Percutaneous puncture accurate dynamic matching and navigation method and system based on AI surgical robot

Abstract

The invention provides a percutaneous puncture accurate dynamic matching and navigation method and system based on an AI surgical robot, and the method comprises the steps: obtaining a preoperative medical image, and generating surgical planning data based on the medical image; determining an ablation path and an ablation area according to the surgical planning data; puncture operation is executed through the robot system, and ablation treatment of the target area is completed; the step S3 further comprises the steps of obtaining real-time image data in the operation for multiple times, and dynamically adjusting the ablation path and the ablation parameters in real time based on the real-time image data in the operation each time. The method comprises the following steps: acquiring and analyzing preoperative and intraoperative medical image data of a patient to generate puncture positioning and navigation puncture schemes in different stages; the purpose of capturing tissue deformation in real time in percutaneous puncture is achieved, the purpose of dynamically optimizing the puncture path is further achieved based on the tissue deformation state captured in real time, the motion trail of the robot is adjusted in real time based on real-time generation of the dynamic puncture path, and therefore the precise navigation and dynamic matching degree of the percutaneous puncture operation is improved, and the accuracy of the percutaneous puncture operation is improved. And the purpose of precise puncture is achieved.

Description

Technical Field

[0001] The present invention relates to the field of percutaneous puncture guidance and positioning technology based on an AI surgical robot, and in particular to a percutaneous puncture precise dynamic matching and navigation method and system based on an AI surgical robot. Background Art

[0002] Percutaneous surgery, a key technology in minimally invasive medicine, plays a crucial role in treatments such as tumor ablation due to its precision and minimal trauma. Precise navigation and dynamic adjustment capabilities directly determine the safety and efficacy of surgery. However, existing methods often exhibit limitations when faced with complex tissue environments. Traditional navigation systems rely on static preoperative imaging and struggle to adapt to intraoperative tissue deformation and displacement, resulting in deviations in the puncture path and incomplete coverage of the ablation area.

[0003] In actual clinical practice, the contradiction between tissue deformation and real-time intraoperative navigation becomes a core challenge. During surgery, tissue deforms due to breathing, changes in patient position, or the action of the instrument, causing the pre-operatively planned puncture path to lose its accuracy. This deformation not only affects the spatial parameters of the path, but also places higher demands on the real-time update of the robot's motion trajectory. If the deformation cannot be accurately captured and the path cannot be dynamically adjusted, the ablation needle may deviate from the target area, resulting in poor treatment effect.

[0004] Therefore, how to capture tissue deformation in real time during surgery and dynamically optimize the puncture path and robot motion trajectory has become a key issue in the precise navigation and dynamic matching of percutaneous puncture surgery. Summary of the Invention

[0005] The present invention provides a method and system for precise dynamic matching and navigation of percutaneous puncture based on an AI surgical robot, which is used to realize real-time capture of tissue deformation during percutaneous puncture, and further realize the purpose of dynamic optimization of the puncture path based on the real-time captured tissue deformation state. Based on the real-time generation of the dynamic puncture path, the robot's motion trajectory is adjusted in real time, thereby improving the precise navigation and dynamic matching of percutaneous puncture surgery and achieving the purpose of precise puncture.

[0006] The present invention provides a percutaneous puncture precise dynamic matching and navigation method based on an AI surgical robot, comprising:

[0007] S1, obtaining preoperative medical images and generating surgical planning data based on the medical images;

[0008] S2, determine the ablation path and ablation area based on the surgical planning data;

[0009] S3, the robot system performs the puncture operation to complete the ablation treatment of the target area;

[0010] Wherein, step S3 further includes: acquiring intraoperative real-time image data multiple times, and dynamically adjusting the ablation path and ablation parameters in real time based on each intraoperative real-time image data.

[0011] Preferably, preoperative imaging data of the patient is obtained, and a three-dimensional model of the lesion area is constructed based on the preoperative imaging data, and initial surgical planning data is generated using the three-dimensional model of the lesion area;

[0012] The initial surgical planning data is used to calculate the spatial parameters of the puncture path, and the target area coverage effect is verified through simulation; the robot joint motion trajectory corresponding to the puncture path is calculated and the puncture operation is controlled and executed; during the puncture process, real-time tissue images are acquired and registered with the three-dimensional model to determine the tissue deformation state; if tissue deformation exists, the spatial parameters of the puncture path are recalculated based on the registration results and the robot motion trajectory is updated;

[0013] The three-dimensional model is simulated and analyzed, and the expansion range of the ablation area is predicted based on the simulation analysis results and the initial surgical planning data is adjusted. When multiple needle punctures are performed, the motion control system is used to synchronously monitor the positioning accuracy of each puncture trajectory and dynamically correct the puncture parameters. After each path parameter adjustment, the finite element simulation verification and robot motion trajectory calculation are re-executed until the preset ablation coverage conditions are met.

[0014] Preferably, the patient's preoperative medical image data is obtained, and the lesion location and tissue characteristics are determined based on the medical image data; a three-dimensional model is constructed according to the lesion location and tissue characteristics; and surgical planning data is generated through the three-dimensional model, wherein the surgical planning data is a surgical planning route.

[0015] Preferably, surgical planning parameters are obtained according to the surgical planning route, and the insertion position and angle of the ablation needle are calculated based on the parameters; the insertion position and angle are optimized so that the puncture path can cover the target area;

[0016] It also includes: verifying the coverage effect of the puncture path on the target area.

[0017] Preferably, the spatial coordinates of the robot joints are calculated based on the surgical planning data; the motion trajectory of the robot joints is determined using the spatial coordinates, and the robot is controlled according to the motion trajectory to accurately position the ablation needle and perform the puncture operation.

[0018] Preferably, real-time tissue images are acquired by an intraoperative image acquisition device, and tissue displacement or deformation information is acquired based on the real-time tissue images; and the ablation path and ablation parameters are adjusted according to the tissue displacement or deformation information.

[0019] Preferably, simulation analysis is performed on the medical image data, and the ablation effect is predicted based on the simulation results; the predicted ablation effect is used to assist in generating surgical planning data and optimizing the surgical plan.

