Endoscope-assisted bronchoscopic navigation method, system, medium, and electronic device

Abstract

The application provides an endoscope-assisted bronchoscopy navigation method, system, medium and electronic equipment. The method comprises the following steps: acquiring a three-dimensional scanning image to establish a three-dimensional virtual bronchial model and plan a navigation path; selecting a target point and an activation point; generating a virtual endoscope image group in the three-dimensional virtual bronchial model at the initial activation point, and generating a target endoscope image in the bronchus; selecting an optimal virtual endoscope image in the virtual endoscope image group; registering and fusing the target endoscope image and the optimal virtual endoscope image, and transforming the three-dimensional virtual model to navigate the endoscope; generating the target endoscope image and obtaining the optimal virtual endoscope image at each activation point, and registering and fusing the target endoscope image and the optimal virtual endoscope image to navigate the endoscope until the target point is reached. The method can establish the correlation between the three-dimensional CT image and the real endoscope image, thereby assisting in determining the navigation path to control the diagnosis and treatment instrument to navigate more accurately.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical instrument navigation, and particularly relates to an endoscope-assisted bronchoscopic intraoperative navigation method, system, medium and electronic device. BACKGROUND

[0002] Lung nodule biopsy based on an endoscope is an important means of lung cancer screening. Before endoscopy, a doctor first performs three-dimensional computed tomography (CT) on a patient to obtain the shape and position of lung and bronchial tissues and the shape and position of lung nodules. Then, in the process of endoscopy, the doctor navigates the endoscope to the desired lung nodule position.

[0003] However, in the navigation process of operating the endoscope, the doctor has no actual position correlation between the three-dimensional CT image and the real endoscope image. The doctor's navigation process of operating the endoscope is actually a blind test. This blind test is highly dependent on the doctor's experience and endoscope operation technology. The uncertainty in the operation process is strong, and the success rate of the operation is limited by the doctor's technical level. Therefore, it is necessary to provide a new bronchoscopic intraoperative navigation method to solve the above problems. SUMMARY

[0004] The present application relates to the technical field of medical instrument navigation, and particularly relates to an endoscope-assisted bronchoscopic intraoperative navigation method, system, medium and electronic device.

[0005] In a first aspect, the endoscope-assisted bronchoscopy navigation method provided by the application comprises: obtaining a three-dimensional scan image of a bronchus, establishing a three-dimensional virtual model of the bronchus according to the three-dimensional scan image, and planning a navigation path according to the three-dimensional virtual model of the bronchus; selecting a target point and N activation points on the navigation path according to a set standard, where N is a positive integer; generating a virtual endoscope image group by performing virtual endoscope rendering at an initial activation point in the three-dimensional virtual model of the bronchus, and generating a target endoscope image by using an endoscope at the initial activation point in the bronchus; comparing the virtual endoscope image group with the target endoscope image, and selecting an optimal virtual endoscope image in the virtual endoscope image group; performing registration and fusion on the target endoscope image and the optimal virtual endoscope image, transforming the three-dimensional virtual model of the bronchus according to a registration matrix to make the three-dimensional virtual model of the bronchus consistent with the bronchus, and navigating the endoscope along the navigation path; performing the generation of the virtual endoscope image group in the three-dimensional virtual model of the bronchus and the generation of the target endoscope image in the bronchus at each activation point, selecting an optimal virtual endoscope image in the virtual endoscope image group, performing registration and fusion on the target endoscope image and the optimal virtual endoscope image generated at the same activation point, and navigating the endoscope according to the registration matrix, until the endoscope reaches the target point to complete the navigation.

[0006] The endoscope-assisted bronchoscopy navigation method provided by the application has the beneficial effects that: based on the three-dimensional reconstruction of the bronchus, the three-dimensional virtual model of the bronchus is obtained, and the correlation between the three-dimensional CT image and the real endoscope image is established by performing virtual endoscope rendering in the three-dimensional virtual model of the bronchus, which can help doctors better navigate to the located nodule or the position to be navigated. The method assists doctors in determining the navigation path and controlling the bronchoscope, biopsy and diagnosis and treatment instruments to navigate more accurately, so as to accurately position the pulmonary nodule and other lesions.

[0007] In a possible embodiment, the comparison of the virtual endoscope image group with the target endoscope image and the selection of the optimal virtual endoscope image in the virtual endoscope image group comprise: performing similarity evaluation on the virtual endoscope images in the virtual endoscope image group and the target endoscope image one by one; and selecting the virtual endoscope image in the virtual endoscope image group with the highest similarity to the target endoscope image as the optimal virtual endoscope image.

