A dual-lumen bronchial tube intubation simulation method, system, device and storage medium

Abstract

The application provides a double-lumen bronchial catheter intubation simulation method, system, device and storage medium, which comprises the following steps: converting a chest thin layer CT scan sequence into mask data; converting the mask data into a bronchial three-dimensional model; extracting a centerline model of the bronchial three-dimensional model; constructing a graph data structure; calculating the shortest path from the intubation starting point to the ending point to generate a path point list; rendering a temporarily selected double-lumen bronchial catheter on the shortest path; following the intubation operation, comparing the size relationship between the airway radius and the tracheal catheter radius and the bronchial catheter radius in real time, and outputting the intubation animation and the catheter diameter comparison result. The application can realize the specification optimization of the double-lumen bronchial catheter through the intubation simulation mode, and assist in improving the safety and effectiveness of the intubation operation; the application can provide a visual reference for path planning by visualizing the intubation process before intubation, which is helpful to reduce the intubation failure risk caused by improper insertion position.

Description

Technical Field

[0001] This application relates to the field of medical device technology, specifically to a method, system, device, and storage medium for simulating dual-lumen bronchial tube insertion. Background Technology

[0002] A double-lumen bronchial catheter is a medical catheter with two independent lumens (such as...). Figure 3 As shown in the image, double-lumen endotracheal tubes (BLTBs) are primarily used in thoracic surgery and some cardiac surgeries to achieve lung isolation and unilateral lung ventilation (collapse of the operated lung to maintain its stillness for easier manipulation, while simultaneously maintaining normal ventilation of the non-operated lung). BLTBs significantly improve the safety and controllability of thoracic surgeries, reducing intraoperative complications, and are an indispensable key tool in modern anesthesiology and thoracic surgery. However, under traditional techniques, the failure rate of BLTB insertion ranges from 32% to 83%.

[0003] In practical clinical applications, the key to successful double-lumen endotracheal tube intubation lies in two aspects: First, the size of the double-lumen endotracheal tube must match the patient's airway anatomy. If the tube diameter is too small, airway resistance increases, leading to poor ventilation of the non-operated lung and potentially causing intraoperative hypoxia; if the tube diameter is too large, the risk of airway injury during intubation increases. Second, the insertion position of the double-lumen endotracheal tube needs to be very accurate (e.g., Figure 4 As shown in the figure, if the insertion position is not appropriate, ideal one-lung ventilation cannot be achieved, and the lung on the surgical side will expand, which will lead to difficulties in surgical operation or intraoperative hypoxia.

[0004] Currently, the selection of the specifications of double-lumen endotracheal tubes and the accurate insertion of the target location highly depend on the anesthesiologist's operational experience and preoperative imaging assessment. However, some anesthesiologists lack sufficient knowledge of imaging, which makes the selection of double-lumen tube specifications and the prediction of the insertion location quite difficult, thus affecting the success rate of intubation and the safety of the operation.

[0005] Therefore, how to design a dual-lumen bronchial tube insertion simulation system that can avoid the mismatch between the specifications of the dual-lumen bronchial tube and the anatomical structure of the patient's airway and improve the accuracy of the insertion position is a technical problem that has not yet been solved in the existing technology. Summary of the Invention

[0006] Therefore, the technical problem to be solved by this application is to overcome the technical defects in the prior art where the selection of the specifications of the double-lumen bronchial tube and the prediction of the insertion position are highly dependent on the experience of the anesthesiologist and the imaging assessment, resulting in improper specification matching and poor accuracy of insertion position. In order to provide a double-lumen bronchial tube insertion simulation method, system, device and storage medium that can avoid the mismatch between the specification selection of the double-lumen bronchial tube and the anatomical structure of the patient's airway and improve the accuracy of insertion position.

[0007] This application mainly includes the following aspects:

[0008] In a first aspect, embodiments of this application provide a method for simulating the insertion of a dual-lumen bronchial catheter. The method includes: acquiring a thin-slice CT scan sequence of the chest; converting the thin-slice CT scan sequence of the chest into mask data; converting the mask data into a three-dimensional bronchial model using a moving cubes algorithm; extracting the centerline model of the three-dimensional bronchial model using an average curvature flow algorithm; constructing a graph data structure based on the three-dimensional bronchial model and the centerline model, and ensuring that the centerline nodes of the centerline model correspond one-to-one with the vertices of the graph data structure, wherein the vertices include the spatial coordinates of the centerline nodes and the surface points of the three-dimensional bronchial model before contraction corresponding to the centerline nodes. The system generates a list of coordinates; obtains the spatial coordinates of the inlet and outlet of the centerline model, calculates the shortest path from the inlet to the outlet using a graph search algorithm, and generates a list of path points; obtains the specifications of a temporarily selected double-lumen bronchial tube, and renders the temporarily selected double-lumen bronchial tube on the shortest path; follows the insertion operation of the temporarily selected double-lumen bronchial tube, updates the coordinates of the tracheal tube tip and the bronchial tube tip in real time, calculates the airway radius corresponding to the coordinates of the tracheal tube tip and the bronchial tube tip respectively in real time, compares the size relationship between the airway radius and the tracheal tube radius and the bronchial tube radius, and outputs the insertion animation and tube diameter comparison results.

[0009] According to one embodiment of this application, the step of calculating the airway radius corresponding to the coordinates of the endotracheal tube tip and the bronchial tube tip in real time, and comparing the size relationship between the airway radius and the endotracheal tube radius and the bronchial tube radius, includes: obtaining the first coordinate value of the next coordinate in the path point list corresponding to the bronchial tube tip coordinate; calculating the first airway radius at the airway position corresponding to the first coordinate value; comparing the size of the first airway radius and the bronchial tube radius, and if the first airway radius is smaller than the bronchial tube radius, displaying the tube diameter comparison result in red; obtaining the second coordinate value of the next coordinate in the path point list corresponding to the endotracheal tube tip coordinate; calculating the second airway radius at the airway position corresponding to the second coordinate value; comparing the size of the second airway radius and the endotracheal tube radius, and if the second airway radius is smaller than the endotracheal tube radius, displaying the tube diameter comparison result in red.

