Bronchial tree model completion method, device and non-volatile storage medium

Abstract

The present application discloses a bronchial tree model completion method, device and non-volatile storage medium. The method includes: determining a first bronchial tree model, wherein the first bronchial tree model is a model to be completed constructed based on electronic computed tomography data; determining a first target point, and determining a second target point in the first bronchial tree model, wherein the first target point is a point outside the first bronchial tree model, and the second target point is the point on the first bronchial tree model that is closest to the first target point; determining a target center point corresponding to the second target point; completing the first bronchial tree model based on the first target point and the target center point to obtain a second bronchial tree model. The present application solves the technical problem of being unable to accurately determine the patient's bronchial tree structure due to the incomplete bronchial branching structure of the bronchial tree model generated in the related art.

Description

Technical Field

[0001] The present application relates to the field of image processing, and more specifically, to a method, device, and non-volatile storage medium for completing a bronchial tree model. Background Art

[0002] Currently, when generating bronchial tree models, interference from the patient's own breathing or lung physiological structure may occur during the CT equipment's data acquisition process, resulting in incomplete bronchial branching structures in the bronchial tree models generated in related technologies. This makes it impossible to accurately determine the patient's bronchial tree structure, affecting subsequent treatment.

[0003] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0004] Embodiments of the present application provide a bronchial tree model completion method, apparatus, and non-volatile storage medium to at least address the technical problem of being unable to accurately determine a patient's bronchial tree structure due to incomplete bronchial branching structures in bronchial tree models generated in related technologies.

[0005] According to one aspect of an embodiment of the present application, a bronchial tree model completion method is provided, comprising: determining a first bronchial tree model, wherein the first bronchial tree model is a model to be completed constructed based on electronic computed tomography data; determining a first target point, and determining a second target point in the first bronchial tree model, wherein the first target point is a point located outside the first bronchial tree model, and the second target point is a point on the first bronchial tree model that is closest to the first target point; determining a target center point corresponding to the second target point, wherein the target center point is a point on a centerline of a target bronchial branch that is shortest to the first target point, and the second target point is located on the target bronchial branch; and completing the first bronchial tree model based on the first target point and the target center point to obtain a second bronchial tree model.

[0006] Optionally, the step of determining the first target point includes: displaying an image section corresponding to the first bronchial tree model to the target object; and determining the first target point in the image section in response to a first operation instruction of the target object.

[0007] Optionally, the step of determining the first target point includes: using a first neural network model to analyze the first bronchial tree model to obtain the first target point, wherein the first neural network model is a neural network model obtained after training with a first training data set, and the training samples in the first training data set include several first sample bronchial tree models, and each bronchial branch contained in the first sample bronchial tree model is marked with a sample point.

[0008] Optionally, the step of completing the first bronchial tree model based on the first target point and the target center point to obtain the second bronchial tree model includes: determining a connection path of a connection line between the first target point and the target center point; connecting the first target point and the target center point according to the connection path to obtain a target connection line; and rendering the target connection line to obtain the second bronchial tree model.

[0009] Optionally, the step of determining the connection path of the connection line between the first target point and the target center point includes: determining the connection path in response to a second operation instruction of the target object; or determining the connection path based on the shape of the target bronchial branch.

[0010] Optionally, it also includes: responding to a third operation instruction of the target object to determine at least one third target point; determining the distance between each of the at least one third target point and the first target point; and connecting the first target point and at least one third target point in order of distance from near to far to obtain an extended target connection line.

[0011] Optionally, the bronchial tree model completion method further includes: processing the target connecting line using a second neural network model to obtain an extended target connecting line, wherein the second neural network model is a neural network model trained by a second training data set, the training samples in the second training data set include a second sample bronchial tree model, and the second sample bronchial tree model is marked with the length of each bronchial branch contained therein; obtaining the extended target connecting line output by the second neural network model.

[0012] Optionally, the step of rendering the target connection line to obtain the second bronchial tree model includes: determining a target center on the target connection line; determining a target circle corresponding to the target center; and smoothly connecting adjacent target circles to obtain the second bronchial model.

