Robot safe tool path planning method and system

Abstract

The invention discloses a robot safe knife path planning method and system. The method comprises the steps that a medical image set containing a to-be-operated focus of a target patient and a three-dimensional anatomy virtual model are acquired; points on the surface of the focus are determined to serve as a target operation point set, and a historical actual knife entering point set of the same to-be-operated type is searched for in a medical big database; determining a to-be-operated knife entering point on the surface of the target patient according to the historical knife entering point set; according to the to-be-operated knife entering point and the target operation point set, utilizing a pre-trained artificial intelligence model to generate a predicted knife path track of the surgical robot in the three-dimensional anatomy virtual model; and according to the predicted knife path track and the historical actual knife path track set of the same to-be-operated type, planning a final to-be-operated knife path track. According to the embodiment of the invention, intelligent knife path planning can be performed according to anatomical features of a patient in a personalized manner, and previous operation experience can be effectively absorbed and utilized, so that the safety and effectiveness of an operation are ensured.

Description

Technical Field

[0001] The present invention belongs to the field of artificial intelligence technology, and in particular to a method and system for planning safe tool path trajectories of a robot. Background Art

[0002] In the modern medical field, robotic surgery has gradually become an important means of surgery due to its advantages of high precision, low trauma and rapid recovery. The introduction of robotic surgical systems enables surgeons to operate more delicately, especially in complex surgical procedures, where robots can effectively reduce the risks caused by human factors. However, despite the continuous development of robotic surgical technology, tool path planning during surgery is still a key factor in ensuring the safety and success of the operation.

[0003] Traditional surgical path planning often relies on the surgeon's experience and intuition, lacking a systematic scientific basis. This method is not only limited by the surgeon's personal skills, but is also easily affected by factors such as the surgical environment, individual differences in patients, and the complexity of anatomical structures, leading to increased surgical risks and unstable results. Summary of the invention

[0004] The purpose of the present invention is to provide a robot safe tool path trajectory planning method and system to address the deficiencies in the prior art, to be able to perform intelligent tool path planning based on the patient's anatomical characteristics in a personalized manner, and to effectively absorb and utilize past surgical experience to ensure the safety and effectiveness of the operation.

[0005] An embodiment of the present application provides a robot safe tool path trajectory planning method, the method comprising:

[0006] Obtaining a medical image set and a three-dimensional anatomical virtual model of a target patient including a lesion to be operated on;

[0007] Determine the points on the lesion surface as the target surgical point set, and search the historical actual surgical point set of the same type of surgery from the medical big data database;

[0008] Determining the surgical entry point on the surface of the target patient according to the historical entry point set;

[0009] According to the entry point to be operated and the target surgical point set, a predicted tool path trajectory of the surgical robot is generated in the three-dimensional anatomical virtual model using a pre-trained artificial intelligence model, wherein the predicted tool path trajectory connects the entry point to be operated and the target surgical point set;

[0010] The final tool path trajectory to be operated is planned according to the predicted tool path trajectory and a historical actual tool path trajectory set of the same type of operation to be operated.

[0011] Optionally, determining the surgical entry point to be performed on the surface of the target patient according to the historical surgical entry point set includes:

[0012] From a set of historical lesion locations of the same type to be operated on in a medical big data database, find a historical lesion location whose distance from the center of the lesion to be operated on is less than a preset distance;

[0013] Determine the historical cutting points corresponding to the positions of the historical lesions, and draw circles for the determined historical cutting points so that the drawn circles include the most historical cutting points;

[0014] The center of the drawn circle is calculated as the surgical entry point on the target patient's surface.

[0015] Optionally, generating a predicted tool path trajectory of a surgical robot in the three-dimensional anatomical virtual model based on the surgical entry point to be operated and the target surgical point set using a pre-trained artificial intelligence model includes:

[0016] In the three-dimensional anatomical virtual model, a partial anatomical virtual model data set related to the lesion to be operated on is obtained;

[0017] The surgical entry point to be operated on, the target surgical point set and the partial anatomical virtual model data set are input into a pre-trained artificial intelligence model to generate a predicted tool path trajectory of the surgical robot in the partial anatomical virtual model, wherein the artificial intelligence model is trained based on historical surgical entry points, historical target surgical point sets, historical actual tool path trajectories and corresponding historical partial anatomical virtual model data sets, and the historical actual tool path trajectory is an artificial actual tool path trajectory, and the historical partial anatomical virtual model data set is the smallest partial anatomical virtual model that includes the historical actual tool path trajectory.

