Television-assisted thoracoscope positioning and navigation method, device and system

Abstract

The invention relates to the technical field of intelligent medical treatment, in particular to a television-assisted thoracoscope positioning and navigation method, device and system, and the method comprises the steps: recognizing a preoperative thoracic image of a target object, obtaining the tissue state data of a thoracic cavity, and obtaining a twin thoracic cavity three-dimensional model; dynamic thoracic cavity data of a target object are imported into the twin thoracic cavity three-dimensional model in the operation, and the structural change rule of thoracic cavity tissue is determined; mapping the actual positioning of the magnetic probe to the twin thoracic cavity three-dimensional model during the working period of the thoracoscope to obtain a virtual probe motion state and displaying the virtual probe motion state on a television screen in real time; further predicting navigation parameters of the magnetic probe in the thoracic cavity according to the motion state and the structure change rule of the virtual probe; and adjusting the motion mode of the magnetic probe in the chest according to the navigation parameters. According to the invention, real-time accurate positioning and navigation can be carried out on probe movement in the process of using the television-assisted thoracoscope by different people, and the operation efficiency and reliability of the thoracoscope are improved.

Description

Technical Field

[0001] This invention relates to the field of smart medical technology, and in particular to a television-assisted thoracoscopy positioning and navigation method, device and system. Background Technology

[0002] With the widespread use of chest CT imaging technology, the detection rate of small pulmonary nodules has gradually increased, enabling early detection of pulmonary nodule lesions, inhibiting their progression towards lung cancer, and improving the early cure rate of pulmonary nodules. Pulmonary nodules are defined as lesions in the lung with a diameter of less than 30 mm, clear borders, a round shape, opaque imaging, and completely surrounded by air-containing lung tissue. As the size of pulmonary nodules increases, the risk of developing into lung cancer also increases. Treatment when pulmonary nodules are still small can significantly reduce the probability of developing lung tumors.

[0003] Video-assisted thoracoscopic surgery (VATS) is widely used in thoracic surgery and has become a routine method for the diagnosis and treatment of small pulmonary nodules, characterized by its minimally invasive nature and short postoperative recovery time. For example, invention patent CN109646110A discloses a VATS positioning method and device. This method obtains positioning information through preoperative planning; locates the lesion according to the selected preoperative positioning method; and uses a positioning probe to mark the located lesion in conjunction with VATS. It provides different preoperative positioning methods to meet the positioning needs of various complex lesions while facilitating thoracoscopic operation. However, the aforementioned invention patent only addresses lesion positioning in the preoperative setting and cannot provide positioning and navigation during the actual operation of the thoracoscopic probe, thus failing to provide accurate and efficient navigation guidance for the probe. Therefore, how to synchronously position and navigate the thoracoscopic probe in real time based on the internal thoracic tissue structure and dynamic conditions through a three-dimensional model is of great significance for improving the probe's motion accuracy and control efficiency. Summary of the Invention

[0004] Considering the differences in the internal thoracic tissue structure and the changes in internal tissue morphology and size caused by thoracic movement among different populations, this invention provides a video-assisted thoracoscopy positioning and navigation method to enable real-time and accurate positioning of the navigation probe during video-assisted thoracoscopy, thereby improving the efficiency and reliability of thoracoscopy operations. The method includes the following steps: S100: Identify the preoperative thoracic cavity image of the target object to obtain the tissue state data of the thoracic cavity; obtain a twin thoracic cavity three-dimensional model based on the tissue state data; and import the dynamic data of the target object's thoracic cavity into the twin thoracic cavity three-dimensional model during the operation to determine the structural change pattern of the thoracic cavity tissue; S200: The actual positioning of the magnetic probe during thoracoscopic work is mapped onto the twin thoracic cavity 3D model to obtain the virtual probe motion state and display it on the television screen in real time; then, based on the virtual probe motion state and the structural change law, the navigation parameters of the magnetic probe in the thoracic cavity are predicted. S300: Adjust the motion mode of the magnetic probe inside the thoracic cavity according to the navigation parameters.

[0005] Preferably, in S100, the thoracic cavity image of the target object is identified to obtain thoracic cavity tissue state data; based on the tissue state data, a three-dimensional twin thoracic cavity model is obtained, specifically as follows: Multimodal preoperative thoracic images of the target object are acquired, and image semantic segmentation and recognition are performed on the preoperative thoracic images of each modality to obtain the tissue spatial morphological features of the preoperative thoracic images of each modality. From the spatial morphological features of the tissue, the perturbation features of each preoperative thoracic cavity image with respect to each identical tissue in all modalities are extracted; wherein, the perturbation features include boundary blurring features and noise interference features; by comparing the perturbation features among the preoperative thoracic cavity images in all modalities, the position and contour data of each tissue in the thoracic cavity of the target object are obtained; Multi-channel dimensional fusion of the location and contour data of all tissues within the thoracic cavity is performed to obtain a twin thoracic cavity 3D model that matches the thoracic cavity of the target object.

[0006] Preferably, in S100, the dynamic data of the target object's thoracic cavity are imported into the twin thoracic cavity three-dimensional model during the operation to determine the structural change pattern of the thoracic cavity tissues, specifically as follows: During the operation, dynamic fluoroscopic images of the chest cavity were acquired during the respiratory movements of the target subject. Tissue contour identification and time evolution analysis were performed on the dynamic fluoroscopic images of the chest cavity to obtain dynamic data of the target subject's chest cavity. The dynamic data of the chest cavity includes dynamic changes in the expansion and contraction amplitude of the tissues within the chest cavity of the target subject. After importing the dynamic data of the target object's thoracic cavity into the twin thoracic cavity 3D model according to the internal tissue layout, the structural change law of the thoracic cavity tissue is determined; wherein, the structural change law includes the time change law of the contour of the internal cavity wall of the thoracic cavity tissue.

