A registration progress detection method, system and electronic device for the lung airway

Abstract

The application provides a registration progress detection method and system for a lung trachea and an electronic device. The method comprises the following steps: obtaining a trachea tree three-dimensional model reconstructed based on a medical image of a lung trachea and a plurality of first key points in the trachea tree three-dimensional model; dividing the trachea tree three-dimensional model based on the plurality of first key points to obtain a plurality of model regions, each model region containing at least one first key point; obtaining first position information of a current position of a positioning sensor in the lung trachea; determining second position information of the positioning sensor in the trachea tree three-dimensional model and a target model region where the positioning sensor is located according to the first position information; calculating a first distance between the positioning sensor and the at least one first key point contained in the target model region according to the second position information; and determining a registration progress for the target model region according to the first distance. The scheme can accurately determine the completion of the registration operation and also ensure the sufficiency of the registration data collection.

Description

Technical Field

[0001] This application relates to the field of medical device technology, and in particular to a method, system and electronic device for detecting the registration progress of the trachea in the lungs. Background Technology

[0002] With the development of computer technology and medical imaging technology, surgical navigation technology, with its advantages of precision, flexibility, and minimally invasiveness, is increasingly widely used in disease diagnosis and treatment. For example, electromagnetic navigation bronchoscope (ENB) is commonly used to examine patients for peripheral lung diseases.

[0003] In intraoperative diagnosis and treatment of patients' lungs using techniques such as ENB, registration is an essential step. The purpose of registration is to match the actual physical space of the patient's lungs and trachea during surgery with the 3D model of the tracheal tree reconstructed preoperatively. This allows for precise positioning of surgical instruments within the 3D model of the tracheal tree, providing a prerequisite for surgical navigation. Currently, the lack of a scientific evaluation process and standards for registration leads to insufficient visualization of progress and inadequate data collection regarding the actual physical space of the patient's lungs and trachea, thus affecting registration efficiency and accuracy. Therefore, there is an urgent need for a technical solution that can provide feedback on registration progress and ensure sufficient data collection during the registration process, thereby improving registration accuracy. Summary of the Invention

[0004] In view of the above problems, this application provides a method, system and electronic device for detecting the registration progress of the lung trachea that solves or at least partially solves the above problems.

[0005] Therefore, in one embodiment of this application, a method for detecting the registration progress of the trachea in the lungs is provided. The method includes:

[0006] Obtain a three-dimensional model of the tracheal tree reconstructed from medical imaging images of the lungs and trachea, and several first key points in the three-dimensional model of the tracheal tree;

[0007] The tracheal tree 3D model is divided based on multiple first key points to obtain multiple model regions, wherein each model region contains at least one first key point;

[0008] Acquire the first position information of the current position of the positioning sensor within the trachea of ​​the lung;

[0009] Based on the first location information, the second location information of the positioning sensor in the tracheal tree 3D model and the target model area where it is located are determined;

[0010] Based on the second location information, calculate the first distance between the positioning sensor and the at least one first key point contained in the target model region;

[0011] Based on the first distance, determine the registration progress for the target model region.

[0012] In another embodiment of this application, a registration progress detection system for the trachea of ​​the lungs is also provided. The system includes:

[0013] A magnetic field generator is used to generate a positioning magnetic field; the trachea of ​​the lungs is placed in the positioning magnetic field;

[0014] A positioning sensor that, when moving within the trachea of ​​the lungs, can generate a positioning signal by sensing the positioning magnetic field and send the positioning signal to a processing device, so that the processing device can determine the position information of the positioning sensor within the trachea of ​​the lungs based on the positioning signal;

[0015] The processing device is used to perform the steps in the registration progress detection method for the lung trachea provided in the above embodiment.

[0016] In one embodiment of this application, an electronic device is provided. The electronic device includes a memory and a processor, wherein the memory is used to store a computer program; and the processor, coupled to the memory, is used to execute the computer program stored in the memory to implement the steps or functions of the lung-tracheal registration progress detection method provided in the above embodiment of this application.

[0017] The technical solutions provided in the embodiments of this application are based on obtaining a three-dimensional model of the tracheal tree reconstructed for the lungs and trachea. The three-dimensional model is then divided into multiple model regions based on multiple first key points in the obtained tracheal tree model, with each model region containing at least one first key point. Further, based on the first position information of the positioning sensor within the lungs and trachea, the second position information of the positioning sensor in the tracheal tree model and its target model region can be determined. Based on this second position information, a first distance can be calculated between the positioning sensor and at least one first key point contained in the target model region, and the registration progress for the target model region can be determined based on this first distance. This application's solution uses the first distance between the positioning sensor and the corresponding first key point in the target model region as a criterion for measuring the registration progress of the target model region. This provides an objective standard for evaluating the registration completion status of lung and trachea registration during surgery, which helps improve the accuracy of determining the registration completion status. In addition, based on the determined registration progress of the target model region, it also helps to provide corresponding registration progress information feedback to users (such as clinicians) in the future. This allows users to intuitively understand the registration completion status of the target model region, and provides effective assistance for users to operate the positioning sensor to move within the lung and trachea. This helps to ensure the sufficiency of registration data acquisition and provides a guarantee for the subsequent precise guidance of surgery. Attached Figure Description

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

[0019] Figures 1a to 1c This is a schematic diagram of the structure of a medical system for lung diagnosis and treatment according to an embodiment of the application;

[0020] Figure 2 A schematic flowchart of a registration progress detection method for the lungs and trachea provided in an embodiment of this application;

[0021] Figure 3a and Figure 3b A frontal plan view of a 3D model of the trachea tree with centerline information provided in an embodiment of this application;

[0022] Figure 4a and Figure 4b A frontal plan view of the model region division of the tracheal tree 3D model provided in the embodiments of this application;

[0023] Figure 5A schematic diagram of trajectory data provided in one embodiment of this application;

[0024] Figure 6 A schematic diagram of the structure of a registration progress detection system for the lungs and trachea provided in an embodiment of this application;

[0025] Figure 7 A schematic diagram of the structure of a registration progress detection device for the lungs and trachea provided in an embodiment of this application;

[0026] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application;

[0027] Figure 9 A schematic diagram of the structure of a computer program product provided in an embodiment of this application;

[0028] Figure 10 and Figure 11 This is a schematic diagram of the surgical registration interface provided in an embodiment of this application. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0030] In some processes described in the specification, claims, and accompanying drawings of this application, multiple operations appearing in a specific order are included. These operations may be executed out of order or in parallel. Operation numbers such as 101, 102, etc., are merely used to distinguish different operations and do not represent any execution order. Furthermore, these processes may include more or fewer operations, and these operations may be executed sequentially or in parallel. It should be noted that the terms "first," "second," etc., used herein are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to different types. The term "or / and" in this application is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A or / and B means that A can exist alone, A and B can exist simultaneously, or B can exist alone. The character " / " in this application generally indicates that the preceding and following related objects have an "or" relationship. It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a product or system comprising a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a product or system. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the product or system including said element. Furthermore, the following embodiments are merely some embodiments of this application, and not all embodiments. 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.

[0031] In the following embodiments of this application, a positioning sensor is involved, such as a positioning sensor disposed on a positioning catheter. This positioning sensor employs the principle of electromagnetic navigation, which differs from ordinary electromagnetic navigation. Ordinary electromagnetic navigation primarily relies on an external magnetic field to attract or repel a permanent magnet in the catheter, influencing the direction of a medical device entering the body. In the embodiments of this application, the positioning sensor operates primarily by outputting current to an external control system (the magnetic navigation device described below) in response to the magnetic field of its surrounding space, allowing the control system to locate the corresponding catheter. Specifically, the positioning sensor and the control system are connected via wired or wireless means (signal). The control system includes a magnetic field generator to generate a magnetic field within a certain range of positioning space. The positioning sensor itself is not magnetic; a coil within the sensor senses the magnetic field generated by the magnetic field generator. The magnetic field generator produces a changing magnetic field within a certain range of positioning space, ensuring that the magnetic field characteristics of each electrode within the positioning space are unique. The coil in the positioning sensor generates current in the changing magnetic field, which is then collected to generate a signal (i.e., the positioning signal described in the context) and transmitted to the control system. The control system analyzes the signal to determine the precise position and direction of the corresponding catheter.

[0032] To facilitate understanding, before introducing the technical solutions provided in the embodiments of this application, a medical system for lung surgery navigation will be first introduced. Specifically,

[0033] Figure 1a and Figure 1b This is a three-dimensional structural diagram of a medical system provided as an embodiment of this application. See also... Figure 1a and Figure 1b As shown, the medical system includes: an operating console 10, a magnetic navigation device 20, a medical imaging device 30, and a positioning medical tool 40. Among them,

[0034] The magnetic navigation device 20 is used to navigate the positioning medical tool 40 to the corresponding target point (or target area) on the medical path according to the medical path.

[0035] The aforementioned medical pathway can be planned by a processing module with pathway planning capabilities. Specifically, the processing module can reconstruct a corresponding three-dimensional model based on medical imaging data (such as CT, MRI, etc.) of the patient's whole body or a specific body part, and perform pathway planning based on this planned three-dimensional model to obtain the corresponding medical pathway. For example, a three-dimensional model of the tracheal tree, including the main trachea and bronchi, can be reconstructed based on preoperative medical imaging data of the patient's lungs, and a navigation path (or planned path) from the main carina through the natural trachea of ​​the lungs to the target point can be planned based on this tracheal tree model. This navigation path is the medical pathway. The main carina refers to the bifurcation of the main trachea, which branches into the left main bronchus and the right main bronchus.

[0036] In practical implementation, the aforementioned processing module can be installed on the magnetic navigation device 20, or it can be installed on, for example, Figure 1c The above-mentioned processing module is on the main control carriage 50 used by the doctor, as shown in the figure. This processing module can be application software, which has functions such as reconstructing 3D models, path planning, and registration. Specifically, it can be installed in control devices such as the main control carriage 50 or the magnetic navigation device 20, for example... Figure 1c The control device 511 shown is (e.g., a computer device). However, to reduce the risk of radiation exposure for doctors and cross-infection between doctors and patients, in this embodiment, the control device 511 is preferably separated from the electromagnetic navigation device 20 and mounted on the main control carriage 50, so that doctors can operate the control device outside the operating room. The main control carriage 50 can communicate with the magnetic navigation device 20 and can be regarded as an extension of the display and control functions of the magnetic navigation device 20. For example, through the display screen included in the control device 511 on the main control carriage 50, specifically the display screen showing a human-computer interaction interface, the reconstructed three-dimensional model (e.g., a tracheal tree three-dimensional model), medical path, surgical progress (e.g., registration progress, real-time navigation progress), endoscopic images, etc.; in addition, doctors can also trigger the registration operation to start by clicking the registration control displayed on the human-computer interaction interface; or, control the medical imaging device 30 to perform scanning through the human-computer interaction interface, etc.

[0037] The aforementioned medical imaging device 30 is used to acquire medical images of a patient. For example, it can acquire medical images of a patient's lungs.

[0038] In specific implementation, the aforementioned medical imaging device 30 can be, but is not limited to, CT scanners, X-ray machines, etc. Where conditions permit, it can refer to any medical imaging device used to image a patient's local or whole body, and its imaging type includes, but is not limited to, two-dimensional images.

