CN117745772A - Pulmonary tracheal registration method, pulmonary tracheal registration system, computing device and computer storage medium - Google Patents

Abstract

The embodiment of the application provides a registration method, a registration system, a calculation device and a computer storage medium for lung trachea. The registration method of the lung trachea comprises the following steps: acquiring central line information of a three-dimensional model of a lung tracheal tree, wherein the three-dimensional model of the lung tracheal tree is reconstructed based on medical images of lung tracheal; a plurality of virtual Long Tudian based on the centerline information; determining a tracheal wall protuberance point corresponding to each virtual protuberance point on the tracheal wall of the three-dimensional model of the pulmonary tracheal tree, and generating a first key point set; acquiring a first moving path point set of a positioning sensor in a lung trachea; based on the first key point set and the first moving path point set, the technical scheme for registering the three-dimensional model of the pulmonary tracheal tree with the pulmonary trachea realizes the technical effects of reducing the registering difficulty and improving the registering efficiency.

Description

Pulmonary tracheal registration method, pulmonary tracheal registration system, computing device and computer storage medium

Technical Field

The embodiment of the invention relates to the technical field of medical instruments, in particular to a pulmonary tracheal registration method, a pulmonary tracheal registration system, computing equipment and a computer storage medium.

Background

With the development of computer technology and medical imaging technology, the surgical navigation technology has the advantages of accuracy, flexibility, minimally invasive and the like, and is widely applied to disease diagnosis and treatment. For example, electromagnetic navigation bronchoscopy techniques (Electromagnetic Navigation Bronchoscope, ENB) are commonly used to examine peripheral diseases of the patient's lungs. In the process of diagnosing and treating the lung of a patient by using ENB (advanced open end system), one indispensable step is registration, and the purpose of the registration is to match the actual physical space of the lung and the trachea tree three-dimensional model reconstructed for the lung of the patient before operation, so as to realize the accurate positioning of the relative positions of surgical instruments and the like in the trachea tree three-dimensional model when the patient enters into real-time surgical navigation subsequently, thereby providing precondition guarantee for surgery.

The inventor finds that, in the process of implementing the inventive concept, when the pulmonary tracheal registration is performed in the related art, the marking points are usually manually selected in the three-dimensional model of the pulmonary tracheal tree, and the registration mode needs professional knowledge and a great deal of experience, which takes a long time.

Disclosure of Invention

The embodiment of the invention provides a pulmonary trachea registration method, a pulmonary trachea registration device, a pulmonary trachea registration system, computing equipment and a computer storage medium.

In a first aspect, an embodiment of the present invention provides a method for registering a pulmonary trachea, including:

acquiring central line information of a three-dimensional model of a pulmonary tracheal tree, wherein the three-dimensional model of the pulmonary tracheal tree is reconstructed based on medical images of pulmonary tracheal;

determining a plurality of virtual Long Tudian in the pulmonary tracheal tree three-dimensional model based on the centerline information;

determining a tracheal wall Long Tudian corresponding to each of the virtual Long Tudian on the tracheal wall of the three-dimensional model of the pulmonary tracheal tree, and acquiring a first set of movement path points of a positioning sensor in the pulmonary tracheal;

and registering the pulmonary tracheal tree three-dimensional model with the pulmonary trachea based on the first set of key points and the first set of movement path points.

In a second aspect, an embodiment of the present invention provides a registration apparatus for pulmonary tracheal, including:

the central line acquisition module is used for acquiring central line information of a three-dimensional model of the pulmonary tracheal tree, wherein the three-dimensional model of the pulmonary tracheal tree is obtained based on medical image reconstruction of the pulmonary tracheal;

long Tudian determining means for determining a plurality of virtual Long Tudian in the three-dimensional model of the pulmonary tracheal tree based on the centerline information;

The key point acquisition module is used for determining a tracheal wall protuberance point corresponding to each virtual Long Tudian on the tracheal wall of the three-dimensional pulmonary tracheal tree model and generating a first key point set;

the path point acquisition module is used for acquiring a first moving path point set of the positioning sensor in the lung trachea;

and the registration module is used for registering the three-dimensional model of the pulmonary tracheal tree with the pulmonary trachea based on the first key point set and the first moving path point set.

In a third aspect, an embodiment of the present invention provides a registration system for pulmonary airways, including:

a magnetic field generator for generating a positioning magnetic field; the lung trachea is in the positioning magnetic field;

a positioning sensor capable of generating a positioning signal by sensing the positioning magnetic field when moving in the lung trachea, and transmitting the positioning signal to a processing device, so that the processing device determines a moving path point of the positioning sensor in the lung trachea according to the positioning signal;

the processing equipment is used for executing the lung trachea registration method provided by the embodiment of the invention.

The embodiment of the invention provides a pulmonary tracheal registration method, which comprises the following steps: acquiring central line information of a three-dimensional model of a lung tracheal tree, wherein the three-dimensional model of the lung tracheal tree is reconstructed based on medical images of lung tracheal; determining a plurality of virtual Long Tudian in the pulmonary tracheal tree three-dimensional model based on the centerline information; determining a tracheal wall protuberance point corresponding to each virtual Long Tudian on the tracheal wall of the three-dimensional pulmonary tracheal tree model, and generating a first key point set; acquiring a first moving path point set of a positioning sensor in a lung trachea; based on the first key point set and the first moving path point set, the technical scheme for registering the three-dimensional model of the pulmonary tracheal tree with the pulmonary trachea realizes the technical effects of reducing registration difficulty and providing registration efficiency.

These and other aspects of the invention will be more readily apparent from the following description of the embodiments.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.

FIGS. 1a to 1c are schematic structural views of a medical system for pulmonary diagnosis and treatment according to an embodiment of the present application;

FIG. 2 schematically illustrates a flow chart of a method for registration of pulmonary airways provided by an embodiment of the invention;

FIG. 3 schematically illustrates a front plan view of a three-dimensional model of a tracheal tree provided by one embodiment of the present invention;

FIG. 4 schematically illustrates a schematic of determining a tracheal wall protuberance point provided by an embodiment of the present invention;

FIG. 5 schematically illustrates a schematic diagram of screening a first intersection point according to an embodiment of the present invention;

FIG. 6 is a schematic illustration of a surgical registration interface provided by an embodiment of the present application;

fig. 7 schematically illustrates a schematic view of a pulmonary tracheal registration system provided in accordance with an embodiment of the present invention;

Fig. 8 schematically illustrates a schematic view of a registration device for pulmonary airways according to an embodiment of the present invention;

FIG. 9 schematically illustrates a schematic diagram of a computing device provided by one embodiment of the invention

Detailed Description

In order to enable those skilled in the art to better understand the present invention, the following description will make clear and complete descriptions of the technical solutions according to the embodiments of the present invention with reference to the accompanying drawings.

