Method, device, electronic device and medium for constructing neural stimulation imaging model

Abstract

The embodiments of the present application disclose a method, device, electronic device and medium for constructing a neural stimulation imaging model. The method includes: in response to a modeling trigger operation on a target neural stimulation imaging model, obtaining neural stimulation imaging data of a target object; based on a plurality of component modules corresponding to a pre-set neural stimulation imaging model, splitting the neural stimulation imaging data into module data corresponding to the component modules; wherein the component modules are independent modules that do not affect each other; based on the module data, performing modeling operations on a plurality of component modules in parallel to obtain component sub-models corresponding to the component modules, and fusing each component sub-model to obtain a target neural stimulation imaging model corresponding to the target object. The technical solution of the embodiments of the present application can reduce the time consumption of constructing a target neural stimulation imaging model, improve the efficiency of model construction, help meet the continuity requirements of the clinical workflow, and make it more convenient for doctors in clinical work.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of neural stimulation technology, and in particular to a method, device, electronic device and medium for constructing a neural stimulation image model. Background Art

[0002] Deep neural stimulation is widely used in the medical clinical treatment of brain function, brain network and brain circuit. Modeling of neural stimulation imaging model of deep neural stimulation has become an important part of completing brain research.

[0003] In the prior art, before building a neural stimulation imaging model, the modeling process is divided into multiple modeling steps, and each modeling step is executed serially. After the last step is executed, the neural stimulation imaging model is obtained. However, in the process of implementing this application, it is found that the prior art has at least the following technical problems: the serial execution of each step results in a long time consumption, which affects the continuity and efficiency of the clinical workflow, and causes the doctor to be unable to understand the actual results after deep nerve stimulation in a timely manner, which brings inconvenience to the doctor's clinical work. Summary of the invention

[0004] The embodiments of the present application provide a method, device, electronic device and medium for constructing a neural stimulation imaging model to achieve the purpose of reducing the time spent in constructing a target neural stimulation imaging model and improving the efficiency of model construction, which is conducive to meeting the continuity requirements of clinical workflows and making it more convenient for doctors in clinical work.

[0005] According to one aspect of the present application, a method for constructing a neural stimulation imaging model is provided, comprising:

[0006] In response to a modeling trigger operation on a target neural stimulation image model, acquiring neural stimulation image data of a target object;

[0007] Based on a plurality of pre-set component modules corresponding to the neural stimulation image model, the neural stimulation image data is split into module data corresponding to the component modules; wherein the component modules are independent modules that do not affect each other;

[0008] Based on the module data, modeling operations are performed on the plurality of component modules in parallel to obtain component sub-models corresponding to the component modules, and each component sub-model is fused to obtain a target neural stimulation image model corresponding to the target object.

[0009] According to another aspect of the present application, a device for constructing a neural stimulation image model is provided, comprising:

[0010] A neural stimulation image data acquisition module, configured to acquire neural stimulation image data of a target object in response to a modeling trigger operation on a target neural stimulation image model;

[0011] A data splitting module, used for splitting the neural stimulation image data into module data corresponding to the component modules based on a plurality of component modules corresponding to the neural stimulation image model set in advance; wherein the component modules are independent modules that do not affect each other;

[0012] The sub-model fusion module is used to perform modeling operations on multiple component modules in parallel based on the module data to obtain component sub-models corresponding to the component modules, and to fuse each component sub-model to obtain a target neural stimulation image model corresponding to the target object.

[0013] According to another aspect of the present application, a medical device is provided, the medical device comprising:

[0014] An input interface configured to provide a physician with an interface for inputting program-controlled parameters;

[0015] A processor, configured to receive and store neural stimulation image data of a target object, and execute the method for constructing a neural stimulation image model described in any embodiment of the present application to obtain a target neural stimulation image model corresponding to the target object;

[0016] The display interface is configured to display the target nerve stimulation image model.

[0017] According to another aspect of the present application, an electronic device is provided, the electronic device comprising:

[0018] at least one processor; and

[0019] a memory communicatively connected to the at least one processor; wherein,

[0020] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for constructing a neural stimulation image model described in any embodiment of the present application.

[0021] According to another aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to execute the method for constructing a neural stimulation imaging model described in any embodiment of the present application.

[0022] The technical solution of the embodiment of the present application obtains the neural stimulation image data of the target object in response to the modeling trigger operation of the target neural stimulation image model; and, through the multiple component modules corresponding to the pre-set neural stimulation image model, the neural stimulation image data is split into module data corresponding to the component modules; since the component modules are independent modules that do not affect each other; therefore, based on the module data, the modeling operation is performed on the multiple component modules in parallel to obtain the component sub-models corresponding to the component modules, and each component sub-model is fused to obtain the target neural stimulation image model corresponding to the target object. In the technical solution of this embodiment, since the component models do not affect each other, when constructing the target neural stimulation image model, the modeling operation is performed on the multiple component modules in a parallel manner, and there is no need to execute the model building process step by step in a serial manner, which reduces the time-consuming construction of the target neural stimulation image model and improves the efficiency of model construction, which is conducive to meeting the continuity requirements of the clinical workflow and makes it more convenient for doctors in clinical work.

