A three-dimensional visualization method and system of brain neural network based on ThreeJS

Abstract

The present application discloses a three-dimensional visualization method and system of a brain neural network based on ThreeJS, the method comprising the following steps: acquiring data, wherein the data comprises neural network data and neuron node data; respectively converting the neural network data and neuron node data into data formats required for rendering a three-dimensional brain neural network; rendering the three-dimensional brain neural network according to the data format by ThreeJS; the method realizes the functions of efficiently and smoothly displaying and interacting with the brain neural network on the browser side by utilizing the ThreeJS technology, including functional modules such as perspective movement and scaling, time sequence node switching, brain area visibility control, activation result analysis, real-time display of rendering performance consumption and personalized customization of color schemes, so that researchers can carry out neural network and neuron node algorithm testing and visualization experiments; the system has the same beneficial effects.

Description

Technical Field

[0001] The present application relates to the field of neural network visualization technology, and in particular to a three-dimensional visualization method and system for a brain neural network based on ThreeJS. Background Art

[0002] With the continuous development of computer technology and neuroscience research, brain neural network visualization technology has become an important branch in the field of neuroscience. Brain neural network visualization technology mainly presents a large number of neurons and the connections between neurons in the form of graphics or animations, which can more intuitively understand the structure and function of the brain. This technology relies on a large amount of neuroimaging data and uses computer algorithms to process and analyze this data. Because the connections between neurons in the brain are very complex, this technology requires the use of very efficient algorithms and computer computing power.

[0003] In order to better display the internal structure of the brain and the connection between neurons, some new brain neural network visualization technologies have emerged in the field of neuroscience research in recent years, such as "electroencephalogram"; this technology can more accurately observe the interaction between various areas inside the brain, as well as the activity status of neurons and information transmission paths; but the formed brain neural network cannot be interactively browsed on the browser side, that is, it does not support dragging and rotation of angles, and the rendering effect is not satisfactory.

[0004] In view of this, it is a technical problem that needs to be solved urgently by those skilled in the art to provide a three-dimensional visualization method and system of the brain neural network based on Three JS that can realize interactive browsing of the brain neural network on the browser side. Summary of the invention

[0005] In order to solve the above technical problems, the purpose of the present invention is to provide a three-dimensional visualization method and system of the brain neural network based on Three JS, which realizes the functions of efficiently and smoothly displaying and interacting with the brain neural network on the browser side, so that researchers can carry out scientific research more efficiently.

[0006] The first object of the present invention is to provide a three-dimensional visualization method of brain neural network based on ThreeJS;

[0007] The technical solution provided by the present invention is as follows:

[0008] A three-dimensional visualization method of brain neural network based on ThreeJS, comprising the following steps:

[0009] Acquiring data, wherein the data includes neural network data and neuron node data;

[0010] Respectively converting the neural network data and the neuron node data into data formats required for rendering a three-dimensional brain neural network;

[0011] The three-dimensional brain neural network is rendered according to the data format using Three JS.

[0012] Preferably, the neural network data is in SWC format, and the neural network data attributes include: interval identifier, neuron type, x coordinate, y coordinate, z coordinate, radius and parent node.

[0013] Preferably, the neuron node data is in GML format, and the neuron node data attributes are x-coordinate, y-coordinate, z-coordinate, flow, superclass, type, brain region, activation state and unique identification code.

[0014] Preferably, the file name of the neural network data is a unique identification code and corresponds to the unique identification code of the neuron node data.

[0015] Preferably, the converting of the neural network data and the neuron node data into data formats required for rendering a three-dimensional brain neural network specifically includes:

[0016] Use MySQL to establish a neuron node database, and input the neuron node data into the neuron node database one by one to establish a Node table;

[0017] Traversing all neural network data files, matching the unique identification code of the neural network data with the Node table, and dividing the table according to the neuron type of the Node table, and inputting the neural network data into the neuron node database one by one according to different neuron types;

[0018] Use Python language to convert all neuron nodes and neural network tables into the data format required to render the three-dimensional brain neural network.