[0008] In another possible embodiment, a three-dimensional virtual model of the bronchus is established based on the three-dimensional scan image, and a navigation path is planned based on the three-dimensional virtual model of the bronchus, including: segmenting the bronchus based on the three-dimensional scan image; performing three-dimensional reconstruction of the bronchus to establish a three-dimensional virtual model of the bronchus; extracting the centerline of the three-dimensional virtual model of the bronchus and traversing the centerline to generate a bronchial tree; identifying nodules in the bronchus based on the three-dimensional scan image and performing three-dimensional reconstruction of the nodules; and planning a navigation path based on the location of the nodules and the bronchial tree.

[0009] In other possible embodiments, planning a navigation path based on the location of the nodule and the bronchial tree includes: selecting a feasible path to the nodule on the bronchial tree based on the location of the nodule; and selecting the shortest path among the feasible paths as the navigation path.

[0010] Selecting N activation points on the navigation path according to the set criteria includes: setting the points at the forks in the bronchus 3D virtual model as nodes; and selecting the nodes on the navigation path as activation points.

[0011] Secondly, the present invention also provides an endoscopic-assisted bronchial navigation system, comprising:

[0012] The path planning unit is used to acquire a three-dimensional scan image of the bronchus, establish a three-dimensional virtual model of the bronchus based on the three-dimensional scan image, and plan a navigation path based on the three-dimensional virtual model of the bronchus.

[0013] The selection unit is used to select the target point and N activation points on the navigation path according to the set criteria, where N is a positive integer.

[0014] The image generation unit is used to perform virtual endoscopy rendering at the initial activation point in the bronchus three-dimensional virtual model to generate a virtual endoscopy image group, and to generate a target endoscopy image at the initial activation point in the bronchus through the endoscope.

[0015] An image selection unit is used to compare the virtual endoscope image group with the target endoscope image and select the optimal virtual endoscope image from the virtual endoscope image group.

[0016] The transformation unit is used to register and fuse the target endoscope image and the optimal virtual endoscope image, transform the bronchial three-dimensional virtual model according to the registration matrix so that the bronchial three-dimensional virtual model is consistent with the orientation of the bronchus, and navigate the endoscope along the navigation path;

[0017] The navigation unit is used to generate a set of virtual endoscope images in the three-dimensional virtual model of the bronchus and a target endoscope image in the bronchus at each activation point, select the best virtual endoscope image in the set of virtual endoscope images, register and fuse the target endoscope image and the best virtual endoscope image generated at the same activation point, and navigate the endoscope according to the registration matrix until the endoscope reaches the target point to complete the navigation.

[0018] The image selection unit compares the virtual endoscope image group with the target endoscope image, and selects the optimal virtual endoscope image from the virtual endoscope image group. Specifically, it performs a similarity evaluation on each virtual endoscope image in the virtual endoscope image group with the target endoscope image; and selects the virtual endoscope image in the virtual endoscope image group with the highest similarity to the target endoscope image as the optimal virtual endoscope image.

[0019] The path planning unit establishes a 3D virtual model of the bronchus based on the 3D scan image, and plans a navigation path based on the 3D virtual model of the bronchus. Specifically, it is used for: segmenting the bronchus based on the 3D scan image; performing 3D reconstruction of the bronchus to establish a 3D virtual model of the bronchus; extracting the centerline of the 3D virtual model of the bronchus and traversing the centerline to generate a bronchial tree; identifying nodules in the bronchus based on the 3D scan image and performing 3D reconstruction of the nodules; and planning a navigation path based on the location of the nodules and the bronchial tree.

[0020] Planning a navigation path based on the location of the nodule and the bronchial tree includes: selecting a feasible path to the nodule on the bronchial tree based on the location of the nodule; and selecting the shortest path among the feasible paths as the navigation path.

[0021] The selection unit selects N activation points on the navigation path according to the set criteria, including: setting the points at the forks in the three-dimensional virtual model of the bronchus as nodes; and selecting the nodes on the navigation path as activation points.

[0022] Thirdly, the present invention also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method.

[0023] Fourthly, the present invention also provides an electronic device, comprising: a processor and a memory; the memory being used to store a computer program; the processor being used to execute the computer program stored in the memory to cause the electronic device to perform the above-described method.

