situations where specific stimulus areas need to be avoided;

[0011] (5) Usually there is no detailed brain region segmentation result selection, and users need to manually locate and find the brain region to be stimulated. Summary of the Invention

[0012] In view of the above situation and to overcome the defects of the prior art, the present invention provides an electrode positioning system based on personalized brain segmentation to solve the aforementioned technical defects.

[0013] To achieve the above objectives, the present invention is implemented through the following technical solution: an electrode positioning system based on personalized brain segmentation, comprising an image data processing unit, an electrode parameter acquisition unit, a target coordinate selection unit, an electrode target analysis unit, a brain region analysis and processing unit, an electrode positioning analysis module, and a display module, wherein the image data processing unit is used to segment the raw image data of the brain.

[0014] The electrode parameter acquisition unit is used to collect and acquire the physical parameters of the electrode to obtain the electrode parameters;

[0015] The target coordinate selection unit is used to select the coordinates of a specific location in the brain to determine the target coordinates for electrode positioning.

[0016] The electrode target analysis unit is used to compare and analyze the electrode parameters and target coordinates, determine the standardization of the electrode parameter information and target coordinates, and then determine the consistency of the electrode parameters with the electrode parameters of the previous run.

[0017] The brain region analysis and processing unit is used to perform brain region navigation calculations, and uses genetic algorithms and particle swarm optimization algorithms to calculate the Pareto front.

[0018] The electrode positioning analysis module is used to obtain a list of results that meet the target requirements from the Pareto front;

[0019] The display module is used to display the electric field distribution data of brain cross sections and 3D models, the electric field statistics of brain regions, and the electric field of user interaction points.

[0020] Furthermore, the raw brain image data is segmented, and the specific processing method is as follows:

[0021] First, an MRI scan of the user's brain is performed to obtain raw brain image data. Then, the raw brain image data is preprocessed to obtain preprocessed images.

[0022] The convolution kernel is slid across the preprocessed image to extract features and perform segmentation. Specifically, the convolution kernel is a 3×3 matrix. The convolution kernel is slid along each position of the preprocessed image and element-wise multiplication and addition operations are performed with the image pixels at that position to extract the edges, textures, and shapes in the preprocessed image, thus obtaining the feature map of each position in the preprocessed image.

[0023] By combining multiple feature maps and processing them through a subsequent fully connected layer, specifically: by inputting the feature map at each location into the fully connected layer, the Softmax classifier is used to classify the features and determine the category of the preprocessed image. During the segmentation of the preprocessed image, pixel-level classification is performed based on the information in the feature maps, and each pixel is assigned to the corresponding category, thereby achieving the segmentation of the preprocessed image.

[0024] Furthermore, the physical parameters of the electrode are acquired by means of: scanning the electrode with a scanning electron microscope to obtain a cross-sectional image of the electrode, measuring the cross-sectional image of the electrode to obtain the electrode cross-sectional shape, electrode size and electrode thickness, and the electrode cross-sectional shape, electrode size and electrode thickness constitute the electrode parameters.

[0025] Furthermore, the target point coordinates can be selected in the following ways:

[0026] (1) By selecting the brain region to be stimulated, the coordinates will be set as the geometric center coordinates of the brain region;

[0027] (2) Select the brain regions to be stimulated by using a multi-level indexing method;

[0028] (3) By inputting the index number of the target brain region;

[0029] (4) Perform a fuzzy search first, and then use the above methods to select the target brain region;

[0030] (5) Manually input the XYZ coordinates;

[0031] (6) Precisely select the location to be stimulated on brain region segmented MRI images.

[0032] Furthermore, the electrode parameters and target coordinates are compared and analyzed, and the specific comparison and analysis method is as follows:

[0033] By comparing the implanted electrode location with the planned target location, the matching degree of the electrode shape and size with the standard electrode shape and size is checked. If the electrode shape and size match the standard electrode shape and size, the electrode parameters from the previous run are compared with the current electrode parameters to obtain the rate of change of the current electrode parameters compared with the previous run electrode parameters.

[0034] Furthermore, the results list includes the channel position of the electrode placement and the corresponding current magnitude, the electric field magnitude at the reference target position, and the average electric field magnitude of the reference whole brain.