In some of the flows described in the specification and claims of the present invention and in the foregoing figures, a plurality of operations occurring in a particular order are included, but it should be understood that the operations may be performed out of order or performed in parallel, with the order of operations such as 101, 102, etc., being merely used to distinguish between the various operations, the order of the operations themselves not representing any order of execution. In addition, the flows may include more or fewer operations, and the operations may be performed sequentially or in parallel. It should be noted that, the descriptions of "first" and "second" herein are used to distinguish different messages, devices, modules, etc., and do not represent a sequence, and are not limited to the "first" and the "second" being different types.

It should be noted that, the user information (including but not limited to user equipment information, user personal information, etc.) and the data (including but not limited to data for analysis, stored data, presented data, etc.) related to the present invention are information and data authorized by the user or fully authorized by each party, and the collection, use and processing of the related data need to comply with the related laws and regulations and standards of the related country and region, and provide corresponding operation entries for the user to select authorization or rejection.

The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to fall within the scope of the invention.

In the following embodiments of the present application, reference will be made to a positioning sensor, for example, a positioning sensor provided on a positioning catheter, which uses the principle of electromagnetic navigation (Electromagetic Navigation), unlike the ordinary principle of electromagnetic navigation. The common electromagnetic navigation principle is mainly as follows: the direction of the medical device into the human body is influenced by attracting or repelling permanent magnets in the catheter in dependence of an external magnetic field. In this embodiment of the application, the theory of operation of positioning sensor mainly is: an electrical current is output to an external control system in response to the magnetic field of the space in which it is located for the control system to locate the position of the corresponding catheter. In detail, the positioning sensor is (signal) connected to the control system by a wired or wireless means. The control system includes a magnetic field generator for generating a magnetic field in a range of positioning spaces. The positioning sensor itself is non-magnetic and the coils in the positioning sensor are used to sense the magnetic field generated by the magnetic field generator. Wherein the magnetic field generator generates a varying magnetic field in a range of positioning space and ensures that the magnetic field characteristics of each point in the positioning space are unique. The coils in the position sensor generate currents in the transformed magnetic fields, which are transmitted to the control system after acquisition of the generated signals (i.e. the position signals described in the context), which are analyzed by the control system to determine the exact position and orientation of the respective catheter.

For ease of understanding, prior to introducing the technical solutions provided by the embodiments of the present application, a medical system for pulmonary surgery navigation will be described. In particular, the method comprises the steps of,

fig. 1a and fig. 1b are schematic perspective views of a medical system according to an embodiment of the present application. As shown with reference to fig. 1a and 1b, the medical system comprises: a console 10, a magnetic navigation device 20, a medical imaging device 30, and a positioning medical tool 40. Wherein,

the magnetic navigation device 20 is used for navigating the positioning medical tool 40 to a corresponding target point (or target area) on the medical path according to the medical path.

The medical path may be planned by a corresponding processing module having a path planning function. Specifically, the processing module may be configured to reconstruct a corresponding three-dimensional model according to medical image data (such as CT, MRI, etc.) of the whole body or a certain body part of the patient, and perform path planning based on the planned three-dimensional model to obtain a corresponding medical path. For example, a three-dimensional model of a tracheal tree including a main trachea and a bronchus can be reconstructed according to medical image data of the lung of a patient before operation, and a navigation path (or a planning path) from the main carina to a target point through the natural trachea of the lung is planned according to the three-dimensional model of the tracheal tree, wherein the navigation path is a medical path. The main carina refers to the bifurcation of the main trachea, which is divided into a left bronchus and a right bronchus.

In practice, the processing module may be provided on the magnetic navigation device 20, or may be provided on a main control trolley 50 for a doctor as shown in fig. 1 c. The above-mentioned processing module may be application software having the functions of reconstructing a three-dimensional model and path planning, registration, etc., which may be installed in a control device such as the master cart 50 or the magnetic navigation device 20, such as the control device 511 (e.g. a computer device) shown in fig. 1 c. However, to reduce the risk of radiation exposure and cross-infection of the doctor, the control device 511 is preferably provided on the main trolley 50 separately from the electromagnetic navigation apparatus 20 so that the doctor can leave the operating room to operate the control device. The master cart 50 can communicate with the magnetic navigation device 20, which can be considered an extension of the display and steering functions of the magnetic navigation device 20. For example: the reconstructed three-dimensional model (such as a three-dimensional model of a tracheal tree), a medical path, an operation progress (such as a registration progress and a real-time navigation progress), an endoscopic image and the like can be displayed through a display screen, in particular a human-computer interaction interface, contained in the control device 511 on the main control trolley 50; in addition, the doctor can trigger the registration operation to start execution by clicking the registration control displayed on the man-machine interaction interface; alternatively, the medical imaging device 30 is controlled to perform scanning through a human-computer interaction interface, and so on.

The medical imaging device 30 is configured to acquire a medical image of a patient. For example, a medical image of a patient's lungs is acquired.

In particular, the medical imaging device 30 may be, but is not limited to, a CT machine, an X-ray machine, etc., and may be broadly referred to as an imaging device for imaging a local or whole body of a patient, including but not limited to, a two-dimensional image, where the conditions allow.

In an example, the medical imaging apparatus 30 includes a C-arm 311 movable relative to the console 10, where two ends of the C-arm 311 are respectively configured to be provided with a radiation module (for emitting corresponding medical radiation, such as X-rays) and an imaging module (not shown in the figure, and may be specifically provided at an end of the C-arm 311 above the console), and the C-opening faces the console. The movement of the C-arm 311 relative to the console means that the opening of the C-arm can move along the length or width direction of the console 10, or that the opening of the C-arm rotates around the console 10, so that the shooting or scanning of the medical imaging device 30 covers the whole console and all directions thereof, and a medical image (i.e. a medical image) with a proper angle can be shot as required, thereby improving the use experience of the medical system.

