Guide pin path navigation method and system based on electromagnetic sensing

Abstract

The invention discloses a guide pin path navigation method and system based on electromagnetic sensing, and the method comprises the steps: detecting a deviation region through an image processing algorithm if the deviation correction path of the position of a guide pin in a dynamic image sequence exceeds a preset safety threshold value, generating a deviation vector, mapping the deviation vector to a three-dimensional coordinate space, and determining the precise adjustment angle and distance of the guide pin; according to the deviation vector and the correction path coordinate sequence, an inverse kinematics algorithm is adopted to calculate a rotation angle and a propulsion distance required by guide pin adjustment, a control signal is generated and transmitted to a guide pin driving device through an electromagnetic feedback system, and an automatic adjustment instruction of the guide pin is obtained; and the position and attitude data of the adjusted guide pin are obtained from the execution result of the guide pin driving device, the position and attitude data are compared with the correction path coordinate sequence, the positioning precision is calculated by adopting an error analysis algorithm, and whether the guide pin meets the requirement of submillimeter precision or not is determined.

Description

Technical Field

[0001] The present invention belongs to the technical field of surgical navigation and visualization, and particularly relates to a guide needle path navigation method and system based on electromagnetic sensing. Background Art

[0002] In the positioning of instruments in the knee joint area, the existing technologies have significant limitations: traditional positioning devices rely on manual experience to determine the position of instruments, lacking precise path planning and real-time guidance, resulting in increased operation complexity and error risk. Traditional methods adjust the instrument direction manually and rely on external observation channels to avoid damage to key structures. This method not only increases the operation complexity but also affects the positioning accuracy due to the lack of real-time position feedback. The core technical challenges are as follows: First, it is impossible to pre-generate the optimal instrument movement path, and it is difficult to dynamically track the three-dimensional position and attitude of the instrument during operation; second, there is a lack of real-time visualization guidance, and additional auxiliary devices are required to observe the path, further increasing the operation complexity; finally, the positioning process lacks an automatic correction mechanism and it is difficult to quickly correct deviations. These technical problems limit the accuracy and operation efficiency of instrument positioning. Therefore, how to integrate electromagnetic tracking, intelligent path planning, and real-time visualization technologies to achieve precise dynamic guidance of the instrument path has become a key issue in improving the performance of the positioning system. Summary of the Invention

[0003] To solve the above technical problems, the present invention proposes a guide needle path navigation method and system based on electromagnetic sensing to solve the problems existing in the above-mentioned prior art.

[0004] In a first aspect, to achieve the above object, the present invention provides a guide needle path navigation method based on electromagnetic sensing, including the following steps:

[0005] Obtain the three-dimensional structure information of the knee joint from the preoperative magnetic resonance imaging data of the patient, and generate a three-dimensional anatomical model including the distribution of blood vessels and nerves;

[0006] For the three-dimensional anatomical model, use an artificial intelligence path planning algorithm to generate a three-dimensional coordinate sequence of the optimal guide needle puncture path;

[0007] Integrate a micro electromagnetic transmitter at the front end of the guide needle, and use an electromagnetic receiver array arranged outside the body to capture the three-dimensional position coordinates and attitude angles of the guide needle in real time;

[0008] If the deviation between the real-time movement trajectory of the guide needle and the planned path exceeds a preset threshold, use a dynamic path calibration algorithm to generate a corrected path coordinate sequence;

[0009] According to the real-time movement trajectory and the corrected path coordinate sequence, use virtual reality rendering technology to generate a dynamic image sequence including guide needle travel guidance information;

[0010] If the position of the guide pin in the dynamic image sequence deviates from the calibration path by more than a preset safety threshold, a deviation vector is generated through an image processing algorithm and mapped to a three-dimensional coordinate space to determine the adjustment angle and distance of the guide pin;

[0011] According to the deviation vector and the calibration path coordinate sequence, an inverse kinematics algorithm is used to generate a control signal to adjust the traveling direction of the guide pin;

[0012] Verify whether the positioning accuracy of the adjusted guide pin meets the sub-millimeter requirement. If it meets, update the navigation image sequence in the virtual reality interface to complete the closed-loop control.