[0039] In one example, the aforementioned medical imaging device 30 includes a C-shaped arm 311 movable relative to the operating table 10. The two ends of the C-shaped arm 311 are respectively used to house a radiation module (for emitting corresponding medical radiation, such as X-rays) and an imaging module (not shown in the figure, but may be located at the end of the C-shaped arm 311 above the operating table), with the C-shaped opening facing the operating table. The movable C-shaped arm 311 relative to the operating table means that the opening of the C-shaped arm can move along the length or width of the operating table 10, or it can mean that the opening of the C-shaped arm can rotate around the operating table 10, so that the medical imaging device 30 can capture or scan the entire operating table and its various directions, capturing medical images (i.e., medical images) at appropriate angles as needed, thus improving the user experience of the medical system.

[0040] It should be noted that the medical imaging device 30 can be connected to the control equipment on the main control carriage 50 or the magnetic navigation device 20, so that the processing module (application software) on the control equipment can receive and process the medical images obtained by the medical imaging device 30.

[0041] The aforementioned operating table 10 can be, but is not limited to, an operating table in an operating room, or a patient treatment bed, etc. This operating table 10 allows X-ray transmission from the medical imaging device 30 without affecting the imaging effect of the medical imaging device 30. Furthermore, the aforementioned medical imaging device 30 and magnetic navigation device 20 can be respectively installed beside the operating table 10.

[0042] The medical positioning tool 40 mentioned above refers to a medical tool with positioning function, such as a biopsy or treatment tool. Specifically, it can be a lead or catheter used for positioning, an ablation catheter, etc.

[0043] The positioning medical tool 40 is connected to the magnetic navigation device 20, or to a portion thereof. For example, the magnetic navigation device 20 has a shape and structure as shown in the image. Figure 1b In the configuration shown, the magnetic navigation device 20 includes a delivery mechanism 21, which can be connected to a positioning medical tool 40. The delivery mechanism 21 guides the positioning medical tool 40 into the patient's body, such as into the airway (or trachea) of the lungs, according to a medical path, and reaches the corresponding target point (or target area) under the control of the magnetic navigation device 20. Figure 1b An example is given of delivering the positioning medical tool 40 into the patient's body via a delivery mechanism. In other embodiments, the positioning medical tool 40 can also be delivered into the patient's body by a physician's operation via a corresponding propulsion device (such as the lifting mechanism 212 described below). The physician uses the display device corresponding to the magnetic navigation device (such as...) Figure 1cThe display device 511 shown in the figure is manually controlled to propel the positioning medical tool 40 along the medical path, thereby reaching the corresponding target point (or target area).

[0044] It should be noted that the aforementioned delivery mechanism 21 may include a robotic arm 211 and a lifting mechanism 212. The lifting mechanism 212 is connected to one end of the positioning medical tool 40. By manually pushing or pulling the lifting mechanism 212, the positioning medical tool 40 can be moved in and out of the human trachea. In addition, the electromagnetic navigation device 20 can also provide... Figure 1b Besides the shapes and structures shown, other shapes and structures are also possible, such as... Figure 1c The shape and structure shown in the figure are not specifically limited to the shape and structure of the electromagnetic navigation device 20 in this embodiment of the application.

[0045] Furthermore, the aforementioned magnetic navigation device 20 may also include a magnetic field generator 22 disposed within the aforementioned operating table 10, and a positioning sensor 23 disposed within the positioning medical tool 40. The magnetic field generator 22 is used to generate a positioning magnetic field to locate the positioning sensor 23.

[0046] In practice, the aforementioned magnetic field generator 22 is installed inside the operating table 10, which can emit a positioning magnetic field towards the bed surface. When the patient lies on the operating table 10, the corresponding body part of the patient (such as the lungs) is located in this positioning magnetic field. Since the patient is generally under general anesthesia on the operating table 10, the relative position of the corresponding body part of the patient (such as the lungs) in the positioning magnetic field is fixed. Because the positioning magnetic field has its own coordinate system, called the magnetic field coordinate system, the relative position of the corresponding body part of the patient (such as the lungs) in the magnetic field coordinate system is fixed. The position and orientation of the positioning medical tool 40 in the patient's body can be represented by the position coordinates of the head of the positioning medical tool 40 in the magnetic field coordinate system. Specifically, the positioning magnetic field can locate the positioning sensor 23 inside the positioning medical tool 40. Since the positioning sensor 23 is located at the head end of the medical tool 40, the position and orientation of the positioning medical tool 40 in the patient's body can be obtained by locating the positioning sensor 23 and obtaining its position coordinates in the magnetic field coordinate system.

[0047] The registration progress detection method for the trachea described below in this application determines the corresponding second position information of the positioning sensor relative to the trachea in the reconstructed tracheal tree model when it moves within the trachea of ​​the lungs, based on the first position information (the position within the trachea in actual physical space (i.e., magnetic field space)). Then, it determines the target model region where the positioning sensor is located in the tracheal tree 3D model based on the second position information, and calculates the distance of the positioning sensor relative to key points in that target model region, which serves as a criterion for judging the registration progress of the target model region. For a detailed description of the model regions included in the tracheal tree 3D model, please refer to the relevant content in other embodiments of this application below; it will not be elaborated here. Once all the model regions that should be registered within the tracheal tree 3D model have been registered, the registration of the entire trachea is complete.

[0048] The registration progress detection method for the lung trachea provided in the embodiments of this application will be described in detail below.

[0049] Figure 2 This diagram illustrates a flowchart of a method for detecting the registration progress of the lung trachea according to an embodiment of this application. The method is executed by a corresponding processing device, such as... Figures 1a to 1c The magnetic navigation device 20 shown in the figure or Figure 1c The control equipment 511 (such as computer equipment) on the main control carriage 50 shown is not specifically limited here. See also Figure 2 As shown, the registration progress detection method for the lungs and trachea includes the following steps:

[0050] 101. Obtain a three-dimensional model of the tracheal tree reconstructed from medical images of the lungs and trachea, and several first key points of the three-dimensional model of the tracheal tree;

[0051] 102. The tracheal tree 3D model is divided based on multiple first key points to obtain multiple model regions; wherein each model region contains at least one first key point;

[0052] 103. Obtain the first position information of the current position of the positioning sensor in the trachea of ​​the lung;

[0053] 104. Based on the first location information, determine the second location information of the positioning sensor in the tracheal tree 3D model and the target model area where it is located;

[0054] 105. Based on the second location information, calculate the first distance between the positioning sensor and at least one first key point contained in the target model region;

[0055] 106. Based on the first distance, determine the registration progress for the target model region.

[0056] In the above 101, the tracheal tree three-dimensional model can be obtained by using three-dimensional reconstruction technology (such as three-dimensional reconstruction software) to process multiple medical images (such as two-dimensional tomographic images, i.e. CT images) collected from different angles of the patient's lungs before surgery.

[0057] For example, before surgery, multiple two-dimensional CT images of the patient's lungs can be obtained by scanning the patient's lungs with a CT tomography scan. Then, these multiple two-dimensional CT images are imported into the processing module described in other embodiments of the above text application (which can be application software with functions such as reconstructing three-dimensional models, path planning, and registration) to perform image recognition and segmentation of tissues such as the lungs and trachea, obtain three-dimensional modeling parameters of the lungs and trachea, and then construct a three-dimensional model of the tracheal tree of the patient's lungs and trachea based on the three-dimensional modeling parameters.

[0058] From the example above, specifically "obtaining a 3D model of the tracheal tree reconstructed from medical imaging images of the lungs and trachea" in section 101 above, can be achieved through the following related processing steps:

[0059] S111. Acquire multiple medical imaging images of the lungs and trachea;

[0060] S112. Recognize the plurality of medical images to obtain the three-dimensional modeling parameters of the lungs and trachea;

[0061] S113. Based on the three-dimensional modeling parameters, construct the three-dimensional model of the tracheal tree.

[0062] After obtaining the 3D model of the tracheal tree, its skeleton can be created to extract the centerline information, providing data support for subsequent segmentation. For example, based on the centerline information, multiple first key points and a reference point can be pre-set in the 3D model of the tracheal tree, so that the segmentation of the 3D model can be achieved based on these multiple first key points and reference points. That is, in one feasible technical solution, the "obtaining multiple first key points in the 3D model of the tracheal tree" in step 101 above can be achieved through the following specific steps:

[0063] S121. Determine the centerline information of the tracheal tree three-dimensional model;

[0064] S122. Based on the centerline information, determine the reference point and multiple first key points in the tracheal tree three-dimensional model;

[0065] In step S121 above, the centerline information of the tracheal tree 3D model can be extracted using, but is not limited to, corresponding thinning algorithms, such as topology thinning algorithms. Thinning algorithms primarily extract the centerline of the target object by repeatedly eroding the surface pixels until only the skeleton remains. For specific implementations of using thinning algorithms to extract the centerline information of the tracheal tree 3D model, please refer to existing related solutions.

[0066] exist Figure 3a and Figure 3b In the frontal view of the tracheal tree 3D model 100 shown in the figure, the center line information of the tracheal tree 3D model is shown in the form of a dashed line.

[0067] After extracting the centerline information of the tracheal tree 3D model, before executing step S122, the centerline information can be analyzed to determine the centerline bifurcation points, and then the multiple tracheal models included in the tracheal tree 3D model can be determined based on the centerline bifurcation points. That is, the steps between S121 and S122 can also include the following:

[0068] A1. Determine the centerline bifurcation point in the centerline information;

[0069] A2. Based on the bifurcation point of the center line, determine the multiple tracheal models included in the three-dimensional model of the tracheal tree.

[0070] In the above, the centerline bifurcation point refers to the intersection of at least two centerline segments. For information on centerline bifurcation points in centerline information, please refer to [link to centerline information]. Figure 3a The bifurcation points b0, b1, and b2 are shown in the figure.

[0071] In reality, the trachea of ​​the human lungs has a tree-like structure. Based on the anatomical structure of the trachea, it can be divided into different levels according to its bifurcation hierarchy. For example, the main trachea (level 1, a tube connecting one end to the pharynx and the other to the bronchus, serving as an air passage) enters the lung through the hilum and branches into two main bronchi (also called lobar main bronchi, level 2): ​​the left main bronchus and the right main bronchus. Furthermore, the two main bronchi further bifurcate; for example, the left main bronchus further bifurcates into the left upper lobe bronchus and the left lower lobe bronchus, and so on. Based on this, for the 3D tracheal tree model obtained in this embodiment, the multiple tracheal models included in the 3D tracheal tree model can be determined based on the central bifurcation points identified above, providing support for subsequent processing steps. Specifically, see [link to documentation]. Figure 3aAs shown, from top to bottom, the 3D model of the tracheal tree includes the following multiple tracheal models: main trachea model 1, right lung bronchus model and left lung bronchus model that are bifurcated and connected to the main trachea model 1. The right lung bronchus model specifically includes: right main bronchus model 11 (one end of which is connected to the main trachea model 1), right upper lobe bronchus model 111 and right lower lobe bronchus model 112 that are bifurcated and connected to the right main bronchus model 11 (specifically the other end of the right main bronchus model 11). The left lung bronchus model specifically includes: left main bronchus model 12 (one end of which is connected to the main trachea model 1), left upper lobe bronchus model 121 and left lower lobe bronchus model 122 that are bifurcated and connected to the left main bronchus model 12 (specifically the other end of the left main bronchus model 12).

[0072] Accordingly, the centerline information mentioned above includes the centerlines of multiple tracheal models in the tracheal tree 3D model.