[0019] Preferably, rendering the three-dimensional brain neural network according to the data format by Three JS specifically includes:

[0020] The three-dimensional brain neural network is rendered in the Scene scene according to the data format using Three JS.

[0021] Preferably, after rendering the three-dimensional brain neural network according to the data format by Three JS, the method further includes:

[0022] WebGL technology is used to render the three-dimensional brain neural network.

[0023] The second object of the present invention is to provide a three-dimensional visualization system of brain neural network based on Three JS;

[0024] The technical solution provided by the present invention is as follows:

[0025] A brain neural network three-dimensional visualization system based on Three JS, including: an acquisition module, a conversion module and a rendering module;

[0026] The conversion module is connected to the acquisition module and the rendering module respectively;

[0027] The acquisition module is used to acquire data, wherein the data includes neural network data and neuron node data;

[0028] The conversion module is used to convert the neural network data and the neuron node data into data formats required for rendering a three-dimensional brain neural network;

[0029] The rendering module is used to render the three-dimensional brain neural network according to the data format through Three JS.

[0030] The third object of the present invention is to provide an electronic device;

[0031] The technical solution provided by the present invention is as follows:

[0032] An electronic device, comprising:

[0033] at least one processor; and

[0034] A memory communicatively connected to the at least one processor, the memory storing a computer program executable by the at least one processor, the computer program being executed by the at least one processor so that the at least one processor can perform any one of the method steps described in a method for three-dimensional visualization of a brain neural network based on Three JS.

[0035] A fourth object of the present invention is to provide a computer readable storage medium;

[0036] The technical solution provided by the present invention is as follows:

[0037] A computer-readable storage medium is used to store a computer program, and the computer program is used to enable a computer to execute any method step described in a three-dimensional visualization method of a brain neural network based on ThreeJS.

[0038] The present invention provides a three-dimensional visualization method of a brain neural network based on ThreeJS, comprising the following steps: acquiring data, wherein the data includes neural network data and neuron node data; respectively converting the neural network data and neuron node data into data formats required for rendering a three-dimensional brain neural network; rendering the three-dimensional brain neural network according to the data format by ThreeJS; the method realizes the functions of efficiently and smoothly displaying and interacting with the brain neural network on the browser side by utilizing the ThreeJS technology, including functional modules such as perspective movement and scaling, time sequence node switching, brain area visibility control, activation result analysis, real-time display of rendering performance consumption, and personalized customization of color schemes, so that researchers can carry out neural network and neuron node algorithm testing and visualization experiments, understand the functions of different neural tissue structures in the brain, and carry out scientific research more efficiently.

[0039] The present invention also provides a three-dimensional visualization system of a brain neural network based on Three JS. Since the system and the three-dimensional visualization method of a brain neural network based on Three JS solve the same technical problem and belong to the same technical concept, they should have the same beneficial effects and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 It is a flowchart of a three-dimensional visualization method of a brain neural network based on Three JS in an embodiment of the present invention;

[0042] Figure 2 Schematic diagrams of visualization of fly brain neural networks in embodiments of the present invention, wherein (a) is a schematic diagram of fly brain neurons rendered according to the visualization type of neuron nodes in fly brain data; (b) is a schematic diagram of fly brain neural networks rendered according to the neuron types in fly brain data;

[0043] Figure 3 Schematic diagrams of visualization of fly brain neural network from different perspectives in an embodiment of the present invention, wherein (a) is a front view of the fly brain neural network; (b) is a side view of the fly brain neural network obtained by rotation; (c) is a rear view of the fly brain neural network obtained by rotation; (d) is a bottom view of the fly brain neural network obtained by rotation;

[0044] Figure 4 This is a schematic diagram of activation of some neurons in the fly brain in an embodiment of the present invention;

[0045] Figure 5 It is a structural schematic diagram of a brain neural network three-dimensional visualization system based on Three JS in an embodiment of the present invention;

[0046] Figure 6 The figure is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to enable those skilled in the art to better understand the technical solutions in this application, the technical solutions in the embodiments of this application will be clearly and completely described below. Obviously, the described embodiments are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0048] It should be noted that when an element is referred to as being "fixed on" or "set on" another element, it can be directly on the other element or indirectly set on the other element; when an element is referred to as being "connected to" another element, it can be directly connected to the other element or indirectly connected to the other element.