[0020] Preferably, the trajectory of the ablation needle is controlled by a robot; a single-point multi-needle puncture operation is performed according to the trajectory of the ablation needle; and the puncture accuracy and stability are monitored in real time for the single-point multi-needle puncture operation.

[0021] Preferably, the intraoperative real-time image is compared with the preoperative model after image registration; based on the comparison results, the tissue changes are judged, and the ablation path and ablation parameters are dynamically adjusted according to the tissue change status.

[0022] The present invention also provides a percutaneous puncture precise dynamic matching and navigation system based on an AI surgical robot. The system utilizes a percutaneous puncture precise dynamic matching and navigation method based on an AI surgical robot to perform dynamic matching and navigation during percutaneous puncture surgery, and performs intelligent guidance for assisted percutaneous puncture surgery based on dynamic matching and navigation.

[0023] The working principle and beneficial effects of the present invention are as follows:

[0024] The present invention provides a precise dynamic matching and navigation method for percutaneous puncture based on an AI surgical robot, comprising: acquiring preoperative medical images and generating surgical planning data based on the medical images; determining the ablation path and ablation area according to the surgical planning data; performing the puncture operation through the robotic system to complete the ablation treatment of the target area; step S3 also includes: acquiring intraoperative real-time image data multiple times, and dynamically adjusting the ablation path and ablation parameters in real time based on each intraoperative real-time image data.

[0025] The present invention provides a method for precise dynamic matching and navigation of percutaneous puncture based on an AI surgical robot. The method generates puncture positioning and navigation schemes for different stages by collecting and analyzing medical image data of patients before and during surgery. The method realizes real-time capture of tissue deformation during percutaneous puncture, and further realizes dynamic optimization of the puncture path based on the real-time captured tissue deformation state. Based on the real-time generation of the dynamic puncture path, the robot's motion trajectory is adjusted in real time, thereby improving the precise navigation and dynamic matching of percutaneous puncture surgery and achieving the purpose of precise puncture.

[0026] The present invention also provides a percutaneous puncture precise dynamic matching and navigation system based on an AI surgical robot. The system utilizes a percutaneous puncture precise dynamic matching and navigation method based on an AI surgical robot to perform dynamic matching and navigation during percutaneous puncture surgery, and performs intelligent guidance for assisted percutaneous puncture surgery based on dynamic matching and navigation.

[0027] More specifically, the present invention utilizes the patient's preoperative medical images to construct a three-dimensional model of the lesion area, thereby generating initial surgical planning data, and then calculating the puncture path and robot motion trajectory using the initial surgical planning data.

[0028] During surgery, the present invention can acquire intraoperative images in real time and align them with the 3D model, determine tissue deformation, and dynamically adjust the ablation path and parameters. Simulation analysis can be used to predict the expansion of the ablation zone, thereby optimizing the surgical plan in real time. The robotic system precisely executes the puncture operation, allowing for real-time monitoring and achieving higher puncture accuracy.

[0029] The present invention realizes intelligent surgical planning and precise surgical execution, improves the safety and effectiveness of tumor ablation surgery, and provides technical support for personalized treatment of complex cases.

[0030] Other features and advantages of the present invention will be described in the following description, and in part will become apparent from the description, or will be understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0031] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0033] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0034] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0035] according to Figure 1 As shown, an embodiment of the present invention provides a percutaneous puncture precise dynamic matching and navigation method based on an AI surgical robot, comprising:

[0036] S1, obtaining preoperative medical images and generating surgical planning data based on the medical images;

[0037] S2, determine the ablation path and ablation area based on the surgical planning data;

[0038] S3, the robot system performs the puncture operation to complete the ablation treatment of the target area;

[0039] Wherein, step S3 further includes: acquiring intraoperative real-time image data multiple times, and dynamically adjusting the ablation path and ablation parameters in real time based on each intraoperative real-time image data.

[0040] Step S1 specifically includes: obtaining preoperative imaging data of the patient, constructing a three-dimensional model of the lesion area based on the preoperative imaging data, and generating initial surgical planning data using the three-dimensional model of the lesion area;

[0041] Step S2 specifically includes: using the initial surgical planning data to calculate the spatial parameters of the puncture path and verifying the target area coverage effect through simulation; calculating the robot joint motion trajectory corresponding to the puncture path and controlling the execution of the puncture operation; acquiring real-time tissue images during the puncture process and aligning them with the 3D model to determine the tissue deformation state; if tissue deformation exists, recalculating the puncture path spatial parameters based on the alignment results and updating the robot motion trajectory;

[0042] The three-dimensional model is simulated and analyzed, and the expansion range of the ablation area is predicted based on the simulation analysis results, and the initial surgical planning data is adjusted. When multiple needle punctures are performed, the motion control system is used to synchronously monitor the positioning accuracy of each puncture trajectory and dynamically correct the puncture parameters. After each path parameter adjustment, finite element simulation verification and robot motion trajectory calculation are re-executed until the preset ablation coverage conditions are met.

[0043] The present invention provides a method for precise dynamic matching and navigation of percutaneous puncture based on an AI surgical robot. The method generates puncture positioning and navigation schemes for different stages by collecting and analyzing medical image data of patients before and during surgery. The method realizes real-time capture of tissue deformation during percutaneous puncture, and further realizes dynamic optimization of the puncture path based on the real-time captured tissue deformation state. Based on the real-time generation of the dynamic puncture path, the robot's motion trajectory is adjusted in real time, thereby improving the precise navigation and dynamic matching of percutaneous puncture surgery and achieving the purpose of precise puncture.

[0044] More specifically, the present invention utilizes the patient's preoperative medical images to construct a three-dimensional model of the lesion area, thereby generating initial surgical planning data, and then calculating the puncture path and robot motion trajectory using the initial surgical planning data.