[0035] Furthermore, a localization method based on a personalized brain segmentation-based electrode localization system specifically includes the following steps:

[0036] Step 101: Input the MRI image data that has undergone personalized brain tissue segmentation and brain region segmentation;

[0037] Step 102, add electrode parameters;

[0038] Step 103, Select target coordinates:

[0039] Step 104: Determine the conformity of the electrode parameter information with the target point;

[0040] Step 105: If the electrode parameter information and target point are not in accordance with the standardization in step 104, the electrode parameter information or target point coordinate information shall be modified again by the user.

[0041] Step 106: Determine the rate of change of the electrode parameters compared to the electrode parameters of the previous run;

[0042] Step 107: If the electrode parameters change, calculate the leadfield matrix.

[0043] Step 108: Perform brain region navigation calculations, using genetic algorithms and particle swarm optimization to calculate the Pareto front;

[0044] Step 109: Obtain a list of results that meet the target requirements through the Pareto front;

[0045] Step 110: Select the data to save;

[0046] Step 111: Save the result data to the location specified by the user;

[0047] Step 112: Select the method for visualizing the electric field;

[0048] Step 113: If electric field visualization is not performed, the process ends.

[0049] Step 114: Calculate the distribution of the brain's electric field using the finite element method;

[0050] Step 115 displays the electric field distribution data of the brain cross-section and three-dimensional model, the electric field statistics of the brain region, and the electric field display of the user interaction point.

[0051] The beneficial effects of this invention are:

[0052] 1. This invention provides a complete system and software that starts from the data segmented from the subject's personalized magnetic resonance imaging, performs source tracing and optimization, and visualizes the electric field, and supports stimulation methods such as time-interference stimulation, transcranial electrical stimulation, and high-precision transcranial electrical stimulation.

[0053] 2. This invention provides a personalized brain tissue and brain region segmentation method, which uses personalized segmented data for calculation in subsequent source tracing and optimization calculations, and places greater emphasis on the influence of individual differences during electrode localization.

[0054] 3. This invention can reduce the calculation time to 10 minutes without sacrificing the accuracy of the results, and can output multiple results that meet the stimulus requirements.

[0055] 4. The electrode positioning system in this invention has a user-friendly graphical interface and data visualization method, providing relevant suggestions for the placement of transcranial electrical stimulation electrodes for various diseases. Attached Figure Description

[0056] The invention will now be further described with reference to the accompanying drawings.

[0057] Figure 1 is a schematic diagram of an electrode positioning system based on personalized brain segmentation according to an embodiment of the present invention;

[0058] Figure 2 is a schematic diagram of the overall process of the electrode localization method based on personalized brain segmentation in an embodiment of the present invention. Detailed Implementation

[0059] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are also within the scope of protection of the present invention.

[0060] As indicated in this invention and the claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not specifically refer to the singular and may also include the plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of explicitly identified steps and elements, which do not constitute an exclusive list, and the method or apparatus may also include other steps or elements.

[0061] While this invention makes various references to certain modules in systems according to embodiments of the invention, any number of different modules can be used and run on user terminals and / or servers. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.

[0062] This invention uses flowcharts to illustrate the operations performed by the system according to embodiments of the invention. It should be understood that the preceding or following operations are not necessarily performed precisely in sequence. Instead, various steps can be processed in reverse order or simultaneously, as needed. Furthermore, other operations can be added to these processes, or one or more steps can be removed from them.

[0063] Hereinafter, exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein. Example

[0064] Please refer to Figures 1 and 2. An electrode localization system based on personalized brain segmentation includes: an image data processing unit, an electrode parameter acquisition unit, a target coordinate selection unit, an electrode target analysis unit, a brain region analysis and processing unit, an electrode localization analysis module, and a display module.

[0065] The image data processing unit is used to segment and process the raw image data of the brain. The specific processing method is as follows:

[0066] First, an MRI scan of the user's brain is performed to obtain raw brain image data. Then, the raw brain image data is preprocessed to obtain preprocessed images. Specific preprocessing methods include: normalization, noise removal, and correction of geometric distortion of the image.

[0067] The convolution kernel is slid across the preprocessed image to extract features and perform segmentation. Specifically, the convolution kernel is a 3×3 matrix. The convolution kernel is slid along each position of the preprocessed image and element-wise multiplication and addition operations are performed with the image pixels at that position to extract edges, textures, and shapes from the preprocessed image, resulting in a feature map for each position in the preprocessed image. The feature map is used to reflect the response intensity of the convolution kernel at different positions on the preprocessed image.