[0018] Optionally, planning a final tool path trajectory to be operated on according to the predicted tool path trajectory and a historical actual tool path trajectory set of the same type of operation to be operated on includes:

[0019] From the historical actual tool path trajectory set of the same type of surgery to be performed, the historical actual tool path trajectory corresponding to the historical lesion position whose distance from the center of the lesion position to be operated on is less than a preset distance is selected;

[0020] The screened historical actual tool path trajectories are segmented according to the anatomical tissue type, and each segment of the historical actual tool path trajectories is correspondingly superimposed;

[0021] For each segment of the historical actual tool path trajectory after superposition, determine the sub-segment trajectory with an overlap degree higher than a preset threshold;

[0022] Deleting the first part of the predicted tool path trajectory corresponding to each part of the sub-segment trajectory, to obtain a first predicted tool path trajectory;

[0023] Determine whether there is a non-cutting tissue structure in the predicted tool path trajectory after deletion, if so, delete the second part of the predicted trajectory corresponding to the non-cutting tissue structure to obtain a second predicted tool path trajectory, otherwise use the first predicted tool path trajectory directly as the second predicted tool path trajectory;

[0024] The second predicted tool path trajectory is spliced ​​with the determined partial sub-segment trajectories to obtain the final tool path trajectory to be operated on.

[0025] Another embodiment of the present application provides a robot safety tool path trajectory planning system, the system comprising:

[0026] An acquisition module, used for acquiring a medical image set and a three-dimensional anatomical virtual model of a target patient including a lesion to be operated on;

[0027] A search module is used to determine the points on the surface of the lesion as the target surgical point set, and to search the historical actual surgical point set of the same type of surgery to be performed from the medical big database;

[0028] A determination module, used for determining a target patient's surface entry point to be operated on according to the historical entry point set;

[0029] A prediction module, for generating a predicted tool path trajectory of the surgical robot in the three-dimensional anatomical virtual model according to the surgical entry point to be operated and the target surgical point set, using a pre-trained artificial intelligence model, wherein the predicted tool path trajectory connects the surgical entry point to be operated and the target surgical point set;

[0030] The planning module is used to plan the final tool path trajectory to be operated on according to the predicted tool path trajectory and a historical actual tool path trajectory set of the same type of operation to be operated on.

[0031] Yet another embodiment of the present application provides a storage medium, wherein the storage medium stores a computer program, wherein the computer program is configured to execute any of the above methods when running.

[0032] Yet another embodiment of the present application provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute any of the methods described above.

[0033] Compared with the prior art, the present invention provides a method for planning safe tool path trajectories of a robot, which obtains a medical image set containing a lesion to be operated on and a three-dimensional anatomical virtual model of a target patient; determines points on the surface of the lesion as a target surgical point set, and searches a medical big data database for a historical actual entry point set of the same type of surgery to be performed; determines the entry points to be operated on the surface of the target patient based on the historical entry point set; generates a predicted tool path trajectory of the surgical robot in the three-dimensional anatomical virtual model based on the entry points to be operated on and the target surgical point set using a pre-trained artificial intelligence model; plans the final tool path trajectory to be operated based on the predicted tool path trajectory and the historical actual tool path trajectory set of the same type of surgery to be performed, thereby being able to perform intelligent tool path planning personalized for the patient's anatomical features, and effectively absorb and utilize past surgical experience to ensure the safety and effectiveness of the operation. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 A hardware structure block diagram of a computer terminal for a robot safety tool path trajectory planning method provided by an embodiment of the present invention;

[0035] Figure 2 A schematic diagram of a flow chart of a robot safe tool path trajectory planning method provided by an embodiment of the present invention;

[0036] Figure 3 A schematic diagram of the structure of a robot safe tool path trajectory planning system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0037] The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, but should not be construed as limiting the present invention.

[0038] The embodiment of the present invention firstly provides a robot safe tool path trajectory planning method, which can be applied to electronic devices such as computer terminals, specifically ordinary computers, etc.

[0039] The following describes it in detail by taking running on a computer terminal as an example. Figure 1 The hardware structure block diagram of a computer terminal of a robot safety tool path trajectory planning method provided by an embodiment of the present invention. Figure 1 As shown, the computer terminal may include one or more ( Figure 1 Only one is shown in the figure) a processor 102 (the processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 104 for storing data. Optionally, the computer terminal may also include a transmission device 106 for communication functions and an input and output device 108. It can be understood by those skilled in the art that Figure 1The structure shown is only for illustration and does not limit the structure of the above-mentioned computer terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations are shown.

[0040] The memory 104 can be used to store software programs and modules of application software, such as program instructions / modules corresponding to the robot safety tool path trajectory planning method in the embodiment of the present application. The processor 102 executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0041] The transmission device 106 is used to receive or send data via a network. The specific example of the above network may include a wireless network provided by a communication provider of a computer terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0042] See also Figure 2 , an embodiment of the present invention provides a robot safety tool path trajectory planning method, which may include the following steps:

[0043] S201, obtaining a medical image set and a three-dimensional anatomical virtual model of a target patient including a lesion to be operated on;

[0044] In this step, it is first necessary to obtain the relevant medical imaging data of the target patient and the three-dimensional anatomical virtual model based on these imaging data. The key to this process lies in the accurate understanding of the internal structure of the patient's body, especially the specific location of the lesion to be operated on and the identification of the surrounding anatomical structures. Medical image sets usually include different types of images, such as CT (computed tomography), MRI (magnetic resonance imaging), etc. These images can provide important visual and spatial information for subsequent surgical planning.