[0045] During surgery, the present invention can acquire intraoperative images in real time and align them with the 3D model, determine tissue deformation, and dynamically adjust the ablation path and parameters. Simulation analysis can be used to predict the expansion of the ablation zone, thereby optimizing the surgical plan in real time. The robotic system precisely executes the puncture operation, allowing for real-time monitoring and achieving higher puncture accuracy.

[0046] The present invention realizes intelligent surgical planning and precise surgical execution, improves the safety and effectiveness of tumor ablation surgery, and provides technical support for personalized treatment of complex cases.

[0047] The present invention also provides a percutaneous puncture precise dynamic matching and navigation system based on an AI surgical robot. The system utilizes a percutaneous puncture precise dynamic matching and navigation method based on an AI surgical robot to perform dynamic matching and navigation during percutaneous puncture surgery, and performs intelligent guidance for assisted percutaneous puncture surgery based on dynamic matching and navigation.

[0048] More specifically, the present invention utilizes the patient's preoperative medical images to construct a three-dimensional model of the lesion area, thereby generating initial surgical planning data, and then calculating the puncture path and robot motion trajectory using the initial surgical planning data.

[0049] During surgery, the present invention can acquire intraoperative images in real time and align them with the 3D model, determine tissue deformation, and dynamically adjust the ablation path and parameters. Simulation analysis can be used to predict the expansion of the ablation zone, thereby optimizing the surgical plan in real time. The robotic system precisely executes the puncture operation, allowing for real-time monitoring and achieving higher puncture accuracy.

[0050] The present invention realizes intelligent surgical planning and precise surgical execution, improves the safety and effectiveness of tumor ablation surgery, and provides technical support for personalized treatment of complex cases.

[0051] In one embodiment, Figure 1 As shown, the present invention provides a percutaneous puncture precise dynamic matching and navigation method based on an AI surgical robot, comprising:

[0052] A three-dimensional model of the lesion area is constructed using the patient's preoperative imaging data, and initial surgical planning data is generated; the spatial parameters of the puncture path are calculated based on the initial surgical planning data to verify the coverage of the target area; the inverse kinematics algorithm is used to calculate the robot joint motion trajectory corresponding to the puncture path, and the puncture operation is controlled; real-time tissue images are acquired and registered with the three-dimensional model to determine the tissue deformation state; if tissue deformation exists, the spatial parameters of the puncture path are recalculated based on the registration results, and the robot motion trajectory is updated; the three-dimensional model is simulated and analyzed to predict the expansion range of the ablation area and adjust the initial surgical planning data; the puncture parameters are dynamically corrected by monitoring the positioning accuracy of the puncture trajectory; verification and trajectory calculation are repeated until the preset ablation coverage conditions are met.

[0053] In this approach, preoperative patient imaging data is acquired and a 3D model of the lesion area is constructed using an image segmentation algorithm to generate initial surgical planning data. A geometric optimization algorithm is then used to calculate this initial planning data and determine the spatial parameters of the puncture path. Next, the target area coverage is verified to obtain a set of path parameters. This set of path parameters is then used to generate the robot's joint motion trajectory, which is then used to execute the puncture operation, resulting in the actual puncture trajectory.

[0054] Real-time tissue images are acquired and registered with the three-dimensional model of the lesion. If the registration deviation exceeds a preset threshold, tissue deformation is determined to exist, and deformation state data is obtained. The spatial parameters of the puncture path are recalculated using the deformation state data, and then the robot motion trajectory is updated to obtain the optimized trajectory data.

[0055] Finite element simulation analysis is used to predict the expansion range of the ablation area based on the three-dimensional model of the lesion. Based on this expansion range, the initial surgical planning data is further optimized to obtain adjusted planning data.

[0056] The positioning accuracy of the optimized trajectory data is monitored and optimized. If the deviation exceeds the preset threshold, the puncture parameters are dynamically adjusted and the verification is repeated until the ablation coverage conditions are met, and the final puncture plan is determined.

[0057] This embodiment provides the following examples to further illustrate the above technical solution: when obtaining the patient's preoperative imaging data, a 1mm slice thickness CT scan is used to obtain a 512×512 pixel DICOM format image, and the liver lesion area is extracted through a threshold segmentation algorithm for three-dimensional modeling; based on the established three-dimensional model, the system automatically generates an initial surgical plan containing 5 ablation targets, each with a diameter of 2-2.5mm and a number of targets of 6-8; the overlapping area is optimized using a sphere stacking algorithm, or the spatial arrangement of the targets is optimized using a greedy algorithm, so that the coverage rate of the ablation area over the lesion area exceeds 90%.

[0058] The puncture path was calculated by detecting collisions with blood vessels and bones using a ray casting method, with a safe path distance set to ≥5 mm. A respiratory motion model was introduced for Monte Carlo simulation, for example, using a sine function to simulate diaphragmatic motion. Monte Carlo simulations were validated 500 times, resulting in a target area coverage rate of 92±3% as measured by path sampling.

[0059] In this scheme, the inverse kinematics calculation is performed through the DH parameter model. Taking the 6-DOF manipulator as an example, the joint angle is calculated by the Jacobian matrix pseudo-inverse method. The puncture motion trajectory is obtained by using the fifth-order B-spline curve interpolation to calculate the motion angle. The position error of the puncture motion trajectory can be controlled within 0.1 mm.

[0060] During the operation, real-time imaging data on the lesion location is acquired. A lesion area model is built based on this data and registered with the preoperative model. Pathway replanning is triggered when liver displacement exceeding 3 mm is detected.

[0061] Finite element analysis based on a biomechanical model is used to calibrate the tensile modulus, distinguish normal liver tissue from the lesion area, and predict tissue deformation based on this, so as to achieve real-time updating of the puncture path inclination and depth. When aligning the lesion area model and the preoperative model, the lesion coverage rate is predicted. When the predicted coverage rate is lower than 85%, an auxiliary target is automatically added. When the cumulative error exceeds the preset threshold, a closed-loop control correction is triggered. During the process, iterative optimization is continuously carried out until the overlap rate between the predicted ablation volume of all targets and the lesion reaches ≥95% of the core area of ​​the lesion and the 5mm safety margin is ≥90%, thus meeting the ablation coverage conditions.