[0024] For the beneficial effects of the second to fourth aspects mentioned above, please refer to the description of the first aspect mentioned above. Attached Figure Description

[0025] Figure 1 A schematic flowchart of the endoscopic-assisted bronchial navigation method provided in an embodiment of the present invention;

[0026] Figure 2 This is a schematic diagram of the structure when the initial visual image is selected to generate a virtual endoscope image using the ray projection method, as provided in an embodiment of the present invention.

[0027] Figure 3 A schematic diagram of a three-dimensional virtual model of the bronchus provided in an embodiment of the present invention;

[0028] Figure 4 This is a schematic diagram showing the result of centerline extraction from a three-dimensional virtual model of the bronchus provided in an embodiment of the present invention;

[0029] Figure 5 This is a schematic diagram of a navigation path planned based on the location of the nodules and the bronchial tree, provided for an embodiment of the present invention.

[0030] Figure 6 This is a randomly generated virtual endoscope image provided in an embodiment of the present invention;

[0031] Figure 7 The target endoscopic image provided in the embodiments of the present invention;

[0032] Figure 8 The optimal virtual endoscope image provided for embodiments of the present invention;

[0033] Figure 9 This is a schematic diagram of the result after registering and fusing the optimal virtual endoscope image and the target endoscope image, provided in an embodiment of the present invention.

[0034] Figure 10 This is a schematic diagram of the endoscopic-assisted bronchial navigation device provided in an embodiment of the present invention.

[0035] Figure 11 This is a schematic diagram of an electronic device structure provided in an embodiment of the present invention. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions in the embodiments of this 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 this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention. Unless otherwise defined, the technical or scientific terms used herein should have the ordinary meaning understood by those skilled in the art. The terms "comprising" and similar expressions used herein mean that the element or object preceding the word covers the element or object listed following the word and its equivalents, but do not exclude other elements or objects.

[0037] To address the problems existing in the prior art, embodiments of the present invention provide an endoscopic-assisted bronchial navigation method, system, medium, and electronic device to solve the problem that there is no actual positional correlation between three-dimensional CT images and real endoscopic images.

[0038] This embodiment provides a method for endoscopic-assisted bronchial navigation during surgery. See the appendix to the instruction manual. Figure 1 The method includes:

[0039] S1: Obtain a 3D scan image of the bronchus, establish a 3D virtual model of the bronchus based on the 3D scan image, and plan a navigation path based on the 3D virtual model of the bronchus.

[0040] In S1, in one possible embodiment, after acquiring a three-dimensional scan image of the bronchus, the quality of the three-dimensional scan image is evaluated. The criteria for evaluating the quality of the three-dimensional scan image include: whether the three-dimensional scan image includes the tracheal inlet and the entire lung region, and whether the resolution meets the set standards.

[0041] In one specific embodiment, the three-dimensional scan image is required to include the tracheal inlet and the entire lung region, with a resolution of less than 0.8 mm and a slice thickness of less than 1 mm. A three-dimensional virtual model of the bronchus is established based on the three-dimensional scan image that meets the quality assessment requirements of the three-dimensional scan image.

[0042] In one possible embodiment, a three-dimensional virtual model of the bronchus is established based on a three-dimensional scan image, and a navigation path is planned based on the three-dimensional virtual model of the bronchus, including: segmenting the bronchus based on the three-dimensional scan image; performing three-dimensional reconstruction of the bronchus to establish a three-dimensional virtual model of the bronchus; extracting the centerline of the three-dimensional virtual model of the bronchus and traversing the centerline to generate a bronchial tree; identifying nodules in the bronchus based on the three-dimensional scan image and performing three-dimensional reconstruction of the nodules; and planning a navigation path based on the location of the nodules and the bronchial tree.

[0043] In one possible embodiment, after establishing the three-dimensional virtual model of the bronchus, the surface of the three-dimensional virtual model of the bronchus is smoothed to make the three-dimensional virtual model of the bronchus more similar to the real bronchus.

[0044] In one possible embodiment, there are several ways to identify nodules in the bronchus based on three-dimensional scan images. For example, nodules can be identified using deep learning or traditional image processing, or nodules can be identified using an interactive method that specifies a point on the nodule based on the three-dimensional scan image, or the overall shape and location of the nodule can be identified based on an algorithm given the outer edge shape of a certain cross-section of the nodule, etc.