[0045] The main purpose of acquiring medical image sets and 3D anatomical virtual models is to provide accurate anatomical background for surgical path planning. With clear image data, surgeons can accurately identify the lesion to be operated on and clarify the relationship between surrounding tissues, thereby formulating safer and more effective surgical strategies. This process not only improves the visualization level of surgery, but also provides basic data support for subsequent artificial intelligence model training, further enhancing the accuracy of path planning.

[0046] Specifically, image data can be obtained from multimodal imaging devices (CT, MRI, etc.) of the target patient, and image registration can be performed using professional image processing software. Image processing technology can ensure that images from different sources are accurately aligned in space to facilitate subsequent information fusion.

[0047] Deep learning segmentation algorithms (such as U-Net) can be applied to process image data to identify the lesion to be operated on and its surrounding anatomical structures. The algorithm classifies the image at the pixel level, and finally obtains the contours of the lesion area and its adjacent important anatomical structures to ensure the accuracy and consistency of the segmentation.

[0048] The lesion and anatomical structure information obtained in the above steps are reconstructed in volume, and a three-dimensional anatomical virtual model is generated using stereo modeling technology (such as the Marching Cubes algorithm). This model should accurately reflect the patient's anatomical characteristics, including the shape, size and location of the lesion, and combine the spatial relationship of adjacent tissues and organs to provide visualization support for surgery.

[0049] The data of the 3D model is optimized, and the computational efficiency and visual quality of the model are improved through mesh simplification and refinement technology. At the same time, redundant noise points and unnecessary details are removed to ensure the accuracy and operability of the final model. Verification is performed on the generated 3D anatomical virtual model, combined with the professional experience of the surgeon to ensure the accuracy and authenticity of the model. Virtual reality technology can be used to allow the surgeon to interact with the model to further confirm the relationship between the lesion location and the surrounding tissue, and ensure the reliability of subsequent tool path planning.

[0050] The integrated medical image set and 3D anatomical virtual model are stored in the cloud database for easy access and sharing. This process also provides the necessary data foundation for subsequent artificial intelligence model training, tool path trajectory planning and surgical auxiliary decision-making.

[0051] Through the above methods, the medical image set and 3D anatomical virtual model of the target patient containing the lesion to be operated on can be successfully obtained. This process not only ensures the accuracy and completeness of the data, but also lays a solid foundation for the subsequent safe surgical path planning. By combining advanced image processing technology with deep learning algorithms, the intelligence and personalization level of robotic surgery has been significantly improved, ultimately promoting the accuracy and safety of surgical operations.

[0052] S202, determining points on the surface of the lesion as a target surgical point set, and searching a historical actual surgical point set of the same type of surgery to be performed from a large medical database;

[0053] In this step, the key points on the lesion surface need to be determined by analyzing the patient's 3D anatomical virtual model. These points will be considered as the target surgical point set. The target surgical point is usually the ideal location for surgical operations on the lesion surface, ensuring that the surgeon can effectively access and treat the lesion. At the same time, it is also necessary to search the medical big data database for the historical actual entry point set of the same type of surgery in the past, that is, the point where the surgeon chose to enter the patient's body when performing similar operations, to help build a reference for surgical planning.

[0054] The process of clarifying the target surgical point and finding the actual historical entry point is crucial to the success of surgical operations. Clarifying the location of the lesion surface provides a direct basis for the operation, while the analysis of historical entry points accumulates valuable experience for finding the best entry path. In this way, doctors can not only improve the safety of the operation and reduce damage to surrounding normal tissues, but also optimize the surgical plan with the help of historical data to ensure the efficiency and success of the operation.

[0055] Specifically, 3D reconstruction technology can be used to construct a clear 3D anatomical model from the acquired medical imaging data. Then, image processing algorithms, such as deep learning models based on graph convolutional networks (GCNs), are used to segment the lesion area and accurately identify the feature points on the lesion surface. These feature points will serve as preliminary target surgical points.

[0056] The extracted feature points on the lesion surface (i.e., the preliminary target surgical points) are converted into point cloud data. Clustering algorithms (such as DBSCAN) can be used to process the point cloud data to extract meaningful feature points and filter out noise and irrelevant points. At the same time, normal calculation and curvature analysis can be used to evaluate the importance of each point in terms of geometry to ensure that the target surgical points finally selected have the best contact conditions when achieving the surgical goal.