[0073] In S122 above, the reference point can correspond to the location of the main carina in the trachea of ​​the lungs. Since the main carina refers to the bifurcation point of the main trachea, the intersection of the centerlines of the three tracheal models (main trachea model, right main bronchus model, and left main bronchus model) in the tracheal tree 3D model can be used as the reference point. Then, based on the reference point and centerline information, multiple first key points are determined. Specifically, in a feasible technical solution, the above-mentioned S122 "determining the reference point and multiple first key points in the tracheal tree 3D model according to the centerline information" can be implemented using the following steps:

[0074] S1221. Obtain the intersection point of the centerline of the main trachea model, the centerline of the right main bronchus model, and the centerline of the left main bronchus model, and determine it as the reference point;

[0075] S1222. Obtain a point on the main trachea model that is above the reference point and at a preset distance from the reference point, and determine it as the key point of the main trachea of ​​the main trachea model;

[0076] S1223. Obtain a point on the end of the right upper lobe bronchus model and the right lower lobe bronchus model that is not connected to the right main bronchus model, and determine it as the right upper lobe key point of the right upper lobe bronchus model and the right lower lobe key point of the right lower lobe bronchus model.

[0077] S1224. Obtain a point on the end of the left upper lobe bronchus model and the left lower lobe bronchus model that is not connected to the left main bronchus model, and determine it as the left upper lobe key point of the left upper lobe bronchus model and the left lower lobe key point of the left lower lobe bronchus model.

[0078] The key points of the upper right lobe, the lower right lobe, the upper left lobe, and the lower left lobe are located on the center lines of the respective bronchial models of the upper right lobe, the lower right lobe, the upper left lobe, and the lower left lobe.

[0079] The preset distance mentioned above can be flexibly set according to the actual situation, and no specific limitation is made here.

[0080] For example, see continue. Figure 3a As shown, the intersection of the centerline of the main trachea model 1, the centerline of the right main bronchus model 11, and the centerline of the left main bronchus model 12, i.e., the aforementioned bifurcation point b0, can be determined as reference point A. Further, a point approximately 10 cm away from reference point A on the main trachea model 1 can be determined as the main trachea key point 10 of the main trachea model 1. Additionally, a point on the centerline of the right upper lobe bronchus model 111, located at the end of the right upper lobe bronchus model 111 that is not connected to the right main bronchus model 111, can be determined as the right upper lobe key point 1110 of the right upper lobe bronchus model 111.

[0081] related Figure 3a The determination of the key point 1120 of the right lower lobe bronchus model, the key point 1210 of the left upper lobe bronchus model, and the key point 1220 of the left lower lobe bronchus model shown in the figure can be specifically referred to in the above-described example of determining the key point 1110 of the right upper lobe bronchus model 111.

[0082] It should be noted that the above steps S1211~S1224 are described in terms of determining multiple first key points by identifying a corresponding key point on each of the main trachea model, the right upper lobe bronchus model, the right lower lobe bronchus model, the left upper lobe bronchus model, and the left lower lobe bronchus model. This method of obtaining multiple first key points ensures that each first key point is located at the end of the corresponding trachea model. This is beneficial for subsequent registration progress detection of the corresponding model area based on the first key points, ensuring that the positioning sensor determines that the registration of the corresponding model area has been completed only after it has fully traversed the corresponding model area.

[0083] Of course, other key points can also be determined on the model described above as the first key point. For example: following the examples given in steps S1221~S1224 above, see... Figure 3bFurthermore, a point approximately 5 cm from reference point A on the main trachea model 1 can be identified as another key point 10' of the main trachea in the main trachea model 1; and, a point on the center line of the right upper lobe bronchus model 111 located between the aforementioned key point 1110 of the right upper lobe and the bifurcation point b1 can also be obtained. Specifically, a point on the center line of the right upper lobe bronchus model 111 located at a set distance from the aforementioned key point 1110 of the right upper lobe can be identified as another key point of the right upper lobe in the right upper lobe bronchus model 111. Figure 3b (Not shown in the text), etc., this embodiment does not limit this. Using this method to obtain multiple first keypoints may result in situations where there are two or more first keypoints within the corresponding model area. In this case, during the registration progress detection process for the corresponding model area, registration progress analysis can be performed based on the two or more first keypoints contained within the model area across multiple registration progress ranges. The specific implementation of performing registration progress analysis across multiple registration progress ranges will be detailed below and will not be described in detail here.

[0084] Preferably, in this embodiment, multiple first key points are obtained through the above steps S1221~S1224.

[0085] Based on the above, the 3D model of the tracheal tree in this embodiment includes multiple tracheal models. Specifically, the multiple tracheal models include: a main trachea model, a right lung bronchus model connected to the main trachea model, and a left lung bronchus model. The right lung bronchus model includes: a right main bronchus model, a right upper lobe bronchus model, and a right lower lobe bronchus model. The left lung bronchus model includes: a left main bronchus model, a left upper lobe bronchus model, and a left lower lobe bronchus model.

[0086] The multiple first key points include: the main trachea key point located on the main trachea model, the right upper lobe key point located on the right upper lobe bronchus model, the right lower lobe key point located on the right lower lobe bronchus model, the left upper lobe key point located on the left upper lobe bronchus model, and the left lower lobe key point located on the left lower lobe bronchus model.

[0087] In step 102 above, the division of the tracheal tree 3D model can be achieved based on a reference plane and multiple first key points. The reference plane can be determined based on the main tracheal key points located on the main tracheal model and the reference points of the tracheal tree 3D model. That is, in one feasible solution, step 102 above, "dividing the tracheal tree 3D model based on multiple first key points to obtain multiple model regions," can specifically include:

[0088] 1021. Obtain the reference point of the tracheal tree three-dimensional model; the reference point is determined based on the intersection of the main trachea model, the right main bronchus model, and the left main bronchus model;

[0089] 1022. Based on the key points of the main trachea and the reference points, determine the reference plane of the three-dimensional model of the tracheal tree;

[0090] 1023. Based on the reference plane and multiple first key points, the tracheal tree three-dimensional model is divided into multiple model regions.

[0091] For a detailed description of the implementation of step S1221 above, please refer to the relevant content of step S1221 above.

[0092] In step 1022 above, the key points of the main trachea can be used as the starting point and the reference point as the ending point to determine a vector that reflects the direction of the main trachea in the main trachea model. Furthermore, this vector can be used as the normal vector of the reference plane to be determined, providing a basis for determining the reference plane. Based on this, in a specific implementable technical solution, step 1022 above, "determining the reference plane of the tracheal tree 3D model based on the key points of the main trachea and the reference point," can be implemented using the following more specific steps:

[0093] 10221. Based on the key points of the main trachea and the reference points, determine a vector to reflect the direction of the main trachea in the main trachea model;

[0094] 10222. A plane that passes through the reference point and is perpendicular to the vector is defined as the reference plane.

[0095] exist Figure 4a On the frontal view of the 3D model of the tracheal tree shown, the direction of the main trachea of ​​the main trachea model is indicated by arrow V, and the reference plane is P.

[0096] In the above 1023, the model region located above the reference plane in the tracheal tree 3D model can be determined as the main tracheal model region; furthermore, the model region located below the reference plane in the tracheal tree 3D model can be divided into left and right parts, and then the left and right parts can be further divided based on the key points of the tracheal model contained in each of the left and right parts, thereby realizing the division of the tracheal tree 3D model into multiple model regions. Specifically, when dividing the model region located below the reference plane into left and right parts, this can be achieved by drawing a perpendicular line through the reference point along the direction of the aforementioned vector. Therefore, in a specific implementable technical solution, the above 1023 "dividing the tracheal tree 3D model into multiple model regions based on the reference plane and multiple second key points" can be implemented using the following steps:

[0097] 10231. The model region located above the reference plane in the tracheal tree 3D model is determined as the main tracheal model region;

[0098] 10232. Based on the reference point and the key point of the main airway, determine a dividing line;

[0099] 10233. Based on the dividing line, the model region located below the reference plane in the tracheal tree 3D model is divided into the right lung bronchus model region and the left lung bronchus model region.

[0100] 10234. Based on the right upper lobe key point of the right upper lobe bronchus model and the right lower lobe key point of the right lower lobe bronchus model contained in the right bronchus model region, the right bronchus model region is divided into the right upper lobe model region and the right lower lobe model region.

[0101] 10235. Based on the key points of the left upper lobe of the left upper lobe bronchus model and the key points of the left lower lobe of the left lower lobe bronchus model contained within the left bronchus model region, the left bronchus model region is divided into the left upper lobe model region and the left lower lobe model region.

[0102] For example, see Figure 4a In the aforementioned 3D tracheal tree model, the model region located above the reference plane P is the main tracheal model region. Further, the line connecting the key point 10 of the main trachea and the reference point A is extended downwards along the direction indicated by arrow V (i.e., the direction of the vector mentioned above, the direction of the main trachea in the main tracheal model), resulting in a dividing line l0; alternatively, the dividing line l0 can also be obtained by drawing a perpendicular line downwards from the reference point A along the direction indicated by arrow V. The determined dividing line l0 will divide the model region located below the reference plane P in the 3D tracheal tree model into two regions: the right bronchus model region and the left bronchus model region. Combined with... Figure 3a It can be seen that the above-mentioned right lung bronchus model region includes the right upper lobe bronchus model and the right lower lobe bronchus model. Therefore, based on the right upper lobe key point 1110 located in the right upper lobe bronchus model and the right lower lobe key point 1220 located in the right lower lobe bronchus model, the right lung bronchus model region can be further divided into the right upper lobe model region and the right lower lobe model region.

[0103] Specifically, see further. Figure 4a A line l1 can be drawn directly between the key point 1110 of the upper right lobe and the key point 1220 of the lower right lobe, and the midpoint c1 of the line l1 can be taken. A horizontal line l11 parallel to the reference plane P can be drawn through the midpoint c1. The horizontal line l11 will divide the right lung bronchus model area into upper and lower parts. Specifically, the model area above the horizontal line l11 in the right lung bronchus model area is the upper right lung model area, and the model area below the horizontal line l11 is the lower right lung model area.

[0104] Alternatively, since the aforementioned key point 1110 of the upper right lobe and key point 1220 of the lower right lobe are often not on the same vertical line, if a line is directly drawn between them, the resulting line is often slanted, which may affect the accuracy of subsequent regional division of the right bronchus model. To improve the accuracy of subsequent regional division of the right bronchus model, a point on the same vertical line as the other key point can be determined for one of the key points 1110 of the upper right lobe and 1220 of the lower right lobe. Specifically, the ordinate of this determined point is the same as the ordinate of one of the key points 1110 of the upper right lobe and 1220 of the lower right lobe, and its abscissa is the same as the abscissa of the other key point 1110 of the upper right lobe and 1220 of the lower right lobe. Furthermore, the right lung bronchus model region can be further divided by connecting the determined point with another key point among the aforementioned right upper lobe key point 1110 and right lower lobe key point 1220. Specifically, for example, see... Figure 4b For the key point 1220 in the right lower lobe, a point 1220' can be determined. The ordinate of point 1220' is the same as that of the key point 1220 in the right lower lobe, and its x-coordinate is the same as that of the key point 1110 in the right upper lobe. A line l1' is drawn between point 1220' and the key point 1220 in the right lower lobe, and the midpoint c1' of this line l1' is taken. A horizontal line l11' perpendicular to the line l1' is drawn through the midpoint c1'. This horizontal line l11' will divide the right bronchus model region into upper and lower parts. Specifically, the model region above the horizontal line l11' is the right upper lobe model region, and the model region below the horizontal line l11' is the right lower lobe model region. The aforementioned line l11' is not only perpendicular to the horizontal line l11', but also parallel to the reference plane P.

[0105] Preferably, in this embodiment, the preferred choice is... Figure 4b The method shown in the figure is used to divide the right lung bronchus model region.

[0106] For details on the further implementation of the left lung bronchus model region division, please refer to the above-described specific implementation of the right lung bronchus model region division, which will not be elaborated here.

