Path Planning Method, Device, Equipment and Readable Storage Medium for Bronchial Lesions

Abstract

The present invention relates to the technical field of surgical path planning, and discloses a path planning method, device, equipment and readable storage medium for bronchial lesions. Among them, the method includes: obtaining a three-dimensional scan image of the bronchus; parsing the three-dimensional scan image to determine target bronchial data and the lesion location; extracting the bronchial centerline from the target bronchial data; performing path search based on the end points, bifurcation points and bronchial inlet points corresponding to the bronchial centerline to generate a target path for the lesion location. By implementing the technical solution of the present invention, the target path can be planned according to the extracted bronchial centerline and the lesion location, without being limited by the complexity of the lesion location, effectively improving the accuracy and precision of path planning.

Description

Technical Field

[0001] The present invention relates to the technical field of surgical path planning, and in particular, to a path planning method, device, equipment and readable storage medium for bronchial lesions. Background Art

[0002] The path planning of bronchial lesions is to use Computed Tomography (CT) images to plan the surgical path from the starting point of the bronchus to the target area of the lesion, so as to assist doctors in reducing surgical errors.

[0003] The path planning methods in the related art mainly include manual experience planning, deep learning model planning, threshold segmentation method, etc. Although they can achieve the path planning for bronchial lesions, it is difficult to ensure the accuracy and precision of these path planning methods. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a path planning method, device, equipment and readable storage medium for bronchial lesions to solve the problem that it is difficult to ensure the accuracy and precision of path planning.

[0005] According to a first aspect, an embodiment of the present invention provides a path planning method for bronchial lesions, including: acquiring a three-dimensional scan image of a bronchus; parsing the three-dimensional scan image to determine target bronchus data and the lesion position; extracting a bronchus centerline from the target bronchus data; and performing path search based on the endpoints, bifurcation points and bronchus inlet points corresponding to the bronchus centerline to generate a target path for the lesion position.

[0006] The path planning method for bronchial lesions provided by the embodiment of the present invention determines the target bronchus data and the lesion position by parsing the three-dimensional scan image of the bronchus, and extracts the bronchus centerline from the target bronchus data. Since the bronchus centerline can represent the shape of the bronchial tree, a corresponding target path is generated according to the endpoints, bifurcation points and bronchus inlet points corresponding to the bronchus centerline, realizing the automatic generation of path planning. This method identifies the bronchial tree to accurately extract the bronchus centerline, and then the target path can be planned according to the bronchus centerline and the lesion position, regardless of the complexity of the lesion position, effectively improving the accuracy and precision of path planning.

[0007] Combined with the first aspect, in the first embodiment of the first aspect, parsing the three-dimensional scan image to determine the target bronchial data includes: parsing the three-dimensional scan data to obtain a plurality of cross-sectional sequence data of the bronchus; in response to a switching operation on the plurality of cross-sectional sequence data, determining a target cross-section with lesions based on the switching operation, and extracting the lesion positions from the target cross-section; performing segmentation processing on the plurality of cross-sectional sequence data based on a preset segmentation model to obtain data segmentation results corresponding to each cross-sectional sequence data; and performing fusion processing on the plurality of data segmentation results to obtain the target bronchial data.

[0008] The bronchial lesion path planning method provided by the embodiments of the present invention facilitates accurately locating the lesion position by viewing the three-dimensional scan data from multiple angles and dimensions. The bronchial data segmentation results are determined from the multi-dimensional cross-sectional sequence data through a preset segmentation model, and the target bronchial data is determined by performing fusion processing on the bronchial data segmentation results in different dimensions, ensuring the accuracy of the extraction of the target bronchial data.

[0009] Combined with the first aspect, in the second embodiment of the first aspect, extracting the bronchial centerline from the target bronchial data includes: performing model drawing on the target bronchial data based on a preset drawing method to generate a bronchial surface model; performing data processing on the bronchial surface model to determine a single voxel value corresponding to the bronchial surface model; and determining the centerline formed by the single voxel values as the bronchial centerline.

[0010] The bronchial lesion path planning method provided by the embodiments of the present invention ensures the accuracy of the extraction of the bronchial center point by extracting the voxel values of the bronchial surface model and determining the centerline formed by the single voxel values as the bronchial centerline, facilitating more accurate path search in the subsequent process.

[0011] In combination with the first aspect, in the third implementation manner of the first aspect, the path search based on the corresponding endpoints, bifurcation points, and bronchial inlet points of the bronchial centerline to generate a target path for the lesion location includes: obtaining the centerline point set of the bronchial centerline; determining the first distances from each endpoint and each bifurcation point to the lesion location; comparing the multiple first distances to determine several location points closest to the lesion location from each endpoint and each bifurcation point; determining the second distances from the bronchial inlet point to each of the location points; comparing the sum of the first distances and the second distances of the several location points to determine a target point closest to the lesion location from the several location points; determining the third distances from each centerline point in the centerline point set to the lesion location; comparing the multiple third distances to determine a target centerline point closest to the lesion location; and determining the target path based on the positional relationship among the bronchial inlet point, the target point, the target centerline point, and the lesion location.