[0013] Optionally, the step of determining a target circle corresponding to the target center includes: determining a fourth target point based on the electronic computed tomography data and the target center, wherein the fourth target point and the target center have the same HU value in the electronic computed tomography data; when the number of fourth target points is greater than a preset number threshold, determining a target connected domain formed by the fourth target points; determining an average distance between the peripheral points of the target connected domain and the target center, and determining the average distance as the radius of the target circle; and determining the target circle based on the radius and the target center.

[0014] According to another aspect of an embodiment of the present application, a bronchial tree model completion device is also provided, including: a first processing module, used to determine a first bronchial tree model, wherein the first bronchial tree model is a model to be completed constructed based on electronic computed tomography data; a second processing module, used to determine a first target point, and to determine a second target point in the first bronchial tree model, wherein the first target point is a point outside the first bronchial tree model, and the second target point is a point on the first bronchial tree model that is closest to the first target point; a third processing module, used to determine a target center point corresponding to the second target point, wherein the target center point is the point on the centerline of the target bronchial branch that is shortest to the first target point, and the second target point is located on the target bronchial branch; a fourth processing module, used to complete the first bronchial tree model based on the first target point and the target center point to obtain a second bronchial tree model.

[0015] According to another aspect of an embodiment of the present application, a bronchial tree completion device is also provided, including a scanning device, a processor, and an interaction module, wherein the scanning device is used to scan a target organ and obtain electronic computed tomography data of the target organ; the processor is used to determine a first bronchial tree model, wherein the first bronchial tree model is a model to be completed constructed based on the electronic computed tomography data; determine a first target point, and determine a second target point in the first bronchial tree model, wherein the first target point is a point outside the first bronchial tree model, and the second target point is a point on the first bronchial tree model that is closest to the first target point; determine a target center point corresponding to the second target point, wherein the target center point is the point on the centerline of the target bronchial branch that is shortest to the first target point, and the second target point is located on the target bronchial branch; complete the first bronchial tree model based on the first target point and the target center point to obtain the second bronchial tree model; the interaction module is used to display the first bronchial tree model, the second bronchial tree model, and receive operation instructions of the target object.

[0016] According to another aspect of an embodiment of the present application, a non-volatile storage medium is provided, in which a program is stored. When the program is running, the device where the non-volatile storage medium is located is controlled to execute the bronchial tree model completion method.

[0017] According to another aspect of an embodiment of the present application, an electronic device is provided, including: a memory and a processor, wherein the processor is configured to run a program stored in the memory, wherein the program executes a bronchial tree model completion method when the program is run.

[0018] In an embodiment of the present application, a first bronchial tree model is determined, wherein the first bronchial tree model is a model to be completed constructed based on electronic computed tomography data; a first target point is determined, and a second target point is determined in the first bronchial tree model, wherein the first target point is a point located outside the first bronchial tree model, and the second target point is a point on the first bronchial tree model that is closest to the first target point; a target center point corresponding to the second target point is determined, wherein the target center point is a point on the centerline of a target bronchial branch that is shortest to the first target point, and the second target point is located on the target bronchial branch; the first bronchial tree model is completed based on the first target point and the target center point to obtain the second bronchial tree model. By completing the first bronchial tree model, the purpose of obtaining a complete bronchial tree model is achieved, thereby achieving the technical effect of accurately determining the patient's bronchial tree structure, and further solving the technical problem of being unable to accurately determine the patient's bronchial tree structure due to the incomplete bronchial branch structure of the bronchial tree model generated in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0020] Figure 1 is a schematic structural diagram of an optional computer terminal according to an embodiment of the present application;

[0021] Figure 2 is a structural diagram of a bronchial tree model completion method according to an embodiment of the present application;

[0022] Figure 3 is a schematic diagram of a target point and a target connection line according to an embodiment of the present application;

[0023] Figure 4 is a schematic diagram of a second bronchial tree model according to an embodiment of the present application;

[0024] Figure 5 Schematic diagram of the structure of a bronchial tree model completion device according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of this application.

[0026] 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 sequential order. 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 a sequence other than those illustrated or described herein. In addition, the terms "including" and "having" 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.