[0107] Based on the above, in a specific feasible solution, the above-mentioned 10234 "dividing the right lung bronchus model region into a right upper lobe model region and a right lower lobe model region according to the right upper lobe key points of the right upper lobe bronchus model and the right lower lobe key points of the right lower lobe bronchus model contained in the right lung bronchus model region" can be implemented by the following steps:

[0108] S21. Based on the key point of the upper right leaf and the key point of the lower right leaf, determine a first horizontal line; wherein the first horizontal line is located between the key point of the upper right leaf and the key point of the lower right leaf and is parallel to the reference plane;

[0109] S22. The model region located above the first horizontal line in the right lung bronchus model region is defined as the right upper lobe model region.

[0110] S23. The model region located below the first horizontal line in the right lung bronchus model region is defined as the right lower lobe model region.

[0111] Specifically, step S21, "determine a first horizontal line based on the key points of the upper right leaf and the lower right leaf," can be implemented using any of the following steps:

[0112] Method 1: The first horizontal line is determined by the center point of the first line connecting the upper right leaf key point and the lower right leaf key point (as described above, line l1) and parallel to the reference plane (as described above, horizontal line l11).

[0113] Method 2: Determine a second key point (such as point 1220' as described above) in the right bronchus model region. The ordinate of the second key point is the same as the ordinate of one of the key points in the right upper lobe and the right lower lobe, and the abscissa of the second key point is the same as the other key point in the right upper lobe and the right lower lobe. The first horizontal line is determined by the center point of the second line connecting the second key point and the other key point in the right upper lobe and the right lower lobe (such as line l1' as described above), and the horizontal line perpendicular to the second line (such as horizontal line l11' as described above, which is also parallel to the reference plane).

[0114] For specific examples of the two implementation methods for the right lung bronchus model region division included in S21~S23, please refer to the above text. Figure 4a , Figure 4b The relevant content described.

[0115] Accordingly, in a specific feasible solution, the above-mentioned 10235, "based on the key points of the left upper lobe of the left upper lobe bronchus model and the key points of the left lower lobe of the left lower lobe bronchus model included in the left bronchus model region, can be implemented by the following steps:

[0116] S31. Based on the key point of the upper left leaf and the key point of the lower left leaf, determine a second horizontal line; wherein the second horizontal line is located between the key point of the upper left leaf and the key point of the lower left leaf and is parallel to the reference plane;

[0117] S32. The model region located above the second horizontal line in the left lung bronchus model region is defined as the left lung upper lobe model region;

[0118] S33. The model region located below the second horizontal line in the left lung bronchus model region is defined as the left lower lobe model region.

[0119] Specifically, step S31, "determine a second horizontal line based on the key points of the upper left leaf and the lower left leaf," can be implemented using any of the following steps:

[0120] Method 3: Determine the second horizontal line as the center point of the third line connecting the key points of the upper left leaf and the lower left leaf, and a line parallel to the reference plane; or

[0121] Method 4: Determine a third key point in the left bronchus model region, wherein the ordinate of the third key point is the same as the ordinate of one of the key points of the left upper lobe and the left lower lobe, and the abscissa of the third key point is the same as the other key point of the left upper lobe and the left lower lobe; determine the second horizontal line as the center point of the fourth line connecting the third key point and the other key point of the left upper lobe and the left lower lobe, and the horizontal line perpendicular to the fourth line (this horizontal line is also parallel to the reference plane).

[0122] For specific examples of the two implementation methods for dividing the left bronchial model region included in S31~S33, please refer to the specific examples of the two implementation methods for dividing the right bronchial model region included in S21~S23 above.

[0123] In the multiple model regions obtained through the above-mentioned content related to step 102, each model region includes at least one of the trachea models, such as: see Figure 4a and combined Figure 3a The main trachea model region includes main trachea model 1; the right upper lobe model region includes right main bronchus model 11 and right upper lobe bronchus model 111; the right lower lobe model region includes right lower lobe bronchus model 112; the left upper lobe model region includes left main bronchus model 12 and left upper lobe bronchus model 121; and the left lower lobe model region includes left lower lobe bronchus model 122.

[0124] Each model region contains at least one first key point. Specifically, assuming the target model region is one of multiple model regions, then the first key point located on at least a portion of the trachea in at least one of the tracheal models included in the target model region is the at least one first key point contained within that target model region. For example, combining... Figure 3a and Figure 4b If the target model region is the right upper lobe model region, which includes the right main bronchus model 11 and the right upper lobe bronchus model 111, then the right upper lobe key point 1110 located in the right upper lobe bronchus model 111 is at least one first key point contained in the right upper lobe model region.

[0125] Based on the acquisition of multiple first key point related content through the above steps S1221~S1224 as described above, in this embodiment, each model region preferably contains one first key point. Specifically, the first key point contained in the main trachea model region is the main trachea key point located on the main trachea model; the first key point contained in the right upper lobe model region is the right upper lobe key point located in the right upper lobe bronchus model; the first key point contained in the right lower lobe model region is the right lower lobe key point located in the right lower lobe bronchus model; the first key point contained in the left upper lobe model region is the left upper lobe key point located in the left upper lobe bronchus model; and the first key point contained in the left lower lobe model region is the left lower lobe key point located in the left lower lobe bronchus model.

[0126] Furthermore, based on the defined model regions of the tracheal tree 3D model, and the first key points and determined reference points within each model region, the point cloud data reflecting clinical positioning signals (i.e., the position data of the positioning sensor in the patient's tracheal space) obtained by real-time tracking of the positioning sensor's position in the patient's lung trachea space (the actual physical space) using a magnetic navigation device can be used to determine whether the positioning sensor has reached the first key point and reference point of each model region in the aforementioned tracheal tree 3D model. If so, the data acquisition required for one registration is considered complete. During the data acquisition process using the positioning sensor, the acquired point cloud data is used to automatically detect the registration progress of the positioning sensor in the target model region of the tracheal tree 3D model. When the registration of each model region in the aforementioned tracheal tree 3D model is determined to be completed, the entire tracheal registration is considered complete.

[0127] Specifically, in this embodiment, the registration progress detection scheme provided in this embodiment is triggered only after the positioning sensor has reached the reference point. For example, during the surgical registration stage, the physician manipulates the positioning sensor to enter and move through the patient's nostrils or mouth into the trachea. During this process, if the positioning sensor is determined to have reached reference point A in the tracheal tree 3D model based on its current position in the trachea, then the registration progress detection scheme will be triggered as follows: Figure 10 The surgical registration interface shown displays a prompt message such as "Positioning sensor placed at the main carina position, click the [Confirm] button to start registration." In response to the physician clicking the "Confirm" button in the prompt message or the "Start Registration" button displayed on the interface, the registration progress detection scheme provided in this embodiment is automatically triggered. The surgical registration interface can be accessed through methods such as... Figure 1c The display screen of the control device 511 shown in the figure displays the information. After the physician clicks a button such as "Confirm," the physician can continue to manipulate the positioning sensor to move through the trachea contained in the patient's lungs. For example, the positioning sensor can first be manipulated to perform a back motion to move through the main trachea in the lungs. After confirming that the main trachea has been traversed, the positioning sensor can then be manipulated to traverse the right main bronchus, right lower lobe bronchus, and so on in sequence. In addition, after detecting that the physician has clicked a button such as "Confirm," the execution subject of this embodiment will trigger the execution of the above steps 103-106 to determine the target model region where the positioning sensor is currently located in the tracheal tree 3D model, thereby realizing automatic detection of the registration progress for the target model region. For details on the automatic detection of registration progress, please refer to the relevant content below.

[0128] In addition to the above, the method provided in this embodiment may also include the following steps:

[0129] When the positioning sensor is detected to have reached the reference point in the trachea 3D model, a prompt message is displayed to prompt the user to confirm the start of registration;

[0130] In response to the user's confirmation action triggered by the prompt information, step 103 above is executed.

[0131] Among the above 103, it can be composed of, for example Figure 1a or Figure 1bThe magnetic navigation device 20 shown in the figure determines the current position information (i.e., first position information) of the positioning sensor in the trachea of ​​the lungs based on the positioning signal transmitted in real time by the positioning sensor as it moves within the trachea of ​​the lungs, and sends it to the execution subject of this application embodiment; wherein, the positioning signal is generated by the positioning sensor based on the current generated by its own internal coil in the changing magnetic field. The changing magnetic field is generated by the magnetic field generator 22 set in the operating table 10 under the control of the magnetic navigation device 20. Since the patient's lungs are under the changing magnetic field when the patient is lying supine in the operating table 10, the positioning sensor can sense the changing magnetic field and generate a corresponding current when it moves within the trachea of ​​the patient's lungs.

[0132] The aforementioned first location information includes the current position and orientation of the positioning sensor within the lung.

[0133] In the above 104, the second position information corresponding to the first position information in the tracheal tree three-dimensional model can be determined according to the spatial coordinate transformation relationship between the magnetic field space and the image space. This second position information is also the position information corresponding to the positioning sensor when it is superimposed on the tracheal tree three-dimensional model in the form of a virtual identifier. According to this second position information, the target model area where the virtual identifier is located when the positioning sensor is superimposed on the tracheal tree three-dimensional model in the form of a virtual identifier can be understood as the target model area where the positioning sensor is located in the tracheal tree three-dimensional model.

[0134] In steps 105-106 above, a corresponding distance metric algorithm can be used to calculate the first distance between the positioning sensor and the corresponding first key point in the target model region (i.e., the distance between the current position of the positioning sensor in the tracheal tree 3D model and the first key point in the target model region) based on the second position information and the third position information of at least one first key point in the target model region. This distance can be used as a metric to measure the registration progress of the target model region. The distance metric algorithm described above can be, but is not limited to, Euclidean distance, cosine similarity, Hamming distance, Fraser distance, Hausdorff distance, Manhattan distance, etc.

[0135] In practice, the registration progress corresponding to the target model area can be divided into a corresponding number of registration progress ranges based on the number of at least one first key point contained within the target model area. Subsequently, when executing steps 105-106 above, the target first key point (e.g., the first key point closest to the current position of the positioning sensor within the target model area) can be found from the at least one first key point contained in the target model area according to a search direction adapted to the target model area. Then, the first distance between the positioning sensor and the target first key point is calculated. Based on this first distance and the registration progress range corresponding to the target first key point, the registration progress for the target model area is determined. If the target model area is the main trachea model area among multiple model areas, the search direction can be the direction of the main trachea (e.g., the direction of the main trachea). Figure 4a The direction opposite to the direction indicated by arrow V; if the target model area is a model area other than the main trachea model area among multiple model areas, then the search direction can be the hierarchical ascending direction of at least one trachea model contained in the target model area. Therefore, one feasible solution for the above-mentioned 105 "calculating the first distance between the positioning sensor and the at least one first key point contained in the target model area based on the second location information" can specifically include:

[0136] Determine the search direction corresponding to the target model region;

[0137] According to the search direction, find the target first key point that is closest to the positioning sensor from the at least one first key point contained in the target model area;

[0138] Based on the second location information, calculate the first distance between the positioning sensor and the first key point of the target;

[0139] And correspondingly, the aforementioned 106 "determining the registration progress for the target model region based on the first distance" may specifically include:

[0140] Obtain the registration progress range corresponding to the first key point of the target;

[0141] Based on the first distance between the positioning sensor and the first key point of the target, and the registration progress range corresponding to the first key point of the target, the registration progress for the target model region is determined.