[0057] It can access a large medical database and use a content-based retrieval system to extract the actual entry point related to the current lesion type and location from historical surgical records. By dynamically annotating historical data, it ensures that it can accurately match the current surgical type.

[0058] S203, determining the surgical entry point to be operated on the surface of the target patient according to the historical surgical entry point set;

[0059] Specifically, a historical lesion location whose distance from the center of the lesion location to be operated on is less than a preset distance may be searched from a set of historical lesion locations of the same type to be operated on in a medical big data database;

[0060] This process aims to find lesion locations similar to the target patient's lesion to be operated on by analyzing historical cases. A large amount of historical case data, including the spatial location of the lesion and the corresponding entry point, is stored in the medical big data database. By calculating the distance, the historical lesion locations that are similar to the current lesion characteristics can be screened out to ensure the reference value of the selected entry point. By using the existing case data, empirical support in medical practice is provided. By comparison, based on similar lesions, the possible entry point for surgery at the current lesion location can be better predicted, reducing surgical risks and improving the success rate of surgery.

[0061] Determine the historical cutting points corresponding to the positions of the historical lesions, and draw circles for the determined historical cutting points so that the drawn circles include the most historical cutting points;

[0062] Once the locations of historical lesions similar to the target lesion are determined, the next step is to find the historical entry points of these lesions. Using the "circle drawing" method, these entry points are aggregated together to form a circular area that contains as many entry points as possible, with the goal of finding a reasonable area that can cover multiple entry points. This method increases the flexibility and rationality of selecting entry points by aggregating similar entry points. Ensure that the selected entry points are statistically reliable, can reflect the successful experience of historical surgery, and reduce errors and risks.

[0063] The center of the drawn circle is calculated as the surgical entry point on the target patient's surface.

[0064] The last step is to calculate the center of the circle, which is the selected entry point for surgery. This is a point with spatial significance that can be used as the starting point for surgery, through which the lesion area can be entered. By calculating the center of the circle, the entry point obtained through historical data analysis is rationalized into a specific location to ensure that surgeons have clear guidance when making surgical plans. This data-driven approach can effectively improve the accuracy of surgery, reduce unnecessary complexity in surgery, and provide patients with a safer surgical experience.

[0065] The above steps systematically determine the target patient's surgical entry point by combining historical case data with geometric analysis. This process not only relies on the statistical characteristics of historical data, but also integrates scientific calculation methods, providing a solid foundation for subsequent surgical planning. In this way, the safety and effectiveness of the operation can be more effectively guaranteed.

[0066] S204, generating a predicted tool path trajectory of the surgical robot in the three-dimensional anatomical virtual model according to the tool entry point to be operated on and the target surgical point set using a pre-trained artificial intelligence model, wherein the predicted tool path trajectory connects the tool entry point to be operated on and the target surgical point set;

[0067] This step aims to improve the operating accuracy of surgical robots and reduce damage to normal tissues through the application of machine learning and intelligent algorithms. The generated predicted tool path provides surgeons with intuitive surgical path planning, enabling them to better control the robot during the operation and optimize the surgical effect. This method can increase the safety of surgery, improve postoperative recovery rates, and reduce the risk of postoperative complications for patients.

[0068] Specifically, a partial anatomical virtual model data set related to the lesion to be operated on may be obtained in the three-dimensional anatomical virtual model;

[0069] This process involves extracting partial data sets related to the lesion to be operated on from the overall three-dimensional anatomical virtual model. These data sets include important anatomical structure information around the lesion, such as blood vessels, nerves and other important tissues. Obtaining relevant partial anatomical model data can help the artificial intelligence model understand the anatomical environment around the lesion more accurately and reduce potential surgical risks. Ensure that the surgical path does not conflict with key anatomical structures and improve the safety and effectiveness of the operation.

[0070] A graphics-based region growing algorithm can be used to automatically extract partial data related to the lesion to be operated on from the overall three-dimensional anatomical model. The algorithm first places a seed point at the location of the lesion to be operated on, and then expands in adjacent voxels based on similarity thresholds (such as color, density, texture, etc.). Through continuous growth, a region containing the lesion and its surrounding related anatomical structures is eventually formed to ensure that the extracted data set covers all key anatomical features that may affect the surgical path.

[0071] The surgical entry point to be operated on, the target surgical point set and the partial anatomical virtual model data set are input into a pre-trained artificial intelligence model to generate a predicted tool path trajectory of the surgical robot in the partial anatomical virtual model, wherein the artificial intelligence model is trained based on historical surgical entry points, historical target surgical point sets, historical actual tool path trajectories and corresponding historical partial anatomical virtual model data sets, and the historical actual tool path trajectory is an artificial actual tool path trajectory, and the historical partial anatomical virtual model data set is the smallest partial anatomical virtual model that includes the historical actual tool path trajectory.