[0023] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 is a flow chart of a method for constructing a neural stimulation imaging model provided in an embodiment of the present application;

[0026] Figure 2 is a flow chart of another method for constructing a neural stimulation imaging model provided in an embodiment of the present application;

[0027] Figure 3 is a schematic diagram of the composition of a neural stimulation imaging model provided according to an embodiment of the present application;

[0028] Figure 4 is a schematic diagram of a task execution process of a neural stimulation imaging model provided according to an embodiment of the present application;

[0029] Figure 5 is a schematic diagram of a modeling subtask execution process provided according to an embodiment of the present application;

[0030] Figure 6is a schematic diagram of a modeling process of a visual neural stimulation image model provided according to an embodiment of the present application;

[0031] Figure 7 is a schematic structural diagram of a device for constructing a neural stimulation imaging model provided in an embodiment of the present application;

[0032] Figure 8 It is a schematic diagram of the structure of an electronic device for implementing the method for constructing a neural stimulation image model according to an embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0034] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "etc." and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0035] It should be noted that the collection, collection, updating, analysis, processing, use, transmission, storage and other aspects of user personal information involved in the technical solution of this disclosure are in compliance with the provisions of relevant laws and regulations, are used for legitimate purposes, and do not violate public order and good morals. Necessary measures are taken for user personal information to prevent illegal access to user personal information data and maintain the security of user personal information and network security.

[0036] Before introducing the technical solution, an example description of the application scenario can be given first. In actual applications, in order to facilitate viewing of the brain condition of the target object after the deep nerve stimulation operation, the doctor needs to model the brain condition of the target object undergoing the deep nerve stimulation operation and obtain the corresponding nerve stimulation image model to facilitate the doctor to conduct accurate analysis. This technical solution can be applied to the application scenario of establishing a nerve stimulation image model of the target object. This technical solution constructs the component sub-models corresponding to the target object in parallel, and fuses the obtained component sub-models to obtain the target nerve stimulation image model. Compared with the serial processing method in the prior art, the parallel processing of this embodiment is conducive to improving the efficiency of constructing the target nerve stimulation image model, which is conducive to meeting the continuity requirements of the clinical workflow, and making it more convenient for doctors in clinical work.

[0037] Figure 1 This is a flow chart of a method for constructing a neural stimulation image model according to an embodiment of the present application. This embodiment can be applied to the case of constructing a neural stimulation image model for reflecting the effect of deep neural stimulation on a target object. The method can be executed by a neural stimulation image model construction device, which can be implemented in the form of hardware and / or software.

[0038] like Figure 1 As shown, the method of this embodiment may specifically include:

[0039] S110 . In response to a modeling triggering operation on a target neural stimulation image model, acquiring neural stimulation image data of a target object.

[0040] The target nerve stimulation image model is a model used to reflect the changes of the target object after the deep nerve stimulation operation. In practical applications, the target nerve stimulation image model can be constructed in the scenario where the effect of deep nerve stimulation on the target object needs to be demonstrated.

[0041] In this embodiment, the modeling trigger operation may be a selection operation of a modeling control displayed on the display interface of the doctor's terminal. Exemplarily, the doctor may click on the modeling control displayed on the display interface through an input device to trigger the modeling operation of the target nerve stimulation image model. Alternatively, the modeling trigger operation may be an input operation of inputting modeling instruction information into an input box displayed on the display interface of the doctor's terminal. Alternatively, the modeling trigger operation is an operation of receiving an end instruction. Exemplarily, the end instruction is an instruction generated when the deep nerve stimulation of the target object is completed, so that after the deep nerve stimulation operation is performed on the target object, the modeling process of the target nerve stimulation image model is automatically entered to improve the convenience of the doctor's work.

[0042] In a specific implementation, in response to a modeling trigger operation, an influence data acquisition instruction may be sent to an image acquisition device to acquire neural stimulation image data of a target object. The image acquisition device may include a computer tomography device and / or a magnetic resonance imaging device. The neural stimulation image data is brain image data acquired by the image acquisition device from the target object. Exemplarily, the neural stimulation image data may be brain image data of the target object acquired during deep neural stimulation of the target object; or may be brain image data of the target object acquired after deep neural stimulation is completed.

[0043] In order to fully and clearly understand the brain changes caused by deep neural stimulation of the target object, the implementation method of obtaining neural stimulation image data of the target object may include: obtaining first brain image data of the target object before the deep neural stimulation operation is performed, and second brain image data after the deep neural stimulation operation is performed; based on the first brain image data and the second brain image data, generating neural stimulation image data; wherein the first brain image data and the second brain image data are both computed tomography data.

[0044] In a specific implementation, in order to facilitate the discovery of the effect of deep nerve stimulation on the target object's brain, the first brain image data of the target object before the deep nerve stimulation operation is performed can be obtained in advance, and the second brain image data of the target object can be obtained after the target object performs the deep nerve stimulation operation. By comparing the first brain image data with the second brain image data, the effect of deep nerve stimulation on the target object's brain can be determined.