[0007] Preferably, in S200, the actual positioning of the magnetic probe during thoracoscopic surgery is mapped onto the twin thoracic cavity 3D model to obtain the virtual probe motion state, which is then displayed on the television screen in real time. Furthermore, based on the virtual probe motion state and the structural change pattern, the navigation parameters of the magnetic probe within the thoracic cavity are predicted, specifically: The target object's thoracic cavity and the twin thoracic cavity's three-dimensional model are aligned using spatial coordinate systems. This allows the actual positioning of the magnetic probe within the target object's thoracic cavity during thoracoscopic surgery to be synchronously mapped onto the twin thoracic cavity's three-dimensional model, resulting in a virtual probe motion state that is displayed in real-time on a television screen. The virtual probe motion state includes the motion path of the virtual probe corresponding to the magnetic probe within the twin thoracic cavity's three-dimensional model. Based on the motion state of the virtual probe and the structural change pattern, the contour of the tissue cavity wall to which the magnetic probe will reach in the next time interval within the thoracic cavity is determined, thereby predicting the navigation parameters of the magnetic probe in the next time interval; wherein, the navigation parameters include the motion path change parameters of the magnetic probe in the tissue cavity space.

[0008] Preferably, in S300, the movement pattern of the magnetic probe inside the thoracic cavity is adjusted according to the navigation parameters, specifically as follows: The real-time motion attitude parameters of the magnetic probe are obtained, and the motion variables of the magnetic probe are determined by comparing the real-time motion attitude parameters with the navigation parameters. Based on the motion variables and the allowable magnetic moment change margin provided by the magnetic field where the magnetic probe is located, determine the time-domain modification strategy of the magnetic vector of the magnetic field in three-dimensional space; According to the time-domain modification strategy of the magnetic vector, the turning mode and walking mode of the magnetic probe inside the thoracic cavity are adjusted; wherein, the turning mode includes a three-dimensional attitude angle change mode; and the walking mode includes a walking speed mode.

[0009] On the other hand, the present invention provides a video-assisted thoracoscopic positioning and navigation device, the device comprising the following modules: The image recognition and processing module is used to recognize the chest cavity image of the target object and obtain the tissue state data of the chest cavity; based on the tissue state data, a twin chest cavity three-dimensional model is obtained; then the dynamic data of the chest cavity of the target object is imported into the twin chest cavity three-dimensional model to determine the structural change law of the chest cavity tissue. The positioning and navigation prediction module, connected to the image recognition and processing module, is used to map the actual positioning of the magnetic probe during thoracoscopic work onto the twin chest cavity three-dimensional model to obtain the virtual probe motion state, and predict the navigation parameters of the magnetic probe in the chest cavity based on the virtual probe motion state and the structural change law. The motion adjustment module, connected to the positioning and navigation prediction module, is used to adjust the motion pattern of the magnetic probe inside the thoracic cavity according to the navigation parameters.

[0010] Preferably, the twin model generation module includes: The first acquisition unit is used to acquire multimodal preoperative thoracic images of the target object, perform image semantic segmentation and recognition on the preoperative thoracic images of each modality, and obtain the tissue spatial morphological features of the preoperative thoracic images of each modality. The feature extraction unit, connected to the first acquisition unit, is used to extract perturbation features of each of the preoperative thoracic images of all modalities with respect to each identical tissue from the tissue spatial morphology features; wherein, the perturbation features include boundary blurring features and noise interference features; by comparing the perturbation features among the preoperative thoracic images of all modalities, the position and contour data of each tissue in the thoracic cavity of the target object are obtained; The feature fusion unit, connected to the feature extraction unit, is used to perform multi-channel dimensional fusion of the position and contour data of all tissues in the thoracic cavity to obtain a twin thoracic cavity three-dimensional model that matches the thoracic cavity of the target object. The second acquisition unit is used to acquire dynamic fluoroscopic images of the chest cavity during the respiratory movements of the target object during the operation, and to perform tissue contour identification and time evolution analysis on the dynamic fluoroscopic images of the chest cavity to obtain dynamic data of the target object's chest cavity; wherein, the dynamic data of the chest cavity includes dynamic changes in the expansion and contraction amplitude of the tissues in the chest cavity of the target object; The data import unit, which is connected to the feature fusion unit and the second acquisition unit respectively, is used to import the dynamic data of the thoracic cavity of the target object into the twin thoracic cavity three-dimensional model according to the internal tissue layout of the thoracic cavity, and then determine the structural change law of the thoracic cavity tissue; wherein, the structural change law includes the time change law of the contour of the internal cavity wall of the thoracic cavity tissue.

[0011] Preferably, the positioning and navigation prediction module includes: A synchronous mapping unit is used to perform spatial coordinate system alignment between the target object's thoracic cavity and the twin thoracic cavity 3D model, thereby synchronously mapping the actual positioning of the magnetic probe in the target object's thoracic cavity during thoracoscopic work to the twin thoracic cavity 3D model, obtaining the virtual probe motion state and displaying it on the television screen in real time; wherein, the virtual probe motion state includes the motion path of the virtual probe corresponding to the magnetic probe within the twin thoracic cavity 3D model; The navigation prediction unit, connected to the synchronization mapping unit, is used to determine the contour of the tissue cavity wall to be reached by the magnetic probe in the next time interval based on the motion state of the virtual probe and the structural change law, thereby predicting the navigation parameters of the magnetic probe in the next time interval; wherein, the navigation parameters include the motion path change parameters of the magnetic probe in the tissue cavity space.

[0012] Preferably, the motion adjustment module includes: An attitude comparison unit is used to acquire the real-time motion attitude parameters of the magnetic probe, compare the real-time motion attitude parameters with the navigation parameters, and determine the motion variables of the magnetic probe. The strategy determination unit, connected to the attitude comparison unit, is used to determine the time-domain change strategy of the magnetic vector of the magnetic field in three-dimensional space based on the motion variables and the allowable magnetic moment change margin provided by the magnetic field where the magnetic probe is located. The mode adjustment unit, connected to the strategy determination unit, is used to adjust the turning mode and walking mode of the magnetic probe inside the thoracic cavity according to the time-domain change strategy of the magnetic vector; wherein, the turning mode includes a three-dimensional attitude angle change mode; and the walking mode includes a walking speed mode.

[0013] On the other hand, the present invention provides a video-assisted thoracoscopic positioning and navigation system, the system comprising: Image acquisition equipment used to acquire chest cavity images of a target object; A magnetic field generating device used to provide a variable magnetic field to drive the movement of a magnetic probe; The aforementioned video-assisted thoracoscopy positioning and navigation device is signal-connected to the image acquisition device and the magnetic field generating device.