It should be noted that the medical imaging apparatus 30 may be connected to the control device on the main control carriage 50 or the magnetic navigation apparatus 20, so that a processing module (application software) on the control device may receive and process the medical image obtained by the medical imaging apparatus 30.

The console 10 may be, but is not limited to, an operating table in an operating room, a patient bed for patient care, or the like. The console 10 is capable of transmitting radiation from the medical imaging device 30, and has the effect of not affecting the imaging effect of the medical imaging device 30. In addition, the medical imaging device 30 and the magnetic navigation device 20 may be disposed beside the console 10.

The medical positioning tool 40 refers to a medical tool having a positioning function, such as biopsy, treatment, etc., specifically: may be a guide wire or catheter for positioning, an ablation catheter, etc.

The positioning medical tool 40 is coupled to the magnetic navigation device 20 or to a portion of the magnetic navigation device 20. For example, in case the shape of the magnetic navigation device 20 is configured as shown in fig. 1b, the magnetic navigation device 20 comprises a delivery mechanism 201, which delivery mechanism 201 is connectable to the positioning medical tool 40, the delivery mechanism 201 driving the positioning medical tool 40 into the patient, such as the lung airways (or airways) of the patient, according to the medical path and reaching the respective target point (or target region) under control of the magnetic navigation device 20. The above-mentioned fig. 1b shows an example of delivering the positioning medical tool 40 into the patient by the delivery mechanism, in other embodiments, the positioning medical tool 40 may be delivered into the patient by a corresponding pushing device (a pulling mechanism 2012 described below) through the operation of a physician, and the physician manually controls the pushing device by means of a display device (a display device 511 shown in fig. 1 c) corresponding to the magnetic navigation device, so that the pushing device drives the positioning medical tool 40 to move according to the medical path, thereby achieving the corresponding target point (or target area).

What needs to be explained here is: the transport mechanism 201 described above may include a robotic arm 2011 and a pulling mechanism 2012. The pulling mechanism 2012 is connected to one end of the positioning medical tool 40. The pulling mechanism 2012 can be pulled by pushing with a hand or a mechanical arm 2011, so as to drive the positioning medical tool 40 to enter and exit the trachea of the human body. In addition, the electromagnetic navigation device 20 may have a shape structure other than the shape structure shown in fig. 1b, for example, the shape structure shown in fig. 1c, and the shape structure of the electromagnetic navigation device 20 is not particularly limited in the embodiment of the present application.

Further, the magnetic navigation device 20 may further include a magnetic field generator 202 disposed within the console 10, and a positioning sensor 203 disposed within the positioning medical tool 40. Wherein the magnetic field generator 202 is configured to generate a positioning magnetic field for positioning the positioning sensor 203.

In particular, the magnetic field generator 202 is disposed in the console 10 and is capable of emitting a positioning magnetic field in a direction of the bed surface, in which a corresponding body part (e.g., lung) of the patient is located when the patient is lying on the console 10, and the relative position of the corresponding body part (e.g., lung) of the patient in the positioning magnetic field is fixed because the patient is generally in a general anesthesia state on the console 10. Since the positioning magnetic field has its own coordinate system, which is called a magnetic field coordinate system, whereby the relative position of the corresponding body part (e.g. lung) of the patient is fixed in the magnetic field coordinate system, and the position and direction of the positioning medical tool 40 in the patient can be represented by the position coordinates of the head of the positioning medical tool 40 in the magnetic field coordinate system, in particular, the positioning magnetic field can position the positioning sensor 203 in the positioning medical tool 40, and since the positioning sensor 203 is disposed at the head end position of the medical tool 40, the position and direction of the positioning medical tool 40 in the patient can be obtained by positioning the positioning sensor 203 to obtain the position coordinates of the positioning sensor in the magnetic field coordinate system.

The following describes in detail a registration method for pulmonary airways provided in an embodiment of the present application.

Fig. 2 schematically illustrates a flowchart of a method for registration of pulmonary airways according to an embodiment of the present invention, including:

201, obtaining central line information of a three-dimensional model of a pulmonary tracheal tree, wherein the three-dimensional model of the pulmonary tracheal tree is obtained based on medical image reconstruction of a pulmonary tracheal;

202, determining a plurality of virtual Long Tudian in a three-dimensional model of a pulmonary tracheal tree based on centerline information;

203, determining a tracheal wall protuberance point corresponding to each virtual protuberance point on the tracheal wall of the three-dimensional model of the pulmonary tracheal tree, and generating a first key point set;

204, acquiring a first moving path point set of the positioning sensor in a lung trachea;

205, registering the pulmonary tracheal tree three-dimensional model with the pulmonary trachea based on the first set of key points and the first set of path of movement points.

According to an embodiment of the present invention, the pulmonary trachea is an actual tracheal tree of the lung, and the corresponding three-dimensional model of the tracheal tree can be obtained by performing correlation processing on a plurality of medical image images (such as two-dimensional tomographic images (CT images) or magnetic resonance images (MRI images) acquired for the lung of the patient from different angles based on a preoperative series of three-dimensional reconstruction techniques (such as three-dimensional reconstruction software).

For example, a plurality of two-dimensional CT images of a patient's lungs may be acquired, such as by CT tomography of the patient's lungs; then, the two-dimensional CT images are led into a processing module (which may be application software having the functions of reconstructing a three-dimensional model, path planning, registration, etc.) in other embodiments of the text application, and image recognition, segmentation, etc. of tissues such as lung and trachea are performed, so as to obtain three-dimensional modeling parameters of lung and trachea, and then a three-dimensional model of a tracheal tree of the lung and trachea of the patient is constructed based on the three-dimensional modeling parameters.

The method for registering a pulmonary trachea provided by the above example, namely the embodiment of the present invention, may further include the following relevant implementation steps for reconstructing a corresponding three-dimensional model of a tracheal tree for the pulmonary trachea:

acquiring a plurality of medical image images acquired for a lung trachea;

identifying a plurality of medical image images to obtain three-dimensional modeling parameters of a lung trachea;

and constructing a three-dimensional model of the tracheal tree based on the three-dimensional modeling parameters.

After the three-dimensional model of the tracheal tree is obtained, the three-dimensional model of the tracheal tree can be skeletonized to extract the central line information of the three-dimensional model of the tracheal tree, and data support is provided for the subsequent hierarchical division of the three-dimensional model of the tracheal tree, the determination of the airway path and the like.