[0142] For example, based on the above, in the preferred embodiment where each model region contains a first key point, i.e., the target model region contains a first key point, the registration progress corresponding to the target model region can be directly divided into a registration progress range: 0~100%. The larger the first distance between the positioning sensor and the first key point contained in the target model region, the smaller the registration progress for the target model region. In this embodiment, when the first distance is greater than a preset distance threshold, the registration progress for the target model region is uniformly set to 0. The preset distance threshold can be flexibly set according to actual conditions and is not limited here. Conversely, the smaller the first distance, the larger the registration progress for the target model region. The maximum registration progress is 100%, indicating that the positioning sensor has reached the first key point of the target model region. However, this does not necessarily mean that registration for the target model region has been completed. To improve the accuracy of determining whether registration for the target model region is complete, this embodiment also combines the number of data in the registration dataset falling into the judgment region corresponding to the target model region for judgment. The judgment region is the area determined by the center point of the first key point of the target model region. A detailed explanation of the determination area will be provided in the relevant content below.

[0143] For example, if the target model region contains two first key points, the registration schedule corresponding to that target model region can be pre-divided into two registration schedule ranges, such as combining... Figure 3b and Figure 4aLet the target model region be the main trachea model region. The main trachea model region contains two first key points: main trachea model key point 10 and main trachea model key point 10'. Then the registration progress corresponding to the main trachea model region can be divided into the following two registration progress ranges: 0~50% (inclusive of 50%) and 50% (exclusive of 50%)~100%. Among them, the registration progress range corresponding to main trachea model key point 10' is 0~50%, and the registration progress range corresponding to main trachea model key point 10 is 50%~100%. If the current position of the positioning sensor in the main trachea model region is between the reference point A and the main trachea model key point 10', then according to the search direction adapted to the main trachea model region (opposite to the main trachea direction), the main trachea model key point 10' can be found as the target first key point from the two first key points contained in the main trachea model region. That is, the main trachea model key point 10' is the target first key point closest to the current position of the positioning sensor in the main trachea model region. Therefore, the first distance D' between the positioning sensor and the main trachea model key point 10', and the registration progress range corresponding to the main trachea model key point 10', can be used to determine the registration progress for the target model region. Wherein, the larger the first distance D', the smaller the registration progress; if the first distance D' is greater than a preset distance threshold, the registration progress is uniformly set to 0; the smaller the first distance D', the larger the registration progress, with a maximum registration progress of 50%. Furthermore, if the positioning sensor subsequently moves to a position within the main trachea model region between the main trachea model key 10' and the main trachea model key 10, then the main trachea model key 10 is the target first key point. Based on the first distance D between the positioning sensor and the main trachea model key point 10, and the registration progress range of 50% to 100% corresponding to the main trachea model key point 10, the registration progress for the target model region can be further determined. The maximum determined registration progress is 100%, meaning the positioning sensor has reached the first key point (i.e., the main trachea model key 10) that is furthest from the reference point among the two first key points contained within the main trachea model region. However, this does not indicate that registration for the main trachea model region is complete. To improve the accuracy of determining whether registration for the main trachea model region is complete, this embodiment also considers the number of data points in the registration dataset falling into the corresponding judgment region within the main trachea model region. The judgment region is an area defined with the main trachea model key 10 as its center point. Similarly, the determination of this judgment region can be found in the relevant content below.

[0144] In this embodiment, to further improve the accuracy of registration progress calculation, an error path judgment is performed for the target model region. Specifically, it determines whether the positioning sensor is moving within the target model region according to the planned path. If so, the registration for the target model region is considered to have entered the correct path, and registration progress is calculated. Furthermore, the path point set along the positioning sensor's movement path within the target model region is added to the registration dataset to provide data support for determining whether registration for the target model region is complete. If not, the registration for the target model region is considered to have not entered the correct path, and registration progress is no longer calculated, nor is the path point set along the positioning sensor's movement path within the target model region added to the registration dataset.

[0145] In this embodiment, each model region contains a first key point. Therefore, when the target model region contains one first key point, the planned path directly refers to the shortest path from the reference point to the first key point of the target model region, which can be planned based on the centerline information of the tracheal tree 3D model. The movement path refers to the shortest movement path for the positioning sensor to move from the reference point to its current position in the target model region within the tracheal tree 3D model. Therefore, when each model region contains one first key point, the method provided in this embodiment may further include the following steps:

[0146] 107. Obtain the planned path obtained by performing path planning for the target model region; wherein, the planned path is the shortest path between the reference point and a first key point contained in the target model region, planned based on the centerline information of the tracheal tree three-dimensional model;

[0147] 108. Determine the shortest movement path for the positioning sensor in the tracheal tree 3D model from the reference point to its current position in the target model region;

[0148] 109. Compare the moving path with the planned path to determine whether the positioning sensor moves according to the planned path;

[0149] 1010. When moving along the planned path, the calculation step in step 105 above is triggered, and all path points on the moving path are added to the registration dataset.

[0150] In the above 107, when performing path planning, all points on the centerline contained in the centerline information of the tracheal tree 3D model can be used as the path point set in the tracheal tree 3D model; then, based on the coordinates of all points on the centerline contained in the extracted centerline information, the corresponding path search algorithm is used to perform forward path search with the reference point as the initial path point, so as to find the shortest path between the reference point and the first key point of each model area, which is used as the planned path.

[0151] For example, see Figure 4b Taking the path between the planning reference point A and the first key point of the right upper lobe model region (right upper lobe key point 1110 of the right upper lobe bronchus model) as an example, assuming that the path search algorithm used during path planning is a coordinate-based path search algorithm (such as the CPS algorithm), then based on the coordinates of all points on the centerline contained in the extracted tracheal tree 3D model centerline information, with the reference point as the first path point (i.e., the initial path point), along the forward search direction (specifically, the direction of increasing tracheal model levels, as shown by the virtual arrow in the figure)... The search proceeds by: (1) determining at least one first adjacent point on the centerline to the right of the first path point and adjacent to it; (2) calculating the distance (e.g., Euclidean distance) between the first path point and each first adjacent point, selecting the first adjacent point with the shortest distance as the second path point, and adding the second path point to the set of planned path points corresponding to the right upper lobe model region; (3) continuing the downward search direction to determine at least one second adjacent point on the centerline adjacent to the second path point, selecting the second adjacent point with the shortest distance from the second path point as the third path point, and adding the third path point to the set of planned path points corresponding to the right upper lobe model region; and so on, until the first key point of the right upper lobe model region (i.e., the right upper lobe key point 1110 of the right upper lobe bronchus model) is found, at which point the path search for the right upper lobe model region can be ended, and a corresponding planned path can be generated based on the set of planned path points corresponding to the right upper lobe model region. This planned path can be superimposed on the tracheal tree 3D model to provide guidance for doctors to control the positioning sensor to move in the lung trachea.

[0152] Similarly, the shortest path between the planned baseline and the first key point of other model regions can also be used as the corresponding planning path. It should be noted that when performing path planning for the main trachea model region, the path search starts from the baseline and proceeds in the backward search direction. Specifically, the backward search direction refers to the direction opposite to that indicated by arrow V (the direction of the main trachea, which in the pulmonary trachea points from the pharynx to the main carina).

[0153] In step 108 above, the virtual trajectory data of the positioning sensor moving from the reference point to its current position in the target model region within the tracheal tree 3D model can be determined based on the actual trajectory data of the positioning sensor moving within the tracheal space. This virtual trajectory data is then processed to obtain the shortest movement path of the positioning sensor from the reference point to its current position in the target model region within the tracheal tree 3D model. The processing described above may include, but is not limited to, deleting duplicate trajectory points generated by the positioning sensor performing a backtracking action. Based on this, in one feasible technical solution, step 108, "determining the shortest movement path of the positioning sensor from the reference point to its current position in the target model region within the tracheal tree 3D model," may specifically include:

[0154] 1081. Obtain the first trajectory data (the actual trajectory) of the positioning sensor moving within the trachea of ​​the lungs.

[0155] 1082. Based on the first trajectory data, determine the second trajectory data (a virtual trajectory) of the positioning sensor moving from the reference point to its current position in the target model area within the 3D model of the tracheal tree.

[0156] 1083. Determine the first type of trajectory points and the second type of trajectory points in the second trajectory data; wherein, the first type of trajectory points are trajectory points that reflect the positioning sensor performing a back-away action, and the second type of trajectory points are trajectory points that correspond to the first type of trajectory points, satisfy the deletion rules, and reflect the positioning sensor performing a forward action;

[0157] 1084. Delete the first type of trajectory points and the second type of trajectory points in the second trajectory data to obtain the deleted second trajectory data;

[0158] 1085. Determine the movement path based on the deleted second trajectory data.

[0159] In practice, the first trajectory data (the real trajectory) is obtained from the point cloud data (the point cloud data of the positioning signal generated in real time) sent by the positioning sensor. After obtaining the first trajectory data, it can be spatially transformed to obtain the third trajectory data (the virtual trajectory) corresponding to the first trajectory data in the tracheal tree 3D model. Then, the second trajectory data of the positioning sensor moving from the reference point to its current position in the target model area in the tracheal tree 3D model can be extracted from the third trajectory data. Afterward, it can be analyzed whether the distance between two trajectory points in the second trajectory data increases relative to the reference point in the time series. If so, it indicates that the two trajectory points correspond to the positioning sensor performing a forward movement, and these two trajectory points are regression trajectory points; if not, it indicates that the two trajectory points correspond to the positioning sensor performing a regression movement, and these two trajectory points are forward trajectory points. If the positioning sensor performs a forward movement, it is considered that duplicate trajectory points exist in the second trajectory data. Therefore, the set of retreat trajectory points reflecting the positioning sensor's retreat movement is deleted from the second trajectory data. Simultaneously, points corresponding to the retreat trajectory points in the set of forward trajectory points reflecting the positioning sensor's forward-backward movement are also deleted. Specifically, points in the set of forward trajectory points that are closest in time to the retreat trajectory point set but earlier in time, and whose corresponding distance range is the same as the retreat trajectory point set, are deleted. After deleting duplicate trajectory points in the second trajectory data, the shortest movement path for the positioning sensor in the tracheal tree 3D model, from the reference point to its current position in the target model region, can be obtained based on the deleted trajectory points in the second trajectory data.

[0160] Based on the above, in one feasible technical solution, "determining the first type of trajectory point in the second trajectory data" in step 1083 may specifically include:

[0161] 10831. Based on the timestamps of multiple trajectory points contained in the second trajectory data, determine multiple pairs of trajectory points with adjacent timestamps;

[0162] 10832. Calculate the second distance and third distance of the first trajectory point and the second trajectory point contained in each pair of trajectory points relative to the reference point, respectively; wherein, the timestamp of the second trajectory point is later than the timestamp of the first trajectory point;

[0163] 10833. Based on the second distance and the third distance, determine whether each pair of trajectory points is a first type of trajectory point.

[0164] In the above, appropriate distance metric algorithms can be used to calculate the second and third distances of the first and second trajectory points contained in each pair of trajectory points relative to the reference point, respectively. For details on the applicable distance metric algorithms, please refer to the relevant descriptions above; they will not be repeated here.

[0165] If the third distance between the second trajectory point and the reference point in a calculated pair of trajectory points is less than the second distance between the first trajectory point and the reference point, then the pair of trajectory points can be determined to be first-type trajectory points; otherwise, the pair of trajectory points can be determined not to be first-type trajectory points.

[0166] That is, if the target pair of trajectory points is one of multiple pairs of trajectory points, then the above-mentioned 10833 "determining whether each pair of trajectory points is a first type of trajectory point based on the second distance and the third distance" can be implemented by the following specific steps:

[0167] If the third distance between the second trajectory point and the reference point in the target pair trajectory points is less than the second distance between the first trajectory point and the reference point, then the target pair trajectory points are of the first type.

[0168] If the third distance between the second trajectory point and the reference point in the target pair trajectory points is greater than or equal to the second distance between the first trajectory point and the reference point, then the target pair trajectory points are not of the first type.