[0010] According to one embodiment of this application, the step of calculating the first airway radius corresponding to the airway position of the first coordinate value includes: extracting the first spatial coordinates corresponding to the first coordinate value and the first surface point coordinate list corresponding to the first spatial coordinates from the graph data structure; calculating the Euclidean distance between the first spatial coordinates and all surface point coordinates in the first surface point coordinate list, and taking the minimum value as the first airway radius; the step of calculating the second airway radius corresponding to the airway position of the second coordinate value includes: extracting the second spatial coordinates corresponding to the second coordinate value and the second surface point coordinate list corresponding to the second spatial coordinates from the graph data structure; calculating the Euclidean distance between the second spatial coordinates and all surface point coordinates in the second surface point coordinate list, and taking the minimum value as the second airway radius.

[0011] According to one embodiment of this application, the chest thin-slice CT scan sequence is converted into the mask data using a deep learning image segmentation model; the deep learning image segmentation model is a three-dimensional segmentation neural network constructed based on the 3DU-Net network; the training parameters of the three-dimensional segmentation neural network include: a sample batch size of 2, and a voxel block size of [missing information]. The normalization scheme uses CTNormalization, with a median voxel size of [234, 509.5, 512] and an image spatial spacing of [1, 0.7333984375, 0.7333984375]. The network parameters of the 3D segmentation neural network include: 32 basic feature channels, [2, 2, 2, 2, 2, 2] convolutional layers in each stage of the encoder, and [2, 2, 2] convolutional layers in each stage of the decoder. [2,2,2], the number of pooling operations for each axis is [4,5,5], the downsampling stride is 2, the convolution kernel size is [[3,3,3],[3,3,3],[3,3,3],[3,3,3],[3,3,3],[3,3,3]], the pooling kernel size is [[1,1,1],[2,2,2],[2,2,2],[2,2,2],[2,2,2],[1,2,2]], the convolution stride is 1, and the convolution padding is 1.

[0012] According to one embodiment of this application, the step of obtaining the specification parameters of a temporarily selected double-lumen bronchial tube and rendering the temporarily selected double-lumen bronchial tube on the shortest path includes: establishing an index value list for the shortest path; obtaining the specification parameters of the temporarily selected double-lumen bronchial tube and determining the front end position of the tracheal tube; based on the index value corresponding to the inlet end of the double-lumen bronchial tube on the shortest path, rendering the double-lumen bronchial tube on the shortest path, and rendering the tracheal tube model and the bronchial tube model respectively after the front end position of the tracheal tube crosses the inlet start point, using the front end position of the tracheal tube as a dividing point.

[0013] According to one embodiment of this application, after rendering the tracheal tube model and the bronchial tube model separately using the front end position of the tracheal tube as the dividing point, the method further includes a step of smoothly transitioning the bronchial tube model at the tracheal carina. Specifically, this includes: if the current bronchial tube front end index value is greater than the tracheal carina index value, it indicates that the bronchial tube portion has entered the bronchus; in the constructed vtkPoints instance, deleting the index point of the tracheal carina index value, and several index points before and after it; inputting the vtkPoints instance after deleting the index points as control points into vtkParametricSpline to generate a parametric curve equation; inputting the parametric curve equation into vtkParametricFunctionSource for interpolation to obtain interpolated discrete curve data; constructing a vtkTubeFilter instance, inputting the interpolated discrete curve data, setting the radius to the radius of the bronchial tube, and setting the end-closure parameter to True; and then using vtkTubeFilter... The output is used as the final rendering data and sent to the VTK rendering pipeline for rendering to achieve a smooth transition rendering effect from the main trachea to the bronchi.

[0014] According to one embodiment of this application, the specifications of the double-lumen bronchial catheter include: bronchial catheter length; tracheal catheter radius; and bronchial catheter radius.

[0015] Secondly, this application also provides a dual-lumen bronchial catheter insertion simulation system, the system comprising: an acquisition module for acquiring a thin-slice chest CT scan sequence, the spatial coordinates of the insertion start and end points, and the specifications of a tentatively selected dual-lumen bronchial catheter; an image segmentation module for converting the thin-slice chest CT scan sequence into mask data; a 3D modeling module for converting the mask data into a bronchial 3D model; a centerline extraction module for extracting the centerline model from the bronchial 3D model; a graph data construction module for constructing a graph data structure; and a path planning module. The module is used to calculate the shortest path from the inlet to the outlet and generate a list of path points; the model rendering module is used to render the endotracheal tube model and the bronchial tube model, including: a smooth transition processing unit: used to achieve a smooth transition of the bronchial tube model at the carina position; a radius calculation and comparison module: used to calculate the airway radius corresponding to the coordinates of the endotracheal tube tip and the bronchial tube tip in real time, and compare the size relationship between the airway radius and the endotracheal tube radius and the bronchial tube radius; the display module is used to display the inlet animation and tube diameter comparison results.

[0016] Thirdly, embodiments of this application also provide a computer device, the computer device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to cause the at least one processor to perform the steps of the method described above when executing the instructions.

[0017] Fourthly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method described above.