[0062] In one embodiment, Figure 1 As shown, the present invention provides a percutaneous puncture precise dynamic matching and navigation method based on an AI surgical robot, comprising:

[0063] Obtain the patient's preoperative imaging data, segment the preoperative imaging data, extract the lesion area features, and construct a three-dimensional model based on the lesion area features; determine the boundary and volume of the lesion area based on the three-dimensional model; use the boundary and volume to generate initial surgical planning data; wherein, the initial surgical planning data includes the puncture point location and puncture depth.

[0064] In this solution, preoperative image data is obtained from a medical imaging device and parsed using the DICOM format to obtain a first image dataset. The first image dataset is preprocessed using anisotropic diffusion filtering or non-local means filtering to obtain a second image dataset.

[0065] Among them, mean filtering denoising reduces noise by averaging the neighborhood pixel values, but it will blur the image edges, especially for low-contrast soft tissue lesions (such as liver tumors), which may lead to a decrease in segmentation accuracy; therefore, anisotropic diffusion filtering is preferred for filtering the second image dataset.

[0066] If the resolution of the second image dataset meets a preset threshold, the second image dataset is segmented, wherein the segmentation of the second image dataset is achieved by using a U-Net algorithm; lesion region features are extracted from the segmented second image dataset to obtain a lesion feature set. If the resolution of the second image dataset does not meet the preset threshold, the resolution is adjusted and the lesion feature set is re-segmented to obtain the lesion feature set.

[0067] A three-dimensional model is constructed based on the lesion feature set using a stereomicroscope method to generate a first three-dimensional model; a boundary tracing algorithm is used to determine the boundary of the lesion area in the first three-dimensional model, and a boundary data set is extracted; voxels of the first three-dimensional model are accumulated using a threshold weighted integration method or a segmentation probability map to obtain volume data; based on the boundary data set and volume data, a geometric optimization algorithm is used to determine the puncture point position and calculate the puncture depth data; and initial surgical planning data are generated based on the puncture point position and puncture depth data.

[0068] Based on coordinate mapping, a puncture path is generated for the initial surgical planning data, resulting in a surgical path dataset. In actual clinical applications, the mapping from the image coordinate system to the surgical robot coordinate system relies on external markers. If the marker positioning error is 0.5mm, the cumulative error after multiple coordinate conversion steps may exceed 1mm. To avoid this problem, this embodiment utilizes optical navigation combined with real-time intraoperative image registration to dynamically correct coordinate system offsets, thereby avoiding the cumulative spatial registration errors of coordinate mapping technology.

[0069] More specifically, preoperative imaging data of the patient is acquired from a medical imaging device, wherein the scanning layer thickness of the preoperative imaging data is set to 1 mm and the resolution is 512×512 pixels, and an image file in DICOM format is generated.

[0070] When segmenting preoperative imaging data, a deep learning algorithm such as the U-Net network is used. With a training set containing 5,000 labeled lesion area data, the model achieves an accuracy of 95%, segmenting the lesion area and extracting its features, such as shape, density, and edge information. At the same time, the Dice coefficient or Hausdorff distance is used to evaluate the boundary segmentation quality; for example, the boundary error is ≤0.3mm.

[0071] When constructing a three-dimensional model based on the characteristics of the lesion area, the MarchingCubes algorithm is used to reconstruct the two-dimensional slice data into three-dimensional volume data with an isotropic model accuracy of 0.5 mm, or super-resolution reconstruction is used to improve the Z-axis resolution to ensure that the geometric morphology of the lesion area is accurately presented.

[0072] When determining the boundaries and volume of the lesion area based on the three-dimensional model, a region growing algorithm is used, the threshold is tightened according to the lesion type, or multi-sequence MRI is combined to assist segmentation; for example, the threshold range is set to 30-80 HU, the lesion volume is calculated to be 15.6 cubic centimeters, and the boundary error is less than 0.5 mm.

[0073] When generating initial surgical planning data based on boundaries and volumes, a path planning algorithm is used to determine the location of the puncture point, for example: 2.2 cm from the skin surface, with a puncture depth of 5.8 cm; the planned path avoids important blood vessels and nerves; for example: setting a dynamic safety boundary, for example, ≥5 mm around the blood vessels, and an elastic buffer zone ≥8 mm during the respiratory cycle.

[0074] In one embodiment, Figure 1 As shown, the present invention provides a percutaneous puncture precise dynamic matching and navigation method based on an AI surgical robot, comprising:

[0075] The starting and ending points of the puncture path are determined based on the initial surgical planning data; the spatial parameters of the puncture path, including the path angle and length, are calculated; the puncture process is simulated through finite element simulation; the coverage of the target area is determined based on the simulation results; if the coverage is lower than the preset threshold, the spatial parameters of the puncture path are adjusted.

[0076] In this scheme, the starting and ending coordinates of the puncture path are obtained from the initial surgical planning data to determine the initial geometric description of the puncture path; then, based on the starting and ending coordinates of the puncture path, the path angle parameter and path length parameter are calculated to obtain the spatial parameter description of the puncture path, where the path angle parameter is the angle between the path and the reference plane, and the path length parameter is the Euclidean distance from the starting point to the end point.

[0077] Finite element simulation was used to simulate the puncture process based on spatial parameter descriptions, revealing the distribution of the puncture path's effects within the target area. Finite element simulation divides the target area into discrete grids and calculates the impact of the puncture path on each grid cell. Based on the simulation results, the coverage of the target area was calculated, yielding a quantitative description of the target area's coverage.

[0078] The coverage calculation formula is:

[0079]

[0080] in Indicates the area effectively covered by the puncture path, Indicates the total area of ​​the target region.

[0081] If the coverage rate C is lower than the preset threshold, the path angle parameter and path length parameter are optimized by the gradient descent algorithm, the spatial parameters of the puncture path are adjusted, and a new spatial parameter description is obtained. At the same time, the gradient descent algorithm is used to iteratively update the parameters.