[0045] Exemplarily, before the target object undergoes a deep nerve stimulation operation (i.e., an electrode implantation operation is performed on the patient), a first brain image of the target object can be collected by a computer tomography device. Computer tomography data before deep nerve stimulation is performed is generated based on the first brain image collected by the computer tomography device. After deep nerve stimulation is performed, a second brain image of the target object can be collected by the computer tomography device, and computer tomography data after deep nerve stimulation is performed is generated based on the second brain image collected by the computer tomography device.

[0046] In this embodiment, neural stimulation image data is generated based on the first brain image data and the second brain image data, so that it is easy to find the impact of deep neural stimulation on the brain of the target object through the neural stimulation image data.

[0047] Furthermore, the acquired nerve stimulation image data may be subjected to noise reduction and registration operations to improve the accuracy and effectiveness of the nerve stimulation image data.

[0048] S120, based on a plurality of component modules corresponding to a preset neural stimulation image model, split the neural stimulation image data into module data corresponding to the component modules; wherein the component modules are independent modules that do not affect each other.

[0049] It should be noted that the neural stimulation imaging model can be embodied through different component modules. When building the component sub-model corresponding to the component module, the building process of each component sub-model is not affected by the building process of other component sub-models, that is, the component modules are independent modules that do not affect each other. Those skilled in the art can set the component model of the neural stimulation imaging model according to the actual application situation. Exemplarily, the component module may include at least one of an electric field module, a nucleus module, a fiber bundle module, an electrode module and a cortical module.

[0050] In this embodiment, for each component module, the image data required to be provided when building the component sub-model corresponding to the component module is extracted from the neural stimulation image data, and the extracted image data is used as the module data corresponding to the component module. Exemplarily, the module data corresponds to the component module one by one, and the module data may include at least one of the data required by the electric field module, the data required by the nucleus module, the data required by the fiber bundle module, the data required by the electrode module, and the data required by the cortex module.

[0051] S130, based on the module data, perform modeling operations on multiple component modules in parallel to obtain component sub-models corresponding to the component modules, fuse each component sub-model to obtain a target neural stimulation image model corresponding to the target object.

[0052] In this embodiment, at least two component modules can be determined from all the component modules for parallel modeling operations. Optionally, all the component models can be modeled in parallel, or the component modules can be modeled in batches, with at least two component modules selected from each batch for parallel modeling operations, until all the component modules are modeled.

[0053] Exemplarily, the number of component modules for parallel modeling each time can be set based on the computing resources of the construction system of the neural stimulation imaging model. For example, if the computing resources of the construction system can be used for modeling operations of three component modules in parallel each time, three groups of module data can be selected first, and modeling operations can be performed in parallel on the component modules corresponding to the three groups of module data. After obtaining the component sub-models corresponding to the three groups of module data, three groups of module data can be selected from the remaining module data for parallel modeling operations until all the component modules are modeled.

[0054] In a specific implementation, after the component module modeling is completed, the component sub-model corresponding to the component module is obtained. After the component sub-model is obtained for each component module, each component sub-model can be fused and the model obtained after the fusion process is used as the target neural stimulation image model.

[0055] In order to help doctors understand the target neural stimulation image model more intuitively and clearly, after each component sub-model is fused to obtain the target neural stimulation image model corresponding to the target object, it also includes: based on graphics rendering technology, graphics rendering is performed on each component sub-model and the target neural stimulation image model to obtain a sub-model image corresponding to each component sub-model and a target model image corresponding to the target neural stimulation image model; the sub-model images and the target model images are displayed according to a preset display method; wherein the component sub-model includes at least one of an electric field sub-model, a nucleus sub-model, a fiber bundle sub-model, an electrode sub-model and a cortical sub-model.

[0056] In this embodiment, in order to allow the doctor to see the conditions of the component sub-models and the target nerve stimulation image model respectively, each component sub-model and the target nerve stimulation image model can be rendered based on the graphics rendering technology. After the component sub-model is rendered, the sub-model image is obtained. After the target nerve stimulation image model is rendered, the target model image is obtained.

[0057] Furthermore, in order to facilitate the doctor's viewing, the sub-model image and the target model image can be displayed on the display interface of the doctor's terminal. During the display process, the image display can be performed according to a preset display method. The preset display method can be used to specify the display area of ​​the sub-model image and the target model image; or, the preset display method can be used to specify whether the sub-model image and the target model image are displayed in a three-dimensional image mode; or, the preset display method is used to indicate whether the sub-model image and the target model image are displayed dynamically.

[0058] In this embodiment, by generating and displaying sub-model images and target model images, doctors can more intuitively and clearly understand the impact of deep nerve stimulation on the target object, thereby improving the convenience of clinical work.