[0049] It should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present application.

[0050] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "multiple" and "several" mean two or more, unless otherwise clearly and specifically defined.

[0051] It should be noted that the structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not used to limit the conditions under which this application can be implemented. Therefore, they have no substantive technical significance. Any structural modification, change in proportional relationship or adjustment of size should still fall within the scope of the technical content disclosed in this application without affecting the effects and purposes that can be achieved by this application.

[0052] like Figure 1 As shown, an embodiment of the present invention provides a three-dimensional visualization method of a brain neural network based on Three JS, comprising the following steps:

[0053] S1. Acquire data, wherein the data includes neural network data and neuron node data;

[0054] In step S1, data required for rendering a three-dimensional brain neural network is obtained, wherein the data of the three-dimensional brain neural network includes neural network data and neuron node data, the neural network data is in SWC format, and the attributes of the neural network data include: interval identifier, neuron type, x-coordinate, y-coordinate, z-coordinate, radius and parent node; the neuron node data is in GML format, and the attributes of the neuron node data include: x-coordinate, y-coordinate, z-coordinate, flow, superclass, type, brain region, activation state and unique identification code; it should be noted that the file name of the neural network data is the unique identification code, and corresponds to the unique identification code of the neuron node data; in this example, there are 141,281 neural network data files in SWC format, with a total file size of 2GB and a total of 23,803,150 data items; the total size of the neuron node data files in GML format is 3.08GB, with a total of 131,459 data items.

[0055] S2. Converting the neural network data and the neuron node data into data formats required for rendering a three-dimensional brain neural network respectively;

[0056] In step S2, since the formats and properties of the neural network data and the neuron node data are different, the neural network data and the neuron node data need to be converted separately to obtain the data format required for rendering the three-dimensional brain neural network.

[0057] S3. Rendering a three-dimensional brain neural network according to the data format using ThreeJS.

[0058] In step S3, the three-dimensional brain neural network is rendered according to the data format obtained in step S2 by using the Three JS framework, thereby realizing the function of efficiently and smoothly displaying and interacting with the brain neural network on the browser side, so that researchers can carry out neural network and neuron node algorithm testing and visualization experiments, understand the functions of different neural tissue structures in the brain, and carry out scientific research more efficiently.

[0059] Preferably, the converting of the neural network data and the neuron node data into data formats required for rendering a three-dimensional brain neural network specifically includes:

[0060] Use MySQL to establish a neuron node database, and input the neuron node data into the neuron node database one by one to establish a Node table;

[0061] Traversing all neural network data files, matching the unique identification code of the neural network data with the Node table, and dividing the table according to the neuron type of the Node table, and inputting the neural network data into the neuron node database one by one according to different neuron types;

[0062] Use Python language to convert all neuron nodes and neural network tables into the data format required to render the three-dimensional brain neural network.

[0063] In the actual application process, MySQL is used to establish a neuron node database, and the neuron node data is entered into the neuron node database one by one to establish a Node table for subsequent processing of neural network data; MySQL is used here because the amount of data is too large, and it is found in the test that MySQL processes such data significantly faster than PostgreSQL; then all neural network data files are traversed, and the unique identification code of the neural network data file name is matched with the Node table, and the table is divided according to the neuron type of the Node table, and the neural network data is entered into the established neuron node database one by one according to the different neuron types. The table division is to prevent the storage of one table from causing too much data, making the query operation abnormally slow; after the above processing, Python language is used to convert all neuron nodes and neural network sub-tables into the data format required for rendering the three-dimensional brain neural network.