[0018] The technical solution provided in this application has the following advantages:

[0019] 1. The double-lumen bronchial tube insertion simulation method of this application is based on converting a thin-slice CT scan sequence of the chest into a three-dimensional model and a centerline model of the bronchus. After obtaining the specifications of the tentatively selected double-lumen bronchial tube, the method simulates the insertion process and continuously compares the size relationship between the airway radius and the tracheal tube radius and the bronchial tube radius step by step, thereby achieving optimal specification of the double-lumen bronchial tube. Physicians can directly judge the compatibility between the tentatively selected double-lumen bronchial tube and the patient's airway based on the comparison results, which can effectively avoid the risk of airway damage caused by excessively large specifications or ventilation problems caused by excessively small specifications, thus helping to improve the safety and effectiveness of intubation operations.

[0020] 2. The double-lumen bronchial tube insertion simulation method of this application, by integrating medical image processing technology and three-dimensional modeling technology, performs a visual simulation of the double-lumen bronchial tube insertion process before intubation, providing an intuitive visual reference for planning the double-lumen bronchial tube insertion path, which helps to reduce the risk of intubation failure due to improper insertion position and reduces the dependence on the anesthesiologist's experience.

[0021] 3. The dual-lumen bronchial tube insertion simulation method of this application, compared with the traditional method that requires principal component analysis to calculate the normal direction and search for the nearest point on the surface point by point, this application pre-constructs a graph data structure and performs Euclidean distance calculation based on the list of surface point coordinates corresponding to the centerline node. This transforms the complex radius calculation into a fast retrieval of fixed data and simple geometric operations, which significantly simplifies the real-time calculation process of airway radius, improves the response efficiency of the simulation system, and provides efficient and accurate technical support for the dynamic evaluation of tube diameter adaptability during intubation.

[0022] 4. The dual-lumen bronchial tube insertion simulation method of this application renders the tracheal and bronchial parts of the dual-lumen bronchial tube as independent units, avoiding the joint calculation of complex geometric structures in the traditional overall rendering mode, significantly reducing the computational load of the rendering engine, improving the rendering speed, and ensuring the smoothness of the simulation process.

[0023] 5. The dual-lumen bronchial tube insertion simulation method of this application, by deleting index points near the carina and reconstructing parametric curves, makes the bronchial tube model conform to the physiological curvature of the human airway at the carina, avoiding image distortion caused by geometric abrupt changes and improving simulation accuracy.

[0024] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0025] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0026] Figure 1 This is the overall flowchart of the dual-lumen bronchial tube insertion simulation method of this application.

[0027] Figure 2 This is the system architecture diagram of this application.

[0028] Figure 3 This is a schematic diagram of an existing double-lumen bronchial tube.

[0029] Figure 4 This is a schematic diagram showing the correct position of a double-lumen bronchial tube.

[0030] Figure 5 This is a schematic diagram of the binarized mask data.

[0031] Figure 6 This is a schematic diagram of a voxel cube unit.

[0032] Figure 7 This is a schematic diagram of the 3D rendering interface after selecting the starting and ending points of the inlet pipe.

[0033] Figure 8 These are schematic diagrams of tracheal tube models and bronchial tube models.

[0034] Figure 9 This is a schematic diagram showing the comparison results of pipe diameters. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. It should be understood that the drawings in this application are for illustrative and descriptive purposes only and are not intended to limit the scope of protection of this application. Furthermore, it should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of this application. It should be understood that the operations in the flowcharts may not be implemented in sequence, and steps without logical contextual relationships may be reversed or implemented simultaneously. In addition, those skilled in the art, guided by the content of this application, may add one or more other operations to the flowcharts, or remove one or more operations from the flowcharts.

[0036] Furthermore, the described embodiments are merely some, not all, of the embodiments of this application. The components of the embodiments of this application described and illustrated herein can typically be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of this application provided in the accompanying drawings is not intended to limit the scope of the claimed application, but merely to illustrate selected embodiments of the application. All other embodiments obtained by those skilled in the art based on the embodiments of this application without inventive effort are within the scope of protection of this application.

[0037] The present application will now be described in detail with reference to the accompanying drawings and embodiments. Example

[0038] like Figure 1 As shown, this embodiment provides a method for simulating the insertion of a double-lumen bronchial tube, including the following steps:

[0039] S101: Acquire thin-section CT scan sequence of the chest;

[0040] S102: Convert thin-section chest CT scan sequences into mask data;

[0041] S103: Convert mask data into a 3D model of the bronchus using the moving cube algorithm;

[0042] S104: Extracting the centerline model of the bronchial 3D model using the average curvature flow algorithm;

[0043] S105: Construct a graph data structure based on the bronchial 3D model and the centerline model, and make the centerline nodes of the centerline model correspond one-to-one with the vertices of the graph data structure. The vertices include the spatial coordinates of the centerline nodes and a list of surface point coordinates of the bronchial 3D model before contraction corresponding to the centerline nodes.

[0044] S106: Obtain the spatial coordinates of the inlet and outlet of the centerline model, calculate the shortest path from the inlet to the outlet using a graph search algorithm, and generate a list of path points;

[0045] S107: Obtain the specifications of the temporarily selected double-lumen bronchial tube and render the temporarily selected double-lumen bronchial tube on the shortest path.

[0046] S108: Follows the insertion operation of the temporarily selected double-lumen endotracheal tube, updates the coordinates of the endotracheal tube tip and the bronchial tube tip in real time, calculates the airway radius corresponding to the coordinates of the endotracheal tube tip and the bronchial tube tip respectively in real time, compares the size relationship between the airway radius and the endotracheal tube radius and the bronchial tube radius, and outputs the insertion animation and tube diameter comparison results.

[0047] The following details each step of the double-lumen endotracheal tube insertion simulation method:

[0048] S101: Acquire thin-section CT scan sequence of the chest;

[0049] Here, chest thin-section CT scan sequence refers to tomographic scan data stored in nii.gz format obtained by performing thin-section scans (slice thickness usually ≤1mm) on the patient's chest using clinical CT equipment. This data retains metadata such as voxel coordinates and spatial spacing of the original images, and can accurately present the subtle anatomical features of airway structures such as the main trachea and bronchi.