[0059] The technical solution of the embodiment of the present application obtains the neural stimulation image data of the target object in response to the modeling trigger operation of the target neural stimulation image model; and, through the multiple component modules corresponding to the pre-set neural stimulation image model, the neural stimulation image data is split into module data corresponding to the component modules; since the component modules are independent modules that do not affect each other; therefore, based on the module data, the modeling operation is performed on the multiple component modules in parallel to obtain the component sub-models corresponding to the component modules, and each component sub-model is fused to obtain the target neural stimulation image model corresponding to the target object. In the technical solution of this embodiment, since the component models do not affect each other, when constructing the target neural stimulation image model, the modeling operation is performed on the multiple component modules in a parallel manner, and there is no need to execute the model building process step by step in a serial manner, which reduces the time-consuming construction of the target neural stimulation image model and improves the efficiency of model construction, which is conducive to meeting the continuity requirements of the clinical workflow and makes it more convenient for doctors in clinical work.

[0060] Figure 2 This is a flowchart of another method for constructing a neural stimulation imaging model provided in accordance with an embodiment of the present application. Based on the above embodiments, this embodiment optionally performs modeling operations on multiple component modules in parallel based on module data, including: for each component module that performs the modeling operation, based on a pre-set splitting method corresponding to the component module, determining at least one modeling subtask corresponding to the component module, and executing each modeling subtask based on a preset subtask priority and the module data corresponding to the component module to complete the modeling operation on the component module. The explanations of the terms that are the same or corresponding to the above embodiments are not repeated here. Figure 2 As shown, the method includes:

[0061] S210 . In response to a modeling triggering operation on a target neural stimulation image model, acquiring neural stimulation image data of a target object.

[0062] S220, based on a plurality of component modules corresponding to a preset neural stimulation image model, split the neural stimulation image data into module data corresponding to the component modules; wherein the component modules are independent modules that do not affect each other.

[0063] S230. For each component module that performs a modeling operation, based on a pre-set splitting method corresponding to the component module, determine at least one modeling subtask corresponding to the component module; based on a preset subtask priority and module data corresponding to the component module, execute each modeling subtask to complete the modeling operation on the component module, obtain a component sub-model corresponding to the component module, fuse each component sub-model, and obtain a target neural stimulation image model corresponding to the target object.

[0064] It should be noted that in order to improve the flexibility of modeling operations on component modules, the modeling process of component modules can be split into at least one modeling subtask according to a pre-set splitting method. Exemplarily, for the nucleus module, the splitting method is to split according to the nucleus type, and it can be split into subthalamic nucleus subtask, nucleus accumbens subtask and amygdala subtask. For the electrode module, the splitting method is to split according to the electrode contact combination sequence, and it can be split into contact combination 1 subtask, contact combination 2 subtask, ..., contact combination n subtask. Wherein, n is a positive integer.

[0065] In this embodiment, the subtask priorities of different modeling subtasks can be preset. The higher the subtask priority, the greater the impact of the modeling subtask on other modeling subtasks; conversely, the smaller the impact of the modeling subtask on other modeling subtasks. In order not to affect the execution of other modeling subtasks, based on the preset subtask priority and the module data corresponding to the component modules, the implementation method of executing each modeling subtask can be: sorting each modeling subtask in order from high to low subtask priority; and executing each modeling subtask in order from small to large order of the modeling subtask sequence value.

[0066] In a specific implementation, the modeling subtasks can be sorted in descending order of subtask priority, and each modeling subtask can be executed in turn based on the module data in descending order of the order value of the modeling subtask, so that the modeling subtask with a higher subtask priority is executed first, and the modeling subtask with a lower subtask priority is executed later. Furthermore, modeling subtasks with the same subtask priority can be executed in parallel.

[0067] This embodiment optimizes the execution order of modeling subtasks to avoid affecting the execution of other modeling subtasks due to arranging modeling subtasks with higher priority for execution later, which is beneficial to improving the efficiency of executing modeling subtasks.

[0068] In order to ensure that the modeling operation of each component module can be effectively performed, before executing each modeling subtask, it also includes: determining the current amount of computing resources; determining whether the current amount of computing resources meets the preset conditions; executing each modeling subtask based on the preset subtask priority and the module data corresponding to the component module, including: when the current amount of computing resources meets the preset conditions, executing each modeling subtask based on the preset subtask priority and the module data corresponding to the component module.

[0069] The current amount of computing resources is the amount of computing resources currently to be allocated for processing the modeling subtask.

[0070] In a specific implementation, before executing the modeling subtask, the amount of idle computing resources in the construction system of the neural stimulation imaging model can be determined, and the amount of resources less than or equal to the idle computing resources can be used as the current computing resources. In order to ensure that all the modeling subtasks of each component module can be executed, it can be determined whether the current computing resources meet the preset conditions. The preset conditions may include that the current computing resources are greater than or equal to the sum of the resource consumption of each modeling subtask. The preset conditions may also include that the current computing resources are greater than a preset fixed threshold. It should be noted that those skilled in the art can determine the preset occupied resource amount and the preset fixed threshold according to the actual modeling process.