[0169] Based on the identification of the first type of trajectory points, and in accordance with the corresponding deletion rules, trajectory points corresponding to the first type of trajectory points and meeting the deletion rule requirements can be determined from the remaining trajectory points in the second trajectory data, excluding the first type of trajectory points. The deletion rules include: a timestamp earlier than the timestamp of the first type of trajectory points; and a distance from the reference point greater than or equal to the distance between the trajectory point with the latest timestamp in the first type of trajectory points and the reference point, and less than or equal to the distance between the trajectory point with the earliest timestamp in the first type of trajectory points and the reference point.

[0170] To facilitate understanding, the following will be combined with Figure 5 To illustrate the above example 1083, let's take an example.

[0171] See also Figure 5The second trajectory data L is shown. Based on this second trajectory data L, by performing steps 10831-10833 above, all trajectory points on trajectory segment l2 are determined to be first-type trajectory points. The first-type trajectory point with the earliest timestamp on trajectory segment l2 is trajectory point g2, and the first-type trajectory point with the latest timestamp is trajectory point g1. The distance between trajectory point g1 and reference point A is d1, and the distance between trajectory point g2 and reference point A is d2 (greater than d1, not shown in the figure). That is, the distance range between the first-type trajectory points and the reference point is [d1, d2]. Therefore, firstly, based on the timestamps of each trajectory point in the second trajectory data L, it can be determined that the timestamps of the trajectory points on the trajectory segment between reference point A and trajectory point g2 are all earlier than the timestamps of the first-type trajectory points. Further, the distance d3 between each trajectory point on the trajectory segment between reference point A and trajectory point g2 and the reference point can be calculated. Then, from all the trajectory points on the trajectory line segment between the reference point A and the trajectory point g2, the trajectory points whose corresponding distance d3 is greater than or equal to the distance d1 and less than or equal to the distance d2 are selected and determined as the second type of trajectory points. For example, all the trajectory points on the trajectory line segment l3 between the trajectory points g2 and g3 are the second type of trajectory points.

[0172] Subsequently, after the first and second type trajectory points are deleted from the second trajectory data L, during the process of determining the movement path based on the deleted second trajectory data, the trajectory points adjacent to trajectory point g3 in the deleted second trajectory data L can be connected to the trajectory points adjacent to trajectory point g1.

[0173] In steps 109-1010 above, the Dynamic Time Warping (DTW) method can be used, but is not limited to, to compare the planned path obtained for the target model region through steps 107-108 above with the determined movement path, to compare the similarity between the planned path and the movement path. If the similarity is greater than or equal to a preset threshold, it is determined that the sensor is moving according to the planned path (in other words, it is considered that the registration for the target model region has entered the correct path), thereby triggering the calculation of the registration progress for the target model region, and adding all path points on the movement path to the registration dataset. If the similarity is less than the preset threshold, it is determined that the positioning sensor is not moving according to the trajectory path (in other words, it is considered that the registration for the target model region has not entered the correct path), thereby triggering the cessation of the calculation of the registration progress for the target model region, and in addition, all path points on the movement path are not added to the registration dataset.

[0174] Using the aforementioned registration dataset, it can be used to determine whether the registration of the target model region is complete, thereby further improving the accuracy of determining whether the registration of the target model region is complete. Specifically, the method provided in this embodiment may further include the following steps:

[0175] 1011. Determine the judgment region by taking a first key point contained in the target model region as the center point;

[0176] 1012. Determine the number of path points contained in the registration dataset within the determination region;

[0177] 1013. Based on the quantity, determine whether the registration for the target model region is complete.

[0178] In the above 1011, the determination region can be a circular region with a radius of R centered on a first key point contained in the target model region; of course, the determination region can also be a region of other shapes, such as rectangle, square, pentagon, hexagon, etc., which is not limited here, as long as the determination region is centered on the first key point of the target model region. In this embodiment, the determination region is preferably a circular region.

[0179] In the above steps 1011 to 1013, when the shape of the determination region is a circular region with the first key point of the target model region as the center and a radius of R, the number of path points in the registration dataset whose distance to the first key point of the target model region is less than or equal to R can be counted. If the number is greater than or equal to a set threshold, it is determined that the registration for the target model region has been completed; if the number is less than the set threshold, it is determined that the registration for the target model region has not been completed.

[0180] Furthermore, after confirming that registration for the target model region is complete, a corresponding prompt can be displayed to indicate that registration for the target model region is successful. For example, see [link to relevant documentation]. Figure 11 The surgical registration interface displays a two-dimensional front view of the tracheal tree 3D model 100. Taking the main trachea model area in the tracheal tree 3D model 100 as an example, the display color of the main trachea model area in the two-dimensional front view can be updated to gray, and a registration completion indicator such as "" can be displayed on the main trachea model area. This indicates that registration has been completed for the main trachea model region.

[0181] The above mainly describes the error path judgment and registration determination for the target model region from the perspective that each model region contains a first key point. If each model region in this embodiment contains at least one first key point, and correspondingly, the target model region contains at least two first key points, then the method provided in this application embodiment may further include the following steps:

[0182] 107'. Obtain the planned path between two target points; wherein, the two target points are two points adjacent to the positioning sensor determined from at least two first key points contained in the reference point and the target model area; the planned path is the shortest path between the two target points planned based on the centerline information of the tracheal tree three-dimensional model.

[0183] 108' Determine the shortest movement path for the positioning sensor in the tracheal tree 3D model from the first target point to its current position in the target model region; the first target point is the target point that the positioning sensor has already surpassed among the two target points;

[0184] 109' Compare the moving path with the planned path to determine whether the positioning sensor moves according to the planned path;

[0185] 1010' When moving along the planned path, the calculation step in step 105 above is triggered, and all path points on the moving path are added to the registration dataset.

[0186] For example, combining Figure 3b and Figure 4a Taking the target model region as the main trachea model region, which contains the following two first key points: main trachea key point 10' and main trachea key point 10, assuming that the current position of the positioning sensor in the main trachea model region is between the reference point A and the main trachea key point 10', then the two points adjacent to the positioning sensor determined from the reference point A, the main trachea key point 10' and the main trachea key point 10 are the reference point A and the main trachea key point 10'; where reference point A is the first target point that the positioning sensor has already moved past; then, the planned path between the obtained reference point A and the main trachea key point 10' can be compared with the determined shortest movement path of the positioning sensor from the reference point A to its current position in the main trachea model region. Based on the comparison result, it is determined whether the positioning sensor moves in the main trachea model region according to the above planned path. If so, the calculation of the registration progress for the main trachea model region is triggered, and the above movement path is added to the registration dataset.

[0187] For details on the specific implementation of the planning path, movement path, comparison, etc. mentioned in steps 107' to 1010' above, please refer to the content related to steps 107 to 1010 above.

[0188] Furthermore, the method provided in this embodiment may also include the following steps:

[0189] 1011'. Determine the judgment area by taking the first key point that is farthest from the reference point among the at least two first key points contained in the target model area as the center point;

[0190] 1012' Determine the number of path points contained in the registration dataset within the determination region;

[0191] 1013'. Based on the quantity, determine whether the registration for the target model region is complete.

[0192] For a detailed description of the implementation of steps 1011' to 1013' above, please refer to the content related to steps 1011 to 1013 above.

[0193] Furthermore, after confirming that registration for the target model region has been completed, if returning to steps 103-104 above and detecting that the positioning sensor has entered the next target model region, steps 105-106 above can be executed again to detect the registration progress for the next target model region, thereby determining whether registration for the next target model region has been completed. Thus, after detecting that registration has been completed for all model regions included in the tracheal tree 3D model, it can be determined that registration for the entire lung trachea has been completed.

[0194] To facilitate doctors' intuitive understanding of the registration progress, this embodiment can also display the registration progress of each model region in the tracheal tree 3D model, and output corresponding prompts upon confirmation of registration completion. These prompts may include, but are not limited to, changing the color of the corresponding model region, adjusting the registration completion marker for the corresponding model region, and providing voice prompts. For a detailed description of the prompts, please refer to the attached document. Figure 11 The aforementioned related content.

[0195] In addition, this embodiment can also calculate and display the bifurcation angle information (including multiple bifurcation angles) of the tracheal tree 3D model to provide a basis for doctors to operate the positioning sensor to move in the lungs and trachea. The above-mentioned bifurcation angle information can be calculated based on the centerline information of the tracheal tree 3D model. Specifically, it can be calculated based on the centerline of each tracheal model in the tracheal tree 3D model. Here, a bifurcation angle refers to the angle between the centerline of one tracheal model and the centerline of another adjacent tracheal model. In other words, a bifurcation angle refers to the angle between the centerlines of two tracheal models that have a bifurcation relationship. That is, the method provided in this embodiment may also include the following steps:

[0196] 1014. Based on the centerline information of the tracheal tree 3D model, determine the centerlines of each of the multiple tracheal models in the tracheal tree 3D model;

[0197] 1015. Based on the centerlines of the multiple tracheal models, determine the bifurcation angle information of the tracheal tree 3D model; wherein, the bifurcation angle information includes multiple bifurcation angles, and a bifurcation angle is the angle between the centerlines of two tracheal models that have a bifurcation relationship;

[0198] 1016. Display the bifurcation angle information on the three-dimensional model of the tracheal tree so that the user can control the positioning sensor to move in the trachea of ​​the lungs based on the bifurcation angle information.

[0199] For example, see Figure 3a The angle between the centerline of the main trachea model 1 and the centerline of the right main bronchus model 11 is one bifurcation angle; the angle between the centerline of the right main bronchus model 11 and the centerline of the right upper lobe bronchus model 111 is another bifurcation angle, and so on. Other remaining bifurcation angles can be obtained by analogy.

[0200] In summary, the technical solution provided in this embodiment is based on obtaining a three-dimensional model of the tracheal tree reconstructed from the lungs and trachea. The model is then divided based on multiple first key points within the obtained tracheal tree three-dimensional model, resulting in multiple model regions, each containing at least one first key point. Furthermore, based on the first position information of the positioning sensor within the lungs and trachea, the second position information of the positioning sensor in the tracheal tree three-dimensional model and its target model region can be determined. The first distance between the positioning sensor and at least one first key point contained in the target model region can be calculated based on this second position information, and the registration progress for the target model region can be determined based on this first distance. The technical solution provided in this embodiment uses the first distance between the positioning sensor and the corresponding first key point in the target model region as a standard for measuring the registration progress of the target model region. This provides an objective standard for evaluating the registration completion status of the lung and trachea during surgery, which helps to improve the accuracy of determining the registration completion status. In addition, based on the determined registration progress of the target model region, it also helps to provide the user (such as a clinician) with corresponding registration progress information feedback, so that the user can intuitively understand the registration completion status of the target model region. This provides effective assistance for the user to operate the positioning sensor to move within the lung and trachea, thereby ensuring the sufficiency of registration data collection and providing a guarantee for the subsequent precise guidance of surgery.

[0201] It's important to note that if the positioning sensor remains stationary within the trachea, the point cloud data it collects (representing the sensor's position within the trachea) is often meaningless. Furthermore, the amount of point cloud data collected at the beginning of registration is typically small. In such cases, processing this data for registration progress calculations and completion checks often results in low accuracy. Therefore, in this embodiment, processing only begins when the number of point clouds collected by the positioning sensor is greater than or equal to a set threshold, and when the sensor's movement range exceeds a set threshold. This processing determines the sensor's current position within the trachea and its trajectory data. This also explains why, as mentioned earlier, the registration progress for the target model region is uniformly set to 0 when the first distance exceeds a preset distance threshold.