[0050] S102: Convert thin-section chest CT scan sequences into mask data;

[0051] In one possible implementation, step S102 involves converting a thin-slice chest CT scan sequence into mask data using a deep learning image segmentation model; the deep learning image segmentation model is a three-dimensional segmentation neural network built based on a 3D U-Net network.

[0052] The training parameters for a 3D segmentation neural network include:

[0053] The batch size is 2, and the patch size is [missing information]. The normalization schemes used were CT Normalization, with a median image size of [234, 509.5, 512] and an image spatial spacing of [1, 0.7333984375, 0.7333984375].

[0054] The network parameters of a 3D segmentation neural network include:

[0055] The base feature channel count (Unet_base_num_features) is 32, the number of convolutional layers per stage of the encoder (n_conv_per_stage_encoder) is [2,2,2,2,2,2], the number of convolutional layers per stage of the decoder (n_conv_per_stage_decoder) is [2,2,2,2,2,2], the number of pooling operations per axis (num_pool_per_axis) is [4,5,5], and the downsampling stride is [4,5,5]. The stride is 2, the convolution kernel size is [[3,3,3],[3,3,3],[3,3,3],[3,3,3],[3,3,3],[3,3,3],[3,3,3]], the pooling kernel size is [[1,1,1],[2,2,2],[2,2,2],[2,2,2],[2,2,2],[1,2,2]], the stride convolution is 1, and the padding convolution is 1.

[0056] This step utilizes a deep learning image segmentation model to accurately identify airway regions from thin-section chest CT scan sequences and converts them into binary mask data (i.e., a matrix where the target region is 1 and the background is 0, such as...). Figure 5 (As shown in the figure). This mask data can intuitively mark the distribution of the airway in three-dimensional space, providing a clear outline boundary for the subsequent construction of a three-dimensional model of the bronchus using the moving cube algorithm, avoiding the subjectivity and error of manual segmentation.

[0057] It is important to note that this deep learning image segmentation model uses a three-dimensional segmentation neural network built on the 3D U-Net network. The 3D U-Net network is a classic architecture in the field of medical image segmentation. Through the combination of an encoder-decoder structure and skip connections, it can extract deep features of the image while preserving shallow spatial information.

[0058] S103: Convert mask data into a 3D model of the bronchus using the moving cube algorithm;

[0059] Specifically, first, input the mask data generated in step S102, and divide the mask data into multiple... voxel cube units (such as) Figure 6As shown in the figure, each cell contains 8 voxels (values ​​of 0 or 1); for each cubic cell, if its 8 voxels contain both 0 and 1 (i.e., there is an airway boundary), the intersection points of the voxel edges and the airway surface are calculated (the coordinates of the intersection points are determined by linear interpolation); then, based on the 0 and 1 distribution of the voxels in the cell, a predefined configuration table is queried to determine the connection method of the intersection points, generating triangular patches to fit the airway surface contour; finally, all cubic cells are traversed, and the generated triangular patches are stitched together to form a complete 3D model of the bronchus.

[0060] Compared to traditional manual modeling, the moving cube algorithm can automatically generate a complete bronchial tree model from mask data, avoiding manual intervention and improving modeling efficiency. In addition, the algorithm can capture the fine structure of the airway through voxel-level intersection calculation, ensuring the consistency between the 3D model and the patient's real anatomical structure, and providing a reliable basis for matching the specifications of dual-lumen tubes.

[0061] S104: Extracting the centerline model of the bronchial 3D model using the average curvature flow algorithm;

[0062] Here, the 3D model of the bronchus (surface triangular mesh) generated in step S103 is first input. The mean curvature flow algorithm is used to shrink the 3D model. By iteratively evolving the model surface, the surface points move along the direction of its mean curvature, eventually converging into the model's centerline skeleton. This process can be implemented using the `extract_mean_curvature_flow_skeleton` function in the CGAL library. Specifically, during the iteration process, the surface mesh in the intermediate shrinkage stage is called the mid-skeleton. After each iteration, the system performs local remeshing of the mid-skeleton through angle segmentation and edge shrinkage. When the change in the mid-skeleton between two iterations is sufficiently small, the process terminates. Each edge shrinkage merges two vertices into one vertex. During this process, the algorithm records the triangular mesh vertices of the original surface mesh and assigns them to the centerline nodes on the final merged centerline.

[0063] The average curvature flow algorithm can accurately preserve the branching point positions and branching angles of the bronchial tree, avoiding the deviation of the centerline bifurcation point due to algorithm errors, and providing a real anatomical reference for the construction of the data structure in the subsequent step S105.

[0064] S105: Construct a graph data structure based on the bronchial 3D model and the centerline model, and make the centerline nodes of the centerline model correspond one-to-one with the vertices of the graph data structure. The vertices include the spatial coordinates of the centerline nodes and a list of surface point coordinates of the bronchial 3D model before contraction corresponding to the centerline nodes.

[0065] Here, we first input the 3D bronchial model generated in step S103 and the centerline model extracted in step S104. We then use the Boost library's adjacency matrix data structure, specifically boost::adjacency_list, to construct a weighted graph data structure. Specifically, each centerline node in the centerline model is used as a vertex in the graph data structure. By traversing the centerline's topology, we ensure a one-to-one correspondence between vertices and centerline nodes.

[0066] Each vertex stores the following attributes: 1) Spatial coordinates: Records the position of the centerline node in three-dimensional space, used to locate airway anatomical structures (such as carina, bronchial branch points); 2) Surface point coordinate list: Stores the coordinates of the airway surface points corresponding to the centerline node before the original three-dimensional model is shrunk; It should be noted that this list is retained during the shrinkage of the average curvature flow algorithm, and the airway surface geometry information can be obtained without additional calculation.