[0082] Based on the adjusted spatial parameter description, the finite element simulation and coverage calculation are repeated to obtain the updated target area coverage. If the updated coverage is still below the preset threshold, the spatial parameter adjustment and simulation process is iterated until the coverage meets the preset threshold, thereby obtaining the optimized puncture path spatial parameters.

[0083] This embodiment provides the following examples to further illustrate the above technical solution: Based on the initial surgical planning data, the starting point of the puncture path is first determined to be the patient's body surface coordinates , the end point is the coordinate of the tumor center .

[0084] Calculate the angle of the puncture path through spatial geometry algorithms is 45°, length

[0085]

[0086] .

[0087] In this example, in order to ensure the positioning accuracy in three-dimensional space, multiple geometric parameters are introduced into the puncture angle parameter, for example, using the pitch angle and yaw angle Jointly define the three-dimensional path direction, so that in actual clinical application, reference planes such as the transverse and sagittal planes can be better identified to improve the accuracy of puncture location;

[0088] Multi-angle calculation can be referred to as follows:

[0089]

[0090] Next, finite element simulation was used to simulate the puncture process. First, the diameter of the puncture needle was set to 2 mm, the puncture speed was set to 5 mm / s, and the simulation time was set to 15 seconds.

[0091] During the simulation, the interaction forces between the puncture needle and the surrounding tissue, as well as the stress distribution along the puncture path, are recorded. Simultaneously, a biomechanical multi-field coupling model is used to simulate the ablation process and calibrate the parameters.

[0092] Based on the simulation results, the coverage of the target area is calculated. Assuming the tumor volume is 1000 cubic millimeters and the puncture path covers 800 cubic millimeters of the tumor volume, the coverage is 80%. If the preset threshold is 85%, the coverage is lower than the threshold. In this case, the spatial parameters of the puncture path need to be adjusted to meet the coverage requirement.

[0093] Specifically, define the spatial coverage weight (e.g., the weight of the lesion core is greater than the edge), and use the weighted coverage ratio:

[0094]

[0095] in, is the weighted coverage; For the The spatial coverage weights of different regions, for example, the lesion core weight > edge weight, reflect the importance of different regions. For the Region, The effective coverage volume of each area is the volume of the tumor actually covered during the ablation process (dynamically calculated by the bioheat equation). For the Region, The total tumor volume of each region, such as the total tumor volume .

[0096] Among them, the biothermal equation (such as the Pennes equation) is combined with the actual tumor volume covered during the ablation process to simulate the expansion of the ablation zone, thereby achieving the purpose of dynamically calculating the effective coverage volume.

[0097] Adjust the puncture path angle to , the length is adjusted to , re-performed finite element simulation, and calculated the new coverage rate to be 85.5%. At this point, the new coverage rate meets the preset threshold requirement.

[0098] In this example, the puncture path angle is directly optimized and puncture path length When the puncture end point is changed (such as adjusting the puncture path length), This may cause the needle tip to fail to reach the center of the lesion or exceed the center of the lesion, thereby deviating from the treatment target. Based on this, this embodiment also proposes the following solutions for further optimization:

[0099] Fix the puncture endpoint as the center of the lesion and optimize the needle entry point or path direction Design a multi-objective optimization function, for example, to optimize the needle entry point position or path direction by calculating the comprehensive optimization objective function E:

[0100] ;

[0101] in, To comprehensively optimize the objective function, the optimal puncture path is achieved by minimizing EE; are weight coefficients; C is the coverage rate; (1 − C) represents the penalty term for the uncovered rate; safety risk quantifies the risk of damage to surrounding healthy tissues along the puncture path, such as the risk of damage to critical structures such as blood vessels and nerves. The robotic arm motion cost quantifies the motion complexity of the robotic arm executing the puncture path, such as the degree of motion complexity corresponding to device energy consumption, joint rotation angle, or path smoothness.

[0102] In one embodiment, Figure 1 As shown, the present invention provides a precise dynamic matching and navigation method for percutaneous puncture based on an AI surgical robot, comprising: determining the posture of the robot end effector according to the spatial parameters of the puncture path; calculating the angles of each joint corresponding to the posture; generating the robot motion trajectory based on the joint angles; driving the robot to execute the motion trajectory through a motion control system; monitoring the robot execution status in real time and recording the puncture operation data.

[0103] In this embodiment, the specific scheme is as follows: obtain the spatial parameters of the puncture path, calculate the target posture of the end effector, and obtain the posture parameters. Based on the posture parameters, the angle of each joint is calculated using the inverse kinematics algorithm, and then the joint angle is obtained. The robot motion trajectory is generated according to the joint angle, and trajectory data is generated, where the trajectory data is the trajectory execution instruction. The robot is driven by the motion control system to execute the trajectory data; the execution status of the robot is monitored in real time based on the execution trajectory data, and at the same time, the sensor feedback data is obtained and the corresponding status information is obtained; if the status information deviates from the preset threshold, the joint angle is adjusted and the trajectory data is updated.

[0104] This embodiment provides the following examples to further illustrate the above technical solution: According to the spatial parameters of the puncture path, the position of the robot end effector is first determined. For example, in three-dimensional space, the position coordinates of the end effector are set to Millimeters, the attitude angle is a quaternion rotation matrix (Quaternion) or a rotation matrix.

[0105] The inverse kinematics algorithm is used to calculate the joint angles corresponding to the posture; assuming that the robot has 6 joints, the joint angles obtained by inverse kinematics calculation are degree; the robot motion trajectory is generated according to the above joint angles; to ensure the smoothness and continuity of the trajectory, the robot motion trajectory is further optimized using the cubic spline interpolation algorithm; in this scheme, the inverse kinematics algorithm can be calculated using the damped least squares method (DLS), so that it can suppress the influence of singular points during the calculation; in addition, to ensure the safety of puncture, the joint limit check and self-collision detection are verified in real time after the inverse kinematics solution to avoid exceeding the physical limit during movement.