[0027] In related technologies, when CT equipment scans a patient's bronchial tree to acquire CT data, interference from the patient's breathing or lung structure can cause errors in the CT data. This can lead to incomplete or disconnected bronchial branch structures in the bronchial tree model generated from the CT data. To address this issue, the present application provides a solution, which is described in detail below.

[0028] According to an embodiment of the present application, a method embodiment of a bronchial tree model completion method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0029] The method embodiments provided in the embodiments of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG1 shows a hardware structure block diagram of a computer terminal (or mobile device) for implementing a bronchial tree model completion method. Figure 1 As shown, the computer terminal 10 (or mobile device 10) may include one or more (illustrated as 102a, 102b, ..., 102n) processors 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data, and a transmission module 106 for communication functions. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It will be understood by those skilled in the art that Figure 1The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0030] It should be noted that the one or more processors 102 and / or other data processing circuits described above may generally be referred to herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuitry may be a single independent processing module, or may be incorporated in whole or in part into any of the other components of the computer terminal 10 (or mobile device). As described in the embodiments of the present application, the data processing circuitry serves as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).

[0031] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the bronchial tree model completion method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, implementing the bronchial tree model completion method of the above-mentioned application. The memory 104 may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely located relative to the processor 102, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0032] The transmission device 106 is configured to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by the communications provider of the computer terminal 10. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is configured to communicate with the Internet wirelessly.

[0033] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 (or mobile device).

[0034] In the above operating environment, the embodiment of the present application provides a bronchial tree model completion method, such as Figure 2 As shown, the method includes the following steps:

[0035] Step S202, determining a first bronchial tree model, wherein the first bronchial tree model is a model to be completed constructed based on electronic computed tomography data;

[0036] In the technical solution provided in step S202, the computed tomography data may also be referred to as CT data. After the CT data of the patient is acquired by a CT device, a first bronchial tree model may be constructed based on the acquired CT data.

[0037] As an optional implementation, the corresponding first bronchial tree model may be obtained by performing three-dimensional construction using CT data obtained from other equipment.

[0038] Step S204, determining a first target point and a second target point in the first bronchial tree model, wherein the first target point is a point outside the first bronchial tree model, and the second target point is a point on the first bronchial tree model that is closest to the first target point;

[0039] In the technical solution provided in step S204, the first target point can be any point near the first bronchial tree model. When determining the first target point, the target subject can select the first target point themselves, or the first target point can be determined by a trained convolutional neural network model. The target subject can be a relevant operator.

[0040] As an optional implementation, when the target object selects the first target point by itself, the image section corresponding to the first bronchial tree model can be displayed to the target object first, and then the first operation instruction of the target object can be responded to, so as to determine the first target point in the image section.

[0041] Specifically, the image slice can be any 2D slice of the first bronchial tree model. In actual operation, the target user can use an interactive device to issue interactive commands to view slices at any angle near the first bronchial tree model. After determining the appropriate slice, the target user can select the first target point within the slice. It should be noted that the slice will display the distribution of lung tissue and blood vessels within the bronchial tree, facilitating the target user's judgment and selection of the appropriate first target point.

[0042] Optionally, when displaying the slices to the target object, it is also possible to choose to display a preferred slice to the target object first, wherein the preferred slice is the slice that is most likely to contain the first target point, determined based on the collected data.

[0043] As an optional implementation, when a convolutional neural network model is used to determine the first target point, the first neural network model can be used to analyze the first bronchial tree model to obtain the first target point, wherein the first neural network model is a neural network model obtained after training with a first training data set, and the training samples in the first training data set include several first sample bronchial tree models, and each bronchial branch contained in the first sample bronchial tree model is marked with a sample point.

[0044] Specifically, when training the first neural network model, a large number of lung CT data of different patients can be obtained clinically, and different 3D virtual bronchial trees can be reconstructed based on the patients' lung CT data. The 3D virtual bronchial trees obtained clinically can then be used as training samples. The 3D virtual bronchial tree of each training sample is marked with a number of sample points at preset intervals. The training samples can be used to train the first neural network model, and the Adam optimizer can be used for optimization to continuously adjust the parameters of the first neural network model until convergence. After obtaining the trained first neural network model, the 3D virtual bronchial tree of any patient can be input into the trained first neural network model to obtain a number of first target points that need to be completed in the bronchial tree output by the first neural network model.