[0067] In addition, edges of the graph data structure are generated based on the connection relationship of the centerline nodes. The weight of the edge is defined as the Euclidean distance between two adjacent centerline nodes, which is used to reflect the actual length of the airway.

[0068] S106: Obtain the spatial coordinates of the inlet and outlet of the centerline model, calculate the shortest path from the inlet to the outlet using a graph search algorithm, and generate a list of path points;

[0069] The spatial coordinates of the inlet and outlet of the bronchus are obtained by the user clicking on the bronchial centerline model in the 3D rendering interface (e.g., ...). Figure 7 As shown in the figure, however, since the user's click position may deviate from the centerline model, when the user clicks with the mouse, the system will traverse all vertices of the graph data structure, calculate the three-dimensional Euclidean distance between the click position and the vertex, and select the point with the smallest distance as the starting or ending point of the ingress pipe.

[0070] Among them, the graph search algorithm adopts the breadth-first search algorithm (such as breadth_first_search in the boost library), which uses the edges and weights of the graph data structure to calculate the shortest path.

[0071] The shortest path calculation does not rely on human experience; it is directly generated by the algorithm based on the patient's individualized airway model, which improves the objectivity of path planning. Combined with the optimized implementation of the boost library, path calculation can be completed in milliseconds, meeting the needs of real-time clinical simulation.

[0072] S107: Obtain the specifications of the temporarily selected double-lumen bronchial tube and render the temporarily selected double-lumen bronchial tube on the shortest path.

[0073] In one possible implementation, the specifications of the double-lumen bronchial tube in step S107 include: bronchial tube length (bronc_len), trachea tube radius (trachea_rad), and bronchus radius (bronchus_rad).

[0074] It is important to note that the length of the main trachea in adults is approximately 11-13 cm (from the glottis to the carina), while the endotracheal tube portion of the clinically commonly used double-lumen endotracheal tube is typically 23-29 cm long. This length design allows for sufficient margin to ensure that the endotracheal tube is inserted through the mouth and covers the entire main trachea, eliminating the need to consider the issue of insufficient length.

[0075] In one possible implementation, the step S107 of obtaining the specification parameters of the temporarily selected double-lumen bronchial catheter and rendering the temporarily selected double-lumen bronchial catheter on the shortest path includes the following steps:

[0076] Step S1071: Create a list of index values ​​for the shortest path;

[0077] Step S1072: Obtain the specifications of the temporarily selected double-lumen endotracheal tube and determine the position of the endotracheal tube tip.

[0078] Step S1073: Based on the index value corresponding to the inlet tip of the double-lumen bronchial tube on the shortest path, render the double-lumen bronchial tube on the shortest path, and after the inlet tip of the tracheal tube crosses the inlet point, render the tracheal tube model and the bronchial tube model respectively with the inlet tip of the tracheal tube as the dividing point.

[0079] Here, the shortest path point list is defined as path_vec; the index of the inlet tip of the double-lumen endotracheal tube is idx_front; the index of the inlet tip of the endotracheal tube is idx_bifur; the length of the endotracheal tube is bronc_len; the radius of the endotracheal tube is trachea_rad; and the radius of the endotracheal tube is bronchus_rad.

[0080] In step S1071, the index value list is an ordered numbering mapping of the shortest path point list path_vec generated in S106. Specifically, the index value list is an integer sequence starting from 0, [0,1,2,…,n-1], where n is the total number of vertices in the shortest path point list path_vec. Each index value i corresponds to the unique spatial coordinates of path_vec[i], forming a one-to-one mapping relationship between "index and vertex". For example, in clinical scenarios, the oropharyngeal position (airway inlet) is often chosen as the starting point, and the target bronchus (such as the first branch of the left main bronchus) is chosen as the ending point. Therefore, the index value of the oropharyngeal position is 0, and the index value of the first branch of the left main bronchus is n-1. If the endotracheal tube does not enter the oropharyngeal position (starting point), its index value is negative, and the model of the endotracheal tube is not rendered in this case.

[0081] like Figure 8 As shown, during rendering, the tracheal tube model is rendered between the position with index value 0 and idx_bifur; the bronchial tube model is rendered between idx_bifur and idx_front. Specifically, when rendering the tracheal tube, firstly, the center line between 0 and idx_bifur is found. Then, using this center line as a reference, the tracheal tube is moved half the radius to the left and right respectively along a direction perpendicular to the center line, generating two auxiliary center lines, path_left and path_right. Then, the left and right portions of the tracheal tube are rendered using these two auxiliary center lines as axes, and finally merged into the entire tracheal tube model. When rendering the bronchial tube, if the front end of the bronchial tube does not reach the tracheal carina, it is treated as an extension of one of the auxiliary center lines for rendering. If the front end of the bronchial tube reaches the tracheal carina, steps S10731 to S10736 are executed to achieve a smooth transition rendering effect from the main trachea to the bronchi.

[0082] In this embodiment, the tracheal and bronchial portions of the dual-lumen bronchial catheter are rendered as independent units, avoiding the joint calculation of complex geometric structures in the traditional overall rendering mode. This significantly reduces the computational load on the rendering engine, improves the rendering speed, and ensures the smoothness of the simulation process.