[0071] In this embodiment, when the current computing resources meet the preset conditions, it means that the current computing resources can support the modeling subtasks corresponding to the component modules, and the execution operation of each modeling subtask can be started. When the current computing resources do not meet the preset conditions, it means that the current computing resources cannot support the modeling subtasks corresponding to the component modules, and the idle computing resources of the construction system of the neural stimulation imaging model can be periodically detected, and the current computing resources are continuously updated based on the spatial computing resources until the current computing resources meet the preset conditions, and each modeling subtask corresponding to the component modules is executed.

[0072] Before executing the modeling subtask, this embodiment determines whether the current amount of computing resources meets the preset conditions, thereby avoiding the situation where the task execution fails due to the current amount of computing resources being unable to support the required resource consumption of the modeling subtask, thereby improving the effectiveness of executing the modeling subtask.

[0073] In this embodiment, the method also includes: detecting the execution degree of each modeling subtask; for each modeling subtask, determining whether the modeling subtask has been completed based on the execution degree corresponding to the modeling subtask, and if the modeling subtask has been completed, releasing the actual occupied resources of the modeling subtask.

[0074] In order to avoid resource waste and improve the utilization rate of computing resources, the execution degree of each modeling subtask can be detected during the execution of the modeling subtask. The higher the execution degree, the closer the modeling subtask is to the end of execution. For example, the execution degree can be represented by a value between [0,1]. The larger the value, the higher the execution degree; otherwise, the lower the execution degree.

[0075] In this embodiment, it can be determined whether the modeling subtask has been completed based on the determined execution degree. For example, when the value corresponding to the execution degree is 0, it means that the modeling subtask has not been executed; when the value corresponding to the execution degree is between (0, 1), it means that the modeling subtask is being executed; when the value corresponding to the execution degree is 1, it means that the modeling subtask has been completed. When the modeling subtask is completed, the actual occupied resources occupied by the modeling subtask can be released so that the released resources can be used to execute other tasks.

[0076] After the modeling subtask is completed, this embodiment releases the actually occupied resources in a timely manner, thereby avoiding resource waste and being beneficial to improving the utilization rate of computing resources.

[0077] The above describes in detail the embodiments corresponding to the method for constructing a neural stimulation image model. In order to make the technical scheme of the present method further clear to those skilled in the art, the modeling process of the neural stimulation image model is explained below for the scenario where multiple objects simultaneously request to construct a neural stimulation image model.

[0078] Figure 3 is a schematic diagram of a neural stimulation imaging model provided according to an embodiment of the present application, such as Figure 3 As shown, the neural stimulation imaging model corresponds to multiple component modules; the component modules may include an electric field module, a nucleus module, and a fiber bundle module. Each electric field module corresponds to electric field 1, ..., electric field n1, with a total of n1 electric fields, each nucleus module corresponds to nucleus 1, ..., nucleus n2, with a total of n2 nuclei, and each fiber bundle model corresponds to fiber bundle 1, ..., fiber bundle n3, with a total of n3 fiber bundles. n1, n2, and n3 are all positive integers.

[0079] In order to distinguish the modeling process of each target object, object tags can be added to the modeling subtasks corresponding to each target object and put into the central task pool to support dynamic update and query of the modeling subtasks. Based on the order of the object priority corresponding to each target object from high to low, the target neural stimulation image model corresponding to the target object is modeled and processed in turn. For target objects with the same object priority, parallel processing can be performed.

[0080] Figure 4 is a schematic diagram of a task execution process of a neural stimulation imaging model provided according to an embodiment of the present application, such as Figure 4As shown, each component module corresponds to a modeling task, for example, the electric field module modeling task, the nucleus module modeling task and the fiber bundle module modeling task; the electric field module modeling task may include multiple different electric field module modeling subtasks; the nucleus module modeling task may include multiple different nucleus module modeling subtasks, and the fiber bundle module modeling task may include multiple different fiber bundle module modeling subtasks. Each modeling task is executed in parallel, and the different modeling subtasks corresponding to each modeling task are executed in a serial execution manner, and finally a model fusion operation is performed to obtain a neural stimulation imaging model.

[0081] In this embodiment, each modeling subtask may correspond to the modeling process of multiple core groups to be modeled. In the process of executing each modeling subtask, for each core group to be modeled, there is a corresponding set of execution steps, each set of execution steps is executed serially, and different sets of execution steps are executed in parallel. Figure 5 is a schematic diagram of the modeling subtask execution process provided according to an embodiment of the present application, such as Figure 5 As shown, the core groups to be modeled corresponding to the core group modeling subtask include core group 1, core group 2, core group 3, ..., core group m, where m is a positive integer. The execution steps corresponding to core group 1 include steps 1-1 and 2-1, etc., the execution steps corresponding to core group 2 include steps 1-2 and 2-2, etc., and the execution steps corresponding to core group m include steps 1-m and 2-m, etc.