[0072] In this step, the surgical entry point, target surgical point set and part of the anatomical virtual model data set are input into the pre-trained artificial intelligence model. The model uses historical data for learning in order to predict the tool path trajectory. By analyzing the input data, the model will calculate an optimal tool path trajectory. Through a data-driven approach, the optimal tool path is provided for robotic surgery. The model is trained based on the experience of historical surgeries, which can effectively reduce the risk of accidents during surgery and greatly improve the accuracy and repeatability of surgery. This AI-based trajectory prediction can help surgeons achieve higher surgical standards and optimize the overall surgical effect.

[0073] Graph Neural Network (GNN) can be used to process some of the extracted anatomical model data sets. By building a graph structure, the entry point to be operated, the target surgical point, and the anatomical feature nodes are connected. The graph convolution layer is used to extract the feature information of the graph nodes and capture their relationship and mutual influence in space. Through the head attention mechanism, the model can better focus on those tool path patterns that show a high success rate in historical data and generate corresponding predicted tool path trajectories.

[0074] S205 , planning a final tool path trajectory for the surgery to be performed according to the predicted tool path trajectory and a set of historical actual tool path trajectories for the same type of surgery to be performed.

[0075] The purpose of this step is to compare and fuse the generated predicted tool path with historical data to ensure that the final surgical tool path is consistent with historical successful cases and can adapt to the specific conditions of the current patient. By analyzing the historical actual tool path set, it is possible to identify which paths are safer and more effective in similar cases. This process usually includes screening, segmenting, and superimposing historical data, as well as optimizing the path according to anatomical features to find the best surgical implementation plan.

[0076] By comparing and fusing the predicted tool path with the historical actual tool path, this step can effectively reduce the risks that may occur during surgery and improve the robustness and reliability of the system. It ensures that the final tool path not only takes into account the specific lesion conditions of the patient, but also draws on the experience of historical successful surgeries, thereby improving the safety and success rate of the surgery. This comprehensive consideration helps surgeons make more informed decisions during operations and optimizes the patient's surgical experience.

[0077] Specifically, the historical actual tool path trajectory corresponding to the historical lesion position whose distance from the center of the lesion position to be operated on is less than a preset distance may be screened from the historical actual tool path trajectory set of the same type of surgery to be operated on;

[0078] This step aims to find the actual tool path corresponding to the historical lesion in the vicinity of the surgical lesion through distance screening. By setting a distance threshold, surgical paths performed under similar anatomical conditions can be effectively screened for reference. The implementation of this process makes the selected historical tool path more relevant, which helps to improve the scientific nature of surgical path selection and avoid the risks caused by selecting irrelevant historical data.

[0079] The selected historical actual tool path trajectories are segmented according to the anatomical tissue type, and each segment of the historical actual tool path trajectories is correspondingly superimposed;

[0080] In this step, by segmenting the historical tool path trajectory, the specific anatomical features of each segment can be better analyzed and processed. Through superposition processing, the overlapping parts of different trajectories in the same anatomical area will be highlighted for subsequent analysis. In this way, critical tissue structures and potential risk areas can be identified to better optimize the surgical tool path.

[0081] For example, 10 historical actual tool path trajectories are screened out, and each historical actual tool path trajectory is divided into 5 segments. Then, the first segment of the 10 historical actual tool path trajectories is superimposed, and the second segment of the 10 historical actual tool path trajectories is superimposed, until the fifth segment of the 10 historical actual tool path trajectories is superimposed.

[0082] For each segment of the historical actual tool path trajectory after superposition, determine the sub-segment trajectory with an overlap degree higher than a preset threshold;

[0083] In this step, by setting the overlap threshold, the tool path trajectories that show high consistency in historical surgeries can be identified. This process helps determine which tool paths are more reliable choices. By focusing on parts with high overlap, unreliable tool paths can be effectively excluded, thereby increasing the certainty of the optimal tool path.

[0084] Deleting the first part of the predicted tool path trajectory corresponding to each part of the sub-segment trajectory, to obtain a first predicted tool path trajectory;

[0085] The corresponding first part of the predicted trajectory is deleted in order to replace the sub-trajectories with higher overlap later, thereby optimizing the safety of the tool path and ensuring that the surgical path remains consistent with the known successful cases in the highly overlapping parts.

[0086] Determine whether there is a non-cutting tissue structure in the predicted tool path trajectory after deletion, if so, delete the second part of the predicted trajectory corresponding to the non-cutting tissue structure to obtain a second predicted tool path trajectory, otherwise use the first predicted tool path trajectory directly as the second predicted tool path trajectory;

[0087] This step ensures that the final knife path matches the target anatomical structure and avoids non-cutting tissue (critical tissue structure that must be avoided) to improve the safety of the surgical process. Through this judgment, it can effectively prevent the wrong area from being cut during the operation and protect the patient's normal tissue structure.

[0088] The second predicted tool path trajectory is spliced ​​with the determined partial sub-segment trajectories to obtain the final tool path trajectory to be operated on.