[0064] It should be noted that for neuron nodes, their attributes need to be stored separately as a JSONB table and indexed according to the unique identification code for fast retrieval. Users can analyze the impact of the algorithm on the overall activation state of the neural network frame by frame by uploading activation state data corresponding to the unique identification code.

[0065] For neural networks, it is necessary to convert the neural network into two one-dimensional arrays of coordinates and indices according to different sub-tables. The coordinate array stores the xyz coordinate data of all nodes, and the index array indicates the connection relationship. For example, [1,5,2,8] means that nodes 1 and 5 are connected as a line, and nodes 2 and 8 are connected as a line. This storage method can greatly reduce the amount of data required to repeatedly store node data. The neural network data of 141,281 files with a size of 2GB is stored as 23 JSON data, eliminating the blocking problem of data transmission between the front and back ends. Among them, the JSONB type of PostgreSQL is used to store data in JSON format, because it provides a series of functions and operators to query and operate these data. Through the JSONB type, the information of nodes and edges in the network can be stored, and query and update operations can be performed quickly.

[0066] In addition, the backend has built multiple interfaces on the server, such as getDataByTableName to obtain neural network data according to different types and getCoordinateById to obtain neuron node coordinate data according to unique identification numbers, all of which are used to transmit PostgreSQL data to the front end. The backend of this embodiment uses the Spring Boot framework, which is a Java-based open source framework for quickly building independent, production-level Spring applications; through SpringBoot, backend services can be quickly built and RESTful API interfaces can be provided for front-end calls.

[0067] Preferably, rendering the three-dimensional brain neural network according to the data format by Three JS specifically includes:

[0068] The three-dimensional brain neural network is rendered in the Scene scene according to the data format using Three JS.

[0069] In the actual application process, Three JS is used at the front end to render the three-dimensional brain neural network in the Scene scene according to the data format; among them, the neural network visualization part: use LineBasicMaterial (line basic material class) to create line segment materials, and customize different colors according to different neural types. Write GLSL Shaders (GLSL shader) files to achieve different colors for each line, which greatly enriches the visualization customization needs; use the index buffer attribute of BufferGeometry (graphics buffer class) to convert index data in Uint32Array (32-bit integer array) format, and use the position buffer attribute in Float32BufferAttribute (32-bit floating point buffer attribute) format to convert coordinate data; then use LineSegments (unclosed line segment class) to create line segment objects; finally, add the Object3D object to the ThreeJS scene for drawing. Neuron node visualization part: Use different materials such as PointsMaterial and ShaderMaterial to customize different neuron node visualization types according to needs; use the position buffer attribute of BufferGeometry to store the coordinates of each node, write GLSL Shaders files and use the colors attribute to store the color of each node, and the size attribute to store the size of each node; use Points to create point objects, add them to Object3D objects, and draw them in the Scene scene, such as Figure 2 As shown, Figure 2 (a) A schematic diagram of fly brain neurons rendered based on the neuron node visualization type in the fly brain data; Figure 2 (b) is a schematic diagram of the fly brain neural network rendered according to the neural types in the fly brain data. The front end of this embodiment uses the Vue.js framework to build a user interface. Vue.js is a popular JavaScript framework that simplifies the development of Web applications in a componentized way, and can build a front-end interface with rich interactivity and good user experience. The UI is designed based on Element Plus UI, which is a UI component library designed for building a component library based on Vue 3. It provides developers with a rich set of UI components and extended functions to help developers quickly build high-quality Web applications.