[0082] In order to facilitate timely determination of the resource status of the construction system of the neural stimulation imaging model, the idle computing resources in the construction system can be continuously monitored. For each component module corresponding to each target object, a task queue is maintained according to the subtask priority of the modeling subtask of the component module. When allocating resources, the modeling subtasks in the task queue are traversed in descending order based on the subtask priority, and it is checked whether the current amount of computing resources is greater than or equal to the sum of the resource consumption of each modeling subtask. If it is greater than or equal to the sum of the resource consumption, resources are allocated to the task queue and the modeling subtask is started, and the current amount of computing resources is updated at the same time. After all the modeling subtasks in the task queue are executed, the resources occupied by them are released immediately, and other task queues waiting to be processed are checked to try to allocate resources for them.

[0083] In order to understand the model construction process from the perspective of the neural stimulation imaging model construction system, please refer to Figure 6 In the construction system of the neural stimulation imaging model, the modeling subtask corresponding to each target object is generated through the visual modeling layer, and the modeling subtask is managed and scheduled through the core task management layer; the management content includes the management of the task queue and the management of the subtask priority. Exemplarily, the visual modeling layer can generate modeling subtasks for target object 1, target object 2, ..., target object M, where M is a positive integer.

[0084] Through the resource management layer, resource allocation operations are performed and load balancing is maintained; computing resources are allocated to each task queue to execute the modeling subtask. In addition, the current amount of computing resources is monitored, and computing resources are released in time for the completed modeling subtask. Computing resources include the number of cores of the central processing unit, the number of graphics processors, and the amount of memory. According to the allocated computing resources, the task queue is transmitted to the parallel processing layer to execute the modeling subtask through different processing nodes. Each processing node can execute tasks independently. Exemplarily, the parallel processing layer includes processing node 1, processing node 2, and processing node 3. The modeling subtask is executed by obtaining the neural stimulation image data of the target object from the object database of the data management layer. The neural stimulation image data includes pre-stored image files and image data obtained by real-time cache. A multi-level cache strategy is implemented through a cache mechanism, which is conducive to accelerating data access.

[0085] Through the user interaction layer, the target neural stimulation image model corresponding to each target object is rendered in three dimensions for visualization and displayed. Through the user interaction layer, program control parameters are input to feed back the program control parameters to the data management layer, so as to facilitate processing of data in the data management layer based on the program control parameters. Furthermore, for the displayed target neural stimulation image model, version management can be performed to facilitate comprehensive and detailed recording of the differences between different target neural stimulation image models corresponding to each target object.

[0086] In this embodiment, a multi-level architecture of a visualization modeling layer, a core task management layer, a data management layer, a parallel processing layer, a resource management layer, and a user interaction layer is adopted to achieve concurrent optimization of the entire process from data processing to user interaction. The overall processing efficiency of the construction system of the neural stimulation imaging model is significantly improved, and the waiting time of deep neural stimulation programming is reduced. The scalability and modularity of the construction system of the neural stimulation imaging model are enhanced to facilitate future functional expansion and maintenance.

[0087] Figure 7 1 is a schematic diagram of a structure of a device for constructing a neural stimulation image model according to an embodiment of the present application, and the device is used to execute the method for constructing a neural stimulation image model provided in any of the above embodiments. The device and the method for constructing a neural stimulation image model in the above embodiments belong to the same inventive concept, and the details not fully described in the embodiment of the device for constructing a neural stimulation image model can be referred to the embodiment of the method for constructing a neural stimulation image model. Figure 7 As shown, the device comprises:

[0088] A neural stimulation image data acquisition module 10 is used to acquire neural stimulation image data of a target object in response to a modeling trigger operation of a target neural stimulation image model;

[0089] The data splitting module 11 is used to split the neural stimulation image data into module data corresponding to the component modules based on a plurality of component modules corresponding to the preset neural stimulation image model; wherein the component modules are independent modules that do not affect each other;

[0090] The sub-model fusion module 12 is used to perform modeling operations on multiple component modules in parallel based on module data to obtain component sub-models corresponding to the component modules, and fuse each component sub-model to obtain a target neural stimulation image model corresponding to the target object.

[0091] Based on any optional technical solution in the embodiment of the present application, optionally, the sub-model fusion module 12 includes:

[0092] The modeling subtask determination unit is used to determine, for each component module that performs a modeling operation, at least one modeling subtask corresponding to the component module based on a pre-set splitting method corresponding to the component module, and execute each modeling subtask based on a preset subtask priority and module data corresponding to the component module to complete the modeling operation on the component module.

[0093] Based on any optional technical solution in the embodiments of the present application, optionally, the modeling subtask determination unit includes:

[0094] The task sorting subunit is used to sort each modeling subtask in descending order of subtask priority;

[0095] The first task execution subunit is used to execute each modeling subtask in sequence according to the sequence value of the modeling subtask from small to large.

[0096] Based on any optional technical solution in the embodiments of the present application, optionally, it also includes:

[0097] A current computing resource amount determination unit is used to determine the current computing resource amount before executing each modeling subtask; wherein the current computing resource amount is the current computing resource amount to be allocated for processing the modeling subtask; and determine whether the current computing resource amount meets a preset condition;

[0098] The modeling subtask determines the unit, including:

[0099] The second task execution subunit is used to execute each modeling subtask based on the preset subtask priority and the module data corresponding to the component modules when the current computing resource amount meets the preset conditions.