[0014] Compared with the prior art, the present invention has the following beneficial effects: The video-assisted thoracoscopy positioning and navigation method, device, and system of the present invention take into account the different internal tissue structures of the thoracic cavity and the changes in the morphology and size of internal tissues caused by thoracic cavity movement in different populations. It achieves real-time and accurate positioning of the navigation probe's movement in different populations during video-assisted thoracoscopy, improving the efficiency and reliability of thoracoscopy operations. Specifically, it is manifested in the following ways: 1) Based on the preoperative chest cavity images and intraoperative chest cavity dynamic data of the target object, a twin chest cavity three-dimensional model is constructed and the changes in chest cavity tissue structure are captured. It can accurately match the differences in the internal tissue structure of the chest cavity of different people, as well as the changes in tissue morphology and size caused by chest cavity movement. This avoids the insufficient adaptation of general positioning schemes to individual differences and provides data support for personalized positioning and navigation. 2) By mapping the actual positioning of the magnetic probe to a 3D twin chest cavity model and combining the changes in chest cavity tissue structure to predict navigation parameters, the movement of the magnetic probe in the chest cavity can be tracked in real time and accurately predicted through the linkage between the virtual probe's motion state and the real chest cavity dynamics. This solves the problems of lag and deviation in positioning and navigation under dynamic changes in the chest cavity, and greatly improves the accuracy and timeliness of positioning and navigation. 3) The magnetic probe motion mode is dynamically adjusted based on the predicted navigation parameters, so that the probe motion always adapts to the dynamic changes of the thoracic tissue. This reduces the time spent on probe adjustment and operation errors caused by changes in tissue morphology during the operation, reduces the difficulty of thoracoscopic operation, and thus improves the overall operation efficiency. At the same time, it enhances the stability and reliability of the operation process, and provides a guarantee for the safety of thoracoscopic operations such as surgery. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below... The accompanying drawings are merely some embodiments of the present invention. Those skilled in the art can obtain other drawings based on these drawings without any creative effort. Wherein: Figure 1 This is a flowchart of a video-assisted thoracoscopic positioning and navigation method provided by the present invention. Figure 2 It is a multimodal image of the chest cavity.

[0016] Figure 3 It is a three-dimensional model of the twin chest cavities.

[0017] Figure 4 It is a curve diagram showing the structural changes of the thoracic cavity tissues. Figure 5 This is a schematic diagram of the motion path navigation of the magnetic probe.

[0018] Figure 6 This is a structural diagram of a television-assisted thoracoscopic positioning and navigation device provided by the present invention.

[0019] Figure 7 This is a structural diagram of a television-assisted thoracoscopic positioning and navigation system provided by the present invention. Detailed Implementation

[0020] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only for explaining the present invention and not for limiting the present invention. Furthermore, it should be noted that, for ease of description, only the parts related to the present invention are shown in the accompanying drawings, not all structures. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without inventive effort are within the scope of protection of the present invention.

[0021] The terms "comprising" and "having," and any variations thereof, used in this invention are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the steps or units listed, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to such process, method, product, or apparatus.

[0022] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0023] Please see Figure 1 As shown, the present invention provides a video-assisted thoracoscopic positioning and navigation method, which includes the following steps: S100: Identify the preoperative thoracic cavity image of the target object to obtain the tissue state data of the thoracic cavity; obtain a twin thoracic cavity three-dimensional model based on the tissue state data; import the dynamic data of the target object's thoracic cavity into the twin thoracic cavity three-dimensional model during the operation to determine the structural change pattern of the thoracic cavity tissue.

[0024] Furthermore, in S100, the preoperative thoracic cavity image of the target object is identified to obtain the tissue state data of the thoracic cavity; based on the tissue state data, a twin thoracic cavity three-dimensional model is obtained, specifically: Multimodal preoperative thoracic images of the target object were acquired, and image semantic segmentation and recognition were performed on each modality of preoperative thoracic images to obtain the tissue spatial morphological features of each modality of preoperative thoracic images. Based on the spatial morphological characteristics of the tissue, the perturbation features of each preoperative thoracic cavity image with respect to each identical tissue in all modalities are extracted; among which, the perturbation features include boundary blurring features and noise interference features; by comparing the perturbation features among all modalities of preoperative thoracic cavity images, the position and contour data of each tissue in the target object's thoracic cavity are obtained. Multi-channel dimensional fusion of the location and contour data of all tissues within the thoracic cavity is performed to obtain a twin 3D model of the thoracic cavity that matches the target object's thoracic cavity.

[0025] Specifically, the main function of video-assisted thoracoscopy is to locate and examine nodules in the pleural cavity (especially the lungs) of a target patient. CT (computed tomography) or MRI (magnetic resonance imaging) techniques can be used to image the pleural cavity. However, CT and MRI images of the same target patient's pleural cavity differ. These differences mainly lie in the imaging quality, such as the clarity of the images of different tissue areas within the pleural cavity (especially the lungs). This difference is primarily influenced by the density and material characteristics of the pleural tissues. For example, for a certain tissue area, CT images have higher imaging clarity than MRI images; while for another tissue area, MRI images have higher imaging clarity than CT images. Please refer to [link to relevant documentation]. Figure 2 (a) and (b) are CT and MRI images of the same region of the lungs of the corresponding target subjects, respectively. Comparing (a) and (b) reveals differences in imaging clarity between CT and MRI images in different tissue locations. This demonstrates that using only a single imaging technique to acquire images of the target subject's pleural cavity cannot achieve high-resolution, clear imaging of the entire pleural cavity.

[0026] To clearly and accurately identify the distribution of intrathoracic nodules in a target subject, one can, as follows: Figure 2 The images show CT and MRI images of the target thoracic cavity, collected as multimodal images. Considering the significant differences in physical characteristics and image features between different modalities (CT or MRI images), the complex structures and diverse features of different thoracic tissues, and the overlapping of different tissues, identifying the spatial morphological features of tissues, such as contours and shapes, in different modalities presents considerable challenges. Therefore, a fully convolutional neural network (FCN) is used to perform semantic segmentation and recognition of preoperative thoracic cavity images of different modalities, obtaining the spatial morphological features of tissues in both CT and MRI images. The FCN is preferably a DeepLab-V2 network, which utilizes dilated convolution operations with multiple sampling rates to achieve parallel sampling of feature maps and fuses the output results to obtain more spatial information, enabling fast and accurate segmentation of CT and MRI images.