[0068] By combining multiple feature maps and processing them through a subsequent fully connected layer, specifically: by inputting the feature map at each location into the fully connected layer, the Softmax classifier is used to classify the features and determine the category of the preprocessed image. During the segmentation of the preprocessed image, pixel-level classification is performed based on the information in the feature maps, and each pixel is assigned to the corresponding category, thereby achieving the segmentation of the preprocessed image.

[0069] The electrode parameter acquisition unit is used to collect and acquire the physical parameters of the electrode to obtain the electrode parameters. The specific acquisition method is as follows: the electrode is scanned by a scanning electron microscope to obtain a cross-sectional image of the electrode. The cross-sectional image of the electrode is then measured to obtain the electrode cross-sectional shape, electrode size, and electrode thickness. The electrode cross-sectional shape, electrode size, and electrode thickness constitute the electrode parameters.

[0070] The target coordinate selection unit is used to select the coordinates of a specific location in the brain to determine the target coordinates for electrode localization. It should be noted that the target coordinates can be used to locate and label brain regions or structures of interest for further analysis and research.

[0071] The target coordinates can be selected in the following ways:

[0072] (1) By selecting the brain region to be stimulated, the coordinates will be set as the geometric center coordinates of the brain region;

[0073] (2) Select the brain regions to be stimulated by using a multi-level indexing method;

[0074] (3) By inputting the index number of the target brain region;

[0075] (4) Perform a fuzzy search first, and then use the above methods to select the target brain region;

[0076] (5) Manually input the XYZ coordinates;

[0077] (6) Precisely select the location to be stimulated on brain region segmented MRI images.

[0078] The electrode target analysis unit is used to compare and analyze electrode parameters and target coordinates, determine the standardization of electrode parameter information and target coordinates, and then determine the consistency of electrode parameters with those from the previous run. For example, it checks for outliers in electrode parameters (such as negative numbers) and anomalies in target coordinates. The specific comparison and analysis method is as follows:

[0079] By comparing the implanted electrode location with the planned target location, the matching degree of the electrode shape and size with the standard electrode shape and size is checked. If the electrode shape and size match the standard electrode shape and size, the electrode parameters from the previous run are compared with the current electrode parameters to obtain the rate of change of the current electrode parameters compared with the previous run electrode parameters. It should be noted that the shape of the electrode should match the shape and size of the target to ensure good contact and stimulation effect.

[0080] The brain region analysis and processing unit is used to perform brain region navigation calculations, and uses genetic algorithms and particle swarm optimization algorithms to calculate the Pareto front.

[0081] It should be noted that the brain region navigation calculation method is as follows: using neuroimaging technology, brain activity data is collected, and the collected data is preprocessed, including noise removal, motion artifact correction, and feature extraction. Based on the preprocessed data, a mathematical model is established to describe the relationship between brain activity and brain regions. Using the established model, brain region navigation calculation is performed. Specifically, by inputting brain activity data, the location of the corresponding brain region is predicted; and the precision of the navigation calculation results is evaluated.

[0082] The process of a genetic algorithm is as follows:

[0083] 1. First, initialize the population by randomly generating an initial solution;

[0084] 2. Calculate the fitness value for each solution based on the objective function of the problem;

[0085] 3. Select the best solutions based on their fitness values ​​as parents for reproducing offspring;

[0086] 4. Generate new offspring solutions by crossing over some genes from the parent solutions;

[0087] 5. Perform gene mutations on some offspring solutions to increase solution diversity;

[0088] 6. Repeat steps 3-5 until the stopping condition is met. Select non-dominated solutions from the final population. These solutions constitute the Pareto front.

[0089] The particle swarm optimization algorithm is as follows:

[0090] 1. First, initialize the particle swarm by randomly generating a group of particles, each representing a potential solution;

[0091] 2. Evaluate the fitness of the particles and calculate the fitness value of each particle based on the objective function;

[0092] 3. Update the particle's velocity and position based on the particle's current position, velocity, individual optimal position, and group optimal position;

[0093] 4. Repeat step 3 until the stopping condition is met, and select non-dominated solutions from the particle swarm to form the Pareto front.