[0045] In one possible embodiment, both the three-dimensional reconstruction of the bronchus and the three-dimensional reconstruction of the nodules are completed using the moving cube isoplanar reconstruction method.

[0046] In one specific embodiment, planning a navigation path based on the location of the nodule and the bronchial tree includes: selecting a feasible path to the nodule on the bronchial tree based on the location of the nodule; and selecting the shortest path among the feasible paths as the navigation path.

[0047] In one specific embodiment, a navigation path is generated by combining human-computer interaction with the bronchial topology. That is, the navigation path is planned by manually specifying the navigation path on the bronchial topology, which makes the navigation path planning more flexible.

[0048] In one possible embodiment, the three-dimensional scan image is a three-dimensional CT image.

[0049] S2: Select the target point and N activation points on the navigation path according to the set criteria, where N is a positive integer.

[0050] In S2, in one possible embodiment, N activation points on the navigation path are selected according to a set criterion, including: setting the points at the forks in the bronchial three-dimensional virtual model as nodes; and selecting nodes on the navigation path as activation points.

[0051] In one possible implementation, if the last point of the navigation path is not a node, it is set as the activation point.

[0052] For example, the target point is a schematic point indicating the location of the nodule.

[0053] S3: At the initial activation point within the bronchial 3D virtual model, virtual endoscopy rendering is performed to generate a virtual endoscopy image group. At the initial activation point within the bronchus, the target endoscopy image is generated using an endoscope.

[0054] In S3, in one possible embodiment, endoscopic navigation is performed along a navigation path, with the first activation point the endoscope aims to reach being the initial activation point. In the bronchus, the initial activation point is located at the carina.

[0055] At the initial activation point within the bronchial 3D virtual model, an angle from which the endoscope acquires an image is selected as the initial visual perspective to begin virtual endoscope rendering and obtain a virtual endoscope image. At the initial activation point, virtual endoscope rendering can be performed at different angles from which the endoscope acquires an image to obtain a virtual endoscope image. Thus, virtual endoscope rendering at the initial activation point can generate a virtual endoscope image group containing multiple images.

[0056] See the instruction manual appendix Figure 2 In one possible embodiment, the initial visual image generated using a ray projection method is chosen, similar to placing a camera inside a reconstructed bronchial model to take a picture. To ensure the generated virtual endoscopic image is as similar as possible to the real endoscopic image, the focal length and field of view of the bronchoscope imaging system need to be measured beforehand. The illuminated bronchial wall can be approximated using a Lambertian illumination model to generate the virtual endoscopic image, satisfying the following formula: Where I(x, y) represents the generated virtual endoscopic image, La represents the ambient light factor, and R represents the distance from the light source to the corresponding point p on the observed surface. Φ is the attenuation factor, θ represents the angle between the camera axis and the point p on the surface, and θ represents the angle between the light source direction and the surface normal at point p.

[0057] In one possible embodiment, the target endoscopic image is generated based on the imaging system integrated into the endoscope.

[0058] S4: Compare the virtual endoscope image set with the target endoscope image, and select the optimal virtual endoscope image from the virtual endoscope image set.

[0059] In S4, in one possible embodiment, comparing the virtual endoscope image group with the target endoscope image and selecting the optimal virtual endoscope image from the virtual endoscope image group includes: evaluating the similarity of each virtual endoscope image in the virtual endoscope image group with the target endoscope image; and selecting the virtual endoscope image in the virtual endoscope image group with the highest similarity to the target endoscope image as the optimal virtual endoscope image.

[0060] In one possible embodiment, the virtual endoscope images in the virtual endoscope image group and the target endoscope image are evaluated for similarity using normalized mutual information calculation. In this embodiment, the initial vision includes six parameters: the three-dimensional position of the virtual camera (x, y, z) and the initial illumination angles (α, β, γ). The parameters to be optimized are the deviations between the actual parameters and the initial parameters: Δx, Δy, Δz, Δα, Δβ, Δγ. The absolute values ​​of the position deviations are set to be less than 5 and the absolute values ​​of the angle deviations to be less than 18. The virtual endoscope image is obtained through optimization.

