Neuron tracking auxiliary method and device, computer device and storage medium

Abstract

The application relates to the technical field of artificial intelligence, and discloses a neuron tracking auxiliary method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring neuron tracking data; generating each concentric circle based on the normal plane of a main branch, the tracking data and each preset radius, wherein the main branch is a selected neuron bifurcation tree shape data in the tracking data, and the normal plane is generated based on the center of a section of the main branch; determining a target point; performing data analysis on each target point corresponding to each different section of the main branch and the preset radius, determining the tree shape data of the neuron bifurcation closest to the main branch as a potential error point. The application can find other neuron branches relatively close to each main branch by using the tracking data of the neuron and the maximum value projection of the concentric circle, so that the content of the potential possible labeling error, i.e. the potential error point, is obtained, the range of the possible error screened out is given to a human being again, and the artificial cost required during the review is effectively reduced.

Description

Technical Field

[0001] This invention relates to the field of artificial intelligence technology, and in particular to a neuron tracking assistance method, device, computer equipment, and storage medium. Background Technology

[0002] To explore the neuronal network structure of the brain, neuronal imaging technology uses viral tracing technology to label target neurons. Then, neuronal annotation is needed to convert imaging data into morphological data. However, with a large amount of manual input, errors can still occur in neuronal morphological data, so manual review of the morphological data is required.

[0003] Currently, manual review is inefficient and lacks specificity, necessitating an algorithm-based automated review function. This function would first use algorithms to automatically filter and narrow down the scope before handing the task over to manual reviewers, thereby effectively reducing the workload of manual reviewers. Simultaneously, the algorithm should aim to retain as many potential errors as possible while simultaneously reducing the scope of manual review and minimizing human effort. Summary of the Invention

[0004] Based on this, it is necessary to address the technical problem of low efficiency in reviewing neuronal morphological data in existing technologies by proposing a neuron tracking assistance method, device, computer equipment, and storage medium.

[0005] Firstly, a neuron tracking assistance method is provided, the method comprising:

[0006] Acquire tracking data of neurons, wherein the tracking data includes tree-like morphological data of each neuron branching, and each of the tree-like morphological data emits fluorescence;

[0007] Based on the normal plane of the main branch, the tracking data, and each preset radius, each concentric circle is generated. The main branch is a tree-like morphological data of a branching neuron selected from the tracking data, and the normal plane is generated based on the center of the cross section of the main branch.

[0008] Identify target points, wherein the target point is the point on each concentric circle that emits the brightest fluorescence;

[0009] Data analysis is performed on each target point and preset radius corresponding to different sections of the main branch to determine the tree-like morphological data of the neuron branch closest to the main branch, which is used as a potential error point.

[0010] Secondly, a neuron tracking assistive device is provided, the device comprising:

[0011] The acquisition module is used to acquire tracking data of neurons, wherein the tracking data includes tree-like morphological data of the branching of each neuron, and each of the tree-like morphological data emits fluorescence;

[0012] The generation module is used to generate concentric circles based on the normal plane of the main branch, the tracking data, and each preset radius. The main branch is a tree-like morphological data of a branching neuron selected from the tracking data, and the normal plane is generated based on the center of the cross section of the main branch.

[0013] A determination module is used to determine a target point, wherein the target point is the point on each concentric circle that emits the brightest fluorescence;

[0014] The analysis module is used to perform data analysis based on the target points and preset radii corresponding to different sections of the main branch, and to determine the tree-like morphological data of the neuron branch closest to the main branch as potential error points.

[0015] Thirdly, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the above-described neuron tracking assist method.

[0016] Fourthly, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described neuron tracking assist method.

[0017] The proposed neuron tracking-assisted method acquires neuron tracking data, including tree-like morphological data of each neuron branch, each of which emits fluorescence. Then, based on the normal plane of the main branch, the tracking data, and preset radii, concentric circles are generated. The main branch is a selected branch of the neuron's tree-like morphological data from the tracking data, and the normal plane is generated based on the center of the main branch's cross-section. Next, target points are determined; these target points are the brightest points emitting fluorescence on each concentric circle. Finally, based on the target points corresponding to different cross-sections of the main branch and the preset radii, data analysis is performed to determine the tree-like morphological data of the neuron branch closest to the main branch, which serves as potential error points. This invention utilizes neuron tracking data to identify other neuron branches relatively close to each main branch through the projection of the maximum value of concentric circles, thereby obtaining potentially erroneous labeling content, i.e., potential error points. The range of possible errors is then handed over to manual review, effectively reducing the manual labor costs required for review. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] in:

[0020] Figure 1 This is a diagram illustrating the application environment of a neuron tracking assistance method in one embodiment;