[0045] In some embodiments of the present application, when determining the second target point, the target area can be determined with the first target point as the reference point, and then the Euclidean distance from each point on the bronchial tree in the target area to the first target point is calculated to determine the second target point that is closest.

[0046] As an optional implementation, the target area can be a sphere centered around the first target point. The radius of this spherical area can be adjusted by the target subject or set based on historical data. When setting the radius of the spherical area, it is necessary to ensure that there is overlap between the spherical area and the bronchial tree. The bronchial tree in the target area refers to the portion of the bronchial tree that overlaps with the target area. By determining the target area and then determining the search range for the second target point based on the overlap between the target area and the bronchial tree, the search range for the second target point can be effectively narrowed, thereby increasing the speed of determining the second target point.

[0047] It should be noted that, in the embodiment of the present application, the first target point and the second target point are both voxel points.

[0048] Step S206, determining a target center point corresponding to the second target point, wherein the target center point is the point on the center line of the target bronchial branch that is closest to the first target point, and the second target point is located on the target bronchial branch;

[0049] In the technical solution provided in step S206, after determining the second target point, a centerline can be determined based on the bronchial branch where the second target point is located, and then the target center point can be determined on the centerline. The centerline is the axis of the bronchial branch where the second target point is located. When determining the target center point, the Euclidean distance from all voxel points that make up the centerline to the first target point can be calculated, and the point with the closest distance can be determined as the target center point.

[0050] Step S208 : completing the first bronchial tree model based on the first target point and the target center point to obtain a second bronchial tree model.

[0051] In the solution provided in step S208, when completing the first bronchial tree model based on the first target point and the target center point, the connection path of the connection line between the first target point and the target center point is first determined; then, the first target point and the target center point are connected according to the connection path to obtain the target connection line; finally, the target connection line is rendered to obtain the second bronchial tree model.

[0052] It should be noted that when the first target point and the target center point are connected according to the connection path to obtain the target connection line, you can choose to connect from the first target point to the target center point, or you can choose to connect from the target center point to the first target point.

[0053] Specifically, when determining the connection path of the connecting line between the first target point and the target center point, the specific connection path can be determined by the target object, or it can be determined by the electronic device that executes the bronchial tree model completion method provided in the embodiment of the present application. When determined by the target object, a second operation instruction of the target object can be received and responded to, and a connection path corresponding to the second operation instruction can be generated. When the connection path is generated by the electronic device, the electronic device can determine the connection path based on the shape of the bronchial branch where the target center point is located. It should be noted that the connection path can be a straight line, a curve, or a combination of a straight line and a curve.

[0054] Specifically, when determining a connection path based on the shape of a bronchial branch, the first bronchial tree model labeled with a first target point and a target center point can be input into a third neural network model, and the target connection line output by the third neural network model is obtained. The third neural network model is a convolutional neural network model trained using a third training dataset, and the training samples in the third training dataset include third sample bronchial tree models labeled with connection lines corresponding to each bronchial branch included. The third neural network model can determine the shape characteristics of the target connection line based on the shape characteristics of the target bronchial branch where the target center point is located, including determining the curvature of each point on the target connection line.

[0055] In some embodiments of the present application, Figure 3 As shown, after the target connection line L1 is determined, it is necessary to determine whether the target connection line needs to be extended. After it is determined that extension is necessary, the target object can automatically determine at least one third target point in the section and determine the connection trajectory between the at least one third target point and the target connection line, thereby completing the extension of the target connection line.

[0056] Optionally, after the target object determines at least one third target point, the electronic device can also autonomously extend the target connection line based on the at least one third target point. Specifically, first, in response to the target object's third operation instruction, at least one third target point is determined; the distance between each of the at least one third target point and the first target point is determined; the first target point and the at least one third target point are sequentially connected in order of the distances from closest to farthest to obtain an extended target connection line; and the extended target connection line is determined as the target connection line. For example, assuming that in response to the target object's third operation instruction, three third target points are determined, and the distances between the three third target points and the first target point are arranged in order from closest to farthest as follows: third target point 1, third target point 2, third target point 3; then, the first target point and third target point 1, third target point 1 and third target point 2, and third target point 2 and third target point 3 can be sequentially connected to extend the target connection line.