[0012] In combination with the third implementation manner of the first aspect, in the fourth implementation manner of the first aspect, the determination of the target path based on the straight-line distances among the bronchial inlet point, the target point, the target centerline point, and the lesion location includes: determining a first path from the bronchial inlet point to the target point based on the positions of the bronchial inlet point and the target point; determining a second path from the target point to the target centerline point based on the positions of the target point and the target centerline point; determining a third path from the target centerline point to the lesion location based on the positions of the target centerline point and the lesion location; and combining the first path, the second path, and the third path to generate the target path.

[0013] The path planning method for bronchial lesions provided by the embodiments of the present invention realizes the optimal planning of the target path by planning the first path from the bronchial inlet point to the target point, the second path from the target point to the target centerline point, and the third path from the target centerline point to the lesion location, and then combining the three parts of the paths.

[0014] In combination with the first aspect, in the fifth implementation manner of the first aspect, the method further includes: in response to an adjustment operation on a path point, determining a target path point based on the adjustment operation; and updating the target path based on the target path point.

[0015] The path planning method for bronchial lesions provided by the embodiments of the present invention supports the adjustment of the path points of the target path, thereby facilitating the real-time adjustment of the target path according to the actual situation of the bronchial lesions and making the planning of the target path more flexible.

[0016] In combination with the first aspect, in the sixth embodiment of the first aspect, the method further includes: in response to a switching operation on the three-dimensional scan image, determining the registration point data of the bronchus; and performing spatial registration on the target path and the bronchus based on the registration point data.

[0017] The path planning method for bronchial lesions provided by the embodiments of the present invention performs spatial registration on the target path and the bronchus through the registration point data of the bronchus to verify the accuracy of the target path, further improving the accuracy of the target path.

[0018] According to a second aspect, an embodiment of the present invention provides a path planning device for bronchial lesions, including: an acquisition module for acquiring a three-dimensional scan image of the bronchus; an analysis module for analyzing the three-dimensional scan image to determine target bronchus data and the lesion location; an extraction module for extracting the bronchial centerline from the target bronchus data; and a generation module for performing path search based on the endpoints, bifurcation points, and bronchial inlet points corresponding to the bronchial centerline to generate a target path for the lesion location.

[0019] According to a third aspect, an embodiment of the present invention provides an electronic device, including: a memory and a processor, which are communicatively connected to each other. The memory stores computer instructions, and the processor executes the computer instructions to execute the path planning method for bronchial lesions according to the first aspect or any embodiment of the first aspect.

[0020] According to a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute the path planning method for bronchial lesions according to the first aspect or any embodiment of the first aspect.

[0021] It should be noted that for the corresponding beneficial effects of the path planning device, electronic device, and computer-readable storage medium for bronchial lesions provided by the embodiments of the present invention, please refer to the description of the corresponding content in the path planning method for bronchial lesions, which will not be elaborated here. Description of the Drawings

[0022] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0023] Figure 1It is a flowchart of a path planning method for bronchial lesions according to an embodiment of the present invention;

[0024] Figure 2 It is another flowchart of a path planning method for bronchial lesions according to an embodiment of the present invention;

[0025] Figure 3 It shows a schematic diagram of the bronchial centerline in an embodiment of the present invention;

[0026] Figure 4 It shows a schematic diagram of target path generation in an embodiment of the present invention;

[0027] Figure 5 It shows a schematic diagram of the target path in each sectional view in an embodiment of the present invention;

[0028] Figure 6 It is yet another flowchart of a path planning method for bronchial lesions according to an embodiment of the present invention;

[0029] Figure 7 It shows a schematic diagram of the adjustment of unreasonable path points in an embodiment of the present invention;

[0030] Figure 8 It is a structural block diagram of a path planning device for bronchial lesions according to an embodiment of the present invention;

[0031] Figure 9 It is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0032] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0033] The path planning methods in the related art mainly include manual experience planning, deep learning model planning, and threshold segmentation methods, etc. Among them, manual experience planning is to manually observe the lesion target area of the CT image or three-dimensional model, and plan the optimal surgical path through surgical experience. However, manual observation takes time and effort, and the surgical path planning results vary greatly due to individual differences in experience. Deep learning can establish an end-to-end surgical path planning model, and learn the annotated samples through the surgical path planning model to output the planned path. However, deep learning requires a large number of lesion location learning samples and annotation training time, and due to the complexity of the lesion location and the influence of various factors in the surgical path, it is difficult to guarantee the accuracy of the surgical path planning model. The threshold segmentation method is to segment the bronchus based on the threshold, directly search for the shortest path according to the bronchial topological structure, and explore the path between nodes based on breadth or depth until the target node is reached, and find the shortest path between two specified nodes. However, the error of segmenting the bronchus is large, resulting in low accuracy of surgical path planning.

[0034] Based on this, the technical solution of the present invention extracts the bronchial centerline by identifying the bronchial tree, and then can plan the target path according to the bronchial centerline and the lesion location, improving the accuracy and precision of path planning.