[0021] Figure 2 Here is a flowchart of a neuron tracking assistance method in one embodiment;

[0022] Figure 3 This is a schematic diagram of neuron tracking data in a neuron tracking assistance method in one embodiment;

[0023] Figure 4 This is a normal cross-section of a neuron in a neuron tracking assistance method in one embodiment;

[0024] Figure 5 This is a schematic diagram of concentric circles for a neuron tracking assistance method in one embodiment;

[0025] Figure 6 This is a Cartesian coordinate system for the neuron tracking assistance method in one embodiment;

[0026] Figure 7 This is a structural block diagram of a neuron tracking assistive device in one embodiment;

[0027] Figure 8 This is a structural block diagram of a computer device in one embodiment;

[0028] Figure 9 This is a structural block diagram of a computer device in another embodiment. Detailed Implementation

[0029] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0030] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0031] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0032] The neuron tracking assistance method provided in this embodiment of the invention can be applied to, for example... Figure 1 In the application environment, client 110 communicates with server 120 via a network. Server 120 can obtain neuron tracking data from client 110. The tracking data includes tree-like morphological data of each neuron branch, and each of the tree-like morphological data emits fluorescence. Then, server 120 generates concentric circles based on the normal plane of the main branch, the tracking data, and each preset radius. The main branch is a tree-like morphological data of a neuron branch selected from the tracking data, and the normal plane is generated based on the center of the cross-section of the main branch. Next, server 120 determines the target point, which is the point on each concentric circle that emits the brightest fluorescence. Finally, server 120 performs data analysis based on the target points corresponding to different cross-sections of the main branch and the preset radii to determine the tree-like morphological data of the neuron branch closest to the main branch as a potential error point. This invention utilizes neuron tracking data to identify other neuron branches relatively close to each main branch through concentric circle maximum value projection, thereby obtaining potentially mislabeled content, i.e., potential error points. The range of possible error occurrences is then handed over to manual review, effectively reducing the manual labor costs required for review. The client 110 can be, but is not limited to, various personal computers, laptops, smartphones, tablets, and portable wearable devices. The server 120 can be implemented using a standalone server or a server cluster consisting of multiple servers. The invention will be described in detail below through specific embodiments.

[0033] Please see Figure 2 As shown, Figure 2 A flowchart illustrating a neuron tracking assistance method according to an embodiment of the present invention includes the following steps:

[0034] Step S101: Acquire tracking data of neurons, wherein the tracking data includes tree-like morphological data of each neuron branching, and each of the tree-like morphological data emits fluorescence;

[0035] refer to Figure 3 The white fluorescent material in the image, which appears in a tree-like shape, represents the tracking data of neurons.

[0036] Specifically, after virus labeling and neuronal imaging, the neuronal imaging data is manually annotated to obtain unreviewed neuronal tracking data.

[0037] Step S102: Based on the normal plane of the main branch, the tracking data, and each preset radius, generate each concentric circle, wherein the main branch is a tree-like morphological data of a neuron branch selected from the tracking data, and the normal plane is generated based on the center of the cross section of the main branch;

[0038] As an example, in the tracking data, the center of the cross-section of the main branch is used as the center of the circle and each preset radius to generate concentric circles on the normal plane where the main branch is located. Each of the concentric circles contains a cross-section of the tree-like morphological data of each neuron branching in the tracking data, and the normal plane coincides with the cross-section.

[0039] Understandably, by inserting a plane into the tracking data and cutting across each neuron branch, a cross-section containing the cross section of each neuron branch can be obtained. On this cross-section, concentric circles are generated with the center of the main branch's cross section according to preset radius values, and the cross section coincides with the normal plane.

[0040] refer to Figure 4 The figure shows the normal cross-section of a neuron. A neuron is represented as a point on the cross-section. It can be seen that there are several other neurons around a neuron that may interfere with the accuracy of the tracking data.

[0041] Step S103: Determine the target point, where the target point is the point on each concentric circle that emits the brightest fluorescence;

[0042] As an example, the brightness value of each section on each concentric circle is calculated; for each concentric circle, the section with the highest brightness value on the concentric circle is determined as the target point.

[0043] refer to Figure 5 This involves a series of concentric circles centered on the main branch. The maximum brightness value is calculated on each concentric circle, thus obtaining the maximum brightness values ​​of concentric circles with different radii.

[0044] Step S104: Based on the target points and preset radii corresponding to different sections of the main branch, perform data analysis to determine the tree-like morphological data of the neuron branch closest to the main branch as potential error points.

[0045] As an example, a Cartesian coordinate system is generated based on the target points corresponding to different sections of the main branch and the preset radius. The Y-axis of the Cartesian coordinate system is the length of the preset radius, and the X-axis is the length of the tree-like morphological data of the neuron branch. Data analysis is performed based on the Cartesian coordinate system to determine the tree-like morphological data of the neuron branch closest to the main branch, which is taken as a potential error point.