[0057] When connecting the first target point and the at least one third target point, the connection trajectory between any two points can be determined by the target object itself, or it can be determined by the electronic device through the third neural network model according to the bronchial branch corresponding to the target connection line.

[0058] As an optional implementation, the electronic device can also completely independently determine whether the target connection line needs to be extended, and if so, automatically extend the target connection line. Specifically, the electronic device can process the target connection line using a second neural network model to obtain an extended target connection line, wherein the second neural network model is a neural network model trained using a second training data set, the training samples in the second training data set including a second sample bronchial tree model, and the second sample bronchial tree model is labeled with the lengths of the individual bronchial branches contained therein; obtain the extended target connection line output by the second neural network model; and determine that the extended target connection line is the target connection line.

[0059] Specifically, a large number of lung CT data of different patients can be obtained clinically, and different 3D virtual bronchial trees can be reconstructed based on the patients' lung CT data. Then, the 3D virtual bronchial trees obtained clinically can be used as training samples, and each bronchial branch contained in the 3D virtual bronchial tree of each training sample is marked with corresponding length information, wherein the 3D virtual bronchial tree of each training sample is the above-mentioned second sample bronchial tree model. The training samples can be used to train the judgment model, and the Adam optimizer can be used for optimization, and the parameters of the judgment model are continuously adjusted until convergence, so as to obtain the trained judgment model (that is, the second neural network model). Subsequently, the 3D virtual bronchial tree of any patient containing the connecting line can be input into the trained judgment model, and the judgment model can determine whether the connecting line needs to be extended and the distance and path to be extended.

[0060] In some embodiments of the present application, after obtaining the target connection line, the target connection line needs to be rendered to obtain the second bronchial tree model. Specifically, during rendering, the target center needs to be determined on the target connection line; a target circle corresponding to the target center needs to be determined; and adjacent target circles need to be smoothly connected to obtain the second bronchial model.

[0061] The number of target circle centers can be multiple. For example, each voxel point on the target connection line can be used as the target circle center. Of course, some voxel points on the target connection line can also be selected as the target circle center, and this specification does not limit this.

[0062] After determining the target center, when determining the target circle corresponding to the target center, it is first necessary to determine the fourth target point based on the electronic computed tomography data and the target center, wherein the fourth target point and the corresponding target center have the same HU value in the electronic computed tomography data; then, when the number of fourth target points is greater than a preset number threshold, determine the target connected domain formed by the fourth target points; secondly, determine the average distance between the peripheral points of the target connected domain and the target center, and determine the average distance as the radius of the target circle; finally, determine the target circle based on the radius and the target center.

[0063] Specifically, after determining the target circle center, voxel points with the same HU value around the center line of the completed bronchial tree can be determined in the CT data. When the number of determined voxel points reaches a threshold, a connected domain consisting of voxel points with the same HU value is obtained, and the average distance from the outermost point in the connected domain to the center line of the completed bronchial tree is calculated. This average distance is the radius. Finally, discrete circles with different center points are obtained, and the discrete circles are smoothly connected to prevent the sudden increase / decrease of the radius, thereby obtaining the following: Figure 4The second bronchial tree model is shown. It should be noted that the completed bronchial tree centerline is the target connection line.

[0064] The HU value can be used to measure the degree of X-ray absorption by different tissues, and voxel points with the same HU value can be considered to correspond to the same organ tissue.

[0065] Through the above steps, it is possible to determine a first bronchial tree model, wherein the first bronchial tree model is a model to be completed constructed based on electronic computed tomography data; determine a first target point, and determine a second target point in the first bronchial tree model, wherein the first target point is a point located outside the first bronchial tree model, and the second target point is a point on the first bronchial tree model that is closest to the first target point; determine a target center point corresponding to the second target point, wherein the target center point is the point on the centerline of the bronchial branch where the second target point is located that is shortest to the first target point; complete the first bronchial tree model based on the first target point and the target center point to obtain the second bronchial tree model, and by completing the first bronchial tree model, the purpose of obtaining a complete bronchial tree model is achieved, thereby achieving the technical effect of accurately determining the patient's bronchial tree structure, and further solving the technical problem of being unable to accurately determine the patient's bronchial tree structure due to the incomplete bronchial branch structure of the bronchial tree model generated in the related art.