[0083] In one possible implementation, after rendering the tracheal tube model and the bronchial tube model respectively using the front end position of the tracheal tube as the dividing point in step S1073, the method further includes a step of smoothly transitioning the bronchial tube model at the tracheal carina, specifically including the following steps:

[0084] Step S10731: If the current bronchial tube tip index value is greater than the tracheal carina index value, it indicates that part of the bronchial tube has entered the bronchus;

[0085] Step S10732: In the constructed vtkPoints instance, delete the index point of the tracheal carina index value, as well as several index points before and after it;

[0086] Step S10733: Input the vtkPoints instances after deleting the index points as control points into vtkParametricSpline to generate the parameterized curve equation;

[0087] Step S10734: Input the parameterized curve equation into vtkParametricFunctionSource for interpolation to obtain the interpolated discrete curve data;

[0088] Step S10735: Construct a vtkTubeFilter instance, input the interpolated discrete curve data, i.e. the output of vtkParametricFunctionSource, set the radius to the bronchial tube radius, and set the end-sealing parameter to True;

[0089] Step S10736: The output of vtkTubeFilter is used as the final rendering data and sent to the vtk rendering pipeline for rendering to achieve a smooth transition rendering effect from the main trachea to the bronchus.

[0090] This embodiment improves simulation accuracy by deleting index points near the carina and reconstructing parametric curves, making the bronchial tube model conform to the physiological curvature of the human airway at the carina, avoiding image distortion caused by geometric abrupt changes.

[0091] S108: Follows the insertion operation of the temporarily selected double-lumen endotracheal tube, updates the coordinates of the endotracheal tube tip and the bronchial tube tip in real time, calculates the airway radius corresponding to the coordinates of the endotracheal tube tip and the bronchial tube tip respectively in real time, compares the size relationship between the airway radius and the endotracheal tube radius and the bronchial tube radius, and outputs the insertion animation and tube diameter comparison results.

[0092] It should be noted that the insertion of the double-lumen bronchial tube is performed through mouse interaction. Specifically, pressing the right mouse button in the 3D rendering window and sliding it to the right will advance the double-lumen bronchial tube model one unit along the airway centerline, i.e., idx_front increments by 1; conversely, pressing the right mouse button and sliding it to the left will retreat the double-lumen bronchial tube model one unit along the airway centerline, i.e., idx_front decrements by 1.

[0093] When the model reaches the endpoint, continuing to slide to the right will stop updating the index value of idx_front and keep it locked. At this time, the front end of the dual-lumen bronchial tube model is fixed at the endpoint coordinate of path_vec to avoid rendering abnormalities due to index out of bounds.

[0094] In one possible implementation, the step S108, which involves calculating the airway radius corresponding to the coordinates of the endotracheal tube tip and the bronchial tube tip in real time, and comparing the airway radius with the endotracheal tube radius and the bronchial tube radius, includes the following cases:

[0095] Scenario 1: If the bronchial tube reaches the insertion point, but the endotracheal tube has not, the steps include:

[0096] Step 1081a: Obtain the first coordinate value of the next coordinate in the list of path points corresponding to the coordinates of the bronchial tube tip.

[0097] Step 1082a: Calculate the first airway radius corresponding to the airway position of the first coordinate value;

[0098] Step 1083a: Compare the size of the first airway radius with the bronchial tube radius. If the first airway radius is smaller than the bronchial tube radius, the tube diameter comparison result will be displayed in red.

[0099] Scenario 2: If the endotracheal tube has already passed the inlet point and the endotracheal tube has reached the inlet point, the steps include:

[0100] Step 1081b: Obtain the first coordinate value of the next coordinate in the list of path points corresponding to the coordinates of the bronchial tube tip.

[0101] Step 1082b: Calculate the first airway radius corresponding to the airway position of the first coordinate value;

[0102] Step 1083b: Compare the size of the first airway radius with the bronchial tube radius. If the first airway radius is smaller than the bronchial tube radius, the tube diameter comparison result will be displayed in red.

[0103] Step 1084b: Obtain the second coordinate value of the next coordinate in the list of path points corresponding to the coordinates of the endotracheal tube tip;

[0104] Step 1085b: Calculate the second airway radius corresponding to the airway position of the second coordinate value;

[0105] Step 1086b: Compare the radius of the second airway with the radius of the endotracheal tube. If the radius of the second airway is smaller than the radius of the endotracheal tube, the tube diameter comparison result will be displayed in red.

[0106] like Figure 9As shown, when the physician finds the tube diameter comparison result to be red, it indicates that the radius of the current double-lumen bronchial tube exceeds the inner diameter of the corresponding airway location, posing a risk of intubation injury. Subsequently, the physician should select the next size of double-lumen bronchial tube and input the new specification parameters. The system will automatically reconstruct the double-lumen bronchial tube model and re-compare the tube diameter. It is important to note that the final selected double-lumen bronchial tube should be the largest size that is smaller than and closest to the patient's airway inner diameter, rather than blindly selecting the smallest size. If the tube diameter is too small, it may lead to increased airway resistance, poor ventilation of the non-surgical lung, and a higher risk of intraoperative hypoxia.

[0107] In one possible implementation, the step of calculating the first airway radius corresponding to the airway position of the first coordinate value in steps 1082a and 1082b includes the following steps:

[0108] Step 10821: Extract the first spatial coordinates corresponding to the first coordinate values ​​and the list of first surface point coordinates corresponding to the first spatial coordinates from the graph data structure;

[0109] Step 10822: Calculate the Euclidean distance between the first spatial coordinates and the coordinates of all surface points in the first surface point coordinate list, and take the minimum value as the first airway radius;

[0110] In one possible implementation, the step of calculating the second airway radius corresponding to the second coordinate value in step 1085b includes the following steps:

[0111] Step 10851: Extract the second spatial coordinates corresponding to the second coordinate values ​​and the list of second surface point coordinates corresponding to the second spatial coordinates from the graph data structure;

[0112] Step 10852: Calculate the Euclidean distance between the second spatial coordinates and the coordinates of all surface points in the second surface point coordinate list, and take the minimum value as the second airway radius.