In particular embodiments, centerline information of the three-dimensional model of the tracheal tree may be extracted using, but not limited to, a corresponding refinement algorithm, such as a topology refinement algorithm. The refinement algorithm is mainly a method for extracting the central line of the target object by repeatedly eroding the surface pixels of the target object until only the skeleton is left. For a specific implementation of extracting centerline information of a three-dimensional model of a tracheal tree using a refinement algorithm, reference may be made to existing correlation schemes.

In the front plan view of the three-dimensional model of the tracheal tree 300 shown in fig. 3, a relatively thin solid line in the three-dimensional model of the tracheal tree 100 is shown, i.e., represents the centerline information of the three-dimensional model of the tracheal tree.

According to an embodiment of the invention, the first set of keypoints may include a plurality of tracheal walls Long Tudian, and the tracheal wall Long Tudian may refer to a real carina located on the tracheal wall.

The first set of movement path points may be obtained from a magnetic navigation device 20 as shown in fig. 1a or 1 b. Specifically, the magnetic navigation device 20 shown in fig. 1a or 1b may determine a first moving path point set (i.e. an actual moving path point set) generated by the movement of the positioning sensor in the lung trachea according to the acquired positioning signal sent in real time when the positioning sensor moves (walks) in the lung trachea, and send the first moving path point set to the execution body of the embodiment of the present application; the positioning signal is generated by the positioning sensor according to the current generated by the acquired self-internal coil in the transformed magnetic field. The magnetic field is changed by the magnetic navigation device 20 controlling the magnetic field generator 202 arranged in the operation table 10, and because the patient is in the operation table 10 when lying on the back, the patient's lung is in the changing magnetic field, the sensor can sense the changing magnetic field and generate corresponding current when moving in the trachea of the patient's lung.

The first set of travel path points includes travel path points that characterize the respective positioning positions of the positioning sensor within the lung.

When executing the step 102, the coordinates of each moving path point included in the first moving path point set may be spatially transformed according to the current spatial coordinate transformation relationship (which is the spatial coordinate transformation relationship between the actual physical space (magnetic space) of the lung trachea and the image space of the three-dimensional model of the tracheal tree), so as to map (or divide) each moving path point included in the first moving path point set into a corresponding level of tracheal model in the three-dimensional model of the tracheal tree, thereby obtaining a second moving path point set of the positioning sensor in each level of tracheal model; then, a path search is performed for a second set of movement path points in each stage of the tracheal model, so as to determine a movement path of the positioning sensor in the tracheal tree three-dimensional model according to the path search result. The purpose of the path search is to find the shortest moving path of the positioning sensor moving in each level of tracheal models, and combine the shortest moving paths of the positioning sensor in each level of tracheal models to obtain the moving path of the positioning sensor finally in the tracheal tree three-dimensional model. In performing the path search, a point corresponding to a main carina of a lung trachea in a three-dimensional model of a tracheal tree may be used as a search starting point.

Based on the determined first key point set of the moving path and the first moving path point set, a corresponding registration algorithm can be utilized to find out the space coordinate transformation relation (or transformation matrix) between the first key point set from the actual physical space coordinate system (magnetic space coordinate system) of the lung trachea and the first moving path point set from the image space coordinate, so that the two can be spatially matched, and the original space coordinate transformation relation is updated into the newly found space coordinate transformation relation. And the spatial matching of the three-dimensional model of the tracheal tree and the actual pulmonary trachea can be accurately realized according to the newly found spatial coordinate transformation relation.

The registration algorithm described above may be, but is not limited to being: ICP (Iterative Closest Point), iterative closest point algorithm), NDT (Normal Distribution Transform, normal distributed point cloud algorithm), deep learning based point cloud registration, and other fine registration algorithms. The present embodiment is preferably an ICP algorithm, and specific implementation of finding a spatial coordinate transformation relationship between the first set of key points and the second set of key points by using the ICP algorithm can be seen in the related content.

According to the embodiment of the invention, the point cloud data acquired by using the positioning sensor is meaningless in consideration that the positioning sensor is always in a non-moving condition in the lung trachea; and, at the time of initial registration, the amount of the point cloud data collected by the positioning sensor is often smaller, in this case, if the point cloud data collected by the positioning sensor is processed for registration calculation or the like, the registration accuracy is often lower, so in this embodiment, when it is determined that the amount of the point cloud collected by the positioning sensor is greater than or equal to the set number threshold value, and when it is determined that the movement range of the positioning sensor is greater than the set range threshold value, the processing of the point cloud data collected by the positioning sensor is started to determine the movement path of the current positioning sensor in the three-dimensional model of the tracheal tree, the first key point set of the movement path, and the like.

According to an embodiment of the present invention, determining a plurality of virtual carina points in a three-dimensional model of a pulmonary tracheal tree based on centerline information may be specifically implemented as:

determining an airway path of the three-dimensional model of the pulmonary tracheal tree according to the central line information;

along the airway path, determining a plurality of virtual Long Tudian located on the airway path;

on the tracheal wall of the three-dimensional model of the pulmonary tracheal tree, tracheal wall carina points corresponding to each virtual carina point are determined.

According to the embodiment of the invention, after the central line information of the three-dimensional model of the air outlet pipe tree is extracted, the path formed by the central line information can be the airway path of the three-dimensional model of the air outlet pipe tree.

According to the embodiment of the invention, since in reality, the lung trachea of a person is tree-shaped, the lung trachea is generally divided into different levels from top to bottom according to bifurcation levels, for example: the main bronchi (level 1, the tube with one end connected to the larynx and the other end connected to the bronchi, the air passage) located in the trunk enter the lung through the hilum, and branch into two main bronchi (also called She Zhuzhi bronchi, level 2): a right main bronchus and a left main bronchus; further, the two main bronchi may be further bifurcated, respectively, such as the right main bronchus further bifurcated into the upper right bronchus, the lower right bronchus, and so on. Based on this, in the above three-dimensional model of the tracheal tree, the present embodiment may further determine the centerline bifurcation point in the centerline information by analyzing the centerline information of the extracted three-dimensional model of the tracheal tree, so that the centerline bifurcation point may be regarded as the virtual Long Tudian on the airway path.

According to an embodiment of the present invention, on the tracheal wall of the three-dimensional model of the pulmonary tracheal tree, determining the tracheal wall carina point corresponding to each virtual carina point may be specifically implemented as:

determining a plurality of first intersection points corresponding to the virtual Long Tudian from the tracheal wall along a plurality of preset directions by taking the virtual protuberance point as a starting point;

from the plurality of first intersection points, the first intersection point closest to the virtual Long Tudian is determined as the tracheal wall protuberance point corresponding to the virtual Long Tudian.