[0066] The present application embodiment provides a bronchial tree model completion device, such as Figure 5 As shown, the device includes: a first processing module 50, used to determine a first bronchial tree model, wherein the first bronchial tree model is a model to be completed constructed based on electronic computed tomography data; a second processing module 52, used to determine a first target point and a second target point in the first bronchial tree model, wherein the first target point is a point outside the first bronchial tree model, and the second target point is a point on the first bronchial tree model that is closest to the first target point; a third processing module 54, used to determine a target center point corresponding to the second target point, wherein the target center point is a point on the centerline of the bronchial branch where the second target point is located that is shortest to the first target point; and a fourth processing module 56, used to complete the first bronchial tree model based on the first target point and the target center point to obtain a second bronchial tree model.

[0067] In some embodiments of the present application, the step of the second processing module 52 determining the first target point includes: displaying the image section corresponding to the first bronchial tree model to the target object; and determining the first target point in the image section in response to the first operation instruction of the target object.

[0068] In some embodiments of the present application, the step of determining the first target point by the second processing module 52 includes: analyzing the first bronchial tree model using a first neural network model to obtain the first target point, wherein the first neural network model is a neural network model obtained after training with a first training data set, and the training samples in the first training data set include the bronchial tree model to be completed marked with the first target point.

[0069] In some embodiments of the present application, the fourth processing module 56 completes the first bronchial tree model based on the first target point and the target center point to obtain the second bronchial tree model, including the following steps: determining a connection path of a connection line between the first target point and the target center point; connecting the first target point and the target center point according to the connection path to obtain a target connection line; and rendering the target connection line to obtain the second bronchial tree model.

[0070] In some embodiments of the present application, the step of the fourth processing module 56 determining the connection path of the connecting line between the first target point and the target center point includes: determining the connection path in response to the second operation instruction of the target object; or determining the connection path based on the shape of the target bronchial branch.

[0071] In some embodiments of the present application, after obtaining the target connection line, the fourth processing module 56 is also used to: respond to the third operation instruction of the target object to determine at least one second target point; determine the distance between each of the at least one second target point and the first target point; and connect the first target point and at least one second target point in order of distance from near to far to obtain an extended target connection line.

[0072] In some embodiments of the present application, after obtaining the target connecting line, the fourth processing module 56 is further used to process the target connecting line using a second neural network model to obtain an extended target connecting line, wherein the second neural network model is a neural network model obtained by training through a second training data set, and the training samples in the second training data set include a bronchial tree model to be completed marked with connecting lines and connecting line distances; and obtain the extended target connecting line output by the second neural network model.

[0073] In some embodiments of the present application, the fourth processing module 56 renders the target connection line, and the steps of obtaining the second bronchial tree model include: determining the target center on the target connection line; determining the target circle corresponding to the target center; and smoothly connecting adjacent target circles to obtain the second bronchial model.

[0074] In some embodiments of the present application, the step of the fourth processing module 56 determining the target circle corresponding to the target circle center includes: determining a fourth target point based on the electronic computed tomography data and the target circle center, wherein the fourth target point and the target circle center have the same HU value in the electronic computed tomography data; when the number of fourth target points is greater than a preset number threshold, determining a target connected domain formed by the fourth target points; determining the average distance between the peripheral points of the target connected domain and the target circle center, and determining the average distance as the radius of the target circle; and determining the target circle based on the radius and the target circle center.

[0075] It should be noted that the various modules in the above-mentioned bronchial tree model completion device can be program modules (for example, a set of program instructions that implement a certain specific function) or hardware modules. For the latter, it can be expressed in the following forms, but is not limited to this: the expression form of each of the above-mentioned modules is a processor, or the functions of each of the above-mentioned modules are implemented by a processor.