[0061] For example, the formula for calculating normalized mutual information is as follows: HMI(A, B) = H(A) + H(B) - H(A, B), where, Similarly, H(B) = -∑ a,b p AB (a, b)log p AB (a, b). Where HMI(A, B) represents the normalized mutual information between the virtual endoscope image and the target endoscope image, H(A) represents the entropy of the target endoscope image, H(B) represents the entropy of the virtual endoscope image, and H(A, B) represents the joint entropy of the target endoscope image and the virtual endoscope image. N is 256, p i p represents the probability of a pixel with gray value i appearing in the image. AB (a, b) is the probability that a pixel at the same location has a gray value of a in image A and a gray value of b in image B.

[0062] S5: Register and fuse the target endoscopic image and the optimal virtual endoscopic image. Transform the 3D virtual model of the bronchus according to the registration matrix so that the 3D virtual model of the bronchus is consistent with the orientation of the bronchus. Navigate the endoscope along the navigation path.

[0063] In S5, one possible embodiment employs a registration method based on normalized mutual information to register and fuse the target endoscopic image and the optimal virtual endoscopic image. Transformations performed on the bronchial 3D virtual model include translation and rotation. In this example, an optimization algorithm is used to optimize the solution parameters, searching the parameter space and determining the optimal transformation mapping the model to the top of the image. Other optimization algorithms capable of performing parameter searches can also be used.

[0064] S6: At each activation point, generate a set of virtual endoscope images in the 3D virtual model of the bronchus and generate a target endoscope image in the bronchus. Select the best virtual endoscope image from the set of virtual endoscope images. Register and fuse the target endoscope image and the best virtual endoscope image generated at the same activation point. Navigate the endoscope according to the registration matrix until the endoscope reaches the target point to complete the navigation.

[0065] In one specific embodiment, a schematic diagram of a three-dimensional virtual model of the bronchus obtained by endoscopic-assisted bronchial navigation method according to the present invention is shown below. Figure 3 As shown, the result of centerline extraction from the 3D virtual model of the bronchus is as follows: Figure 4 As shown, the navigation path planned based on the location of the nodule and the bronchial tree is as follows: Figure 5 As shown. One of the randomly generated frames of a virtual endoscope image is as follows. Figure 6 As shown, the target endoscopic image is as follows Figure 7 As shown, the optimal virtual endoscope image selected from the virtual endoscope image group after comparing the virtual endoscope image group with the target endoscope image is as follows. Figure 8 As shown, the result after registering and fusing the optimal virtual endoscope image and the target endoscope image is as follows: Figure 9 As shown.

[0066] The endoscopic-assisted bronchial navigation method provided by this invention has the following beneficial effects: Based on the three-dimensional reconstruction of the bronchus to obtain a three-dimensional virtual model of the bronchus, and by rendering a virtual endoscope within the three-dimensional virtual model of the bronchus, it assists in establishing a correlation between three-dimensional CT images and real endoscopic images. This helps doctors better navigate to located nodules or other areas requiring navigation. This method assists doctors in determining the navigation path and controlling the bronchoscope, biopsy, and diagnostic instruments for more accurate navigation, thereby precisely locating lesions such as lung nodules and improving the positive rate of lung cancer biopsies.

[0067] See the instruction manual appendix Figure 10 This embodiment also provides an endoscopic-assisted bronchial navigation system, which includes:

[0068] The path planning unit 101 is used to acquire a three-dimensional scan image of the bronchus, establish a three-dimensional virtual model of the bronchus based on the three-dimensional scan image, and plan a navigation path based on the three-dimensional virtual model of the bronchus.

[0069] Selection unit 102 is used to select the target point and N activation points on the navigation path according to the set criteria, where N is a positive integer.

[0070] The image generation unit 103 is used to generate a virtual endoscope image group by performing virtual endoscope rendering at the initial activation point in the bronchus three-dimensional virtual model, and to generate a target endoscope image by using an endoscope at the initial activation point in the bronchus.

[0071] The image selection unit 104 is used to compare the virtual endoscope image group with the target endoscope image and select the optimal virtual endoscope image from the virtual endoscope image group.

[0072] The transformation unit 105 is used to register and fuse the target endoscope image and the optimal virtual endoscope image, transform the bronchial 3D virtual model according to the registration matrix so that the bronchial 3D virtual model is consistent with the bronchial orientation, and navigate the endoscope along the navigation path.

[0073] The navigation unit 106 is used to generate a set of virtual endoscope images in the three-dimensional virtual model of the bronchus and a target endoscope image in the bronchus at each activation point, select the best virtual endoscope image in the set of virtual endoscope images, register and fuse the target endoscope image and the best virtual endoscope image generated at the same activation point, and navigate the endoscope according to the registration matrix until the endoscope reaches the target point to complete the navigation.