[0046] Understandably, the X-axis represents the length of the tree-like morphological data of neuron branching, or it can be understood as the length of the target point.

[0047] It is possible to calculate the distance from each point on the main bifurcation from the beginning to the end to other neuron bifurcations, thereby determining the closest point of other neuron bifurcations to the main bifurcation, and thus identifying this closest point as a potential error point.

[0048] refer to Figure 6 In a Cartesian coordinate system, the x-coordinate represents the distance from each point along a neuron's bifurcation from one end to the other to the starting point, and the y-coordinate represents the radius of the concentric circles. The color of each point indicates whether that neuron's bifurcation can detect other neuron bifurcations at a fixed normal distance from that point. Other neuron bifurcations are represented by white lines, and the points closest to the main bifurcation are the closest points between other neuron bifurcations and the main bifurcation. The set of these points can be considered the set of potential error points. For example... Figure 6 In the diagram, the white line at the bottom closest to the horizontal axis represents the main bifurcation being tracked. In the area selected by the red box in the diagram, another white line approaches the horizontal axis and then moves away, representing another neuron bifurcation that approaches the main bifurcation being tracked and then moves away. Therefore, the area near the red box can be considered a potential error and submitted for manual analysis.

[0049] Manual review of potential errors: Using the set of potential error points obtained above, the corresponding locations in the tracking data and neuron imaging data are obtained again for another round of manual review to check for labeling errors.

[0050] Manual review complete: The tracking results obtained through review greatly reduce the probability of errors. Multiple reviews can be conducted if the accuracy needs to be improved.

[0051] Please see Figure 7As shown, in one embodiment, a neuron tracking assist device is provided. The device includes: an acquisition module 10, used to acquire tracking data of neurons, wherein the tracking data includes tree-like morphological data of each neuron branching, and each of the tree-like morphological data emits fluorescence;

[0052] The generation module 20 is used to generate concentric circles based on the normal plane of the main branch, the tracking data, and each preset radius. The main branch is a tree-like morphological data of a branching neuron selected from the tracking data, and the normal plane is generated based on the center of the cross section of the main branch.

[0053] The determination module 30 is used to determine the target point, wherein the target point is the point that emits the brightest fluorescence on each concentric circle;

[0054] Analysis module 40 is used to perform data analysis based on the target points and preset radii corresponding to different sections of the main branch, and to determine the tree-like morphological data of the neuron branch closest to the main branch as potential error points.

[0055] Based on the center of the cross-section of the main branch in the tracking data, and with each preset radius, concentric circles are generated on the normal plane. Each of the concentric circles contains a cross-section of the tree-like morphological data of each neuron branching in the tracking data, and the normal plane is parallel to the cross-section.

[0056] Module 30 is used for:

[0057] Calculate the brightness value of each cross section on each concentric circle;

[0058] For each concentric circle, the section with the highest brightness value on the concentric circle is determined as the target point.

[0059] Analysis module 40 is used for:

[0060] Based on the preset radius and the target points corresponding to the different sections of the main branch, a Cartesian coordinate system is generated, wherein the Y-axis of the Cartesian coordinate system is the length of the preset radius, and the X-axis is the length of the tree-like data of the neuron branching.

[0061] Data analysis is performed based on the Cartesian coordinate system to determine the tree-like morphological data of the neuron branch closest to the main branch, which is used as a potential error point.

[0062] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile and / or volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with external clients via a network connection. When the computer program is executed by the processor, it implements the functions or steps of a neuron tracking-assisted method on the server side.

[0063] In one embodiment, a computer device is provided, which may be a client, and its internal structure diagram may be as follows: Figure 9 As shown, the computer device includes a processor, memory, network interface, display screen, and input devices connected via a system bus. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The network interface is used to communicate with an external server via a network connection. When executed by the processor, the computer program implements the functions or steps on the client side of a neuron tracking assistive method.

[0064] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, performs the following steps:

[0065] Acquire tracking data of neurons, wherein the tracking data includes tree-like morphological data of each neuron branching, and each of the tree-like morphological data emits fluorescence;

[0066] Based on the normal plane of the main branch, the tracking data, and each preset radius, each concentric circle is generated. The main branch is a tree-like morphological data of a branching neuron selected from the tracking data, and the normal plane is generated based on the center of the cross section of the main branch.

[0067] Identify target points, wherein the target point is the point on each concentric circle that emits the brightest fluorescence;

[0068] Data analysis is performed on each target point and preset radius corresponding to different sections of the main branch to determine the tree-like morphological data of the neuron branch closest to the main branch, which is used as a potential error point.