[0094] The electrode positioning analysis module is used to obtain a list of results that meet the target requirements from the Pareto front. Specifically, the list of results includes the channel position of the electrode placement and the corresponding current magnitude, the electric field magnitude at the reference target position, and the average electric field magnitude of the reference whole brain.

[0095] The display module is used to display the electric field distribution data of brain cross sections and 3D models, the electric field statistics of brain regions, and the electric field of user interaction points. Example

[0096] As shown in Figure 2, this embodiment also discloses an electrode localization method based on personalized brain segmentation, which specifically includes the following steps:

[0097] Step 101: Input the MRI image data that has undergone personalized brain tissue segmentation and brain region segmentation;

[0098] Step 102, add electrode parameters;

[0099] Step 103, Select target coordinates:

[0100] Step 104: Determine the conformity of the electrode parameter information with the target point;

[0101] Step 105: If the electrode parameter information and target point are not in accordance with the standardization in step 104, the electrode parameter information or target point coordinate information shall be modified again by the user.

[0102] Step 106: Determine the rate of change of the electrode parameters compared to the electrode parameters of the previous run;

[0103] Step 107: If the electrode parameters change, calculate the leadfield matrix.

[0104] Step 108: Perform brain region navigation calculations, using genetic algorithms and particle swarm optimization to calculate the Pareto front;

[0105] Step 109: Obtain a list of results that meet the target requirements through the Pareto front. The list of results includes the channel position of the electrode placement and the corresponding current magnitude, the electric field magnitude of the reference target position, and the average electric field magnitude of the reference whole brain.

[0106] Step 110: Select the data to save;

[0107] Step 111: Save the result data to the location specified by the user;

[0108] Step 112: Select the method for visualizing the electric field;

[0109] Step 113: If electric field visualization is not performed, the process ends.

[0110] Step 114: Calculate the distribution of the brain's electric field using the finite element method;

[0111] Step 115 displays the electric field distribution data of the brain cross-section and three-dimensional model, the electric field statistics of the brain region, and the electric field display of the user interaction point.

[0112] Furthermore, those skilled in the art will understand that aspects of the present invention can be described and illustrated through several patentable types or situations, including any new and useful combination of processes, machines, products, or substances, or any new and useful improvements thereof. Accordingly, aspects of the present invention can be implemented entirely by hardware, entirely by software (including firmware, resident software, microcode, etc.), or by a combination of hardware and software. All of the above hardware or software may be referred to as a "data block," "module," "engine," "unit," "component," or "system." Furthermore, aspects of the present invention may be embodied as a computer product located on one or more computer-readable media, the product comprising computer-readable program code.

[0113] Unless otherwise defined, all terms used herein (including technical and scientific terms) shall have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. It should also be understood that terms such as those defined in a common dictionary shall be interpreted as having a meaning consistent with their meaning in the context of the relevant art, and not as having an idealized or highly formalized meaning, unless expressly defined herein.

[0114] The foregoing description is illustrative of the invention and should not be construed as limiting it. Although several exemplary embodiments of the invention have been described, those skilled in the art will readily understand that many modifications can be made to the exemplary embodiments without departing from the novel teachings and advantages of the invention. Therefore, all such modifications are intended to be included within the scope of the invention as defined in the claims. It should be understood that the foregoing description is illustrative of the invention and should not be construed as limiting it to the specific embodiments disclosed, and modifications to the disclosed embodiments and other embodiments are intended to be included within the scope of the appended claims. The invention is defined by the claims and their equivalents.

Claims

1. An electrode localization system based on personalized brain segmentation, comprising an image data processing unit, an electrode parameter acquisition unit, a target coordinate selection unit, an electrode target analysis unit, a brain region analysis and processing unit, an electrode localization analysis module, and a display module, characterized in that: The image data processing unit is used to segment the raw image data of the brain. The electrode parameter acquisition unit is used to collect and acquire the physical parameters of the electrode to obtain the electrode parameters; The target coordinate selection unit is used to select the coordinates of a specific location in the brain to determine the target coordinates for electrode positioning. The electrode target analysis unit is used to compare and analyze the electrode parameters and target coordinates, determine the standardization of the electrode parameter information and target coordinates, and then determine the consistency of the electrode parameters with the electrode parameters of the previous run. The brain region analysis and processing unit is used to perform brain region navigation calculations, and uses genetic algorithms and particle swarm optimization algorithms to calculate the Pareto front. The electrode positioning analysis module is used to obtain a list of results that meet the target requirements from the Pareto front; The display module is used to display the electric field distribution data of brain cross sections and 3D models, the electric field statistics of brain regions, and the electric field of user interaction points.