[0013] Optionally, the process of generating the three-dimensional anatomical model includes:

[0014] Separate the tibia, femur, and posterior cruciate ligament stump regions from the nuclear magnetic resonance imaging data;

[0015] Mark the bone region through a threshold segmentation algorithm;

[0016] Adopt a region growing algorithm to expand from the boundary of the bone region to mark the blood vessel region and the nerve region.

[0017] Optionally, the process of generating the optimal guide pin puncture path includes:

[0018] Analyze the geometric constraints of the tibia positioning point and the femoral connection region;

[0019] Combined with the blood vessel and nerve distribution data, use the A* path planning algorithm to avoid high-risk areas and generate a node coordinate sequence;

[0020] Use the cubic spline interpolation method to smooth the node coordinate sequence.

[0021] Optionally, the process of real-time capturing the three-dimensional position coordinates and attitude angles of the guide pin includes:

[0022] Calculate the relative distance between the front end of the guide pin and the electromagnetic receiver array through the triangulation algorithm of the electromagnetic field signal intensity;

[0023] Determine the real-time three-dimensional coordinates of the guide pin based on the geometric layout of the receiver array.

[0024] Optionally, the implementation process of the dynamic path calibration algorithm includes:

[0025] Use the least squares method to fit the coordinate sequences of the real-time trajectory and the planned path;

[0026] Calculate the included angle between the current traveling direction of the guide pin and the calibration path direction;

[0027] If the included angle exceeds the preset angle threshold, generate a direction adjustment parameter and update the motion control parameter of the guide pin.

[0028] Optionally, the process of verifying the positioning accuracy of the guide needle includes:

[0029] Comparing the position data of the guide needle after adjustment with the calibration path coordinate sequence;

[0030] Calculating the average deviation distance through an error analysis algorithm;

[0031] If the average deviation distance is less than the sub-millimeter threshold, it is determined that the positioning accuracy meets the standard.

[0032] In a second aspect, the present invention also provides a guide needle path navigation system based on electromagnetic sensing for implementing a guide needle path navigation method based on electromagnetic sensing. The system includes:

[0033] A three-dimensional structure information acquisition module for acquiring three-dimensional knee joint structure information from the preoperative magnetic resonance imaging data of the patient and generating a three-dimensional anatomical model including the distribution of blood vessels and nerves;

[0034] An artificial intelligence path planning module for generating a three-dimensional coordinate sequence of the optimal guide needle puncture path for the three-dimensional anatomical model;

[0035] An electromagnetic positioning module for capturing the three-dimensional position coordinates and attitude angles of the guide needle in real time through a micro electromagnetic transmitter integrated at the front end of the guide needle and an electromagnetic receiver array arranged outside the body;

[0036] A dynamic path calibration module for generating a corrected path coordinate sequence when the deviation between the real-time movement trajectory of the guide needle and the planned path exceeds a preset threshold;

[0037] A virtual reality navigation module for generating a dynamic image sequence including guide needle travel guidance information according to the real-time movement trajectory and the corrected path coordinate sequence;

[0038] A deviation detection module for generating a deviation vector and mapping it to a three-dimensional coordinate space when the position of the guide needle in the dynamic image sequence deviates from the corrected path by more than a preset safety threshold;

[0039] A guide needle adjustment control module for generating a control signal to adjust the travel direction of the guide needle according to the deviation vector and the corrected path coordinate sequence;

[0040] A positioning accuracy verification module for verifying whether the positioning accuracy of the adjusted guide needle meets the sub-millimeter level requirement;

[0041] A navigation image update module for updating the navigation image sequence in the virtual reality interface when the positioning accuracy meets the standard to complete the closed-loop control.

[0042] Optionally, the three-dimensional structure information acquisition module includes:

[0043] An image segmentation unit for separating the tibia, femur, and posterior cruciate ligament stump regions from nuclear magnetic resonance imaging data;

[0044] A bone marking unit for marking bone regions through a threshold segmentation algorithm;

[0045] A vascular and nerve marking unit for expanding and marking vascular regions and nerve regions from the boundaries of bone regions using a region growing algorithm.