[0113] It should be noted that the traditional method for calculating the airway radius involves first determining the measurement point of the centerline. , and then with Using the center point as the reference point, obtain several neighboring points before and after it. , , , ...), and then through principal component analysis, we obtain Vector of the tangent direction at the point Rotate this vector ,get Vector of point normal direction And find the point closest to the original bronchial model surface point in the normal direction. Find the Euclidean distance between the two points, which gives the airway radius at the current point.

[0114] For a dual-lumen bronchial tube model, the airway radius needs to be calculated every unit it advances along the airway centerline. However, traditional calculation methods, from sampling neighboring points to principal component analysis, require sequential operations such as coordinate centering, covariance matrix calculation, and eigenvalue decomposition. Taking 10 neighboring points as an example, solving the covariance matrix requires 10×3 matrix multiplication, and eigenvalue decomposition involves iterative calculations, resulting in high computational overhead and demanding high hardware computing power.

[0115] Compared to traditional methods that require principal component analysis to calculate the normal direction and search for the nearest point on the surface point by point, this application pre-constructs a graph data structure and performs Euclidean distance calculation based on the list of surface point coordinates corresponding to the centerline node. This transforms the complex radius calculation into a fast retrieval of fixed data and simple geometric operations, significantly simplifying the real-time calculation process of the airway radius, improving the response efficiency of the simulation system, and providing efficient and accurate technical support for the dynamic evaluation of tube diameter adaptability during intubation.

[0116] like Figure 2 As shown, based on the same application concept, this application embodiment also provides a dual-lumen bronchial tube insertion simulation system, including: an acquisition module: used to acquire the chest thin-slice CT scan sequence, the spatial coordinates of the insertion start and end points, and the specification parameters of a tentatively selected dual-lumen bronchial tube; an image segmentation module: used to convert the chest thin-slice CT scan sequence into mask data; a 3D modeling module: used to convert the mask data into a bronchial 3D model; a centerline extraction module: used to extract the centerline model from the bronchial 3D model; a graph data construction module: used to construct a graph data structure; a path planning module: used to calculate the shortest path from the insertion start point to the end point and generate a path point list; a model rendering module: used to render the tracheal tube model and the bronchial tube model, including: a smooth transition processing unit: used to achieve a smooth transition of the bronchial tube model at the tracheal carina; a radius calculation and comparison module: used to calculate the airway radius corresponding to the tracheal tube tip coordinates and the bronchial tube tip coordinates in real time, and compare the size relationship between the airway radius and the tracheal tube radius and the bronchial tube radius; and a display module: used to display the insertion animation and tube diameter comparison results.

[0117] Based on the same concept, embodiments of this application also provide a computer device, including at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by a processor, the instructions being executed by the at least one processor to cause the at least one processor to implement the above-described method when executing the instructions.

[0118] Based on the same concept, embodiments of this application also provide a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the above-described method.

[0119] In this embodiment, the computer program, when run by the processor, can also execute other machine-readable instructions to perform other methods as described in the embodiments. For details on the specific execution steps and principles, please refer to the description of the embodiments, which will not be repeated here.

[0120] In the embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. The apparatus embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some communication interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0121] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0122] In addition, the functional units in the embodiments provided in this application 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.

[0123] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, 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.) 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 USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0124] It should be noted that similar labels and letters in the following figures indicate similar items. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0125] Finally, it should be noted that the above-described embodiments are merely specific implementations of this application, used to illustrate the technical solutions of this application, and not to limit them. The protection scope of this application is not limited thereto. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments, or make equivalent substitutions for some of the technical features, within the scope of the technology disclosed in this application; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application. All should be covered within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A method for simulating the insertion of a double-lumen bronchial tube, characterized in that, include: Obtain thin-section CT scan sequences of the chest; The chest thin-section CT scan sequence was converted into mask data; The mask data is converted into a 3D model of the bronchus using the moving cube algorithm. The centerline model of the bronchus 3D model was extracted using the average curvature flow algorithm. A graph data structure is constructed based on the bronchus 3D model and the centerline model, and the centerline nodes of the centerline model correspond one-to-one with the vertices of the graph data structure. The vertices include the spatial coordinates of the centerline nodes and a list of surface point coordinates of the bronchus 3D model before contraction corresponding to the centerline nodes. Obtain the spatial coordinates of the inlet and outlet points of the centerline model, calculate the shortest path from the inlet to the outlet point using a graph search algorithm, and generate a list of path points. Obtain the specifications of the temporarily selected double-lumen bronchial catheter and render the temporarily selected double-lumen bronchial catheter on the shortest path. Following the insertion operation of the temporarily selected double-lumen bronchial tube, the coordinates of the endotracheal tube tip and the bronchial tube tip are updated in real time. The airway radius corresponding to the coordinates of the endotracheal tube tip and the bronchial tube tip is calculated in real time. The airway radius is compared with the endotracheal tube radius and the bronchial tube radius. The insertion animation and tube diameter comparison results are output.

2. The method for simulating the insertion of a double-lumen bronchial catheter according to claim 1, characterized in that, The step of calculating the airway radius corresponding to the coordinates of the endotracheal tube tip and the bronchial tube tip in real time, and comparing the size relationship between the airway radius and the endotracheal tube radius and the bronchial tube radius, includes: Obtain the first coordinate value of the next coordinate in the list of path points corresponding to the coordinates of the front end of the bronchial tube; Calculate the first airway radius corresponding to the first coordinate value; Compare the radius of the first airway with the radius of the bronchial tube. If the radius of the first airway is smaller than the radius of the bronchial tube, the tube diameter comparison result will be displayed in red. And / or, obtain the second coordinate value of the next coordinate in the list of path points corresponding to the coordinates of the front end of the endotracheal tube; Calculate the second airway radius corresponding to the airway position of the second coordinate value; Compare the radius of the second airway with the radius of the endotracheal tube. If the radius of the second airway is smaller than the radius of the endotracheal tube, the tube diameter comparison result is displayed in red.