[0202] In the above processing, the point cloud data collected by the positioning sensor is first preprocessed to remove abnormal data, such as outliers and invalid data caused by signal loss. For example, if the coil inside the positioning sensor cannot sense a magnetic field due to interference, it will be unable to generate current and will send a default signal to the execution subject of this embodiment. This received default signal becomes invalid data or may be outlier data. After the above preprocessing is completed, the preprocessed point cloud data can be rasterized to downsample the point cloud data, laying the foundation for further analysis and improving the efficiency of further analysis. The purpose of further analysis includes, but is not limited to, determining the current position information of the positioning sensor in the trachea of ​​the lungs and the trajectory data of its movement in the trachea of ​​the lungs. For the specific implementation of data rasterization, please refer to the existing relevant content, which will not be elaborated here.

[0203] An embodiment of this application also provides a registration progress detection system for the lungs and trachea corresponding to the above-described method embodiments. See also... Figure 6 As shown, the registration progress detection system for lung surgery navigation may include:

[0204] A magnetic field generator is used to generate a positioning magnetic field; the trachea of ​​the lungs is placed in the positioning magnetic field;

[0205] A positioning sensor that, when moving within the trachea of ​​the lungs, can generate a positioning signal by sensing the positioning magnetic field and send the positioning signal to a processing device, so that the processing device can determine the position information of the positioning sensor within the trachea of ​​the lungs based on the positioning signal;

[0206] A processing device for performing the steps in the embodiments of the registration progress detection method for the lungs and trachea provided in this application.

[0207] For a detailed description of the aforementioned magnetic field generator and positioning sensor, please refer to the relevant content in other embodiments of the above application; further details will not be repeated here.

[0208] The aforementioned processing equipment can be a control device with data processing capabilities, such as... Figure 1c The control device 511 shown is an example of a computer device. The control device can be independently set up, for example... Figure 1c The doctor's main control console 50 shown in the image, or it can be used with, for example... Figure 1a The magnetic navigation device 20 shown is integrated into the magnetic navigation device 20, but this embodiment does not limit this.

[0209] It should be noted that the lung and trachea registration progress detection system provided in the above embodiments may include other devices or equipment besides those described above. Regarding the other devices or equipment that may be included, please refer to the above-mentioned... Figures 1a to 1c This section introduces information related to the medical system.

[0210] Figure 7 A structural block diagram of a registration progress detection device for the lungs and trachea provided in an embodiment of this application is shown. Figure 7 As shown, the registration progress detection device for the lungs and trachea includes: an acquisition module 61, a division module 62, a determination module 63, and a calculation module 64; wherein,

[0211] The acquisition module 61 is used to acquire a three-dimensional model of the tracheal tree reconstructed from medical imaging images of the lungs and trachea and a number of first key points in the three-dimensional model of the tracheal tree;

[0212] The segmentation module 62 is used to segment the tracheal tree three-dimensional model based on multiple first key points to obtain multiple model regions, wherein each model region contains at least one first key point;

[0213] The acquisition module 61 is also used to acquire first position information of the current position of the positioning sensor in the trachea of ​​the lung;

[0214] The determining module 63 is used to determine the second position information of the positioning sensor in the tracheal tree 3D model and the target model area it is located in, based on the first position information;

[0215] Calculation module 64 is used to calculate, based on the second location information, a first distance between the positioning sensor and the at least one first key point contained in the target model region;

[0216] The determining module 63 is further configured to determine the registration progress for the target model region based on the first distance.

[0217] Furthermore, the aforementioned tracheal tree 3D model includes multiple tracheal models, and each model region includes at least one of the tracheal models. The multiple tracheal models include: a main trachea model, a right lung bronchus model connected to the main trachea model, and a left lung bronchus model. The right lung bronchus model includes: a right main bronchus model, a right upper lobe bronchus model, and a right lower lobe bronchus model. The left lung bronchus model includes: a left main bronchus model, a left upper lobe bronchus model, and a left lower lobe bronchus model. The multiple first key points include: a main trachea key point located on the main trachea model, a right upper lobe key point located on the right upper lobe bronchus model, a right lower lobe key point located on the right lower lobe bronchus model, a left upper lobe key point located on the left upper lobe bronchus model, and a left lower lobe key point located on the left lower lobe bronchus model.

[0218] The aforementioned partitioning module 62, when used to partition the tracheal tree 3D model based on multiple first key points to obtain multiple model regions, is specifically used for: obtaining the reference point of the tracheal tree 3D model; the reference point is determined based on the intersection of the main trachea model, the right main bronchus model, and the left main bronchus model; determining the reference plane of the tracheal tree 3D model according to the main trachea key point and the reference point; and partitioning the tracheal tree 3D model into multiple model regions according to the reference plane and multiple first key points.

[0219] Furthermore, the aforementioned division module 62, when used to determine the reference plane of the tracheal tree three-dimensional model based on the key points of the main trachea and the reference point, is specifically used to: determine a vector reflecting the direction of the main trachea of ​​the main trachea model based on the key points of the main trachea and the reference point; and determine a plane that passes through the reference point and is perpendicular to the vector as the reference plane.

[0220] Further, the aforementioned division module 62, when used to divide the tracheal tree three-dimensional model into multiple model regions based on the reference plane and multiple first key points, is specifically used for: determining the model region located above the reference plane in the tracheal tree three-dimensional model as the main tracheal model region; determining a dividing line based on the reference point and the main tracheal key point; dividing the model region located below the reference plane in the tracheal tree three-dimensional model into a right lung bronchus model region and a left lung bronchus model region according to the dividing line; dividing the right lung bronchus model region into a right upper lobe model region and a right lower lobe model region based on the right upper lobe key point and the right lower lobe key point contained in the right lung bronchus model region; and dividing the left lung bronchus model region into a left upper lobe model region and a left lower lobe model region based on the left upper lobe key point and the left lower lobe key point contained in the left lung bronchus model region.

[0221] Further, the aforementioned division module 62, when used to divide the right bronchus model region into a right upper lobe model region and a right lower lobe model region based on the right upper lobe key point and the right lower lobe key point contained within the right bronchus model region, is specifically used to: determine a first horizontal line based on the right upper lobe key point and the right lower lobe key point; wherein, the first horizontal line is located between the right upper lobe key point and the right lower lobe key point and is parallel to the reference plane; the model region located above the first horizontal line in the right bronchus model region is determined as the right upper lobe model region; and the model region located below the first horizontal line in the right bronchus model region is determined as the right lower lobe model region.

[0222] Further, the aforementioned division module 62, in determining a first horizontal line based on the right upper lobe key point and the right lower lobe key point, includes: determining a horizontal line parallel to the reference plane and passing through the center point of the first line connecting the right upper lobe key point and the right lower lobe key point as the first horizontal line; or, determining a second key point in the right lung bronchus model region, wherein the ordinate of the second key point is the same as the ordinate of one of the key points of the right upper lobe key point and the right lower lobe key point, and the abscissa of the second key point is the same as the other key point of the right upper lobe key point and the right lower lobe key point; and determining a horizontal line perpendicular to the second line and passing through the center point of the second line connecting the second key point and the other key point of the right upper lobe key point and the right lower lobe key point as the first horizontal line.

[0223] Furthermore, the aforementioned division module 62, when used to divide the left bronchus model region into a left upper lobe model region and a left lower lobe model region based on the left upper lobe key point and the left lower lobe key point contained within the left bronchus model region, is specifically used to: determine a second horizontal line based on the left upper lobe key point and the left lower lobe key point; wherein the second horizontal line is located between the left upper lobe key point and the left lower lobe key point and is parallel to the reference plane; determine the model region in the left bronchus model region located above the second horizontal line as the left upper lobe model region; and determine the model region in the left bronchus model region located below the second horizontal line as the left lower lobe model region.

[0224] Further, the aforementioned division module 62, in determining a second horizontal line based on the left upper lobe key point and the left lower lobe key point, includes: determining a horizontal line parallel to the reference plane and passing through the center point of the third line connecting the left upper lobe key point and the left lower lobe key point as the second horizontal line; or, determining a third key point in the left bronchus model region, wherein the ordinate of the third key point is the same as the ordinate of one of the key points of the left upper lobe key point and the left lower lobe key point, and the abscissa of the third key point is the same as the other key point of the left upper lobe key point and the left lower lobe key point; and determining a horizontal line perpendicular to the fourth line connecting the third key point and the other key point of the left upper lobe key point and the left lower lobe key point as the second horizontal line.

[0225] Furthermore, each of the model regions includes a first key point; and the acquisition module 61 described above can also be used to acquire a planned path obtained by performing path planning for the target model region; wherein the planned path is the shortest path between the reference point and a first key point included in the target model region, planned based on the centerline information of the tracheal tree three-dimensional model.

[0226] The aforementioned determining module 63 can also be used to determine the shortest movement path for the positioning sensor in the tracheal tree three-dimensional model from the reference point to its current position in the target model region;

[0227] Furthermore, the apparatus provided in this application embodiment may further include: a comparison module, configured to compare the movement path with the planned path to determine whether the positioning sensor moves according to the planned path; and a trigger module, configured to, when moving according to the planned path, trigger the execution of the step of calculating the first distance between the positioning sensor and a first key point contained in the target model region based on the second location information, and add all path points on the movement path to the registration dataset.

[0228] Further, the aforementioned determining module 63, when determining the shortest movement path for the positioning sensor to move from the reference point to its current position in the target model region within the tracheal tree 3D model, can be specifically used for: acquiring first trajectory data of the positioning sensor's movement within the trachea of ​​the lungs; determining second trajectory data of the positioning sensor's movement from the reference point to its current position in the target model region within the tracheal tree 3D model based on the first trajectory data; determining first-type trajectory points and second-type trajectory points in the second trajectory data; wherein, the first-type trajectory points are trajectory points reflecting the positioning sensor's backward movement, and the second-type trajectory points are trajectory points corresponding to the first-type trajectory points that satisfy deletion rules and reflect the positioning sensor's forward movement; deleting the first-type and second-type trajectory points in the second trajectory data; determining the movement path based on the deleted second trajectory data; wherein, satisfying the deletion rules includes: a timestamp earlier than the timestamp of the first-type trajectory points; and a distance greater than or equal to the distance between the latest timestamp of the first-type trajectory points and the reference point, and less than or equal to the distance between the earliest timestamp of the first-type trajectory points and the reference point.

[0229] Furthermore, the aforementioned determining module 63, when used to determine the first type of trajectory points in the second trajectory data, can be specifically used to: determine multiple pairs of trajectory points with adjacent timestamps based on the timestamps of the multiple trajectory points contained in the second trajectory data; calculate the second distance and the third distance of the first trajectory point and the second trajectory point contained in each pair of trajectory points relative to the reference point, respectively; wherein the timestamp of the second trajectory point is later than the timestamp of the first trajectory point; and determine whether each pair of trajectory points is a first type of trajectory point based on the second distance and the third distance.

[0230] Furthermore, the target pair of trajectory points is one of multiple pairs of trajectory points; and the aforementioned determining module 63, when used to determine whether the target pair of trajectory points is a first type of trajectory point based on the second distance and the third distance corresponding to the target pair of trajectory points, can be specifically used to: if the third distance is less than the second distance, then the target pair of trajectory points is a first type of trajectory point; if the third distance is greater than or equal to the second distance, then the target pair of trajectory points is not a first type of trajectory point.

[0231] Furthermore, the aforementioned determining module 63 is also used to determine a judgment region with a first key point contained in the target model region as the center point; determine the number of path points contained in the registration dataset within the judgment region; and determine whether registration for the target model region is completed based on the number.