2. The electrode localization system based on personalized brain segmentation according to claim 1, characterized in that: The raw brain image data is segmented and processed in the following way: First, an MRI scan of the user's brain is performed to obtain raw brain image data. Then, the raw brain image data is preprocessed to obtain preprocessed images. The convolution kernel is slid across the preprocessed image to extract features and perform segmentation. Specifically, the convolution kernel is a 3×3 matrix. The convolution kernel is slid along each position of the preprocessed image and element-wise multiplication and addition operations are performed with the image pixels at that position to extract the edges, textures, and shapes in the preprocessed image, thus obtaining the feature map of each position in the preprocessed image. By combining multiple feature maps and processing them through a subsequent fully connected layer, specifically: by inputting the feature map at each location into the fully connected layer, the Softmax classifier is used to classify the features and determine the category of the preprocessed image. During the segmentation of the preprocessed image, pixel-level classification is performed based on the information in the feature maps, and each pixel is assigned to the corresponding category, thereby achieving the segmentation of the preprocessed image.

3. The electrode localization system based on personalized brain segmentation according to claim 1, characterized in that: The physical parameters of the electrode are acquired by means of scanning the electrode with a scanning electron microscope to obtain a cross-sectional image of the electrode, measuring the cross-sectional shape, size and thickness of the electrode based on the cross-sectional image, and the electrode parameters are constituted by the cross-sectional shape, size and thickness of the electrode.

4. The electrode localization system based on personalized brain segmentation according to claim 1, characterized in that: The target point coordinates can be selected in the following ways: (1) By selecting the brain region to be stimulated, the coordinates will be set as the geometric center coordinates of the brain region; (2) Select the brain regions to be stimulated by using a multi-level indexing method; (3) By inputting the index number of the target brain region; (4) Perform a fuzzy search first, and then use the above methods to select the target brain region; (5) Manually input the XYZ coordinates; (6) Precisely select the location to be stimulated on brain region segmented MRI images.

5. The electrode localization system based on personalized brain segmentation according to claim 1, characterized in that: The comparison and analysis of electrode parameters and target coordinates are performed using the following specific methods: By comparing the implanted electrode location with the planned target location, the matching degree of the electrode shape and size with the standard electrode shape and size is checked. If the electrode shape and size match the standard electrode shape and size, the electrode parameters from the previous run are compared with the current electrode parameters to obtain the rate of change of the current electrode parameters compared with the previous run electrode parameters.

6. The electrode localization system based on personalized brain segmentation according to claim 1, characterized in that: The results list includes the channel position of the electrodes and the corresponding current magnitude, the electric field magnitude at the reference target position, and the average electric field magnitude of the reference whole brain.

7. A localization method for an electrode localization system based on personalized brain segmentation according to claim 1, characterized in that, Specifically, the following steps are included: Step 101: Input the MRI image data that has undergone personalized brain tissue segmentation and brain region segmentation; Step 102, add electrode parameters; Step 103, Select target coordinates: Step 104: Determine the conformity of the electrode parameter information with the target point; Step 105: If the electrode parameter information and target point are not in accordance with the standardization in step 104, the electrode parameter information or target point coordinate information shall be modified again by the user. Step 106: Determine the rate of change of the electrode parameters compared to the electrode parameters of the previous run; Step 107: If the electrode parameters change, calculate the leadfield matrix. Step 108: Perform brain region navigation calculations, using genetic algorithms and particle swarm optimization to calculate the Pareto front; Step 109: Obtain a list of results that meet the target requirements through the Pareto front; Step 110: Select the data to save; Step 111: Save the result data to the location specified by the user; Step 112: Select the method for visualizing the electric field; Step 113: If electric field visualization is not performed, the process ends. Step 114: Calculate the distribution of the brain's electric field using the finite element method; Step 115 displays the electric field distribution data of the brain cross-section and three-dimensional model, the electric field statistics of the brain region, and the electric field display of the user interaction point.

Images