3. The method for simulating the insertion of a double-lumen bronchial catheter according to claim 2, characterized in that, The steps for calculating the first airway radius corresponding to the first coordinate value include: Extract the first spatial coordinates corresponding to the first coordinate values ​​and the list of first surface point coordinates corresponding to the first spatial coordinates from the graph data structure; Calculate the Euclidean distance between the first spatial coordinates and the coordinates of all surface points in the first surface point coordinate list, and take the minimum value as the first airway radius; And / or, the step of calculating the second airway radius corresponding to the airway position of the second coordinate value includes: Extract the second spatial coordinates corresponding to the second coordinate values ​​and the list of second surface point coordinates corresponding to the second spatial coordinates from the graph data structure; Calculate the Euclidean distance between the second spatial coordinates and the coordinates of all surface points in the second surface point coordinate list, and take the minimum value as the second airway radius.

4. The method for simulating the insertion of a double-lumen bronchial catheter according to claim 1, characterized in that: The chest thin-slice CT scan sequence is converted into the mask data using a deep learning image segmentation model; the deep learning image segmentation model is a three-dimensional segmentation neural network built based on a 3D U-Net network; The training parameters of the three-dimensional segmentation neural network include: The batch size is 2, and the patch size is [missing information]. The normalization schemes used were CT Normalization, with median image size invoxels of [234, 509.5, 512] and image spatial spacing of [1, 0.7333984375, 0.7333984375]. The network parameters of the three-dimensional segmentation neural network include: The base feature channel count (Unet_base_num_features) is 32, the number of convolutional layers per stage of the encoder (n_conv_per_stage_encoder) is [2,2,2,2,2,2], the number of convolutional layers per stage of the decoder (n_conv_per_stage_decoder) is [2,2,2,2,2,2], the number of pooling operations per axis (num_pool_per_axis) is [4,5,5], and the downsampling stride is [4,5,5]. The stride is 2, the convolution kernel size is [[3,3,3],[3,3,3],[3,3,3],[3,3,3],[3,3,3],[3,3,3],[3,3,3]], the pooling kernel size is [[1,1,1],[2,2,2],[2,2,2],[2,2,2],[2,2,2],[1,2,2]], the stride convolution is 1, and the padding convolution is 1.

5. The method for simulating the insertion of a double-lumen bronchial catheter according to claim 1, characterized in that, The steps of obtaining the specifications of the temporarily selected double-lumen bronchial catheter and rendering the temporarily selected double-lumen bronchial catheter on the shortest path include: Create a list of index values ​​for the shortest path; Obtain the specifications of the tentatively selected double-lumen endotracheal tube and determine the position of the endotracheal tube tip. Based on the index value corresponding to the inlet tip of the dual-lumen bronchial tube on the shortest path, the dual-lumen bronchial tube is rendered on the shortest path. After the inlet tip of the tracheal tube crosses the inlet point, the tracheal tube model and the bronchial tube model are rendered separately, with the inlet tip of the tracheal tube as the dividing point.

6. The method for simulating the insertion of a double-lumen bronchial catheter according to claim 5, characterized in that: After rendering the tracheal tube model and the bronchial tube model separately, using the front end of the tracheal tube as a dividing point, the process further includes a step of smoothly transitioning the bronchial tube model at the tracheal carina, specifically including: If the current bronchial catheter tip index value is greater than the tracheal carina index value, it indicates that part of the bronchial catheter has entered the bronchus; In the constructed vtkPoints instance, delete the index point of the tracheal carina index value, as well as several index points before and after it; The vtkPoints instances after deleting the index points are used as control points and input into vtkParametricSpline to generate parameterized curve equations; The parameterized curve equation is input into vtkParametricFunctionSource for interpolation to obtain the interpolated discrete curve data. Construct a vtkTubeFilter instance, input the interpolated discrete curve data, set the radius to the radius of the bronchial tube, and set the end sealing parameter to True; The output of vtkTubeFilter is used as the final rendering data and sent to the vtk rendering pipeline for rendering to achieve a smooth transition rendering effect from the main trachea to the bronchus.

7. The method for simulating the insertion of a double-lumen bronchial catheter according to claim 1, characterized in that, The specifications of the double-lumen endotracheal tube include: Bronchial tube length (bronc_len); Tracheal tube radius (trachea_rad); Bronchus duct radius (bronchus_rad).

8. A dual-lumen bronchial tube insertion simulation system, characterized in that, include: Acquisition module: used to acquire the chest thin-section CT scan sequence, the spatial coordinates of the inlet and outlet of the endotracheal tube, and the specifications of the tentatively selected double-lumen endotracheal tube; Image segmentation module: used to convert the chest thin-slice CT scan sequence into mask data; 3D modeling module: used to convert the mask data into a 3D model of the bronchus; Centerline extraction module: used to extract the centerline model from the bronchial 3D model; Graph data construction module: used to construct graph data structures; Path planning module: Used to calculate the shortest path from the entry point to the destination and generate a list of path points; Model rendering module: used to render tracheal tube and bronchial tube models, including: smooth transition processing unit: used to achieve smooth transition of bronchial tube model at the tracheal carina position; Radius calculation and comparison module: used to calculate the airway radius corresponding to the coordinates of the endotracheal tube tip and the bronchial tube tip in real time, and compare the airway radius with the endotracheal tube radius and the bronchial tube radius. Display module: Used to display inlet animation and pipe diameter comparison results.

9. A computer device, characterized in that, include: At least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to cause the at least one processor to perform the steps of the method according to any one of claims 1 to 7 when executing the instructions.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images