[0076] In some embodiments of the present application, a bronchial tree model completion device is also provided, including a scanning device, a processor, and an interaction module, wherein the scanning device is used to scan a target organ and obtain electronic computed tomography data of the target organ; the processor is used to determine a first bronchial tree model, wherein the first bronchial tree model is a model to be completed constructed based on the electronic computed tomography data; determine a first target point, and determine a second target point in the first bronchial tree model, wherein the first target point is a point outside the first bronchial tree model, and the second target point is a point on the first bronchial tree model that is closest to the first target point; determine a target center point corresponding to the second target point, wherein the target center point is the point on the centerline of the target bronchial branch that is shortest to the first target point, and the second target point is located on the target bronchial branch; complete the first bronchial tree model based on the first target point and the target center point to obtain the second bronchial tree model; and the interaction module is used to display the first bronchial tree model, the second bronchial tree model, and receive operation instructions of the target object.

[0077] It should be noted that the above-mentioned bronchial tree model completion device can be used to perform the following Figure 2 The bronchial tree model completion method shown in Figure 2 The relevant explanations of the method for completing the bronchial tree model shown in are also applicable to the embodiments of the present application and will not be repeated here.

[0078] In some embodiments of the present application, a non-volatile storage medium is further provided. The non-volatile storage medium stores a program, wherein when the program is executed, the device where the non-volatile storage medium is located is controlled to execute the following bronchial tree model completion method: determining a first bronchial tree model, wherein the first bronchial tree model is a model to be completed constructed based on electronic computed tomography data; determining a first target point, and determining a second target point in the first bronchial tree model, wherein the first target point is a point outside the first bronchial tree model, and the second target point is a point on the first bronchial tree model that is closest to the first target point; determining a target center point corresponding to the second target point, wherein the target center point is a point on the centerline of a target bronchial branch that is shortest to the first target point, and the second target point is located on the target bronchial branch; completing the first bronchial tree model based on the first target point and the target center point to obtain a second bronchial tree model.

[0079] In some embodiments of the present application, an electronic device is also provided, including a memory and a processor, the processor being used to run a program stored in the memory, wherein the following bronchial tree completion method is executed when the program is run: determining a first bronchial tree model, wherein the first bronchial tree model is a model to be completed constructed based on electronic computed tomography data; determining a first target point, and determining a second target point in the first bronchial tree model, wherein the first target point is a point outside the first bronchial tree model, and the second target point is a point on the first bronchial tree model that is closest to the first target point; determining a target center point corresponding to the second target point, wherein the target center point is a point on the centerline of a target bronchial branch that is shortest to the first target point, and the second target point is located on the target bronchial branch; completing the first bronchial tree model based on the first target point and the target center point to obtain a second bronchial tree model.

[0080] The serial numbers of the above embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0081] In the above embodiments of the present application, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0082] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0083] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0084] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0085] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the relevant technology or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0086] The above is only a preferred embodiment of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for completing a bronchial tree model, characterized in that: include: determining a first bronchial tree model, wherein the first bronchial tree model is a model to be completed constructed based on electronic computed tomography data; determining a first target point and determining a second target point in the first bronchial tree model, wherein the first target point is a point outside the first bronchial tree model, and the second target point is a point on the first bronchial tree model that is closest to the first target point; Determining a target center point corresponding to the second target point, wherein the target center point is a point on the centerline of the target bronchial branch that is shortest from the first target point, and the second target point is located on the target bronchial branch; The first bronchial tree model is completed according to the first target point and the target center point to obtain a second bronchial tree model.

2. The bronchial tree model completion method according to claim 1, characterized in that: The step of determining the first target point comprises: presenting an image slice corresponding to the first bronchial tree model to the target subject; In response to a first operation instruction of the target object, the first target point is determined in the image slice.

3. The bronchial tree model completion method according to claim 1, characterized in that: The step of determining the first target point comprises: The first bronchial tree model is analyzed using a first neural network model to obtain the first target point, wherein the first neural network model is a neural network model obtained by training with a first training data set, the training samples in the first training data set include several first sample bronchial tree models, and each bronchial branch contained in the first sample bronchial tree model is marked with a sample point.