According to the embodiment of the invention, for each virtual Long Tudian, rays can be sent out along a plurality of preset directions by taking the virtual protuberance point as a starting point, and the intersection point of the rays and the tracheal wall can be determined as a first intersection point.

Since virtual Long Tudian is a centerline bifurcation point, i.e., virtual Long Tudian connects two bronchi, an angle with the virtual carina point as the vertex and the centerline at the two bronchi as the edge can be determined, which can be denoted as angle α, according to an embodiment of the present invention.

After the angle alpha is determined, an angular bisector of the angle alpha can be used as a starting point, rays are respectively taken in the directions of central lines of two bronchi according to a preset angle, and the intersection point of the rays and the tracheal wall is determined to be a first intersection point.

Fig. 4 schematically illustrates a schematic of determining a tracheal wall protuberance point provided by an embodiment of the present invention.

As shown in fig. 4, 401 may represent a centerline, 402 may represent a virtual Long Tudian, 404 may represent a tracheal wall.

In fig. 4, a virtual Long Tudian 402 connects a first bronchus 4031 and a second bronchus 4032, and a center line 4011 at the first bronchus and a center line 4012 at the second bronchus meet at a virtual Long Tudian.

Thus, the virtual Long Tudian, center line 4011 and center line 4012 form an angle α with the virtual protuberance 402 as the vertex. Then, an angular bisector 404 of the angle α may be taken, and a plurality of rays 405 may be taken along a preset angle with the angular bisector 404 as a starting point, and an intersection point of each ray 405 and the tracheal wall may be determined as a first intersection point 406.

After determining the first intersection point 406, the length of each ray may be determined based on the positions of the first intersection point 40 and the virtual Long Tudian, and the first intersection point 406 corresponding to the ray with the shortest length may be determined as the carina point of the tracheal wall.

According to an embodiment of the present invention, the first plurality of intersection points are points located on the tracheal wall corresponding to the virtual Long Tudian, and these points may be candidate carina points of the tracheal wall.

According to an embodiment of the present invention, determining, from a plurality of first intersection points, that the first intersection point closest to the virtual Long Tudian is the tracheal wall protuberance point corresponding to the virtual Long Tudian may be specifically implemented as:

screening the first intersection points, and determining the tracheal wall protuberance point from the first intersection points remained after screening.

According to an embodiment of the present invention, there may be some obviously erroneous first intersection points among the plurality of first intersection points, which may be the first intersection points that are not the first intersection points of the tracheal wall Long Tudian although the distance from the virtual carina point is the shortest, and thus, the points where there are errors need to be screened.

According to one embodiment of the present invention, the screening of the plurality of first intersections may be specifically implemented as:

determining a first distance of the virtual Long Tudian from the tracheal entrance and a second distance of each first intersection point from the tracheal entrance;

and removing the first intersection point corresponding to the second distance smaller than the first distance.

According to another embodiment of the present invention, the screening of the plurality of first intersections may be specifically implemented as:

dividing a first region including the first intersection point and the virtual Long Tudian into a first sub-region and a second sub-region by connecting the first intersection point and the virtual Long Tudian;

Determining a first data amount of the first subarea and a second data amount of the second subarea respectively;

determining a difference between the first data amount and the second data amount;

and removing the first intersection point corresponding to the second data quantity with the difference value larger than the preset threshold value.

In one embodiment of the invention, the false first intersection point may be screened based on the virtual Long Tudian and the distance of the first intersection point from the tracheal entrance, respectively. In general, the virtual carina point should be closer to the tracheal entrance than the first intersection point, i.e. the virtual Long Tudian and tracheal entrance should be more distant than the first intersection point. Thus, a first distance between the virtual Long Tudian and the tracheal entrance, and a second distance between each first intersection point and the tracheal entrance, respectively, may be determined, and the first intersection point corresponding to the second distance smaller than the first distance may be removed.

In determining the first distance and the second distance, according to embodiments of the present invention, the first intersection point and the distance of the virtual Long Tudian from the tracheal entrance in the vertical direction may be determined.

In another embodiment of the invention, the first intersection of errors may also be screened based on the gap in data volume.

Fig. 5 schematically illustrates a schematic diagram of screening a first intersection point according to an embodiment of the present invention.

501 may represent a main gas pipe, in which main gas pipe 501 a virtual Long Tudian 502 and a first intersection 503 are determined.

504 may represent a first region comprising a first intersection 502 and a virtual Long Tudian 502, and further, the first region 502 may also comprise a tracheal segment in which the virtual Long Tudian 502 is located, which may comprise, for example, a main trachea and a bronchus.

By connecting 505 the virtual Long Tudian 502 and the first intersection 503, the connection 505 can be extended to the boundary of the first area 504, if desired, whereby the first area 504 can be divided into a first sub-area 5041 on one side of the connection 505 and a second sub-area 5042 on the other side of the connection 505.

After dividing the first region 504 into the first sub-region 5041 and the second sub-region 5042, a first amount of data contained in the first sub-region 5041 and a second amount of data contained in the second sub-region 5042 may be determined, respectively. Wherein the first data volume and the second data volume may comprise tracheal data in the first sub-region and the second sub-region.

In general, the first data amount and the second data amount should be the same or close, and thus, it can be judged whether the first intersection point should be removed by comparing the first data amount and the second data amount.

According to the embodiment of the invention, based on the first key point set and the first moving path point set, registering the three-dimensional model of the pulmonary tracheal tree with the pulmonary trachea can be specifically realized as follows:

determining a second set of key points corresponding to the first set of key points in the pulmonary trachea;

and registering the three-dimensional model of the pulmonary tracheal tree with the pulmonary trachea based on the second key point set and the first moving path point set.

According to an embodiment of the present invention, the first set of key points is the standard positions of the carina points of the tracheal wall determined in the three-dimensional model of the pulmonary tracheal tree, and before registration, the position of each of the parietal key points included in the first set of key points may be converted into the pulmonary tracheal, i.e. a second set of key points corresponding to the position of the tracheal wall Long Tudian included in the first set of key points needs to be found in the pulmonary tracheal, to form the second set of key points.