[0035] According to an embodiment of the present invention, an embodiment of a path planning method for bronchial lesions 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 the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0036] In this embodiment, a path planning method for bronchial lesions is provided, which can be used in electronic devices such as computers, servers, hosts, etc. Figure 1 It is a flowchart of the path planning method for bronchial lesions according to an embodiment of the present invention, as Figure 1 shown, and the process includes the following steps:

[0037] S11, obtain a three-dimensional scan image of the bronchus.

[0038] The three-dimensional scan image is an image obtained by performing computed tomography scanning on the bronchus. The electronic device can be communicatively connected to the scanning device. When the scanning device generates three-dimensional scan data of the bronchus, it transmits it to the electronic device. Correspondingly, the electronic device can obtain the three-dimensional scan image. The three-dimensional scan image can also be stored in a data storage medium, such as a hard disk, a USB flash drive, an optical disc, etc. The electronic device can obtain the three-dimensional scan image by reading the data storage medium. Of course, the three-dimensional scan image can also be obtained by other means, which is not specifically limited here.

[0039] S12. Analyze the three-dimensional scanned image to determine the target bronchial data and the lesion location.

[0040] The target bronchial data is used to characterize the topological structure of the bronchial tree, and the lesion location indicates the position of the lesion in the bronchus. The electronic device analyzes the three-dimensional scanned image and resolves it into sectional data such as the coronal plane, sagittal plane, and cross-sectional plane. By responding to the doctor's switching of the sectional data, it switches to the area where the lesion is located and extracts the lesion location from this area.

[0041] Perform bronchial segmentation on the sectional data of the coronal plane, sagittal plane, and cross-sectional plane respectively to obtain the three-dimensional data voxel positions of the bronchi in each section. If any three-dimensional data voxel position is a bronchial area, fuse the corresponding three-dimensional data voxel positions to obtain the target bronchial data.

[0042] S13. Extract the bronchial centerline from the target bronchial data.

[0043] The bronchial centerline is the topological line of the bronchial tree and is used to characterize the topology from the bronchial inlet to each bifurcation. Specifically, the electronic device can use a three-dimensional topology refinement algorithm to extract bronchial voxels from the target bronchial data, determine a single voxel based on the extracted bronchial voxels, and determine the centerline composed of the single voxels as the bronchial centerline.

[0044] S14. Perform path search based on the endpoints, bifurcation points, and bronchial inlet points corresponding to the bronchial centerline to generate a target path for the lesion location.

[0045] The target path is the shortest path from the bronchial inlet point to the lesion location. The endpoint is the starting point or ending point corresponding to the bronchial tree, the bifurcation point is the bifurcation position point of the bronchial tree, and the bronchial inlet point is the source point of the target path, that is, the starting point of the target path.

[0046] The electronic device determines multiple endpoints, bifurcation points, and bronchial inlet points based on the topological structure of the bronchial centerline, performs path search according to the multiple endpoints, bifurcation points, and bronchial inlet points, uses the bronchial inlet point as the source point, and uses each endpoint and bifurcation point as the target point to search for the shortest path from the source point to the target point and retain the path distance and path points. Then, construct the shortest path from the bronchial inlet point to the lesion location point based on each shortest path and each path point to obtain the target path.

[0047] The path planning method for bronchial lesions provided in this embodiment determines the target bronchial data and the lesion location by parsing the three-dimensional scan image of the bronchus, and extracts the bronchial centerline from the target bronchial data. Since the bronchial centerline can represent the shape of the bronchial tree, corresponding target paths are generated based on the end points, bifurcation points, and bronchial inlet points corresponding to the bronchial centerline, realizing the automatic generation of path planning. This method identifies the bronchial tree to accurately extract the bronchial centerline, and then the target path can be planned according to the bronchial centerline and the lesion location, regardless of the complexity of the lesion location, effectively improving the accuracy and precision of path planning.

[0048] In this embodiment, a path planning method for bronchial lesions is provided, which can be used in electronic devices such as computers, servers, hosts, etc. Figure 2 It is a flowchart of the path planning method for bronchial lesions according to an embodiment of the present invention, as Figure 2 shown, and the process includes the following steps:

[0049] S21, obtain the three-dimensional scan image of the bronchus. For detailed description, refer to the relevant description corresponding to the above embodiment, which will not be elaborated here.

[0050] S22, parse the three-dimensional scan image to determine the target bronchial data and the lesion location.

[0051] Specifically, the above step S22 may include:

[0052] S221, parse the three-dimensional scan data to obtain multiple slice sequence data of the bronchus.

[0053] Parse the three-dimensional scan data along the three dimensions of the coronal axis, sagittal axis, and transverse axis respectively to obtain slice sequence data such as the coronal plane, sagittal plane, and cross-section of the bronchus. Among them, the index of the slice sequence data in each dimension starts from 0 to the extreme value.

[0054] S222, in response to the switching operation on the multiple slice sequence data, determine the target slice with lesions based on the switching operation, and extract the lesion location from the target slice.