4. The bronchial tree model completion method according to claim 1, characterized in that: The step of completing the first bronchial tree model based on the first target point and the target center point to obtain a second bronchial tree model includes: Determining a connection path of a connecting line between the first target point and the target center point; Connecting the first target point and the target center point according to the connection path to obtain a target connection line; The target connection line is rendered to obtain the second bronchial tree model.

5. The bronchial tree model completion method according to claim 4, characterized in that: The step of determining a connection path of a connection line between the first target point and the target center point comprises: In response to a second operation instruction of the target object, determining the connection path; or, The connection path is determined according to the shape of the target bronchial branch.

6. The bronchial tree model completion method according to claim 4, characterized in that: The bronchial tree model completion method further includes: In response to a third operation instruction of the target object, determining at least one third target point; determining a distance between each of the at least one third target point and the first target point; The first target point and the at least one third target point are sequentially connected in the order of the distance from near to far to obtain the extended target connection line.

7. The bronchial tree model completion method according to claim 4, characterized in that: The bronchial tree model completion method further includes: processing the target connecting line using a second neural network model to obtain an extended target connecting line, wherein the second neural network model is a neural network model trained using a second training data set, the training samples in the second training data set include a second sample bronchial tree model, and the second sample bronchial tree model is marked with the length of each bronchial branch contained therein; Obtain the extended target connecting line output by the second neural network model.

8. The bronchial tree model completion method according to claim 4, characterized in that: The step of rendering the target connection line to obtain the second bronchial tree model includes: Determine the target center on the target connecting line; determining a target circle corresponding to the target circle center; The adjacent target circles are smoothly connected to obtain the second bronchus model.

9. The method for completing the bronchial tree model according to claim 8, characterized in that: The step of determining a target circle corresponding to the target circle center comprises: determining a fourth target point based on the CT data and the target circle center, wherein the fourth target point and the target circle center have the same HU value in the CT data; When the number of the fourth target points is greater than a preset number threshold, determining a target connected domain formed by the fourth target points; Determine an average distance between the peripheral points of the target connected domain and the center of the target circle, and determine the average distance as the radius of the target circle; The target circle is determined according to the radius and the target circle center.

10. A bronchial tree model completion device, characterized in that: include: a first processing module, configured to determine a first bronchial tree model, wherein the first bronchial tree model is a model to be completed constructed based on electronic computed tomography data; a second processing module, configured to determine a first target point and a second target point in the first bronchial tree model, wherein the first target point is a point outside the first bronchial tree model, and the second target point is a point on the first bronchial tree model that is closest to the first target point; a third processing module, configured to determine a target center point corresponding to the second target point, wherein the target center point is a point on a centerline of a target bronchial branch that is shortest from the first target point, and the second target point is located on the target bronchial branch; The fourth processing module is configured to complete the first bronchial tree model according to the first target point and the target center point to obtain a second bronchial tree model.

11. A bronchial tree model completion device, characterized in that: It includes a scanning device, a processor, and an interactive module, wherein: The scanning device is used to scan the target organ and obtain computerized tomography data of the target organ; The processor is configured to determine a first bronchial tree model, wherein the first bronchial tree model is a model to be completed constructed based on electronic computed tomography data; determine a first target point, and determine a second target point in the first bronchial tree model, wherein the first target point is a point located outside the first bronchial tree model, and the second target point is a point on the first bronchial tree model that is closest to the first target point; determine a target center point corresponding to the second target point, wherein the target center point is a point on a centerline of a target bronchial branch that is shortest to the first target point, and the second target point is located on the target bronchial branch; and complete the first bronchial tree model based on the first target point and the target center point to obtain a second bronchial tree model; The interaction module is used to display the first bronchial tree model, the second bronchial tree model, and receive operation instructions from the target object.

12. A non-volatile storage medium, characterized in that: The non-volatile storage medium stores a program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute the bronchial tree model completion method according to any one of claims 1 to 9.

13. An electronic device, characterized in that: include: A memory and a processor, wherein the processor is configured to run a program stored in the memory, wherein the program, when running, executes the bronchial tree model completion method according to any one of claims 1 to 9.

Images