[0074] All relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0075] In other embodiments of this application, an electronic device is disclosed, such as... Figure 11 As shown, the electronic device 110 may include: one or more processors 111; a memory 112; a display 113; one or more application programs (not shown); and one or more computer programs 114. These devices can be connected via one or more communication buses 115. The one or more computer programs 114 are stored in the memory 112 and configured to be executed by the one or more processors 111. The one or more computer programs 114 include instructions that can be used to perform actions such as... Figure 1 And the various steps in the corresponding embodiments.

[0076] Through the above description of the embodiments, those skilled in the art will clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. The specific working process of the system, device, and unit described above can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0077] In the embodiments of this application, the functional units can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0078] If the integrated unit is implemented as 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 solutions of the embodiments of this application, essentially, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as flash memory, portable hard disk, read-only memory, random access memory, magnetic disk, or optical disk.

[0079] The above description is merely a specific implementation of the embodiments of this application, but the protection scope of the embodiments of this application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the embodiments of this application should be covered within the protection scope of the embodiments of this application. Therefore, the protection scope of the embodiments of this application should be determined by the protection scope of the claims.

Claims

1. An endoscopic-assisted bronchial navigation system, characterized in that, include: The path planning unit is used to acquire a three-dimensional scan image of the bronchus, establish a three-dimensional virtual model of the bronchus based on the three-dimensional scan image, and plan a navigation path based on the three-dimensional virtual model of the bronchus. The selection unit is used to select the target point and N activation points on the navigation path according to the set criteria, where N is a positive integer. The image generation unit is used to select an angle for obtaining images with an endoscope at the initial activation point in the bronchus three-dimensional virtual model as the initial vision, select the initial vision and use the ray projection method to generate a virtual endoscope image group by rendering the virtual endoscope according to the pre-measured focal length and field of view of the bronchoscope imaging system, and generate a target endoscope image at the initial activation point in the bronchus through the endoscope. An image selection unit is used to compare the virtual endoscope image group with the target endoscope image and select the optimal virtual endoscope image from the virtual endoscope image group. The transformation unit is used to register and fuse the target endoscope image and the optimal virtual endoscope image, transform the bronchial three-dimensional virtual model according to the registration matrix so that the bronchial three-dimensional virtual model is consistent with the orientation of the bronchus, and navigate the endoscope along the navigation path; The navigation unit is used to generate a set of virtual endoscope images in the three-dimensional virtual model of the bronchus and a target endoscope image in the bronchus at each activation point, select the best virtual endoscope image in the set of virtual endoscope images, register and fuse the target endoscope image and the best virtual endoscope image generated at the same activation point, and navigate the endoscope according to the registration matrix until the endoscope reaches the target point to complete the navigation.

2. The system according to claim 1, characterized in that, The image selection unit compares the virtual endoscope image group with the target endoscope image, and selects the optimal virtual endoscope image from the virtual endoscope image group, specifically for: The similarity between each virtual endoscope image in the virtual endoscope image group and the target endoscope image is evaluated. The virtual endoscope image with the highest similarity to the target endoscope image in the virtual endoscope image group is selected as the optimal virtual endoscope image.

3. The system according to claim 1, characterized in that, The path planning unit establishes a three-dimensional virtual model of the bronchus based on the three-dimensional scan image, and plans a navigation path based on the three-dimensional virtual model of the bronchus, specifically for: Bronchi segmentation is performed based on the three-dimensional scan images; Perform three-dimensional reconstruction of the bronchi to establish a three-dimensional virtual model of the bronchi; Extract the centerline of the three-dimensional virtual model of the bronchus, and traverse the centerline to generate a bronchial tree; Based on the three-dimensional scan image, nodules in the bronchus are identified, and three-dimensional reconstruction of the nodules is performed; Navigation paths are planned based on the location of the nodules and the bronchial tree.

4. The system according to claim 3, characterized in that, Navigation paths are planned based on the location of the nodules and the bronchial tree, including: Based on the location of the nodule, a feasible path to the nodule is selected on the bronchial tree; Select the shortest path from the available paths as the navigation path.

5. The system according to claim 1, characterized in that, The selection unit selects N activation points on the navigation path according to a set criterion, including: Set the points at the forks in the three-dimensional virtual model of the bronchus as nodes; Select the node on the navigation path as the activation point.

Images