[0055] The doctor operates on the slice sequence data through the control module of the electronic device (such as interactive devices such as a mouse, keyboard, handle, touch screen, trackball, etc.). Correspondingly, the electronic device can respond to the doctor's switching operation on the multiple slice sequence data, switch the respective slice views of the bronchus, and determine the target slice with lesions. The target slice can be any one or more of the coronal plane, sagittal plane, and cross-section. When the target slice is determined, the electronic device can determine the three-dimensional coordinates of the lesion location according to the index of each slice sequence data.

[0056] S223. Perform segmentation processing on multiple cross-sectional sequence data based on a preset segmentation model to obtain data segmentation results corresponding to each cross-sectional sequence data.

[0057] The preset segmentation model is a pre-constructed Unet network model. The preset segmentation model is deployed in the electronic device. Input multiple cross-sectional sequence data into the preset segmentation model, and through the preset segmentation model, perform segmentation of the bronchial region and the background region on each cross-sectional sequence data to obtain data segmentation results corresponding to each part of the cross-sectional sequence data.

[0058] Among them, the construction method of the preset segmentation model is specifically as follows: First, obtain three-dimensional scan images and parse them into cross-sectional sequence data such as coronal plane, sagittal plane, and cross-sectional plane as sample data; Second, perform annotation of the bronchi on each part of the cross-sectional sequence data. For example, use data annotation software labelme to surround and annotate the bronchial region in the cross-sectional sequence data by connecting points, and obtain an annotated image; Third, input the annotated image into the Unet network model for end-to-end training, and use the trained Unet network model as the preset segmentation model.

[0059] S224. Perform fusion processing on multiple data segmentation results to obtain target bronchial data.

[0060] Stack the data segmentation results corresponding to each part of the cross-sectional sequence data in three dimensions along the coronal axis, sagittal axis, and transverse axis, and perform rotation transformation to make the voxel positions of each part of the three-dimensional data correspond. Specifically, the data segmentation result output by the preset segmentation model is a single-frame 2D image of each part of the cross-sectional sequence data, and the 2D images corresponding to each part of the cross-sectional sequence data are stacked in three dimensions along the coronal axis, sagittal axis, and transverse axis to form three-dimensional data.

[0061] Perform fusion judgment on the data segmentation results after three-dimensional stacking to obtain the final target bronchial data. Specifically, fuse the data segmentation results of each part of the cross-sectional sequence data to obtain fusion data, and compare the voxels of the fusion data with the background threshold to determine the area where the bronchi are located. If a certain voxel can be determined to be in the bronchial region through voxel comparison, then determine its location as the bronchial region, and thus combine the determined bronchial region to determine the target bronchial data.

[0062] S23. Extract the bronchial centerline from the target bronchial data.

[0063] Specifically, the above step S23 may include:

[0064] S231. Perform model drawing on the target bronchial data based on a preset drawing method to generate a bronchial surface model.

[0065] The preset rendering method is a pre-set model rendering method, such as the isosurface algorithm. The electronic device performs three-dimensional surface reconstruction of the bronchus on the target bronchus data using the preset rendering method to generate a bronchial surface model.

[0066] S232. Process the data of the bronchial surface model to determine the single voxel value corresponding to the bronchial surface model.

[0067] Clean the data of the bronchial surface model to remove duplicate data points, and obtain the bronchial surface model after duplicate removal processing. Subsequently, use the three-dimensional topological thinning algorithm to process the bronchial surface model to determine bronchial voxels, and process the bronchial voxels to retain the single voxel value representing the bronchial topological structure.

[0068] S233. Determine the centerline composed of the single voxel values as the bronchial centerline.

[0069] The single voxel value corresponds to a corresponding coordinate. The electronic device sequentially connects the coordinates corresponding to each single voxel value to generate a centerline, and this centerline is the bronchial centerline, as Figure 3 shown.

[0070] S24. Perform path search based on the end points, bifurcation points, and bronchial inlet points corresponding to the bronchial centerline to generate a target path for the lesion location.

[0071] Specifically, the above step S24 may include:

[0072] S241. Obtain the centerline point set of the bronchial centerline.

[0073] The centerline point set is the point cloud constituting the bronchial centerline. When the electronic device generates the bronchial centerline based on the single voxel value, it can save the centerline point set corresponding to the bronchial centerline to the storage space. When performing target path planning, directly read this centerline point set from the storage space.

[0074] S242. Determine the first distance from each end point and each bifurcation point to the lesion location.

[0075] The first distance is used to represent the Euclidean distance from the end point to the lesion location and the Euclidean distance from the bifurcation point to the lesion location. Specifically, taking each end point and each bifurcation point as the starting point and the lesion location as the ending point, the electronic device calculates the Euclidean distance from each end point and each bifurcation point to the lesion location respectively according to the distance formula between points to obtain a plurality of first distances.

[0076] It should be noted that the bronchial inlet point can also be used as an end point, and the Euclidean distance from the bronchial inlet point to the lesion location is calculated according to the distance formula between points.

[0077] S243. Compare multiple first distances, and determine several position points that are closest to the lesion location from each endpoint and each bifurcation point.