[0106] In one embodiment, Figure 1 As shown, the present invention provides a percutaneous puncture precise dynamic matching and navigation method based on an AI surgical robot, comprising:

[0107] Acquire real-time tissue images and extract tissue feature points; align the feature points with corresponding points in the three-dimensional model; calculate the tissue deformation variable based on the alignment result; if the deformation variable exceeds a preset threshold, it is determined that tissue deformation exists.

[0108] In this scheme, real-time tissue images are acquired through intraoperative imaging equipment to generate first image data; the first image data is preprocessed using denoising and edge enhancement algorithms to obtain second image data; feature points are extracted from the second image data, and further three-dimensional feature points are extracted, and the key point positions are calculated based on voxel gradients. And description vector, further generate feature point set , feature point set Each point contains the position coordinates And description vector. The feature point set A set of predefined corresponding points in the 3D model Perform registration and calculate the transformation matrix using the iterative closest point algorithm , get the registration result; according to the transformation matrix in the registration result , calculate the tissue deformation And get the value of the deformation variable.

[0109] Among them, the transformation matrix For: feature point set To the corresponding point set spatial mapping;

[0110] Tissue deformation For: feature point set Each point in the transformation matrix After transformation and corresponding point set The mean Euclidean distance of corresponding points in .

[0111] If the tissue deformation Exceeding the preset threshold , it is determined that there is tissue deformation, and when there is deformation, a deformation state identifier is generated;

[0112] If the tissue deformation Less than or equal to the preset threshold , it is judged that there is no significant deformation and a normal state mark is generated.

[0113] According to the deformation state identifier described above, the three-dimensional model parameters are updated, and the geometric parameters of the corresponding area in the model are adjusted using the deformation state identifier to obtain updated three-dimensional model data.

[0114] This embodiment provides the following example to further illustrate the above technical solution: During the first image data preprocessing, speckle noise is suppressed using anisotropic diffusion filtering (4 iterations, with a transfer coefficient k=0.05k=0.05). Next, image edges are enhanced using contrast-limited histogram equalization (CLAHE) to further ensure image clarity. Feature points are extracted using the 3D-SIFT algorithm, with a contrast threshold of 0.04 and an edge threshold of 10. Approximately 200-300 stable feature points can be extracted from each image frame.

[0115] Furthermore, during registration, the iterative nearest point algorithm was used for iterative optimization, and the initial matching was accelerated by the nearest neighbor search through KD-Tree. The maximum number of iterations was set to 50 times, the convergence threshold was set to 0.001 mm, and the final registration error was controlled within 0.5 mm.

[0116] The registered feature point cloud is subjected to deformation analysis. When it is detected that the deformation of a local area exceeds the preset threshold of 2mm, the system automatically triggers a deformation alarm and classifies the deformation type. For example, when the displacement of a certain area in the right lobe of the liver reaches 2.3mm, a deformation alarm is triggered. Among them, the alarm mark for the classified deformation type is: elastic deformation is marked as the first warning, and permanent damage is marked as the second warning.

[0117] In one embodiment, Figure 1 As shown, the present invention provides a percutaneous puncture precise dynamic matching and navigation method based on an AI surgical robot, comprising:

[0118] The position of the lesion area after tissue deformation is determined based on the alignment results; the starting and end points of the puncture path are recalculated and the spatial parameters of the puncture path are updated, including the path angle and length; the position of the robot end effector is recalculated based on the updated spatial parameters of the puncture path; and the robot joint motion trajectory is updated using the inverse kinematics algorithm.

[0119] In this solution, the registration result is obtained, and the tissue deformation data is extracted through image processing technology to determine the spatial coordinate position of the lesion area after deformation, and the coordinates of the lesion area are obtained. The starting point and end point coordinates of the puncture path are calculated based on the coordinates of the lesion area in combination with the geometric algorithm to obtain the path starting point coordinates and path end point coordinates. The vector direction and distance are calculated using the path starting point coordinates and path end point coordinates, and then the path angle and path length are updated to obtain the spatial parameters. Based on the spatial parameters, the position of the robot end effector is calculated to obtain the end effector position. If the end effector position exceeds the robot workspace, the joint angle is adjusted through the inverse kinematics algorithm to generate the joint motion trajectory to obtain the joint motion trajectory. Through the joint motion trajectory, the motion planning algorithm is used to optimize the robot motion path to obtain the optimized robot trajectory. Based on the optimized robot trajectory, control instructions are generated, and the robot motion parameters are updated based on the control instructions to obtain the final motion parameters.

[0120] This embodiment provides the following example to further illustrate the above technical solution: In the registration result processing stage, the tissue deformation field is first calculated by the bidirectional registration algorithm, and the preoperative CT coordinate system and the intraoperative ultrasound coordinate system are spatially mapped. Assume that the coordinates of the lesion center in the preoperative CT are After registration, it was found that the lesion was displaced to , the deformation vector is .

[0121] In this example, in actual clinical practice, there will be certain non-uniform deformation of other tissues along the puncture path, such as non-uniform deformation caused by flexible or resilient tissues such as skin and fascia. Based on this, in actual clinical practice, the following improvements to the above technical issues may be considered:

[0122] Multiple control points are sampled along the puncture path, such as one point every 10 mm; the path is updated segmentally according to the local deformation field; at the same time, the finite element deformation model is combined to predict the tissue displacement distribution along the path, and the puncture path planning is based on the predicted results of the tissue displacement distribution, which is more conducive to the success rate of puncture positioning.

[0123] The puncture path parameters are recalculated using spatial geometric transformation. The original path starting point is Adjust to The endpoint is synchronously updated to the deformed coordinates. The starting point of the original path is set as the skin entry point; the end point is set as the lesion target.

[0124] Furthermore, the path angle is re-solved through vector operations, using the direction vector Calculate and get the new pitch angle , yaw angle The path length is updated to 55.7 mm using the Euclidean distance formula. The specific values ​​in this example are for illustrative purposes only. In actual clinical applications or during puncture experiments on experimental models, anatomical feasibility checks and puncture angle limits are performed before path planning to reduce the risk of complications. Anatomical feasibility checks involve 3D CT reconstruction of rib and organ positions; examples of puncture angle limits include 40° ≤ θ ≤ 70°.