[0089] The last step is to combine the optimized tool path with each sub-segment trajectory to form a complete surgical tool path. This makes the tool path not only safe and effective, but also highly consistent with the historical experience and actual needs of the surgery, ensuring that the final tool path can achieve the purpose of the surgery while maintaining safety and improving the operability of the surgery.

[0090] For example, a "path smoothing algorithm" such as B-spline interpolation can be used to consider potential smoothness and continuity during the splicing process to avoid unnecessary turns in the tool path. This method ensures the smoothness and naturalness of the final tool path by controlling the position information of the splicing points, thereby improving the operating accuracy and stability of the robot scalpel.

[0091] It can be seen that a medical image set and a three-dimensional anatomical virtual model of the target patient containing the lesion to be operated on are obtained; points on the surface of the lesion are determined as the target surgical point set, and a historical actual entry point set of the same type of surgery to be operated on is searched from the medical big data database; based on the historical entry point set, the entry point to be operated on the surface of the target patient is determined; based on the entry point to be operated on and the target surgical point set, a pre-trained artificial intelligence model is used to generate a predicted tool path trajectory of the surgical robot in the three-dimensional anatomical virtual model; based on the predicted tool path trajectory and the historical actual tool path trajectory set of the same type of surgery to be operated on, the final tool path trajectory to be operated is planned, so that intelligent tool path planning can be performed according to the patient's anatomical characteristics in a personalized manner, and previous surgical experience can be effectively absorbed and utilized to ensure the safety and effectiveness of the operation.

[0092] Another embodiment of the present invention provides a robot safety tool path trajectory planning system, see Figure 3 , the system may include:

[0093] An acquisition module 301 is used to acquire a medical image set and a three-dimensional anatomical virtual model of a target patient including a lesion to be operated on;

[0094] Search module 302, used to determine the points on the surface of the lesion as the target surgical point set, and search the historical actual surgical point set of the same type of surgery to be performed from the medical big database;

[0095] A determination module 303 is used to determine the target patient's surface entry point to be operated on according to the historical entry point set;

[0096] A prediction module 304 is used to generate a predicted tool path trajectory of the surgical robot in the three-dimensional anatomical virtual model according to the entry point to be operated and the target surgical point set using a pre-trained artificial intelligence model, wherein the predicted tool path trajectory connects the entry point to be operated and the target surgical point set;

[0097] The planning module 305 is used to plan the final tool path trajectory to be operated on according to the predicted tool path trajectory and a set of historical actual tool path trajectories of the same type of operation to be operated on.

[0098] It can be seen that a medical image set and a three-dimensional anatomical virtual model of the target patient containing the lesion to be operated on are obtained; points on the surface of the lesion are determined as the target surgical point set, and a historical actual entry point set of the same type of surgery to be operated on is searched from the medical big data database; based on the historical entry point set, the entry point to be operated on the surface of the target patient is determined; based on the entry point to be operated on and the target surgical point set, a pre-trained artificial intelligence model is used to generate a predicted tool path trajectory of the surgical robot in the three-dimensional anatomical virtual model; based on the predicted tool path trajectory and the historical actual tool path trajectory set of the same type of surgery to be operated on, the final tool path trajectory to be operated is planned, so that intelligent tool path planning can be performed according to the patient's anatomical characteristics in a personalized manner, and previous surgical experience can be effectively absorbed and utilized to ensure the safety and effectiveness of the operation.

[0099] An embodiment of the present invention further provides a storage medium, in which a computer program is stored, wherein the computer program is configured to execute the steps of any of the above method embodiments when running.

[0100] Specifically, in this embodiment, the above storage medium may be configured to store a computer program for performing the following steps:

[0101] S201, obtaining a medical image set and a three-dimensional anatomical virtual model of a target patient including a lesion to be operated on;

[0102] S202, determining points on the surface of the lesion as a target surgical point set, and searching a historical actual surgical point set of the same type of surgery to be performed from a large medical database;

[0103] S203, determining the surgical entry point to be operated on the surface of the target patient according to the historical surgical entry point set;

[0104] S204, generating a predicted tool path trajectory of the surgical robot in the three-dimensional anatomical virtual model according to the tool entry point to be operated on and the target surgical point set using a pre-trained artificial intelligence model, wherein the predicted tool path trajectory connects the tool entry point to be operated on and the target surgical point set;

[0105] S205 , planning a final tool path trajectory for the surgery to be performed according to the predicted tool path trajectory and a set of historical actual tool path trajectories for the same type of surgery to be performed.