[0027] This study extracts boundary blurring features (e.g., degree of boundary blurring) and noise interference features (e.g., noise intensity ratio) corresponding to the same tissue within the thoracic cavity from CT and MRI images. These features characterize the imaging quality of the same tissue site from both CT and MRI images, considering both boundary blurring and noise interference intensity. A convolutional neural network model is used to process the boundary blurring and noise interference intensity corresponding to the imaging of the same tissue site, obtaining imaging quality evaluation values ​​for the same tissue site in both CT and MRI images. Imaging blocks corresponding to tissue sites with higher imaging quality evaluation values ​​are then extracted from both CT and MRI images. This process is repeated for each tissue site within the target object's thoracic cavity, comparing the imaging quality evaluation values ​​on CT and MRI images, and extracting imaging blocks corresponding to tissue sites with higher imaging quality evaluation values ​​from either CT or MRI images. Finally, the extracted imaging blocks of all tissue sites are fused and stitched together to obtain a combined image of the target object's thoracic cavity. Analysis of this combined image yields the location and contour data of each tissue site within the target object's thoracic cavity. The location and contour data of the tissue parts obtained through the above method simultaneously possess the location and contour features of the best imaging quality image blocks of each multimodal image, thereby enabling multimodal image fusion processing.

[0028] After obtaining the location and contour data of each tissue, the process also includes using an image generator that combines a Transformer with a multi-head self-attention mechanism and a Generative Adversarial Network (GAN) to perform multi-channel dimensional fusion of the location and contour data of all tissue parts within the target object's thoracic cavity, generating a twin thoracic cavity 3D model that matches the target object's thoracic cavity. Please refer to... Figure 3 The generated twin chest cavity 3D model matches the target object's chest cavity in terms of tissue structure, thereby synchronously reproducing the chest cavity tissue structure state of the target object in a 3D virtual level. Subsequently, based on the twin chest cavity 3D model, it can synchronously reflect the changes in the shape and size of the target object's chest cavity tissue structure, providing an accurate reference for determining whether the thoracoscopic magnetic probe can continue to move forward inside the chest cavity.

[0029] Furthermore, in S100, the dynamic data of the target patient's thoracic cavity are imported into a twin thoracic cavity 3D model during the operation to determine the structural changes of the thoracic tissues, specifically as follows: During the operation, dynamic fluoroscopic images of the chest cavity were acquired during the respiratory movements of the target subject. Tissue contour identification and time evolution analysis were performed on the dynamic fluoroscopic images of the chest cavity to obtain dynamic data of the target subject's chest cavity. Among them, dynamic data of the chest cavity included dynamic changes in the expansion and contraction amplitude of the tissues in the target subject's chest cavity. After importing the dynamic data of the target object's thoracic cavity into the twin 3D model of the thoracic cavity according to the layout of the thoracic cavity tissues, the structural change law of the thoracic cavity tissues is determined; among which, the structural change law includes the time change law of the contour of the wall of the thoracic cavity tissue.

[0030] Specifically, during video-assisted thoracoscopy (VATS) manipulation of the target subject's thoracic cavity, the target subject simultaneously undergoes respiratory movements. During exhalation and inhalation, the thoracic cavity contracts and expands synchronously, causing the intrapleural tissues to shrink and expand accordingly. Once the thoracoscope's magnetic probe enters the target subject's thoracic cavity, it moves forward within the thoracic tissue cavity, which shrinks and expands accordingly during respiration. When the intrapleural tissue cavity shrinks, it cannot provide sufficient space for the magnetic probe to move forward and / or turn; when it expands, it provides sufficient space for the probe to move forward and / or turn. This analysis shows that when the thoracoscope needs to move through a portion of the target subject's thoracic cavity during operation, it can only move smoothly and / or turn when these cavities are in an expanded state. These changes in the shrinking and expanding of these intrapleural cavities are synchronous in time with the target subject's exhalation and inhalation.

[0031] To this end, dynamic fluoroscopic images of the chest cavity were acquired during the respiratory movements of the target subject. These images directly reflect the contour changes of the intrathoracic tissues during the alternating exhalation and inhalation. Tissue contour identification and temporal evolution analysis were then performed on the dynamic fluoroscopic images to obtain dynamic data on the expansion and contraction amplitudes of the intrathoracic tissues. Sub-data on the dynamic expansion and contraction amplitudes of each intrathoracic tissue region, as well as the location data of each region's intrathoracic cavity, were extracted from this data and imported into a twin 3D chest cavity model. The twin 3D chest cavity model synchronously maps the imported data to the corresponding intrathoracic tissue cavities within the model, thereby determining the temporal variation patterns of the spatial wall contours of the intrathoracic tissue cavities within the model. Please refer to [link to relevant documentation]. Figure 4 The contours of the pleural cavity walls within the model exhibit periodic expansion and contraction over time. Specifically, the contours of the pleural cavity walls alternate between expansion and contraction at corresponding periodic intervals (e.g., approximately 2 seconds), resulting in synchronized expansion and contraction of the pleural cavity space. Analysis shows that the expansion and contraction of the aforementioned twin pleural cavity 3D model are synchronous with the target object's pleural cavity. The structural change curves in Figure 4 accurately reflect the actual expansion and contraction movements of the target object's pleural cavity over time. Further research will follow... Figure 4The duration of the chest cavity expansion movement of the target object is determined by adaptively adjusting the magnetic probe in motion. This helps the magnetic probe to move smoothly forward and turn within the chest cavity, and avoids collisions between the magnetic probe and the walls of the tissue cavity.

[0032] S200: The actual positioning of the magnetic probe during thoracoscopic work is mapped onto a twin 3D model of the thoracic cavity to obtain the virtual probe motion state and display it on the television screen in real time; then, based on the virtual probe motion state and structural change law, the navigation parameters of the magnetic probe in the thoracic cavity are predicted.