[0070] It is important to note that the real-time display of rendering performance consumption and the coordinate axis display plug-in are also drawn, as well as the consumption of real-time browser rendering performance and the regional status of the current perspective. Finally, ambient light and point light sources are added to enhance the three-dimensional effect. Users can observe the structure, activation state, partition and type of the neural network by changing the camera perspective, including operations such as zooming, translating and rotating, such as Figure 3 As shown, different views of the fly brain neural network can be seen through operations such as zooming, translating, and rotating. Figure 3 (a) is a front view of the fly brain neural network; Figure 3 (b) is a side view of the fly brain neural network obtained by rotation; Figure 3 (c) is a posterior view of the fly brain neural network obtained by rotation; Figure 3 (d) A bottom view of the fly brain neural network obtained by rotation; the activation state in this embodiment is to activate some neurons in the brain through stimulation experiments to study the stimulus response and its potential mechanism, such as Figure 4 As shown, some neurons in the fly brain were activated through stimulation experiments.

[0071] Preferably, after rendering the three-dimensional brain neural network according to the data format by Three JS, the method further includes:

[0072] WebGL technology is used to render the three-dimensional brain neural network.

[0073] In the actual application process, WebGL technology, namely GPU acceleration technology, is used to improve rendering performance. GPU acceleration technology utilizes the computing power of the graphics processing unit (GPU) and significantly improves rendering speed and efficiency through parallel processing and stream processing modes. By utilizing the GPU acceleration function of Three.js, especially by creating objects through Float32BufferAttribute, each object contains its position information in three-dimensional space, which greatly improves the rendering speed and fluency.

[0074] like Figure 5 As shown, an embodiment of the present invention also provides a brain neural network three-dimensional visualization system based on Three JS, including: an acquisition module, a conversion module and a rendering module;

[0075] The conversion module is connected to the acquisition module and the rendering module respectively;

[0076] The acquisition module is used to acquire data, wherein the data includes neural network data and neuron node data;

[0077] The conversion module is used to convert the neural network data and the neuron node data into data formats required for rendering a three-dimensional brain neural network;

[0078] The rendering module is used to render the three-dimensional brain neural network according to the data format through Three JS.

[0079] In the actual application process, in the brain neural network three-dimensional visualization system based on Three JS, an acquisition module, a conversion module and a rendering module are set up, and the conversion module is connected with the acquisition module and the rendering module respectively; the acquisition module transmits the data including the neural network data and the neuron node data to the conversion module; the conversion module converts the neural network data and the neuron node data into the data format required for rendering the three-dimensional brain neural network, and transmits the data format to the rendering module; the rendering module renders the three-dimensional brain neural network according to the data format through Three JS; this system realizes the function of efficiently and smoothly displaying and interacting with the brain neural network on the browser side through the cooperation of the acquisition module, the conversion module and the rendering module, so that researchers can carry out neural network and neuron node algorithm testing and visualization experiments, understand the functions of different neural tissue structures in the brain, and carry out scientific research more efficiently.

[0080] Furthermore, the present application also discloses an electronic device. Figure 6 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content in the diagram cannot be regarded as any limitation on the scope of use of the present application.

[0081] Figure 6 A schematic diagram of the structure of an electronic device 20 provided in an embodiment of the present application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 is used to store a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the three-dimensional visualization method of the brain neural network based on Three JS disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0082] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0083] In addition, the memory 22, as a carrier for storing resources, can be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon may include an operating system 221, a computer program 222 and data 223, etc. The storage method can be temporary storage or permanent storage.

[0084] Among them, the operating system 221 is used to manage and control the hardware devices and computer programs 222 on the electronic device 20 to realize the operation and processing of the data 223 in the memory 22 by the processor 21, which can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program that can be used to complete the brain neural network three-dimensional visualization method based on Three JS executed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks. In addition to including data transmitted from an external device received by the brain neural network three-dimensional visualization device based on ThreeJS, the data 223 can also include data collected by its own input and output interface 25, etc.

[0085] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0086] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the aforementioned disclosed method for visualizing a brain neural network based on ThreeJS is implemented. The specific steps of the method can be referred to the corresponding contents disclosed in the aforementioned embodiments, and will not be described in detail here.