[0106] It can be seen that a medical image set and a three-dimensional anatomical virtual model of the target patient containing the lesion to be operated on are obtained; points on the surface of the lesion are determined as the target surgical point set, and a historical actual entry point set of the same type of surgery to be operated on is searched from the medical big data database; based on the historical entry point set, the entry point to be operated on the surface of the target patient is determined; based on the entry point to be operated on and the target surgical point set, a pre-trained artificial intelligence model is used to generate a predicted tool path trajectory of the surgical robot in the three-dimensional anatomical virtual model; based on the predicted tool path trajectory and the historical actual tool path trajectory set of the same type of surgery to be operated on, the final tool path trajectory to be operated is planned, so that intelligent tool path planning can be performed according to the patient's anatomical characteristics in a personalized manner, and previous surgical experience can be effectively absorbed and utilized to ensure the safety and effectiveness of the operation.

[0107] An embodiment of the present invention further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0108] Specifically, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0109] Specifically, in this embodiment, the processor may be configured to perform the following steps through a computer program:

[0110] S201, obtaining a medical image set and a three-dimensional anatomical virtual model of a target patient including a lesion to be operated on;

[0111] S202, determining points on the surface of the lesion as a target surgical point set, and searching a historical actual surgical point set of the same type of surgery to be performed from a large medical database;

[0112] S203, determining the surgical entry point to be operated on the surface of the target patient according to the historical surgical entry point set;

[0113] S204, generating a predicted tool path trajectory of the surgical robot in the three-dimensional anatomical virtual model according to the tool entry point to be operated on and the target surgical point set using a pre-trained artificial intelligence model, wherein the predicted tool path trajectory connects the tool entry point to be operated on and the target surgical point set;

[0114] S205 , planning a final tool path trajectory for the surgery to be performed according to the predicted tool path trajectory and a set of historical actual tool path trajectories for the same type of surgery to be performed.

[0115] It can be seen that a medical image set and a three-dimensional anatomical virtual model of the target patient containing the lesion to be operated on are obtained; points on the surface of the lesion are determined as the target surgical point set, and a historical actual entry point set of the same type of surgery to be operated on is searched from the medical big data database; based on the historical entry point set, the entry point to be operated on the surface of the target patient is determined; based on the entry point to be operated on and the target surgical point set, a pre-trained artificial intelligence model is used to generate a predicted tool path trajectory of the surgical robot in the three-dimensional anatomical virtual model; based on the predicted tool path trajectory and the historical actual tool path trajectory set of the same type of surgery to be operated on, the final tool path trajectory to be operated is planned, so that intelligent tool path planning can be performed according to the patient's anatomical characteristics in a personalized manner, and previous surgical experience can be effectively absorbed and utilized to ensure the safety and effectiveness of the operation.

[0116] The above describes in detail the structure, features and effects of the present invention based on the embodiments shown in the drawings. The above is only a preferred embodiment of the present invention, but the present invention is not limited to the scope of implementation shown in the drawings. Any changes made according to the concept of the present invention, or modifications to equivalent embodiments with equivalent changes, which still do not exceed the spirit covered by the description and drawings, should be within the protection scope of the present invention.

Claims

1. A robot safe tool path trajectory planning method, characterized in that: The method comprises: Obtaining a medical image set and a three-dimensional anatomical virtual model of a target patient including a lesion to be operated on; Determine the points on the lesion surface as the target surgical point set, and search the historical actual surgical point set of the same type of surgery from the medical big data database; Determining the surgical entry point on the surface of the target patient according to the historical entry point set; According to the entry point to be operated and the target surgical point set, a predicted tool path trajectory of the surgical robot is generated in the three-dimensional anatomical virtual model using a pre-trained artificial intelligence model, wherein the predicted tool path trajectory connects the entry point to be operated and the target surgical point set; The final tool path trajectory to be operated is planned according to the predicted tool path trajectory and a historical actual tool path trajectory set of the same type of operation to be operated.

2. The method according to claim 1, characterized in that Determining the surgical entry point on the surface of the target patient to be operated on according to the historical surgical entry point set includes: From a set of historical lesion locations of the same type to be operated on in a medical big data database, find a historical lesion location whose distance from the center of the lesion to be operated on is less than a preset distance; Determine the historical cutting points corresponding to the positions of the historical lesions, and draw circles for the determined historical cutting points so that the drawn circles include the most historical cutting points; The center of the drawn circle is calculated as the surgical entry point on the target patient's surface.

3. The method according to claim 2, characterized in that The method of generating a predicted tool path trajectory of a surgical robot in the three-dimensional anatomical virtual model based on the surgical entry point to be operated and the target surgical point set by using a pre-trained artificial intelligence model includes: In the three-dimensional anatomical virtual model, a partial anatomical virtual model data set related to the lesion to be operated on is obtained; The surgical entry point to be operated on, the target surgical point set and the partial anatomical virtual model data set are input into a pre-trained artificial intelligence model to generate a predicted tool path trajectory of the surgical robot in the partial anatomical virtual model, wherein the artificial intelligence model is trained based on historical surgical entry points, historical target surgical point sets, historical actual tool path trajectories and corresponding historical partial anatomical virtual model data sets, and the historical actual tool path trajectory is an artificial actual tool path trajectory, and the historical partial anatomical virtual model data set is the smallest partial anatomical virtual model that includes the historical actual tool path trajectory.