[0232] It should be noted that the registration progress detection device for the lungs and trachea provided in the above embodiments can realize the technical solutions described in the method embodiments of the present application. The specific implementation principles of each module or unit can be found in the corresponding content of the method embodiments for registration progress detection of the lungs and trachea provided in the present application, and will not be repeated here.

[0233] Figure 8 A schematic diagram of the structure of an electronic device provided according to an embodiment of this application is shown. Figure 8 As shown, the electronic device includes a memory 71 and a processor 72. The memory 71 stores a computer program; the processor, coupled to the memory, executes the computer program stored in the memory to implement the steps or functions of the lung and trachea registration progress detection method embodiments provided in this application.

[0234] The aforementioned memory 71 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0235] The aforementioned electronic devices may refer to the above-mentioned Figure 6 The processing device shown in the figure.

[0236] Furthermore, such as Figure 8 As shown, the electronic device may also include other components such as a communication component 73, a display 74, a power supply component 75, and an audio component 76. Figure 8 The diagram only shows some components and does not imply that the electronic device includes only these components. Figure 8 The components shown.

[0237] Accordingly, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when executed by a computer, can implement the steps or functions in the registration progress detection method for lungs and trachea provided in the embodiments of this application.

[0238] The methods in this application can be implemented, in whole or in part, by software, hardware, firmware, or any combination thereof. When implemented in software, they can be implemented, in whole or in part, as a computer program product. Figure 9 A block diagram of a computer program product provided in this application is schematically shown. The computer program product includes a computer program / instructions 81, which, when the computer program / instructions 81 are executed by, for example... Figure 8 When the processor 72 shown is executed, it can perform all or part of the steps or functions in the registration progress detection method for the lungs and trachea provided in the various embodiments of this application. The computer can be a general-purpose computer, a special-purpose computer, a computer network, a network device, a user equipment, a core network device, an OAM, or other programmable device.

[0239] The computer program or instructions may be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions may be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium may be any available medium that a computer can access, or a data storage device such as a server or data center that integrates one or more available media. The available medium may be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; or an optical medium, such as a digital video optical disc; or a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both volatile and non-volatile types of storage media.

[0240] The device embodiments described above are merely illustrative. 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 modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0241] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0242] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for detecting the registration progress of the trachea in the lungs, characterized in that, include: Obtain a three-dimensional model of the tracheal tree reconstructed from medical imaging images of the lungs and trachea, and several first key points in the three-dimensional model of the tracheal tree; The tracheal tree 3D model is divided based on multiple first key points to obtain multiple model regions, wherein each model region contains at least one first key point; Acquire the first position information of the current position of the positioning sensor within the trachea of ​​the lung; Based on the first location information, the second location information of the positioning sensor in the tracheal tree 3D model and the target model area where it is located are determined; Based on the second location information, calculate the first distance between the positioning sensor and the at least one first key point contained in the target model region; Based on the first distance, determine the registration progress for the target model region.

2. The method according to claim 1, characterized in that, The tracheal tree 3D model includes multiple tracheal models, and each model region includes at least one tracheal model, wherein... The plurality of tracheal models include: a main trachea model, a right lung bronchus model connected to the main trachea model, and a left lung bronchus model, wherein the right lung bronchus model includes: a right main bronchus model, a right upper lobe bronchus model, and a right lower lobe bronchus model; the left lung bronchus model includes: a left main bronchus model, a left upper lobe bronchus model, and a left lower lobe bronchus model. The multiple first key points include: the main trachea key point located on the main trachea model, the right upper lobe key point located on the right upper lobe bronchus model, the right lower lobe key point located on the right lower lobe bronchus model, the left upper lobe key point located on the left upper lobe bronchus model, and the left lower lobe key point located on the left lower lobe bronchus model.

3. The method according to claim 2, characterized in that, The tracheal tree 3D model is divided based on multiple first key points to obtain multiple model regions, including: The reference points of the tracheal tree 3D model are obtained; the reference points are determined based on the intersection of the main trachea model, the right main bronchus model, and the left main bronchus model. Based on the key points of the main trachea and the reference points, determine the reference plane of the tracheal tree three-dimensional model; Based on the reference plane and multiple first key points, the tracheal tree 3D model is divided into multiple model regions.

4. The method according to claim 3, characterized in that, Based on the key points of the main trachea and the reference points, the reference plane is determined, including: Based on the key points of the main trachea and the reference points, a vector is determined to reflect the direction of the main trachea in the main trachea model. A plane that passes through the reference point and is perpendicular to the vector is defined as the reference plane.

5. The method according to claim 3, characterized in that, Based on the reference plane and multiple first key points, the tracheal tree 3D model is divided into multiple model regions, including: The model region located above the reference plane in the tracheal tree 3D model is defined as the main tracheal model region; Based on the reference point and the key point of the main airway, a dividing line is determined; Based on the dividing line, the model region located below the reference plane in the 3D model of the tracheal tree is divided into the right lung bronchus model region and the left lung bronchus model region. Based on the right upper lobe key points and the right lower lobe key points contained in the right lung bronchus model region, the right lung bronchus model region is divided into the right upper lobe model region and the right lower lobe model region. Based on the fact that the left bronchus model region includes the key points of the left upper lobe and the key points of the left lower lobe, the left bronchus model region is divided into the left upper lobe model region and the left lower lobe model region.

6. The method according to claim 5, characterized in that, Based on the key points of the right upper lobe and the right lower lobe contained within the right bronchus model region, the right bronchus model region is divided into a right upper lobe model region and a right lower lobe model region, including: A first horizontal line is determined based on the key point of the upper right leaf and the key point of the lower right leaf; wherein the first horizontal line is located between the key point of the upper right leaf and the key point of the lower right leaf and is parallel to the reference plane; The model region located above the first horizontal line in the right lung bronchus model region is defined as the right upper lobe model region. The model region located below the first horizontal line in the right lung bronchus model region is defined as the right lower lobe model region.

7. The method according to claim 6, characterized in that, Based on the key points of the upper right leaf and the lower right leaf, a first horizontal line is determined, including: The first horizontal line is defined as the horizontal line that passes through the center point of the first line connecting the upper right leaf key point and the lower right leaf key point and is parallel to the reference plane; or A second key point is determined in the right bronchus model region, wherein the ordinate of the second key point is the same as the ordinate of one of the key points of the right upper lobe and the right lower lobe, and the abscissa of the second key point is the same as the other key point of the right upper lobe and the right lower lobe. The first horizontal line is determined by the center point of the second line connecting the second key point and the other key point of the right upper lobe and the right lower lobe, and is perpendicular to the second line.

8. The method according to claim 5, characterized in that, Based on the key points of the left upper lobe and the left lower lobe included in the left bronchial model region, the left bronchial model region is divided into a left upper lobe model region and a left lower lobe model region, including: A second horizontal line is determined based on the key point of the upper left leaf and the key point of the lower left leaf; wherein the second horizontal line is located between the key point of the upper left leaf and the key point of the lower left leaf and is parallel to the reference plane; The model region located above the second horizontal line in the left lung bronchus model region is defined as the left upper lobe model region; The model region located below the second horizontal line in the left bronchus model region is defined as the left lower lobe model region.

9. The method according to claim 8, characterized in that, Based on the key points of the upper left leaf and the lower left leaf, a second horizontal line is determined, including: The horizontal line that passes through the center point of the third line connecting the upper left leaf key point and the lower left leaf key point, and is parallel to the reference plane, is defined as the second horizontal line; or A third key point is determined in the left bronchus model region, wherein the ordinate of the third key point is the same as the ordinate of one of the key points of the left upper lobe and the left lower lobe, and the abscissa of the third key point is the same as the other key point of the left upper lobe and the left lower lobe. The horizontal line that passes through the center point of the fourth line connecting the third key point and the other key point of the left upper lobe and the left lower lobe, and is perpendicular to the fourth line, is determined as the second horizontal line.

10. The method according to any one of claims 3 to 9, characterized in that, Each of the model regions contains a first keypoint; Furthermore, the method further includes: Obtain the planned path obtained by performing path planning for the target model region; wherein, the planned path is the shortest path between the reference point and a first key point contained in the target model region, planned based on the centerline information of the tracheal tree 3D model; Determine the shortest movement path for the positioning sensor in the tracheal tree 3D model from the reference point to its current position in the target model region; The movement path is compared with the planned path to determine whether the positioning sensor moves according to the planned path; When moving along the planned path, the step of calculating the first distance between the positioning sensor and a first key point contained in the target model area based on the second location information is triggered, and all path points on the moving path are added to the registration dataset.

11. The method according to claim 10, characterized in that, Determining the shortest movement path for the positioning sensor in the tracheal tree 3D model from the reference point to its current position in the target model region includes: Acquire the first trajectory data of the positioning sensor moving within the trachea of ​​the lung; Based on the first trajectory data, determine the second trajectory data of the positioning sensor moving from the reference point to its current position in the target model area within the tracheal tree 3D model; Determine the first type of trajectory points and the second type of trajectory points in the second trajectory data; wherein, the first type of trajectory points are trajectory points that reflect the positioning sensor performing a back-away action, and the second type of trajectory points are trajectory points that correspond to the first type of trajectory points, satisfy the deletion rules, and reflect the positioning sensor performing a forward action; Delete the first type of trajectory points and the second type of trajectory points from the second trajectory data; The movement path is determined based on the deleted second trajectory data; The deletion rules include: the timestamp is earlier than the timestamp of the first type of trajectory point; the distance to the reference point is greater than or equal to the distance between the trajectory point with the latest timestamp in the first type of trajectory point and the reference point, and less than or equal to the distance between the trajectory point with the earliest timestamp in the first type of trajectory point and the reference point.

12. The method according to claim 11, characterized in that, Determining the first type of trajectory points in the second trajectory data includes: Based on the timestamps of multiple trajectory points contained in the second trajectory data, determine multiple pairs of trajectory points with adjacent timestamps; Calculate the second distance and third distance of each pair of trajectory points relative to the reference point, including the first trajectory point and the second trajectory point; wherein the timestamp of the second trajectory point is later than the timestamp of the first trajectory point. Based on the second distance and the third distance, determine whether each pair of trajectory points is a first type of trajectory point.

13. The method according to claim 12, characterized in that, The target pair of trajectory points is one of multiple pairs of trajectory points; Based on the second distance and the third distance corresponding to the target pair trajectory point, determine whether the target pair trajectory point is a first type of trajectory point, including: If the third distance is less than the second distance, then the target pair trajectory point is a first type of trajectory point; If the third distance is greater than or equal to the second distance, then the target pair trajectory point is not a first type trajectory point.

14. The method according to claim 10, characterized in that, Also includes: The determination region is determined by taking a first key point contained in the target model region as the center point; Determine the number of path points contained in the registration dataset within the decision region; Based on the quantity, determine whether registration for the target model region is complete.

15. A registration progress detection system for the trachea of ​​the lungs, characterized in that, include: A magnetic field generator is used to generate a positioning magnetic field; the trachea of ​​the lungs is placed in the positioning magnetic field; A positioning sensor that, when moving within the trachea of ​​the lungs, can generate a positioning signal by sensing the positioning magnetic field and send the positioning signal to a processing device, so that the processing device can determine the position information of the positioning sensor within the trachea of ​​the lungs based on the positioning signal; A processing device for performing the steps in the registration progress detection method for the lung trachea as described in any one of claims 1 to 14.

16. An electronic device, characterized in that, include: Memory and processor, among which, The memory is used to store computer programs; The processor, coupled to the memory, is configured to execute the computer program stored in the memory to implement the steps in the registration progress detection method for the lung trachea according to any one of claims 1 to 14.

Images