[0125] In this example, reachability analysis is used before surgery to verify the target position and determine whether the robot's workspace is within the preset working range. Inverse kinematics is then performed using the DH parameter model. This model integrates the obstacle distance field to identify and avoid physical obstructions within the robot's motion range during surgery.

[0126] In one embodiment, Figure 1 As shown, the present invention provides a percutaneous puncture precise dynamic matching and navigation method based on an AI surgical robot, comprising:

[0127] A finite element simulation model is established based on the three-dimensional model and the ablation process is simulated to obtain the expansion range of the ablation area; the coverage rate of the ablation area and the lesion area is determined based on the expansion range; if the coverage rate is lower than a preset threshold, the puncture point position and ablation parameters in the initial surgical planning data are adjusted; and the initial surgical planning data is updated.

[0128] In this approach, geometric structure data is obtained from the three-dimensional model, a finite element simulation model is constructed, a meshing algorithm is used to generate a discretized mesh, and simulation boundary conditions are determined to obtain the finite element simulation model. The ablation process is simulated based on the finite element simulation model; the temperature distribution is calculated using the heat conduction equation to determine the extension range of the ablation area; the coverage ratio between the ablation area and the lesion area is calculated using the extension range and the geometric data of the lesion area, and the overlapping volume ratio is calculated using stereological methods to obtain coverage data; alternatively, the overlapping volume ratio between the ablation area and the lesion is calculated using three-dimensional geometric Boolean operations to obtain coverage data; if the coverage ratio is lower than a preset threshold, the puncture point position and ablation parameters are adjusted, and the puncture point coordinates and ablation power are optimized using a gradient descent algorithm or a particle swarm optimization (PSO) algorithm to determine the adjusted puncture point position and ablation parameters. Based on the adjusted puncture point position and ablation parameters, the surgical planning data is updated to generate a new surgical planning dataset, obtaining updated surgical planning data. The updated surgical planning data is used to obtain new puncture point locations and ablation parameters. The finite element simulation model is reconstructed, and a new discretized mesh is generated using a meshing algorithm. New simulation boundary conditions are determined to obtain a new finite element simulation model. Based on this new finite element simulation model, the ablation process is re-simulated, and the new temperature distribution is calculated using the heat conduction equation. The new ablation zone extension range and coverage are determined to obtain the optimized surgical planning data.

[0129] This embodiment provides the following example to further illustrate the above technical solution: Based on the patient's liver CT scan data, a three-dimensional model containing the tumor lesion is reconstructed using Mimics software, and the model accuracy is set to 0.5mm voxel resolution. A finite element simulation model is established using ANSYS, and the thermal conductivity coefficient of the liver tissue is set to 0.5W / (m·K), the specific heat capacity is 3600J / (kg·K), and the blood perfusion rate is 0.03s⁻¹. In the radiofrequency ablation simulation, the temperature field distribution is calculated using the Pennes bioheat equation, the electrode power is set to 50W, the action time is 300 seconds, and the tissue damage range is calculated using the Arrhenius damage integral model. When the tissue damage range value is greater than 1, it is determined to be an ablation zone.

[0130] At this time, the simulation results showed that the maximum diameter of the ablation zone was 3.2 cm, and the matching degree with the 2.8 cm lesion area planned before surgery was only 78%, which was lower than the clinical requirement threshold. At this time, the system automatically starts the optimization algorithm, and uses the gradient descent algorithm or the particle swarm optimization (PSO) algorithm to iteratively adjust the puncture point coordinates in 3D space. Each iteration calculates the new ablation coverage and safety margin. When the puncture point moves 4 mm toward the head and the power is increased to 55 W, the simulation shows that the ablation zone expands to 3.5 cm and the coverage rate increases to 93%. The system automatically updates the surgical planning data, and the minimum distance between the new puncture path and the intrahepatic blood vessels increases from 1.2 mm to 2.1 mm. At the same time, it predicts that the safety distance between the ablation zone and the bile duct will remain above 2.5 mm. The entire optimization process took 2 hours and 17 minutes, and a total of 36 parameter combination evaluations were completed. The final planning data was directly transmitted to the navigation system.

[0131] In one embodiment, Figure 1 As shown, the present invention provides a percutaneous puncture precise dynamic matching and navigation method based on an AI surgical robot, comprising:

[0132] The motion control system obtains real-time position data of each puncture trajectory; calculates the deviation between the real-time position data and the target trajectory; adjusts the puncture parameters, including puncture speed and angle, if the deviation exceeds a preset threshold; synchronously monitors the deviation of each trajectory in the multi-needle puncture mode; and updates the robot motion control instructions based on the adjusted puncture parameters.

[0133] In this solution, the motion control system acquires the real-time position data of the puncture needle and uses sensors to collect three-dimensional coordinate information to generate a dynamic position dataset of the puncture trajectory. This dynamic position dataset is compared with the preset target trajectory, and the real-time deviation is calculated using Euclidean distance to obtain the deviation value. If the deviation value exceeds the preset threshold, the puncture speed v and angle θ are adjusted using a gradient descent algorithm or a PID control algorithm to obtain the adjusted puncture parameters. A parallel processing module synchronously monitors the trajectory deviation of multiple needles, and the data of each needle is aligned using timestamps to generate a multi-needle deviation dataset.

[0134] The Euclidean distance calculation formula is:

[0135] ,

[0136] in, is the real-time coordinate, is the target coordinate;

[0137] Furthermore, based on the multi-needle deviation data set, it is determined whether any needle deviation exceeds a preset threshold. If so, the adjustment parameters of each needle are fused through the weighted average method to obtain a unified parameter adjustment value.

[0138] Among them, the weighted average algorithm formula is:

[0139] ,

[0140] in, is a single needle parameter, is the weight,

[0141] Furthermore, when the deviation of multiple needle trajectories exceeds the threshold, the weight is assigned according to the inverse of the deviation of each needle:

[0142] ,

[0143] The fused parameters are:

[0144] .