[0033] Furthermore, in S200, the actual positioning of the magnetic probe during thoracoscopic surgery is mapped onto a 3D twin thoracic cavity model to obtain the virtual probe motion state; based on the virtual probe motion state and structural change patterns, the navigation parameters of the magnetic probe within the thoracic cavity are predicted, specifically: Spatial coordinate system alignment is performed on the three-dimensional models of the target object's thoracic cavity and the twin thoracic cavity to synchronously map the actual positioning of the magnetic probe in the target object's thoracic cavity during thoracoscopic work onto the three-dimensional model of the twin thoracic cavity, thereby obtaining the virtual probe motion state; wherein, the virtual probe motion state includes the motion path of the virtual probe corresponding to the magnetic probe within the three-dimensional model of the twin thoracic cavity; Based on the motion state and structural change patterns of the virtual probe, the contour of the tissue cavity wall to which the magnetic probe will reach in the next time interval is determined, thereby predicting the navigation parameters of the magnetic probe in the next time interval; among which, the navigation parameters include the motion path change parameters of the magnetic probe in the tissue cavity space.

[0034] The above analysis shows that after importing the dynamic data of the target object's thoracic cavity into the twin thoracic cavity 3D model, it can be synchronously displayed on the television screen for real-time viewing by the surgeon during operation. The twin thoracic cavity 3D model will exhibit movements that are synchronous and consistent with the actual activities of the target object's thoracic cavity. The motion simulation prediction of the virtual probe in the twin thoracic cavity 3D model can determine the forward motion state and / or turning state of the virtual probe when passing through the tissue cavity in the twin thoracic cavity 3D model without colliding with the tissue cavity space wall. This can provide accurate reference guidance for controlling the forward motion state and / or turning state of the magnetic probe in the target object's thoracic cavity. The virtual probe in the twin thoracic cavity 3D model refers to a virtual probe with the same shape and size as the magnetic probe of the video-assisted thoracoscopy and applicable to the 3D model level. The virtual probe can be freely adjusted in its forward motion state and / or turning state within the twin thoracic cavity 3D model. To facilitate matching of the target chest cavity and twin chest cavity 3D models within the same spatial coordinate system, and thus synchronously monitor the movement status of the magnetic probe and the virtual probe, the spatial coordinate system of the target chest cavity and the twin chest cavity 3D models is first aligned. That is, both the target chest cavity and the twin chest cavity 3D models are mapped to the same spatial coordinate system (such as the world coordinate system). In this way, during thoracoscopy, the actual positioning of the magnetic probe within the target chest cavity will be synchronously mapped onto the virtual probe in the twin chest cavity 3D model. This will cause the virtual probe to form the same position and movement state as the magnetic probe, realizing the spatial dynamic linkage between the virtual probe and the magnetic probe. This ensures that the movement path of the virtual probe in the twin chest cavity 3D model is synchronized with the movement path of the magnetic probe in the target chest cavity, allowing the operator to intuitively observe the relative position of the magnetic probe and the chest cavity tissue, and thus intuitively judge whether the magnetic probe has accurately reached the target point.

[0035] Considering that the virtual probe's motion state is synchronized with the magnetic probe's motion state, the tissue cavity space of the target object's thoracic cavity that the magnetic probe will pass through in the next moment will be directly reflected on the virtual probe. That is, the tissue cavity space of the twin thoracic cavity 3D model that the virtual probe will pass through in the next moment is the same as the tissue cavity space that the magnetic probe will pass through. After the aforementioned twin thoracic cavity 3D model is imported into the target object's thoracic cavity dynamic data, the time change law of the wall contour of the target object's thoracic cavity tissue cavity space has been obtained. In this way, the expansion and contraction of the thoracic cavity tissue cavity space over time can be obtained. Only when the thoracic cavity tissue cavity space is within the duration range of the expansion action can the magnetic probe smoothly pass through the corresponding thoracic cavity tissue cavity space without collision. In summary, based on the above structural change patterns, the duration of the expansion movement of the thoracic cavity is determined. Then, based on the virtual probe's motion state, the contour (shape and size) of the tissue cavity wall reached by the magnetic probe in the next time interval (i.e., the aforementioned duration of the expansion movement) is determined. This allows for the prediction of the changes in the magnetic probe's motion path parameters in the tissue cavity in the next time interval (i.e., changes in parameters such as the orientation of the magnetic probe's motion path in the tissue cavity).

[0036] Please see Figure 5 This describes the navigation of the magnetic probe's movement path within the tissue cavity of the target object's chest cavity. The current center point of the magnetic probe is K1, and its axial vector is n0. Based on the above analysis, the magnetic probe is only allowed to move through the tissue cavity during the duration of the expanding movement within the target object's chest cavity (i.e., the next time interval mentioned above). In the next time interval (i.e., the next moment), the target object's tissue cavity expands, and the shape and size of the tissue cavity wall also change. Combining the shape and size of the magnetic probe itself with the changed shape and size of the tissue cavity wall, several collision points C1 and C2 can be identified on the tissue cavity wall that may collide with the magnetic probe. To avoid actual collisions between the magnetic probe and these collision points C1 and C2, motion path modification parameters need to be set for the magnetic probe. Specifically, this corresponds to... Figure 5The magnetic probe can be set to rotate by an angle θm based on the current center point K1, so that the axial vector n0 of the magnetic probe becomes n1; then the magnetic probe is set to move at a predetermined speed with the axial vector n1 as the forward direction; when the magnetic probe moves to a position close to the possible collision point C2, the magnetic probe is set to rotate by an angle θm based on the current center point K2, so that the axial vector n1 of the magnetic probe becomes n2, and so on, predicting the change parameters of the magnetic probe's motion path in the tissue cavity space. This ensures that the magnetic probe moves smoothly through the tissue cavity space in a short time interval when the tissue cavity space is in an expanded state, avoiding collisions between the magnetic probe and the surface of the tissue cavity space. By combining the prediction of the actual motion path change of the magnetic probe with the twin thoracic cavity 3D model, it helps to improve the motion control efficiency of the magnetic probe, predict the motion adjustment of the magnetic probe, and reduce the probability of motion control errors of the magnetic probe.

[0037] S300: Adjust the motion pattern of the magnetic probe within the thoracic cavity according to navigation parameters. Further, in S300, the adjustment of the magnetic probe's motion pattern within the thoracic cavity according to navigation parameters specifically involves: The real-time motion attitude parameters of the magnetic probe are obtained, and the motion variables of the magnetic probe are determined by comparing the real-time motion attitude parameters with the navigation parameters. Based on the motion variables and the allowable magnetic moment change margin provided by the magnetic field where the magnetic probe is located, the time-domain modification strategy of the magnetic vector in three-dimensional space is determined. Based on the temporal variation strategy of the magnetic vector, the turning and walking modes of the magnetic probe inside the thoracic cavity are adjusted; the turning mode includes a three-dimensional attitude angle change mode; the walking mode includes a walking speed mode.