[0078] The electronic device compares multiple first distances, and determines multiple endpoints or bifurcation points that are closest to the lesion location as position points. For example, by calculating the Euclidean distances from each endpoint and each bifurcation point to the lesion location, two points with the smallest distances are selected from each endpoint and each bifurcation point as position points.

[0079] S244. Determine the second distances from the bronchial inlet point to each position point.

[0080] The second distances are used to represent the path distances from the bronchial inlet point to each position point, and the second distances are calculated based on the adjacency matrix. Specifically, there is a shortest path from the bronchial inlet point to each position point. There are multiple path points on the path. The sum of the Euclidean distances calculated between each path point is the path distance, that is, the second distance.

[0081] S245. Compare the sum of the first distances and the second distances of several position points, and determine the target point that is closest to the lesion location from several position points.

[0082] The electronic device can calculate the sum of the first distance and the second distance corresponding to each position point respectively, and compare the sum of the first distances and the second distances of multiple position points to determine the minimum distance. Then, based on the minimum distance, the position point that is closest to the lesion location can be determined, and this position point is determined as the target point.

[0083] For example, by calculating the Euclidean distances from each endpoint and each bifurcation point to the lesion location, two position points with the smallest distances are selected from each endpoint and each bifurcation point, and then the path distances from the bronchial inlet point to these two position points are calculated. By comparing the two calculated path distances, the target point is selected from these two position points, and this target point is the optimal point that is closest to the lesion location.

[0084] S246. Determine the third distances from each centerline point in the centerline point set to the lesion location.

[0085] The third distance is the Euclidean distance from the centerline point to the lesion location. Specifically, taking the centerline point as the starting point and the lesion location as the ending point, the electronic device calculates the Euclidean distances from each centerline point to the lesion location respectively according to the distance formula between points, and obtains multiple third distances.

[0086] S247. Compare multiple third distances, and determine the target centerline point that is closest to the lesion location.

[0087] The electronic device compares multiple third distances, determines the centerline point closest to the lesion location, and determines this centerline point as the target centerline point.

[0088] S248. Based on the positional relationship among the bronchial inlet point, the target point, the target centerline point, and the lesion location, determine the target path.

[0089] According to the positional relationship among the bronchial inlet point, the target point, the target centerline point, and the lesion location, multiple Euclidean distances can be determined respectively. Combining these multiple Euclidean distances to construct the target path from the bronchial inlet to the lesion location, as Figure 4 shown.

[0090] Specifically, the above step S248 may include:

[0091] (1) Based on the positions of the bronchial inlet point and the target point, determine the first path between the bronchial inlet point and the target point.

[0092] (2) Based on the positions of the target point and the target centerline point, determine the second path between the target point and the target centerline point.

[0093] (3) Based on the positions of the target centerline point and the lesion location, determine the third path between the target centerline point and the lesion location.

[0094] (4) Combine the first path, the second path, and the third path to generate the target path.

[0095] The electronic device numbers the centerline point set and constructs an adjacency matrix. Assuming there are n centerline points in the centerline point set, an n*n adjacency matrix is established according to the topological relationship. The matrix point at the corresponding x-th row and y-th column in the matrix represents the connection relationship and connection distance between the x-th point and the y-th point. 0 is used to represent non-connection, and a non-zero value represents connection and the Euclidean distance between the two points.

[0096] Taking the bronchial inlet point as the source point denoted as A, each endpoint and bifurcation point as the target point, search for the shortest path from the source point to the target point and retain the path distance and path points. Taking the lesion location as the target point, calculate the Euclidean distance from the lesion location to each endpoint and bifurcation point and the sum of the paths from each endpoint and bifurcation point to the source point A, and determine the endpoint or bifurcation point closest to the lesion location; re-take this endpoint or bifurcation point as the source point, denoted as B, and then calculate the centerline point with the smallest Euclidean distance to the lesion location as the target point, denoted as C; based on the adjacency matrix, determine the shortest path between points B and C; combine the path from A to B, the path from B to C, and the path from C to the lesion location to obtain the optimal path, that is, the target path from the bronchial inlet to the lesion location, and display this target path in the three-dimensional bronchial view or sectional view, as Figure 5 shown.

[0097] The bronchial lesion path planning method provided in this embodiment facilitates accurate positioning to the lesion location by viewing three-dimensional scan data from multiple angles and dimensions. By using a preset segmentation model to determine the bronchial data segmentation result from the multi-dimensional cross-section sequence data, and performing fusion processing on the bronchial data segmentation results in different dimensions to determine the target bronchial data, the accuracy of extracting the target bronchial data is ensured. By extracting the voxel values of the bronchial surface model and determining the centerline composed of single voxel values as the bronchial centerline, the accuracy of extracting the bronchial center point is guaranteed, which facilitates more accurate path search in the subsequent process. By planning the first path between the bronchial inlet point and the target point, the second path between the target point and the target centerline point, and the third path between the target centerline point and the lesion location, and merging the three parts of the paths to generate the target path, the optimal planning of the target path is achieved through the optimal planning of each path.