[0100] Based on any optional technical solution in the embodiments of the present application, optionally, it also includes:

[0101] An execution degree detection unit, used to detect the execution degree of each modeling subtask;

[0102] The resource releasing unit is used to determine, for each modeling subtask, whether the modeling subtask has been executed based on the execution degree of the modeling subtask, and release the actual occupied resources of the modeling subtask if the modeling subtask has been executed.

[0103] Based on any optional technical solution in the embodiments of the present application, optionally, it also includes:

[0104] A graphics rendering module is used to perform graphics rendering on each component sub-model and the target neural stimulation image model based on a graphics rendering technology after fusing each component sub-model to obtain a target neural stimulation image model corresponding to the target object, so as to obtain a sub-model image corresponding to each component sub-model and a target model image corresponding to the target neural stimulation image model;

[0105] An image display module, used to display the sub-model image and the target model image according to a preset display method;

[0106] The component sub-models include at least one of an electric field sub-model, a nucleus sub-model, a fiber bundle sub-model, an electrode sub-model and a cortex sub-model.

[0107] Based on any optional technical solution in the embodiment of the present application, optionally, the nerve stimulation image data acquisition module 10 includes:

[0108] A data acquisition unit, configured to acquire first brain image data of the target subject before a deep nerve stimulation operation is performed, and second brain image data of the target subject after the deep nerve stimulation operation is performed;

[0109] a data generating unit, configured to generate the neural stimulation image data based on the first brain image data and the second brain image data;

[0110] Wherein, the first brain image data and the second brain image data are both computer tomography data.

[0111] The technical solution of the embodiment of the present application obtains the neural stimulation image data of the target object in response to the modeling trigger operation of the target neural stimulation image model; and, through the multiple component modules corresponding to the pre-set neural stimulation image model, the neural stimulation image data is split into module data corresponding to the component modules; since the component modules are independent modules that do not affect each other; therefore, based on the module data, the modeling operation is performed on the multiple component modules in parallel to obtain the component sub-models corresponding to the component modules, and each component sub-model is fused to obtain the target neural stimulation image model corresponding to the target object. In the technical solution of this embodiment, since the component models do not affect each other, when constructing the target neural stimulation image model, the modeling operation is performed on the multiple component modules in a parallel manner, and there is no need to execute the model building process step by step in a serial manner, which reduces the time-consuming construction of the target neural stimulation image model and improves the efficiency of model construction, which is conducive to meeting the continuity requirements of the clinical workflow and makes it more convenient for doctors in clinical work.

[0112] It is worth noting that in the embodiment of the above-mentioned device for constructing a neural stimulation imaging model, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application.

[0113] Figure 8 It is a schematic diagram of the structure of an electronic device for implementing the method for constructing a neural stimulation imaging model of an embodiment of the present application. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workbenches, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0114] like Figure 8As shown, the electronic device 20 includes at least one processor 21, and a memory connected to the at least one processor 21, such as a read-only memory (ROM) 22, a random access memory (RAM) 23, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 21 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 22 or the computer program loaded from the storage unit 28 to the random access memory (RAM) 23. In RAM23, various programs and data required for the operation of the electronic device 20 can also be stored. The processor 21, ROM22 and RAM23 are connected to each other through a bus 24. An input / output (I / O) interface 25 is also connected to the bus 24.

[0115] A number of components in the electronic device 20 are connected to the I / O interface 25, including: an input unit 26, such as a keyboard, a mouse, etc.; an output unit 27, such as various types of displays, speakers, etc.; a storage unit 28, such as a disk, an optical disk, etc.; and a communication unit 29, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 29 allows the electronic device 20 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0116] The processor 21 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 21 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 21 executes the various methods and processes described above, such as a method for constructing a neural stimulation imaging model.

[0117] In some embodiments, the method for constructing a neural stimulation image model may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 28. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 20 via the ROM 22 and / or the communication unit 29. When the computer program is loaded into the RAM 23 and executed by the processor 21, one or more steps of the method for constructing a neural stimulation image model described above may be performed. Alternatively, in other embodiments, the processor 21 may be configured to execute the method for constructing a neural stimulation image model in any other appropriate manner (e.g., by means of firmware).

[0118] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0119] The computer programs for implementing the methods of the present application may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer programs are executed by the processor, the functions / operations specified in the flow charts and / or block diagrams are implemented. The computer programs may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0120] In the context of the present application, a computer readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device or equipment. A computer readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer readable storage medium may be a machine readable signal medium. A more specific example of a machine readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0121] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0122] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0123] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0124] This embodiment also provides a medical device, which includes: an input interface configured to provide a doctor with an interface for inputting programmed parameters; a processor configured to receive and store neural stimulation image data of a target object, and execute the neural stimulation image model construction method of any one of claims 1 to 7 to obtain a target neural stimulation image model corresponding to the target object; and a display interface configured to display the target neural stimulation image model.