[0038] Specifically, the magnetic probe moves within the tissue cavity of the target object's thoracic cavity, and at each current moment, it has corresponding real-time motion attitude parameters (such as real-time motion attitude angles). After predicting the navigation parameters of the magnetic probe in the next time interval, the real-time motion attitude parameters and navigation parameters are compared to determine the motion variables (such as changes in motion attitude angles and changes in motion path trajectory) that the magnetic probe needs to undergo from the current moment to the next time interval, thus providing accurate guidance for subsequently driving the magnetic probe's movement.

[0039] Furthermore, the magnetic probe moves under the influence of a magnetic moment generated by changes in the external magnetic field. Whether the magnetic probe can accurately exhibit these motion variables depends on the magnetic moment provided by the external magnetic field. In practical applications, a triaxial orthogonal Helmholtz coil system can be constructed and connected to a three-phase frequency converter. This system generates a triaxially variable external magnetic field under the drive of the three-phase frequency converter. By adjusting the current output from the three-phase frequency converter to the triaxial orthogonal Helmholtz coils, a corresponding magnetic moment can be generated. When this magnetic moment is applied to the magnetic probe, it drives the probe to move. Considering that the magnetic moment generated by the triaxial orthogonal Helmholtz coil system under the drive of a three-phase frequency converter is limited to a certain range, in order to ensure that the magnetic moment can accurately drive the magnetic probe to generate the required motion variables, the temporal variation strategy of the magnetic vector in three-dimensional space is first determined based on the motion variables and the allowable magnetic moment variation margin provided by the magnetic field where the magnetic probe is located (i.e., the maximum allowable magnetic moment variation). For example, based on the motion variables and the allowable magnetic moment variation margin provided by the magnetic field where the magnetic probe is located, the changes in the direction of motion and the length of the motion path of the magnetic probe are determined when the magnetic moment provided by the magnetic field undergoes a preset fixed change. This establishes the correlation between the change in magnetic moment and the changes in the direction of motion and the length of the motion path of the magnetic probe, thereby determining the temporal variation strategy of the magnetic vector in three-dimensional space. The aforementioned temporal variation strategy refers to the strategy for the magnitude change of the magnetic vector generated by the magnetic field on the X-axis, Y-axis, and Z-axis in three-dimensional space with time. This ensures that the magnetic probe can smoothly pass through the tissue cavity space with a suitable motion posture and speed within the corresponding time interval.

[0040] Once the time-domain modification strategy of the magnetic vector is determined, the three-phase frequency converter outputs a frequency-matched current in the time domain to the three-axis orthogonal Helmholtz coil system. This enables the three-axis orthogonal Helmholtz coil system to generate appropriate magnetic vectors in the corresponding X, Y, and Z axes in three-dimensional space. Under the action of the magnetic vectors in the above three-axis directions, the magnetic probe undergoes three-dimensional attitude angle changes and travel speed changes, accurately navigating the movement of the magnetic probe inside the chest cavity of the target object, thus improving the efficiency and reliability of thoracoscopy.

[0041] Please see Figure 6 As shown, the present invention provides a video-assisted thoracoscopic positioning and navigation device, which includes the following modules: Image recognition and processing module 1 is used to recognize the preoperative thoracic cavity image of the target object and obtain the tissue state data of the thoracic cavity; based on the tissue state data, a twin thoracic cavity three-dimensional model is obtained; then, during the operation, the dynamic data of the target object's thoracic cavity is imported into the twin thoracic cavity three-dimensional model to determine the structural change law of the thoracic cavity tissue; The positioning and navigation prediction module 2 is connected to the image recognition and processing module 1. It is used to map the actual positioning of the magnetic probe during thoracoscopic work onto the three-dimensional model of the twin chest cavity, obtain the virtual probe motion state and display it on the TV screen in real time; and then predict the navigation parameters of the magnetic probe in the chest cavity based on the virtual probe motion state and structural change law. The motion adjustment module 3 is connected to the positioning and navigation prediction module 2 and is used to adjust the motion mode of the magnetic probe inside the thoracic cavity according to the navigation parameters.

[0042] Furthermore, the image recognition processing module 1 includes: The first acquisition unit 11 is used to acquire multimodal preoperative thoracic images of the target object, perform image semantic segmentation and recognition on each modality of preoperative thoracic images, and obtain the tissue spatial morphological features of each modality of preoperative thoracic images. The feature extraction unit 12, connected to the first acquisition unit 11, is used to extract the perturbation features of each preoperative thoracic cavity image of all modalities with respect to each identical tissue from the tissue spatial morphology features; wherein, the perturbation features include boundary blurring features and noise interference features; by comparing the perturbation features between the preoperative thoracic cavity images of all modalities, the position and contour data of each tissue in the thoracic cavity of the target object are obtained. The feature fusion unit 13, connected to the feature extraction unit 12, is used to perform multi-channel dimensional fusion of the position and contour data of all tissues in the thoracic cavity to obtain a twin thoracic cavity 3D model that matches the target object's thoracic cavity. The second acquisition unit 14 is used to acquire dynamic fluoroscopic images of the chest cavity during the respiratory action of the target object, perform tissue contour identification and time evolution analysis on the dynamic fluoroscopic images of the chest cavity, and obtain dynamic data of the chest cavity of the target object; wherein, the dynamic data of the chest cavity includes dynamic changes in the expansion and contraction amplitude of the tissues in the chest cavity of the target object. The data import unit 15 is connected to the feature fusion unit 13 and the second acquisition unit 14 respectively. It is used to import the dynamic data of the thoracic cavity of the target object into the twin thoracic cavity three-dimensional model according to the internal tissue layout of the thoracic cavity, and then determine the structural change law of the thoracic cavity tissue. The structural change law includes the time change law of the contour of the internal cavity wall of the thoracic cavity tissue.