4. The method according to claim 3, characterized in that The method of planning a final tool path trajectory to be operated on according to the predicted tool path trajectory and a historical actual tool path trajectory set of the same type of operation to be operated on comprises: From the historical actual tool path trajectory set of the same type of surgery to be performed, the historical actual tool path trajectory corresponding to the historical lesion position whose distance from the center of the lesion position to be operated on is less than a preset distance is selected; The screened historical actual tool path trajectories are segmented according to the anatomical tissue type, and each segment of the historical actual tool path trajectories is correspondingly superimposed; For each segment of the historical actual tool path trajectory after superposition, determine the sub-segment trajectory with an overlap degree higher than a preset threshold; Deleting the first part of the predicted tool path trajectory corresponding to each part of the sub-segment trajectory, to obtain a first predicted tool path trajectory; Determine whether there is a non-cutting tissue structure in the predicted tool path trajectory after deletion, if so, delete the second part of the predicted trajectory corresponding to the non-cutting tissue structure to obtain a second predicted tool path trajectory, otherwise use the first predicted tool path trajectory directly as the second predicted tool path trajectory; The second predicted tool path trajectory is spliced ​​with the determined partial sub-segment trajectories to obtain the final tool path trajectory to be operated on.

5. A robot safe tool path trajectory planning system, characterized in that: The system comprises: An acquisition module, used for acquiring a medical image set and a three-dimensional anatomical virtual model of a target patient including a lesion to be operated on; A search module is used to determine the points on the surface of the lesion as the target surgical point set, and to search the historical actual surgical point set of the same type of surgery to be performed from the medical big database; A determination module, used for determining a target patient's surface entry point to be operated on according to the historical entry point set; A prediction module, for generating a predicted tool path trajectory of the surgical robot in the three-dimensional anatomical virtual model according to the entry point to be operated and the target surgical point set, using a pre-trained artificial intelligence model, wherein the predicted tool path trajectory connects the entry point to be operated and the target surgical point set; The planning module is used to plan the final tool path trajectory to be operated on according to the predicted tool path trajectory and a historical actual tool path trajectory set of the same type of operation to be operated on.

6. The system according to claim 5, characterized in that The determination module is specifically used for: From a set of historical lesion locations of the same type to be operated on in a medical big data database, find a historical lesion location whose distance from the center of the lesion to be operated on is less than a preset distance; Determine the historical cutting points corresponding to the positions of the historical lesions, and draw circles for the determined historical cutting points so that the drawn circles include the most historical cutting points; The center of the drawn circle is calculated as the surgical entry point on the target patient's surface.

7. The system according to claim 6, characterized in that The prediction module is specifically used for: In the three-dimensional anatomical virtual model, a partial anatomical virtual model data set related to the lesion to be operated on is obtained; The surgical entry point to be operated on, the target surgical point set and the partial anatomical virtual model data set are input into a pre-trained artificial intelligence model to generate a predicted tool path trajectory of the surgical robot in the partial anatomical virtual model, wherein the artificial intelligence model is trained based on historical surgical entry points, historical target surgical point sets, historical actual tool path trajectories and corresponding historical partial anatomical virtual model data sets, and the historical actual tool path trajectory is an artificial actual tool path trajectory, and the historical partial anatomical virtual model data set is the smallest partial anatomical virtual model that includes the historical actual tool path trajectory.

8. The system according to claim 7, characterized in that The planning module is specifically used for: From the historical actual tool path trajectory set of the same type of surgery to be performed, the historical actual tool path trajectory corresponding to the historical lesion position whose distance from the center of the lesion position to be operated on is less than a preset distance is selected; The screened historical actual tool path trajectories are segmented according to the anatomical tissue type, and each segment of the historical actual tool path trajectories is correspondingly superimposed; For each segment of the historical actual tool path trajectory after superposition, determine the sub-segment trajectory with an overlap degree higher than a preset threshold; Deleting the first part of the predicted tool path trajectory corresponding to each part of the sub-segment trajectory, to obtain a first predicted tool path trajectory; Determine whether there is a non-cutting tissue structure in the predicted tool path trajectory after deletion, if so, delete the second part of the predicted trajectory corresponding to the non-cutting tissue structure to obtain a second predicted tool path trajectory, otherwise use the first predicted tool path trajectory directly as the second predicted tool path trajectory; The second predicted tool path trajectory is spliced ​​with the determined partial sub-segment trajectories to obtain the final tool path trajectory to be operated on.

9. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program is configured to execute the method according to any one of claims 1 to 4 when executed.

10. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to perform the method according to any one of claims 1 to 4.

Images