[0145] The robot generates motion control instructions based on the unified parameter adjustment values, and uses an inverse kinematics algorithm to calculate joint angles to obtain updated motion instructions. These updated motion instructions are transmitted to the motion control system via a real-time feedback loop. Finally, closed-loop control adjusts the puncture needle trajectory to obtain optimized puncture trajectory data.

[0146] In this embodiment, in order to take into account the system delay, feedforward control and timestamp prediction are taken into consideration, thereby achieving the purpose of compensating for the delay time from the sensing device to the execution device.

[0147] This embodiment provides the following examples to further illustrate the above technical solution: the motion control system obtains real-time position data of each puncture trajectory and uses an optical positioning system or electromagnetic sensor for real-time monitoring to ensure that the position data has an accuracy of 0.1 mm; the deviation between the real-time position data and the target trajectory is calculated using the Euclidean distance formula; if the deviation exceeds a preset threshold of 0.5 mm, the puncture parameters, including the puncture speed and angle, are adjusted dynamically using a gradient descent algorithm or a PID control algorithm;

[0148] The speed adjustment formula is: , the angle adjustment formula is ,

[0149] in and are the initial velocity and angle, and is the adjustment factor.

[0150] The system simultaneously monitors the deviation of each trajectory in the multi-needle puncture mode and uses multi-threading technology to process each trajectory data in parallel, ensuring real-time and accuracy. The robot motion control instructions are updated based on the adjusted puncture parameters and sent to each actuator via the CAN bus, ensuring the synchronization and accuracy of the robot motion control, ultimately achieving high-precision positioning and dynamic correction of the puncture trajectory.

[0151] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A percutaneous puncture precise dynamic matching and navigation method based on AI surgical robot, characterized in that: include: S1, obtaining preoperative medical images and generating surgical planning data based on the medical images; S2, determine the ablation path and ablation area based on the surgical planning data; S3, the robot system performs the puncture operation to complete the ablation treatment of the target area; Wherein, step S3 further includes: acquiring intraoperative real-time image data multiple times, and dynamically adjusting the ablation path and ablation parameters in real time based on each intraoperative real-time image data.

2. The AI ​​surgical robot-based percutaneous puncture precise dynamic matching and navigation method according to claim 1, characterized in that: Obtain the patient's preoperative imaging data, construct a three-dimensional model of the lesion area based on the preoperative imaging data, and use the three-dimensional model of the lesion area to generate initial surgical planning data; The spatial parameters of the puncture path are calculated using the initial surgical planning data, and the target area coverage effect is verified through simulation; Calculating the robot joint motion trajectory corresponding to the puncture path and controlling the execution of the puncture operation; acquiring real-time tissue images during the puncture process and registering them with the three-dimensional model to determine the tissue deformation state; If there is tissue deformation, the spatial parameters of the puncture path are recalculated according to the registration results and the robot motion trajectory is updated; Perform simulation analysis on the 3D model, predict the ablation zone expansion range based on the simulation analysis results, and adjust the initial surgical planning data; when multiple needle punctures are performed, use the motion control system to synchronously monitor the positioning accuracy of each puncture trajectory and dynamically adjust the puncture parameters; After each path parameter adjustment, the finite element simulation verification and robot motion trajectory calculation are re-executed until the preset ablation coverage condition is met.

3. The method for accurate dynamic matching and navigation of percutaneous puncture based on an AI surgical robot according to claim 1, characterized in that: Obtain the patient's preoperative medical image data, determine the lesion location and tissue characteristics based on the medical image data; construct a three-dimensional model based on the lesion location and tissue characteristics; The surgical planning data is generated through the three-dimensional model, wherein the surgical planning data is the surgical planning route.

4. The method for accurate dynamic matching and navigation of percutaneous puncture based on an AI surgical robot according to claim 3, characterized in that: Obtaining surgical planning parameters based on the surgical planning route, and calculating the insertion position and angle of the ablation needle based on the parameters; optimizing the insertion position and angle so that the puncture path can cover the target area; It also includes: verifying the coverage effect of the puncture path on the target area.

5. The AI ​​surgical robot-based percutaneous puncture precise dynamic matching and navigation method according to claim 4, characterized in that: The spatial coordinates of the robot joints are calculated based on the surgical planning data; the motion trajectory of the robot joints is determined using the spatial coordinates, and the robot is controlled according to the motion trajectory to accurately position the ablation needle and perform puncture operations.

6. The AI ​​surgical robot-based percutaneous puncture precise dynamic matching and navigation method according to claim 5, characterized in that: Real-time tissue images are acquired through intraoperative image acquisition equipment, and tissue displacement or deformation information is acquired based on the real-time tissue images; the ablation path and ablation parameters are adjusted according to the tissue displacement or deformation information.

7. The AI ​​surgical robot-based percutaneous puncture precise dynamic matching and navigation method according to claim 6, characterized in that: Simulation analysis is performed on medical image data, and the ablation effect is predicted based on the simulation results. The predicted ablation effect is used to assist in generating surgical planning data and optimizing the surgical plan.

8. The AI ​​surgical robot-based percutaneous puncture precise dynamic matching and navigation method according to claim 7, characterized in that: The trajectory of the ablation needle is controlled by a robot; single-point multi-needle puncture operations are performed according to the trajectory of the ablation needle; for single-point multi-needle puncture operations, the puncture accuracy and stability are monitored in real time.

9. The AI ​​surgical robot-based percutaneous puncture precise dynamic matching and navigation method according to claim 8, characterized in that: The intraoperative real-time image is registered with the preoperative model and then compared; based on the comparison results, the tissue changes are judged, and the ablation path and ablation parameters are dynamically adjusted according to the tissue change status.

10. A percutaneous puncture precise dynamic matching and navigation system based on AI surgical robot, characterized by: The system uses the AI ​​surgical robot-based precise dynamic matching and navigation method for percutaneous puncture to perform dynamic matching and navigation during percutaneous puncture surgery, and provides intelligent guidance for assisted percutaneous puncture surgery based on dynamic matching and navigation.

Images