[0043] Furthermore, the positioning and navigation prediction module 2 includes: The synchronous mapping unit 21 is used to perform spatial coordinate system alignment between the three-dimensional models of the target object's thoracic cavity and the twin thoracic cavity, thereby synchronously mapping the actual positioning of the magnetic probe in the target object's thoracic cavity during thoracoscopic work to the three-dimensional model of the twin thoracic cavity, obtaining the virtual probe's motion state and displaying it on the television screen in real time; wherein, the virtual probe's motion state includes the motion path of the virtual probe corresponding to the magnetic probe within the three-dimensional model of the twin thoracic cavity. The navigation prediction unit 22, connected to the synchronization mapping unit 21, is used to predict the navigation parameters of the magnetic probe in the thoracic cavity based on the motion state and structural change law of the virtual probe. Specifically, it determines the contour of the tissue cavity wall to be reached by the magnetic probe in the next time interval based on the motion state and structural change law of the virtual probe, and predicts the navigation parameters of the magnetic probe in the next time interval. The navigation parameters include the motion path change parameters of the magnetic probe in the tissue cavity space.

[0044] Furthermore, the motion adjustment module 3 is used to include: The attitude comparison unit 31 is used to acquire the real-time motion attitude parameters of the magnetic probe, compare the real-time motion attitude parameters with the navigation parameters, and determine the motion variables of the magnetic probe. The strategy determination unit 32, connected to the attitude comparison unit 31, is used to determine the time-domain change strategy of the magnetic vector in three-dimensional space based on the motion variables and the allowable magnetic moment change margin provided by the magnetic field where the magnetic probe is located. The mode adjustment unit 33 and the connection strategy determination unit 32 are used to adjust the turning mode and walking mode of the magnetic probe inside the thoracic cavity according to the time-domain change strategy of the magnetic vector; wherein, the turning mode includes a three-dimensional attitude angle change mode; and the walking mode includes a walking speed mode.

[0045] The operation and effect of the TV-assisted thoracoscopy positioning and navigation device of the present invention are consistent with the above-mentioned TV-assisted thoracoscopy positioning and navigation method, and the TV-assisted thoracoscopy positioning and navigation device will not be described again here.

[0046] Please see Figure 7 As shown, the present invention provides a video-assisted thoracoscopic positioning and navigation system, the system comprising: An image acquisition device is used to acquire preoperative thoracic images of a target subject; wherein, the image acquisition device may include a CT imaging device and an MRI imaging device, which acquire CT images and MRI images of the target subject's thoracic cavity respectively, thereby achieving multimodal imaging of the target subject; A magnetic field generating device is used to provide a variable magnetic field to drive the movement of a magnetic probe; wherein, the magnetic field generating device may include a triaxial orthogonal Helmholtz coil system and a three-phase frequency converter, the triaxial orthogonal Helmholtz coil system generating a three-axis variable external magnetic field under the drive of the three-phase frequency converter. The aforementioned video-assisted thoracoscopy positioning and navigation device is connected to the image acquisition equipment and the magnetic field generating equipment.

[0047] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of a necessary general-purpose hardware platform, or by a combination of hardware and software. 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 computer product. The present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0048] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Other embodiments may also be used. Although the present invention 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 the present invention.

Claims

1. A video-assisted thoracoscopic positioning navigation method, characterized in that, The method Includes the following steps: S100: Identify the preoperative thoracic cavity image of the target object to obtain the tissue state data of the thoracic cavity; obtain a twin thoracic cavity three-dimensional model based on the tissue state data; and import the dynamic data of the target object's thoracic cavity into the twin thoracic cavity three-dimensional model during the operation to determine the structural change pattern of the thoracic cavity tissue; S200: The actual positioning of the magnetic probe during thoracoscopic work is mapped onto the twin thoracic cavity 3D model to obtain the virtual probe motion state and display it on the television screen in real time; then, based on the virtual probe motion state and the structural change law, the navigation parameters of the magnetic probe in the thoracic cavity are predicted. S300: Adjust the motion mode of the magnetic probe inside the thoracic cavity according to the navigation parameters.

2. The method of claim 1, wherein, In S100, the preoperative thoracic cavity image of the target object is identified to obtain the tissue state data of the thoracic cavity; based on the tissue state data, a three-dimensional twin thoracic cavity model is obtained, specifically: Multimodal preoperative thoracic images of the target object are acquired, and image semantic segmentation and recognition are performed on the preoperative thoracic images of each modality to obtain the tissue spatial morphological features of the preoperative thoracic images of each modality. From the spatial morphological features of the tissue, the perturbation features of each preoperative thoracic cavity image with respect to each identical tissue in all modalities are extracted; wherein, the perturbation features include boundary blurring features and noise interference features; by comparing the perturbation features among the preoperative thoracic cavity images in all modalities, the position and contour data of each tissue in the thoracic cavity of the target object are obtained; Multi-channel dimensional fusion of the location and contour data of all tissues within the thoracic cavity is performed to obtain a twin thoracic cavity 3D model that matches the thoracic cavity of the target object.

3. The method of claim 2, wherein, In S100, the dynamic data of the target object's thoracic cavity are imported into the twin thoracic cavity 3D model during the operation to determine the structural change patterns of the thoracic tissues, specifically as follows: During the operation, dynamic fluoroscopic images of the chest cavity were acquired during the respiratory movements of the target subject. Tissue contour identification and time evolution analysis were performed on the dynamic fluoroscopic images of the chest cavity to obtain dynamic data of the target subject's chest cavity. The dynamic data of the chest cavity includes dynamic changes in the expansion and contraction amplitude of the tissues within the chest cavity of the target subject. After importing the dynamic data of the target object's thoracic cavity into the twin thoracic cavity 3D model according to the internal tissue layout, the structural change law of the thoracic cavity tissue is determined; wherein, the structural change law includes the time change law of the contour of the internal cavity wall of the thoracic cavity tissue.

4. The method of claim 1, wherein, In S200, the actual positioning of the magnetic probe during thoracoscopic surgery is mapped onto the three-dimensional twin thoracic cavity model to obtain the virtual probe motion state, which is displayed on the television screen in real time. Then, based on the virtual probe motion state and the structural change patterns, the navigation parameters of the magnetic probe within the thoracic cavity are predicted, specifically: The target object's thoracic cavity and the twin thoracic cavity's three-dimensional model are aligned using spatial coordinate systems. This allows the actual positioning of the magnetic probe within the target object's thoracic cavity during thoracoscopic surgery to be synchronously mapped onto the twin thoracic cavity's three-dimensional model, resulting in a virtual probe motion state that is displayed in real-time on a television screen. The virtual probe motion state includes the motion path of the virtual probe corresponding to the magnetic probe within the twin thoracic cavity's three-dimensional model. Based on the motion state of the virtual probe and the structural change pattern, the contour of the tissue cavity wall to which the magnetic probe will reach in the next time interval within the thoracic cavity is determined, thereby predicting the navigation parameters of the magnetic probe in the next time interval; wherein, the navigation parameters include the motion path change parameters of the magnetic probe in the tissue cavity space.