According to the embodiment of the invention, based on the second key point set and the first moving path point set, registering the three-dimensional model of the pulmonary tracheal tree with the pulmonary trachea can be specifically realized as follows:

acquiring point cloud data generated by movement of a positioning sensor in a lung trachea;

the following operations are performed iteratively:

Determining a plurality of third key points corresponding to each second key point in the second key point set in the point cloud data, and generating a third key point set;

performing registration calculation based on the third key point set and the first key point set to obtain a first registration matrix;

and determining whether a registration completion condition is met based on the third key point set, if so, generating a registration result based on the first registration matrix, and if not, re-determining the third key point set.

According to an embodiment of the invention, the point cloud data may include the location position at each point in time at which the location sensor is located as it walks around the lungs.

According to the embodiment of the invention, when the positioning sensor moves around the lung, the positioning sensor may not accurately reach the standard position of the tracheal wall protuberance point, so that one point cloud data closest to each second key point can be respectively found in the point cloud data, and the point cloud data is determined as a third key point to generate a third key point set.

According to the embodiment of the invention, in the registering process, the method can be iteratively circulated for a plurality of times, and in each circulation, the registering calculation is carried out according to the first key point set and the third key point set determined by the circulation to obtain a first registering matrix, if the first registering matrix does not meet the registering completion condition, the third key point set can be recalculated, then the next circulation is carried out, and the registering calculation is carried out by utilizing the redetermined third key point set and the first key point set until the obtained first registering matrix meets the registering completion condition, so that a registering result can be generated based on the first registering matrix obtained by the circulation.

According to an embodiment of the present invention, based on the third set of key points, determining whether the registration completion condition is satisfied may be specifically implemented as:

respectively determining whether a plurality of third key points in the third key point set are positioned in the tracheal cavity or not to obtain a first proportion, wherein the first proportion is used for representing the proportion of the third key points positioned in the tracheal cavity in the third key point set;

judging whether the first proportion is larger than a preset threshold value, if so, determining that the registration result is met, otherwise, determining that the registration result is not met.

According to the embodiment of the invention, whether the third key points in the third key point set are positioned in the tracheal cavity or not can be respectively determined, and the proportion of the third key points positioned in the tracheal cavity in the whole third key point set can be obtained.

According to an embodiment of the present invention, the preset threshold may be a preset ratio value, that is, the registration result is determined to be satisfied when the ratio of the key points located in the tracheal lumen in the entire third key point set is greater than the ratio value.

According to another embodiment of the present invention, the preset threshold may also be dynamically determined, for example, a plurality of scale values obtained in the previous n iteration cycles may be collected, the plurality of scale values may be averaged, and the average value may be set as the preset threshold.

According to another embodiment of the present invention, the preset threshold may further be a maximum value of a plurality of scale values obtained by collecting the previous n iteration cycles, and setting a scale value corresponding to the maximum value as the preset threshold.

According to an embodiment of the present invention, the redefining of the third set of key points may be implemented specifically as:

interpolation is carried out between the corresponding key points in the first moving path point set and the second key point set, and a fourth key point set is obtained;

and determining a plurality of third key points corresponding to each fourth key point in the fourth key point set respectively in the point cloud data, and generating a third key point set.

According to the implementation of the invention, the fourth key point set can be obtained by interpolating the corresponding key points in the first moving path point set and the second key point set

According to embodiments of the present invention, for the ith waypoint in the first moving waypoint set and the ith waypoint in the second waypoint set, linear interpolation or other interpolation methods may be used to calculate interpolation points therebetween.

The linear interpolation may be achieved by the following formula:

interpolation point = i-th path point in the first set of moving path points (1-t) +i-th key point in the second set of key points.

Here, the range of t is usually [0,1], where 0 represents the ith path point in the first set of moving path points, and 1 represents the ith key point in the second set of key points. The step size of t can be set as desired.

In this embodiment, since points corresponding to the main carina of the trachea of the lung in the three-dimensional model of the tracheal tree are used as reference points, the registration scheme provided in this embodiment is triggered to be executed only when the positioning sensor is detected to reach the reference points, for example: in the lung operation navigation, if the positioning sensor is determined to reach the datum point A in the three-dimensional model of the tracheal tree according to the current positioning position of the positioning sensor in the lung trachea during the movement of the lung trachea of the patient by a doctor, a prompt message such as "the positioning sensor is placed in the main carina position and the registration is started by clicking the [ confirm ] button" is displayed on an operation registration interface as shown in fig. 6, and the registration is automatically executed after responding to the "confirm" button in the prompt message clicked by the doctor. Wherein the surgical registration interface described above may be displayed by a display screen of a control device 511 as shown in fig. 1 c; during registration, the physician may continue to manipulate the positioning sensor to move in the patient's lung airways. Based on the above-mentioned example, the technical solution provided in this embodiment, when starting to process the point cloud data collected by using the positioning sensor to perform the registration, the positioning sensor reaches at least the end of the primary tracheal model (the primary tracheal model) in the tracheal three-dimensional model, which also makes the above first key point set include at least one movement path bifurcation point. In addition, based on the above example, when setting the above setting range threshold, the embodiment of the present application may be flexibly set according to practical situations, so long as it is ensured that when processing using the point cloud data acquired by the positioning sensor is started, the movement range of the positioning sensor has exceeded the area of the primary tracheal model (i.e., the primary tracheal model) of the three-dimensional model of the tracheal tree, that is, it is ensured that the positioning sensor is not currently in the primary tracheal model of the three-dimensional model of the tracheal tree.

In the processing process, the point cloud data acquired by using the positioning sensor is preprocessed first to delete some abnormal data, such as outlier data and invalid data generated by signal loss. For example, the coil in the positioning sensor is disturbed to sense the magnetic field, so that no current can be generated by itself, and at this time, the positioning sensor sends a default signal to the execution body of the embodiment, and the received default signal becomes invalid data or may be outlier data.

Fig. 7 schematically illustrates a schematic diagram of a pulmonary tracheal registration system according to an embodiment of the invention, where as shown in fig. 7, the pulmonary tracheal registration system 700 includes:

a magnetic field generator 701 for generating a positioning magnetic field; the lung trachea is in a positioning magnetic field;

a positioning sensor 702 which can generate a positioning signal by sensing a positioning magnetic field when moving in the lung trachea and send the positioning signal to the processing device, so that the processing device can determine the moving path point of the positioning sensor in the lung trachea according to the positioning signal;

processing device 703 is configured to perform steps in the pulmonary tracheal registration method provided in an embodiment of the present invention.