[0098] In this embodiment, a bronchial lesion path planning method is provided, which can be used in electronic devices such as computers, servers, hosts, etc. Figure 6 It is a flowchart of the bronchial lesion path planning method according to an embodiment of the present invention, as Figure 6 shown, and the process includes the following steps:

[0099] S31, obtain a three-dimensional scan image of the bronchus. For detailed description, refer to the relevant description corresponding to the above embodiment, and details will not be repeated here.

[0100] S32, analyze the three-dimensional scan image to determine the target bronchial data and the lesion location. For detailed description, refer to the relevant description corresponding to the above embodiment, and details will not be repeated here.

[0101] S33, extract the bronchial centerline from the target bronchial data. For detailed description, refer to the relevant description corresponding to the above embodiment, and details will not be repeated here.

[0102] S34, perform path search based on the endpoints, bifurcation points, and bronchial inlet point corresponding to the bronchial centerline to generate a target path for the lesion location. For detailed description, refer to the relevant description corresponding to the above embodiment, and details will not be repeated here.

[0103] S35, in response to an adjustment operation on the path point, determine the target path point based on the adjustment operation.

[0104] After generating the target path, the doctor can view the target path through the visualization device (such as a display screen) of the electronic device, and use the control module to rotate, zoom in and out, and pan the three-dimensional bronchial view or sectional view to view the planned target path from multiple angles and dimensions. If the doctor finds that the target path passes through the lesion location of the bronchus, the path points constituting the target path can be adjusted through the control module. Correspondingly, the electronic device can respond to the doctor's adjustment operation on the path points, and update the path points of the target path according to the adjustment operation to obtain the target path points, as Figure 7 shown.

[0105] S36, update the target path based on the target path points.

[0106] The electronic device re-plans the path for the lesion location according to the target path points to update the target path. Specifically, the electronic device can respond to the doctor's movement operation on the unreasonable path points, and synchronously update the target path in the three-dimensional bronchial view and the sectional view according to the movement operation. The electronic device can also respond to the doctor's deletion operation on the unreasonable path points, and after deleting the unreasonable path points, automatically complete the path between adjacent path points to realize the real-time update of the target path. The electronic device can also calculate the length of the target path in real time, quantify the path information, so as to view the adjustment changes of the target path in real time, which is convenient for the doctor to select a suitable surgical path.

[0107] S37, in response to the switching operation of the three-dimensional scan image, determine the registration point data of the bronchus.

[0108] The registration point data is the registration point coordinates between the three-dimensional scan image and the human body area. The doctor uses the control module of the electronic device to switch the visualization area of the three-dimensional scan image, and selects the registration point data of the bronchus from the three-dimensional scan image. Correspondingly, the electronic device can respond to the doctor's switching operation on the visualization area, and determine the selected registration point data based on the switching operation.

[0109] S38, perform spatial registration on the target path and the bronchus based on the registration point data.

[0110] There is a mapping ratio between the three-dimensional scan image and the real human body area. The registration point data is converted through the mapping ratio, and the mapped and converted registration points are added to the electronic device for spatial registration of the target path and the bronchus, so as to verify the accuracy of the target path. The electronic device can also save and export the target path, and the exported target path can be read, displayed or adjusted again through the electronic device.

[0111] The path planning method for bronchial lesions provided in this embodiment supports adjusting the path points of the target path, thereby facilitating real-time adjustment of the target path according to the actual situation of the bronchial lesions, making the planning of the target path more flexible. The target path is spatially registered with the bronchus through the registration point data of the bronchus to verify the accuracy of the target path, further improving the accuracy of the target path.

[0112] In this embodiment, a path planning device for bronchial lesions is also provided. This device is used to implement the above-mentioned embodiment and preferred implementation manners, and those that have been described will not be repeated. As used hereinafter, the term "module" can be a combination of software and / or hardware that realizes a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, implementation in hardware, or a combination of software and hardware is also possible and contemplated.

[0113] This embodiment provides a path planning device for bronchial lesions, as Figure 8 shown, including:

[0114] An acquisition module 41, configured to acquire a three-dimensional scan image of the bronchus.

[0115] An analysis module 42, configured to analyze the three-dimensional scan image to determine the target bronchus data and the lesion location.

[0116] An extraction module 43, configured to extract the bronchial centerline from the target bronchus data.

[0117] A generation module 44, configured to perform path search based on the end points, bifurcation points, and bronchial inlet points corresponding to the bronchial centerline, and generate a target path for the lesion location.

[0118] Optionally, the above analysis module 42 may specifically include:

[0119] An analysis sub-module, configured to analyze the three-dimensional scan data to obtain a plurality of cross-sectional sequence data of the bronchus.

[0120] A response sub-module, configured to respond to a switching operation on the plurality of cross-sectional sequence data, determine a target cross-section with a lesion based on the switching operation, and extract the lesion location from the target cross-section.

[0121] A segmentation sub-module, configured to perform segmentation processing on the plurality of cross-sectional sequence data based on a preset segmentation model to obtain data segmentation results corresponding to each cross-sectional sequence data.