[0046] In a third aspect, the present invention also provides a computer terminal device, including:

[0047] One or more processors;

[0048] A memory coupled to the processor for storing one or more programs;

[0049] When the one or more programs are executed by the one or more processors, the one or more processors implement a method for guiding a needle path based on electromagnetic sensing.

[0050] In a fourth aspect, the present invention also provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, it implements a method for guiding a needle path based on electromagnetic sensing.

[0051] Compared with the prior art, the present invention has the following advantages and technical effects:

[0052] A method and system for guiding a needle path based on electromagnetic sensing provided by the present invention are used to assist in the precise positioning of medical devices in the knee joint area. The system analyzes the patient's preoperative nuclear magnetic resonance imaging to generate a three-dimensional anatomical model containing the distribution of blood vessels and nerves, and uses intelligent algorithms to plan the movement path of the needle. During the positioning process, the spatial position of the needle is captured in real time through electromagnetic positioning technology, and combined with a dynamic path calibration algorithm and virtual reality display, navigation guidance information is generated. When the needle deviates from the preset path, the system automatically calculates adjustment parameters and performs precise adjustment through electromagnetic feedback, achieving a positioning accuracy of sub-millimeters. The present invention significantly improves the precision and operation safety of device positioning by integrating electromagnetic sensing, dynamic calibration, and virtual reality technologies. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The accompanying drawings forming a part of the present invention are used to provide a further understanding of the present invention. The schematic embodiments and descriptions thereof of the present invention are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0054] Figure 1 is a flowchart of the method for guiding a needle path based on electromagnetic sensing according to an embodiment of the present invention;

[0055] Figure 2 Brief schematic diagram of partial processing logic of the needle guiding path navigation method based on electromagnetic sensing according to an embodiment of the present invention;

[0056] Figure 3 Brief schematic diagram of partial processing logic of the needle guiding path navigation method based on electromagnetic sensing according to an embodiment of the present invention;

[0057] Figure 4 Schematic structural diagram of the needle guiding path navigation system based on electromagnetic sensing according to an embodiment of the present invention. Detailed implementation manners

[0058] It should be noted that, without conflict, the embodiments in the present invention and the features in the embodiments may be combined with each other. The present invention will be described in detail below with reference to the drawings and in conjunction with the embodiments.

[0059] It should be noted that the steps shown in the flowchart of the drawings may be executed in a computer system such as a set of computer-executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than here.

[0060] Embodiment 1

[0061] As Figures 1 to 3 shown, in this embodiment, a needle guiding path navigation method based on electromagnetic sensing is provided, including:

[0062] Obtain the three-dimensional structure information of the knee joint from the pre-operative nuclear magnetic resonance imaging data of the patient, and generate a three-dimensional anatomical model including the distribution of blood vessels and nerves;

[0063] For the three-dimensional anatomical model, use an artificial intelligence path planning algorithm to generate a three-dimensional coordinate sequence of the optimal needle puncture path;

[0064] Integrate a micro electromagnetic transmitter at the front end of the needle, and use an electromagnetic receiver array arranged outside the body to capture the three-dimensional position coordinates and attitude angles of the needle in real time;

[0065] If the deviation between the real-time movement trajectory of the needle and the planned path exceeds a preset threshold, use a dynamic path calibration algorithm to generate a corrected path coordinate sequence;

[0066] According to the real-time movement trajectory and the corrected path coordinate sequence, use virtual reality rendering technology to generate a dynamic image sequence including needle travel guiding information;

[0067] If the position of the needle in the dynamic image sequence deviates from the corrected path by more than a preset safety threshold, use an image processing algorithm to generate a deviation vector and map it to the three-dimensional coordinate space to determine the adjustment angle and distance of the needle;

[0068] According to the deviation vector and the correction path coordinate sequence, an inverse kinematics algorithm is used to generate a control signal to adjust the direction of the guide needle;

[0069] Verify whether the adjusted guide needle positioning accuracy meets the submillimeter requirement. If so, update the navigation image sequence in the virtual reality interface to complete closed-loop control.