The above detailed description of the magnetic field generator and the positioning sensor may be referred to in other embodiments of the above text application, and will not be repeated here.

The processing device may be a control device having data processing functions, such as the control device 511 shown in fig. 1c (e.g. a computer device). The control device may be provided independently on the main control carriage 50 for doctor as shown in fig. 1c, or may be provided integrally with the magnetic navigation device 20 as shown in fig. 1a, i.e. may be provided on the magnetic navigation device 20, which is not limited in this embodiment.

It should be noted that, in addition to the above devices or apparatuses, other devices or apparatuses may be included in the registration system for pulmonary airways provided in the embodiment of the present application, and the related other devices or apparatuses may include other devices or apparatuses may participate in the medical system described in fig. 1a to 1 c.

Fig. 8 schematically illustrates a schematic diagram of a pulmonary tracheal registration device according to an embodiment of the invention, where, as shown in fig. 8, the pulmonary tracheal registration device 800 may include:

the central line acquisition module 801 is configured to acquire central line information of a three-dimensional model of a pulmonary tracheal tree, where the three-dimensional model of the pulmonary tracheal tree is reconstructed based on a medical image of a pulmonary tracheal;

Long Tudian determining module 802 for determining a plurality of virtual Long Tudian in a three-dimensional model of a pulmonary tracheal tree based on centerline information;

the key point acquisition module 803 is configured to determine, on a tracheal wall of the three-dimensional model of the pulmonary tracheal tree, a tracheal wall protuberance point corresponding to each virtual protuberance point, and generate a first key point set;

the path point acquisition module 804 is used for acquiring a first moving path point set of the positioning sensor in the lung trachea;

a registration module 805 is configured to register the pulmonary tracheal tree three-dimensional model with the pulmonary trachea based on the first set of key points and the first set of movement path points.

According to an embodiment of the invention, the carina point determination module 802 includes:

the path determination submodule is used for determining the airway path of the three-dimensional model of the pulmonary tracheal tree according to the central line information;

virtual Long Tudian determination submodule for determining a plurality of virtual Long Tudian located on an airway path along the airway path;

long Tudian a determination sub-module for determining, on the tracheal wall of the three-dimensional model of the pulmonary tracheal tree, tracheal wall carina points corresponding to each virtual carina point.

According to an embodiment of the invention, the carina point determination submodule includes:

An intersection point determining unit for determining a plurality of first intersection points corresponding to the virtual Long Tudian from the tracheal wall along a plurality of preset directions with the virtual protuberance point as a starting point;

long Tudian determining unit for determining, from the plurality of first intersection points, the first intersection point closest to the virtual Long Tudian as the tracheal wall carina point corresponding to the virtual Long Tudian.

According to an embodiment of the present invention, the carina point determination unit includes:

and the screening subunit is used for screening the first intersection points and determining the tracheal wall protuberance points from the first intersection points remained after screening.

According to an embodiment of the invention, the screening subunit is specifically configured to: determining a first distance of the virtual Long Tudian from the tracheal entrance and a second distance of each first intersection point from the tracheal entrance; and removing the first intersection point corresponding to the second distance smaller than the first distance.

According to an embodiment of the invention, the screening subunit is specifically configured to: dividing a first region including the first intersection point and the virtual Long Tudian into a first sub-region and a second sub-region by connecting the first intersection point and the virtual Long Tudian; determining a first data amount of the first subarea and a second data amount of the second subarea respectively; determining a difference between the first data amount and the second data amount; and removing the first intersection point corresponding to the second data quantity with the difference value larger than the preset threshold value.

According to an embodiment of the present invention, the registration module 805 includes:

the key point conversion submodule is used for determining a second key point set corresponding to the first key point set in the lung trachea;

and the registration sub-module is used for registering the three-dimensional model of the pulmonary tracheal tree with the pulmonary trachea based on the second key point set and the first moving path point set.

According to an embodiment of the invention, the registration submodule comprises:

the point cloud data acquisition unit is used for acquiring point cloud data generated by the movement of the positioning sensor in the lung trachea;

a registration unit for iteratively performing the following operations:

determining a plurality of third key points corresponding to each second key point in the second key point set in the point cloud data, and generating a third key point set;

performing registration calculation based on the third key point set and the first key point set to obtain a first registration matrix;

and determining whether a registration completion condition is met based on the third key point set, if so, generating a registration result based on the first registration matrix, and if not, re-determining the third key point set.

According to an embodiment of the invention, the registration unit is specifically for: respectively determining whether a plurality of third key points in the third key point set are positioned in the tracheal cavity or not to obtain a first proportion, wherein the first proportion is used for representing the proportion of the third key points positioned in the tracheal cavity in the third key point set; judging whether the first proportion is larger than a preset threshold value, if so, determining that the registration result is met, otherwise, determining that the registration result is not met.

According to an embodiment of the invention, the registration unit is specifically for: interpolation is carried out between the corresponding key points in the first moving path point set and the second key point set, and a fourth key point set is obtained; and determining a plurality of third key points corresponding to each fourth key point in the fourth key point set respectively in the point cloud data, and generating a third key point set.

The pulmonary tracheal registration device shown in fig. 8 may perform the pulmonary tracheal registration method in the embodiment shown in fig. 2, and its implementation principle and technical effects are not repeated. The specific manner in which the various modules, units, perform the operations of the above-described embodiment of the pulmonary tracheal registration device have been described in detail in connection with embodiments of the method, and will not be described in detail herein.

In one possible design, the pulmonary tracheal registration device provided by embodiments of the present invention may be implemented as a computing device, as shown in fig. 9, which may include a storage component 901 and a processing component 902;

the storage component 901 stores one or more computer instructions, where the one or more computer instructions are called by the processing component 902 to execute, so as to implement the pulmonary tracheal registration method provided by the embodiment of the present invention.

Of course, the computing device may necessarily include other components, such as input/output interfaces, communication components, and the like. The input/output interface provides an interface between the processing component and a peripheral interface module, which may be an output device, an input device, etc. The communication component is configured to facilitate wired or wireless communication between the computing device and other devices, and the like.

The computing device may be a physical device or an elastic computing host provided by the cloud computing platform, and at this time, the computing device may be a cloud server, and the processing component, the storage component, and the like may be a base server resource rented or purchased from the cloud computing platform.