[0122] A fusion sub-module, configured to perform fusion processing on the plurality of data segmentation results to obtain the target bronchus data.

[0123] Optionally, the above extraction module 43 may specifically include:

[0124] A model drawing sub-module, configured to perform model drawing on target bronchial data based on a preset drawing method to generate a bronchial surface model.

[0125] A data processing sub-module, configured to process the data of the bronchial surface model to determine a single voxel value corresponding to the bronchial surface model.

[0126] A determination sub-module, configured to determine the centerline composed of the single voxel values as the bronchial centerline.

[0127] Optionally, the above-mentioned generation module 44 may specifically include:

[0128] A point set acquisition sub-module, configured to acquire the centerline point set of the bronchial centerline.

[0129] A first distance determination sub-module, configured to determine the first distance from each endpoint and each bifurcation point to the lesion location.

[0130] A first comparison sub-module, configured to compare multiple first distances to determine several position points closest to the lesion location from each endpoint and each bifurcation point.

[0131] A second distance determination sub-module, configured to determine the second distance from the bronchial inlet point to each position point.

[0132] A second comparison sub-module, configured to compare the sum of the first distance and the second distance of several position points to determine a target point closest to the lesion location from the several position points;

[0133] A third distance determination sub-module, configured to determine the third distance from each centerline point in the centerline point set to the lesion location.

[0134] A third comparison sub-module, configured to compare multiple third distances to determine a target centerline point closest to the lesion location.

[0135] A path determination sub-module, configured to determine a target path based on the positional relationship among the bronchial inlet point, the target point, the target centerline point, and the lesion location.

[0136] Optionally, the above-mentioned path determination sub-module is configured to: determine a first path between the bronchial inlet point and the target point based on the positions of the bronchial inlet point and the target point; determine a second path between the target point and the target centerline point based on the positions of the target point and the target centerline point; determine a third path between the target centerline point and the lesion location based on the positions of the target centerline point and the lesion location; merge the first path, the second path, and the third path to generate a target path.

[0137] Optionally, the above-mentioned path planning device for bronchial lesions may further include:

[0138] A path point adjustment module, configured to determine a target path point based on an adjustment operation in response to an adjustment operation on a path point.

[0139] An update module, configured to update a target path based on the target path point.

[0140] Optionally, the above-mentioned path planning device for bronchial lesions may further include:

[0141] A switching module, configured to determine registration point data of the bronchus in response to a switching operation on a three-dimensional scan image.

[0142] A registration module, configured to perform spatial registration on the target path and the bronchus based on the registration point data.

[0143] The path planning device for bronchial lesions in this embodiment is presented in the form of functional units. Here, the unit refers to an ASIC circuit, a processor and a memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0144] The further function descriptions of the above-mentioned various modules and sub-modules are the same as those in the corresponding embodiments above, and will not be elaborated here.

[0145] The path planning device for bronchial lesions provided in this embodiment determines target bronchus data and lesion positions by parsing three-dimensional scan images of the bronchus, and extracts the bronchial centerline from the target bronchus data. Since the bronchial centerline can represent the shape of the bronchial tree, corresponding target paths are generated according to the end points, bifurcation points and bronchial inlet points corresponding to the bronchial centerline, realizing the automatic generation of path planning. The device identifies the bronchial tree to accurately extract the bronchial centerline, so that the target path can be planned according to the bronchial centerline and the lesion position, regardless of the complexity of the lesion position, effectively improving the accuracy and precision of path planning.

[0146] An embodiment of the present invention further provides an electronic device having the above-mentioned Figure 8 path planning device for bronchial lesions as shown.

[0147] Please refer to Figure 9 , Figure 9 which is a schematic structural diagram of an electronic device provided by an optional embodiment of the present invention. As shown in Figure 9As shown, the electronic device may include: at least one processor 501, such as a Central Processing Unit (CPU), at least one communication interface 503, a memory 504, and at least one communication bus 502. Among them, the communication bus 502 is used to realize the connection and communication between these components. Among them, the communication interface 503 may include a display screen and a keyboard. Optionally, the communication interface 503 may further include a standard wired interface and a wireless interface. The memory 504 may be a high-speed volatile random access memory (RAM), or a non-volatile memory, such as at least one disk memory. Optionally, the memory 504 may also be at least one storage device located far from the aforementioned processor 501. Among them, the processor 501 may be combined with Figure 8 the described device, the memory 504 stores an application program, and the processor 501 calls the program code stored in the memory 504 to execute any of the above method steps.

[0148] Among them, the communication bus 502 may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus 502 may be divided into an address bus, a data bus, a control bus, etc. For the sake of representation, Figure 9 only a thick line is used to represent it in the figure, but it does not mean that there is only one bus or one type of bus.

[0149] Among them, the memory 504 may include a volatile memory, such as a random-access memory (RAM); the memory may also include a non-volatile memory, such as a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD); the memory 504 may further include a combination of the above types of memories.

[0150] Among them, the processor 501 may be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and an NP.