[0087] It should be understood that the use of "method", "device", "unit" and / or "module" in this application is only a method for distinguishing different components, elements, parts, portions or assemblies at different levels. However, if other words can achieve the same purpose, the word can be replaced by other expressions.

[0088] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "a kind" and / or "the" do not refer to the singular, but also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements. The elements defined by the sentence "includes a..." do not exclude the existence of other identical elements in the process, method, commodity or device that includes the elements.

[0089] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features.

[0090] If a flow chart is used in the present application, the flow chart is used to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, each step can be processed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or a certain step or several steps of operations can be removed from these processes.

[0091] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A three-dimensional visualization method of brain neural network based on ThreeJS, characterized in that: The steps include: Acquiring data, wherein the data includes neural network data and neuron node data; Respectively converting the neural network data and the neuron node data into data formats required for rendering a three-dimensional brain neural network; Rendering a three-dimensional brain neural network according to the data format using Three JS; The converting of the neural network data and the neuron node data into data formats required for rendering a three-dimensional brain neural network specifically includes: Use MySQL to establish a neuron node database, and input the neuron node data into the neuron node database one by one to establish a Node table; Traversing all neural network data files, matching the unique identification code of the neural network data with the Node table, and dividing the table according to the neuron type of the Node table, and inputting the neural network data into the neuron node database one by one according to different neuron types; Use Python language to convert all neuron nodes and neural network tables into the data format required to render a three-dimensional brain neural network; The neural network data is in SWC format, and the neural network data attributes include: interval identifier, neuron type, x coordinate, y coordinate, z coordinate, radius and parent node; The neuron node data is in GML format, and the neuron node data attributes are x-coordinate, y-coordinate, z-coordinate, flow, superclass, type, brain region, activation state and unique identification code; The file name of the neural network data is a unique identification code and corresponds to the unique identification code of the neuron node data.

2. The brain neural network three-dimensional visualization method based on ThreeJS according to claim 1, characterized in that: The rendering of the three-dimensional brain neural network according to the data format by Three JS specifically includes: The three-dimensional brain neural network is rendered in the Scene scene according to the data format using Three JS.

3. The brain neural network three-dimensional visualization method based on ThreeJS according to claim 1, characterized in that: After rendering the three-dimensional brain neural network according to the data format by Three JS, the method further includes: WebGL technology is used to render the three-dimensional brain neural network.

4. A three-dimensional visualization system of brain neural network based on ThreeJS, characterized in that: include: Get module, transform module and render module; The conversion module is connected to the acquisition module and the rendering module respectively; The acquisition module is used to acquire data, wherein the data includes neural network data and neuron node data; The conversion module is used to convert the neural network data and the neuron node data into data formats required for rendering a three-dimensional brain neural network; The rendering module is used to render the three-dimensional brain neural network according to the data format through Three JS; The conversion module is specifically used for: Use MySQL to establish a neuron node database, and input the neuron node data into the neuron node database one by one to establish a Node table; Traversing all neural network data files, matching the unique identification code of the neural network data with the Node table, and dividing the table according to the neuron type of the Node table, and inputting the neural network data into the neuron node database one by one according to different neuron types; Use Python language to convert all neuron nodes and neural network tables into the data format required to render a three-dimensional brain neural network; The neural network data is in SWC format, and the neural network data attributes include: interval identifier, neuron type, x coordinate, y coordinate, z coordinate, radius and parent node; The neuron node data is in GML format, and the neuron node data attributes are x-coordinate, y-coordinate, z-coordinate, flow, superclass, type, brain region, activation state and unique identification code; The file name of the neural network data is a unique identification code and corresponds to the unique identification code of the neuron node data.

5. An electronic device, characterized in that: include: at least one processor; as well as A memory communicatively connected to the at least one processor, the memory storing a computer program executable by the at least one processor, the computer program being executed by the at least one processor so that the at least one processor can execute the method according to any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that: The storage medium is used to store a computer program, and the computer program is used to enable a computer to execute the method according to any one of claims 1 to 3.

Images