[0069] This invention can utilize neuron tracking data to identify other neuron branches that are relatively close to each main branch through the projection of the maximum value of concentric circles, thereby obtaining content that may have labeling errors, i.e. potential error points. The range of possible errors selected is then handed over to manual review, thereby effectively reducing the manual cost required for review.

[0070] In one embodiment, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program that, when executed by a processor, performs the following steps:

[0071] Acquire tracking data of neurons, wherein the tracking data includes tree-like morphological data of each neuron branching, and each of the tree-like morphological data emits fluorescence;

[0072] Based on the normal plane of the main branch, the tracking data, and each preset radius, each concentric circle is generated. The main branch is a tree-like morphological data of a branching neuron selected from the tracking data, and the normal plane is generated based on the center of the cross section of the main branch.

[0073] Identify target points, wherein the target point is the point on each concentric circle that emits the brightest fluorescence;

[0074] Data analysis is performed on each target point and preset radius corresponding to different sections of the main branch to determine the tree-like morphological data of the neuron branch closest to the main branch, which is used as a potential error point.

[0075] This invention can utilize neuron tracking data to identify other neuron branches that are relatively close to each main branch through the projection of the maximum value of concentric circles, thereby obtaining content that may have labeling errors, i.e. potential error points. The range of possible errors selected is then handed over to manual review, thereby effectively reducing the manual cost required for review.

[0076] It should be noted that the functions or steps that can be implemented by the computer-readable storage medium or computer device described above can be referred to the relevant descriptions on the server side and client side in the foregoing method embodiments. To avoid repetition, they will not be described one by one here.

[0077] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAM bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0078] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is used as an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0079] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included within the protection scope of the present invention.

Claims

1. A neuron tracking assistance method, characterized in that, The neuron tracking assistance method includes: Acquire tracking data of neurons, wherein the tracking data includes tree-like morphological data of each neuron branching, and each of the tree-like morphological data emits fluorescence; Based on the normal plane of the main branch, the tracking data, and each preset radius, each concentric circle is generated. The main branch is a tree-like morphological data of a branching neuron selected from the tracking data, and the normal plane is generated based on the center of the cross section of the main branch. Identify target points, wherein the target point is the point on each concentric circle that emits the brightest fluorescence; Data analysis is performed on each target point and preset radius corresponding to different sections of the main branch to determine the tree-like morphological data of the neuron branch closest to the main branch, which is used as a potential error point.

2. The neuron tracking assistance method according to claim 1, characterized in that, The step of generating each concentric circle based on the normal plane of the main branch, the tracking data, and each preset radius includes: Based on the center of the cross-section of the main branch in the tracking data, and with each preset radius, concentric circles are generated on the normal plane. Each of the concentric circles contains a cross-section of the tree-like morphological data of each neuron branching in the tracking data, and the normal plane is parallel to the cross-section.

3. The neuron tracking assistance method according to claim 2, characterized in that, The steps for determining the target point include: Calculate the brightness value of each cross section on each concentric circle; For each concentric circle, the section with the highest brightness value on the concentric circle is determined as the target point.

4. The neuron tracking assistance method according to claim 3, characterized in that, The step of analyzing data based on target points and preset radii corresponding to different sections of the main branch to determine the tree-like morphological data of the neuron branch closest to the main branch as potential error points includes: Based on the preset radius and the target points corresponding to the different sections of the main branch, a Cartesian coordinate system is generated, wherein the Y-axis of the Cartesian coordinate system is the length of the preset radius, and the X-axis is the length of the tree-like data of the neuron branching. Data analysis is performed based on the Cartesian coordinate system to determine the tree-like morphological data of the neuron branch closest to the main branch, which is used as a potential error point.

5. A neuron tracking assistive device, characterized in that, The neuron tracking assist device includes: The acquisition module is used to acquire tracking data of neurons, wherein the tracking data includes tree-like morphological data of the branching of each neuron, and each of the tree-like morphological data emits fluorescence; The generation module is used to generate concentric circles based on the normal plane of the main branch, the tracking data, and each preset radius. The main branch is a tree-like morphological data of a branching neuron selected from the tracking data, and the normal plane is generated based on the center of the cross section of the main branch. A determination module is used to determine a target point, wherein the target point is the point on each concentric circle that emits the brightest fluorescence; The analysis module is used to perform data analysis based on the target points and preset radii corresponding to different sections of the main branch, and to determine the tree-like morphological data of the neuron branch closest to the main branch as potential error points.

6. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the neuron tracking assistance method as described in any one of claims 1 to 4.

7. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the neuron tracking assistance method as described in any one of claims 1 to 4.

Images