[0125] This embodiment also provides a computer program product, including a computer program, which, when executed by a processor, implements the method for constructing a neural stimulation imaging model as provided in any embodiment of the present application.

[0126] In the process of implementation, the computer program product can be written in one or more programming languages ​​or a combination thereof to perform the computer program code of the present application, and the programming language includes an object-oriented programming language, such as Java, Smalltalk, C++, and also includes a conventional procedural programming language, such as "C" language or similar programming language. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, using an Internet service provider to connect through the Internet).

[0127] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this application can be executed in parallel, sequentially or in different orders, as long as the expected results of the technical solution of this application can be achieved, and this document is not limited here.

[0128] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A method for constructing a neural stimulation imaging model, characterized in that: include: In response to a modeling trigger operation on a target neural stimulation image model, acquiring neural stimulation image data of a target object; Based on a plurality of pre-set component modules corresponding to the neural stimulation image model, the neural stimulation image data is split into module data corresponding to the component modules; wherein the component modules are independent modules that do not affect each other; Based on the module data, modeling operations are performed on the plurality of component modules in parallel to obtain component sub-models corresponding to the component modules, and each component sub-model is fused to obtain a target neural stimulation image model corresponding to the target object.

2. The method according to claim 1, characterized in that The performing modeling operations on the plurality of component modules in parallel based on the module data includes: For each component module that performs the modeling operation, based on a pre-set splitting method corresponding to the component module, at least one modeling subtask corresponding to the component module is determined, and based on a preset subtask priority and module data corresponding to the component module, each modeling subtask is executed to complete the modeling operation on the component module.

3. The method according to claim 2, characterized in that The step of executing each of the modeling subtasks based on the preset subtask priority and the module data corresponding to the component modules includes: Sorting each of the modeling subtasks in descending order of priority of the subtasks; Each of the modeling subtasks is executed in sequence according to the order of the sequence value of the modeling subtask from small to large.

4. The method according to claim 2, characterized in that: Before executing each of the modeling subtasks, the method further includes: Determine the current amount of computing resources; wherein the current amount of computing resources is the amount of computing resources currently to be allocated for processing the modeling subtask; Determining whether the current amount of computing resources meets a preset condition; The step of executing each of the modeling subtasks based on the preset subtask priority and the module data corresponding to the component modules includes: When the current amount of computing resources meets the preset conditions, each of the modeling subtasks is executed based on the preset subtask priority and the module data corresponding to the component modules.

5. The method according to claim 2, characterized in that: Also includes: Detecting the execution degree of each of the modeling subtasks; For each of the modeling subtasks, it is determined whether the modeling subtask has been completed based on the execution degree corresponding to the modeling subtask. If the modeling subtask has been completed, the actually occupied resources of the modeling subtask are released.

6. The method according to claim 1, characterized in that After fusing each of the component sub-models to obtain a target nerve stimulation image model corresponding to the target object, the method further includes: Based on the graphics rendering technology, graphics rendering is performed on each of the component sub-models and the target neural stimulation image model to obtain a sub-model image corresponding to each of the component sub-models and a target model image corresponding to the target neural stimulation image model; Displaying the sub-model image and the target model image according to a preset display method; The component sub-models include at least one of an electric field sub-model, a nucleus sub-model, a fiber bundle sub-model, an electrode sub-model and a cortex sub-model.

7. The method according to claim 1, characterized in that The step of obtaining the neural stimulation image data of the target object includes: Acquiring first brain image data of the target subject before deep nerve stimulation is performed, and second brain image data of the target subject after deep nerve stimulation is performed; generating the neural stimulation image data based on the first brain image data and the second brain image data; The first brain image data and the second brain image data are both computer tomography data.

8. A device for constructing a neural stimulation image model, characterized in that: include: A neural stimulation image data acquisition module, configured to acquire neural stimulation image data of a target object in response to a modeling trigger operation on a target neural stimulation image model; A data splitting module, used for splitting the neural stimulation image data into module data corresponding to the component modules based on a plurality of component modules corresponding to the neural stimulation image model set in advance; wherein the component modules are independent modules that do not affect each other; The sub-model fusion module is used to perform modeling operations on multiple component modules in parallel based on the module data to obtain component sub-models corresponding to the component modules, and to fuse each component sub-model to obtain a target neural stimulation image model corresponding to the target object.

9. A medical device, characterized in that: The medical equipment includes: An input interface configured to provide a physician with an interface for inputting program-controlled parameters; A processor configured to receive and store neural stimulation image data of a target object, and execute the method for constructing a neural stimulation image model according to any one of claims 1 to 7 to obtain a target neural stimulation image model corresponding to the target object; The display interface is configured to display the target nerve stimulation image model.

10. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for constructing a neural stimulation image model according to any one of claims 1 to 7.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for constructing a neural stimulation image model according to any one of claims 1 to 7 when executed.

Images