When the computing device is a physical device, the computing device may be implemented as a distributed cluster formed by a plurality of servers or terminal devices, or may be implemented as a single server or a single terminal device.

The embodiment of the invention also provides a computer readable storage medium which stores a computer program, and the computer program can realize the lung trachea registration method provided by the embodiment of the invention when being executed by a computer.

The embodiment of the invention also provides a computer program product, which comprises a computer program, wherein the computer program can realize the lung trachea registration method provided by the embodiment of the invention when being executed by a computer.

Wherein the processing components of the respective embodiments above may include one or more processors to execute computer instructions to perform all or part of the steps of the methods described above. Of course, the processing component may also be implemented as one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic elements for executing the methods described above.

The storage component is configured to store various types of data to support operation in the device. The memory component may be implemented by any type or combination of volatile or nonvolatile memory devices 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 memory, flash memory, magnetic or optical disk.

It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.

The apparatus embodiments described above are merely illustrative, wherein the elements illustrated as separate elements may or may not be physically separate, and the elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.

From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.

Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims (13)

1. A method of pulmonary tracheal registration, comprising:

acquiring central line information of a three-dimensional model of a pulmonary tracheal tree, wherein the three-dimensional model of the pulmonary tracheal tree is reconstructed based on medical images of pulmonary tracheal;

determining a plurality of virtual Long Tudian in the pulmonary tracheal tree three-dimensional model based on the centerline information;

determining a tracheal wall protuberance point corresponding to each virtual Long Tudian on the tracheal wall of the three-dimensional pulmonary tracheal tree model, and generating a first key point set;

acquiring a first moving path point set of a positioning sensor in the lung trachea;

and registering the pulmonary tracheal tree three-dimensional model with the pulmonary trachea based on the first set of key points and the first set of movement path points.

2. The method of claim 1, wherein determining a plurality of virtual carina points in the three-dimensional model of the pulmonary tracheal tree based on the centerline information comprises:

determining an airway path of the three-dimensional model of the pulmonary tracheal tree according to the central line information;

a plurality of virtual carina points located on the airway path are determined along the airway path.

3. The method of claim 1, wherein said determining, on the tracheal wall of said three-dimensional model of the pulmonary tracheal tree, tracheal wall carina points corresponding to each of said virtual Long Tudian comprises:

determining a plurality of first intersection points corresponding to the virtual Long Tudian from the tracheal wall along a plurality of preset directions with the virtual Long Tudian as a starting point;

from the plurality of first intersection points, a first intersection point closest to the virtual Long Tudian is determined as a tracheal wall protuberance point corresponding to the virtual Long Tudian.

4. The method of claim 3, wherein the determining, from the plurality of first intersection points, that the first intersection point closest to the virtual Long Tudian is the tracheal wall protuberance point corresponding to the virtual Long Tudian comprises:

screening the first intersection points, and determining the carina point of the tracheal wall from the first intersection points remained after screening.

5. The method of claim 4, wherein the screening the plurality of first intersections comprises:

determining a first distance of the virtual Long Tudian from the tracheal entrance and a second distance of each of the first intersection points from the tracheal entrance;

and removing the first intersection point corresponding to the second distance smaller than the first distance.

6. The method of claim 4 or 5, wherein said screening said first plurality of intersections comprises:

dividing a first region including the first intersection and the virtual Long Tudian into a first sub-region and a second sub-region by connecting the first intersection with the virtual Long Tudian;

determining a first data amount of the first sub-region and a second data amount of the second sub-region respectively;

determining a difference between the first data amount and the second data amount;

and removing the first intersection point corresponding to the second data quantity with the difference value larger than the preset threshold value.

7. The method of claim 1, wherein the registering the pulmonary tracheal tree three-dimensional model with the pulmonary trachea based on the first set of keypoints and the first set of travel path points comprises:

Determining a second set of keypoints in the pulmonary trachea corresponding to the first set of keypoints;

and registering the pulmonary tracheal tree three-dimensional model with the pulmonary trachea based on the second set of key points and the first set of movement path points.

8. The method of claim 7, wherein the registering the pulmonary tracheal tree three-dimensional model with the pulmonary trachea based on the second set of keypoints and the first set of travel path points comprises:

acquiring point cloud data generated by movement of a positioning sensor in the lung trachea;

the following operations are performed iteratively:

determining a plurality of third key points corresponding to each second key point in the second key point set in the point cloud data, and generating a third key point set;

performing registration calculation based on the third key point set and the first key point set to obtain a first registration matrix;

and determining whether a registration completion condition is met based on the third key point set, if yes, generating a registration result based on the first registration matrix, and if not, re-determining the third key point set.

9. The method of claim 8, wherein the determining whether a registration completion condition is satisfied based on the third set of keypoints comprises:

Respectively determining whether a plurality of third key points in the third key point set are positioned in the tracheal cavity or not to obtain a first proportion, wherein the first proportion is used for representing the proportion of the third key points positioned in the tracheal cavity in the third key point set;

judging whether the first proportion is larger than a preset threshold value, if so, determining that the registration result is met, otherwise, determining that the registration result is not met.

10. The method of claim 8, wherein the re-determining the third set of keypoints comprises:

interpolation is carried out between the corresponding key points in the first moving path point set and the second key point set, so that a fourth key point set is obtained;

and determining a plurality of third key points corresponding to each fourth key point in the fourth key point set respectively in the point cloud data, and generating the third key point set.

11. A pulmonary tracheal registration system, comprising:

a magnetic field generator for generating a positioning magnetic field; the lung trachea is in the positioning magnetic field;

a positioning sensor capable of generating a positioning signal by sensing the positioning magnetic field when moving in the lung trachea, and transmitting the positioning signal to a processing device, so that the processing device determines a moving path point of the positioning sensor in the lung trachea according to the positioning signal;

Processing device for performing the steps of the method of registration of a pulmonary trachea according to any of claims 1 to 10.

12. A computing device comprising a processing component and a storage component;

the storage component stores one or more computer instructions; the one or more computer instructions are to be invoked for execution by the processing component;

the storage component stores one or more computer instructions; the one or more computer instructions are to be invoked by the processing component to perform the method of pulmonary tracheal registration of any one of claims 1 to 10.

13. A computer storage medium, characterized in that a computer program is stored, which, when being executed by a computer, implements the method of registration of pulmonary airways according to any one of claims 1 to 10.