5. The method of claim 1, wherein, In S300, the movement pattern of the magnetic probe inside the thoracic cavity is adjusted according to the navigation parameters, specifically as follows: The real-time motion attitude parameters of the magnetic probe are obtained, and the motion variables of the magnetic probe are determined by comparing the real-time motion attitude parameters with the navigation parameters. Based on the motion variables and the allowable magnetic moment change margin provided by the magnetic field where the magnetic probe is located, the time-domain modification strategy of the magnetic vector in three-dimensional space is determined. According to the time-domain modification strategy of the magnetic vector, the turning mode and walking mode of the magnetic probe inside the thoracic cavity are adjusted; wherein, the turning mode includes a three-dimensional attitude angle change mode; and the walking mode includes a walking speed mode.

6. A video-assisted thoracoscopic positioning navigation apparatus, characterized by, The device Includes the following modules: The image recognition and processing module is used to identify the preoperative thoracic cavity image of the target object and obtain the tissue state data of the thoracic cavity; based on the tissue state data, a twin thoracic cavity three-dimensional model is obtained; then, during the operation, the dynamic data of the target object's thoracic cavity is imported into the twin thoracic cavity three-dimensional model to determine the structural change pattern of the thoracic cavity tissue. The positioning and navigation prediction module, connected to the image recognition and processing module, is used to map the actual positioning of the magnetic probe during thoracoscopic work onto the twin thoracic cavity three-dimensional model, obtain the virtual probe motion state and display it on the television screen in real time, and then predict the navigation parameters of the magnetic probe in the thoracic cavity based on the virtual probe motion state and the structural change law. The motion adjustment module, connected to the positioning and navigation prediction module, is used to adjust the motion pattern of the magnetic probe inside the thoracic cavity according to the navigation parameters.

7. The apparatus of claim 6, wherein, The image recognition and processing module includes: The first acquisition unit is used to acquire multimodal preoperative thoracic images of the target object, perform image semantic segmentation and recognition on the preoperative thoracic images of each modality, and obtain the tissue spatial morphological features of the preoperative thoracic images of each modality. The feature extraction unit, connected to the first acquisition unit, is used to extract perturbation features of each of the preoperative thoracic images of all modalities with respect to each identical tissue from the tissue spatial morphology features; wherein, the perturbation features include boundary blurring features and noise interference features; by comparing the perturbation features among the preoperative thoracic images of all modalities, the position and contour data of each tissue in the thoracic cavity of the target object are obtained; The feature fusion unit, connected to the feature extraction unit, is used to perform multi-channel dimensional fusion of the position and contour data of all tissues in the thoracic cavity to obtain a twin thoracic cavity three-dimensional model that matches the thoracic cavity of the target object. The second acquisition unit is used to acquire dynamic fluoroscopic images of the chest cavity during the respiratory movements of the target object during the operation, and to perform tissue contour identification and time evolution analysis on the dynamic fluoroscopic images of the chest cavity to obtain dynamic data of the target object's chest cavity; wherein, the dynamic data of the chest cavity includes dynamic changes in the expansion and contraction amplitude of the tissues in the chest cavity of the target object; The data import unit, which is connected to the feature fusion unit and the second acquisition unit respectively, is used to import the dynamic data of the thoracic cavity of the target object into the twin thoracic cavity three-dimensional model according to the internal tissue layout of the thoracic cavity, and then determine the structural change law of the thoracic cavity tissue; wherein, the structural change law includes the time change law of the contour of the internal cavity wall of the thoracic cavity tissue.

8. The apparatus of claim 6, wherein, The positioning and navigation prediction module includes: A synchronous mapping unit is used to perform spatial coordinate system alignment between the target object's thoracic cavity and the twin thoracic cavity 3D model, thereby synchronously mapping the actual positioning of the magnetic probe in the target object's thoracic cavity during thoracoscopic work to the twin thoracic cavity 3D model, obtaining the virtual probe motion state and displaying it on the television screen in real time; wherein, the virtual probe motion state includes the motion path of the virtual probe corresponding to the magnetic probe within the twin thoracic cavity 3D model; The navigation prediction unit, connected to the synchronization mapping unit, is used to determine the contour of the tissue cavity wall to be reached by the magnetic probe in the next time interval based on the motion state of the virtual probe and the structural change law, thereby predicting the navigation parameters of the magnetic probe in the next time interval; wherein, the navigation parameters include the motion path change parameters of the magnetic probe in the tissue cavity space.

9. The apparatus of claim 6, wherein, The motion adjustment module includes: An attitude comparison unit is used to acquire the real-time motion attitude parameters of the magnetic probe, compare the real-time motion attitude parameters with the navigation parameters, and determine the motion variables of the magnetic probe. The strategy determination unit, connected to the attitude comparison unit, is used to determine the time-domain change strategy of the magnetic vector of the magnetic field in three-dimensional space based on the motion variables and the allowable magnetic moment change margin provided by the magnetic field where the magnetic probe is located. The mode adjustment unit, connected to the strategy determination unit, is used to adjust the turning mode and walking mode of the magnetic probe inside the thoracic cavity according to the time-domain change strategy of the magnetic vector; wherein, the turning mode includes a three-dimensional attitude angle change mode; and the walking mode includes a walking speed mode.

10. A video-assisted thoracoscopic positioning and navigation system, characterized in that The system include: Image acquisition equipment is used to acquire preoperative thoracic images of the target patient; A magnetic field generating device used to provide a variable magnetic field to drive the movement of a magnetic probe; The television-assisted thoracoscopic positioning and navigation device as described in any one of claims 6-9, wherein the television-assisted thoracoscopic positioning and navigation device is signal-connected to the image acquisition device and the magnetic field generating device.

Images