[0151] Among them, the processor 501 may further include a hardware chip. The above-mentioned hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The above-mentioned PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0152] Optionally, the memory 504 is further configured to store program instructions. The processor 501 may call the program instructions to implement the path planning method for bronchial lesions as shown in the above embodiments of the present application.

[0153] The embodiment of the present invention further provides a non-transitory computer storage medium. The computer storage medium stores computer-executable instructions, and the computer-executable instructions can execute the path planning method for bronchial lesions in any of the above method embodiments. Among them, the storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), a random access memory (RAM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD), etc.; the storage medium may also include a combination of the above types of memories.

[0154] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A path planning method for bronchial lesions, characterized in that Including: Obtaining a three-dimensional scan image of the bronchus; Analyzing the three-dimensional scan image to determine target bronchus data and the lesion location; Extracting the bronchus centerline from the target bronchus data; Performing a path search based on the endpoints, bifurcation points, and bronchus inlet point corresponding to the bronchus centerline to generate a target path for the lesion location, including: obtaining the centerline point set of the bronchus centerline; determining the first distance from each endpoint and each bifurcation point to the lesion location; comparing multiple of the first distances to determine several position points closest to the lesion location from each endpoint and each bifurcation point; determining the second distance from the bronchus inlet point to each of the position points; comparing the sum of the first distance and the second distance of several of the position points to determine a target point closest to the lesion location from the several position points; determining the third distance from each centerline point in the centerline point set to the lesion location; comparing multiple of the third distances to determine a target centerline point closest to the lesion location; determining the target path based on the positional relationship among the bronchus inlet point, the target point, the target centerline point, and the lesion location.

2. The method according to claim 1, characterized in that The analyzing the three-dimensional scan image to determine target bronchus data includes: Analyzing the three-dimensional scan image to obtain multiple cross-sectional sequence data of the bronchus; In response to a switching operation on the multiple cross-sectional sequence data, determining a target cross-section with a lesion based on the switching operation and extracting the lesion location from the target cross-section; Performing a segmentation process on the multiple cross-sectional sequence data based on a preset segmentation model to obtain data segmentation results corresponding to each cross-sectional sequence data; Performing a fusion process on multiple of the data segmentation results to obtain the target bronchus data.

3. The method according to claim 1, characterized in that, The extracting the bronchus centerline from the target bronchus data includes: Performing a model drawing on the target bronchus data based on a preset drawing method to generate a bronchus surface model; Performing data processing on the bronchus surface model to determine a single voxel value corresponding to the bronchus surface model; Determining the centerline composed of the single voxel values as the bronchus centerline.

4. The method according to claim 1, wherein The determining the target path based on the straight-line distances among the bronchus inlet point, the target point, the target centerline point, and the lesion location includes: Determining a first path from the bronchus inlet point to the target point based on the positions of the bronchus inlet point and the target point; Determining a second path from the target point to the target centerline point based on the positions of the target point and the target centerline point; Determining a third path from the target centerline point to the lesion location based on the positions of the target centerline point and the lesion location; Combining the first path, the second path, and the third path to generate the target path.

5. The method according to claim 1, wherein It also includes: In response to an adjustment operation on a path point, determining a target path point based on the adjustment operation; Updating the target path based on the target path point.

6. The method according to claim 1, wherein It also includes: In response to a switching operation on the three-dimensional scanned image, determine the registration point data of the bronchus; Perform spatial registration of the target path and the bronchus based on the registration point data.

7. A path planning device for bronchial lesions, characterized in that, Comprising: An acquisition module, configured to acquire a three-dimensional scanned image of the bronchus; An analysis module, configured to analyze the three-dimensional scanned image to determine target bronchus data and the lesion location; An extraction module, configured to extract the bronchial centerline from the target bronchus data; A generation module, configured to perform path search based on the end points, bifurcation points, and bronchial inlet points corresponding to the bronchial centerline, and generate a target path for the lesion location; Wherein, the generation module includes: a point set acquisition sub-module, configured to acquire the centerline point set of the bronchial centerline; a first distance determination sub-module, configured to determine the first distance from each end point and each bifurcation point to the lesion location; a first comparison sub-module, configured to compare multiple first distances, and determine several position points closest to the lesion location from each end point and each bifurcation point; a second distance determination sub-module, configured to determine the second distance from the bronchial inlet point to each of the position points; a second comparison sub-module, configured to compare the sum of the first distance and the second distance of several position points, and determine a target point closest to the lesion location from the several position points; a third distance determination sub-module, configured to determine the third distance from each centerline point in the centerline point set to the lesion location; a third comparison sub-module, configured to compare multiple third distances, and determine a target centerline point closest to the lesion location; a path determination sub-module, configured to determine the target path based on the positional relationship between the bronchial inlet point, the target point, the target centerline point, and the lesion location.

8. An electronic device, characterized in that, Comprising: A memory and a processor, the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to execute the path planning method for bronchial lesions according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions, and the computer instructions are used to cause a computer to execute the path planning method for bronchial lesions according to any one of claims 1-6.

Images