[0070] Specifically, the three-dimensional structural information of the knee joint is obtained from the patient's preoperative MRI data. An image segmentation algorithm is used to separate the tibia, femur, and posterior cruciate ligament stump area, and a three-dimensional anatomical model including vascular and nerve distribution is generated to determine the initial surgical planning area.

[0071] Based on the 3D anatomical model, an artificial intelligence path planning algorithm is used to generate the optimal guide needle puncture path by analyzing the geometric constraints of the tibial positioning point and the femoral connection area, combined with vascular and nerve distribution data, and obtaining the 3D coordinate sequence of the planned path;

[0072] A micro electromagnetic transmitter is integrated at the front end of the guide needle, and an electromagnetic receiver array is arranged outside the body. Through the triangulation positioning algorithm of the electromagnetic field signal strength, the position coordinates and posture angle of the guide needle in three-dimensional space are captured in real time to obtain the real-time motion trajectory data of the guide needle;

[0073] If the deviation between the real-time motion trajectory data of the guide needle and the three-dimensional coordinate sequence of the planned path exceeds a preset threshold, a dynamic path calibration algorithm is used to fit the real-time trajectory and the planned path through the least squares method to generate a corrected path coordinate sequence and determine the adjusted guide needle travel direction;

[0074] Based on the real-time motion trajectory data of the guide needle and the corrected path coordinate sequence, virtual reality rendering technology is used to superimpose the 3D anatomical model, the planned path, and the current position of the guide needle, generating a dynamic image sequence including a stereoscopic visual navigation interface, and obtaining intuitive guide needle guidance information.

[0075] If the guide needle position in the dynamic image sequence deviates from the correction path by more than a preset safety threshold, the deviation area is detected through an image processing algorithm, a deviation vector is generated and mapped into a three-dimensional coordinate space, and the precise adjustment angle and distance of the guide needle are determined;

[0076] Based on the deviation vector and the correction path coordinate sequence, the inverse kinematics algorithm is used to calculate the rotation angle and advancement distance required for guide needle adjustment, generate a control signal, and transmit it to the guide needle drive device through the electromagnetic feedback system to obtain the automatic adjustment instruction of the guide needle;

[0077] The adjusted guide needle position and posture data are obtained from the execution results of the guide needle drive device. By comparing it with the correction path coordinate sequence, the positioning accuracy is calculated using an error analysis algorithm to determine whether the guide needle meets the sub-millimeter accuracy requirement;

[0078] If the positioning accuracy meets the preset threshold, the superimposed display of the guide pin position and the three-dimensional anatomical model is updated through the virtual reality interface to generate the final navigation image sequence, determine the real-time guidance data for the surgical path, and complete the full-process closed-loop control of the guide pin positioning.

[0079] As an implementation manner in this embodiment, the process of generating the three-dimensional anatomical model includes:

[0080] Separate the tibia, femur, and the residual stump area of the posterior cruciate ligament from the nuclear magnetic resonance imaging data;

[0081] Mark the bone area through the threshold segmentation algorithm;

[0082] Adopt the region growing algorithm to expand from the boundary of the bone area and mark the blood vessel area and the nerve area.

[0083] Specifically, in step S101, obtain the three-dimensional structure information of the knee joint from the preoperative nuclear magnetic resonance imaging data of the patient, use the image segmentation algorithm to separate the tibia, femur, and the residual stump area of the posterior cruciate ligament, generate a three-dimensional anatomical model including the blood vessel and nerve distribution, and determine the initial surgical planning area.

[0084] Obtain the original three-dimensional structure data from the nuclear magnetic resonance imaging data, use the stereomicroscope algorithm to reconstruct the three-dimensional structure, perform preliminary positioning on the tibia area, femur area, and the residual stump area of the posterior cruciate ligament to obtain the three-dimensional structure dataset including bones and soft tissues. According to the three-dimensional structure dataset, use the threshold segmentation algorithm for processing. If the pixel gray value is greater than the preset bone threshold, it is marked as the bone area to obtain the separated bone area dataset. Through the bone area dataset, use the region growing algorithm to expand outward from the boundary of the bone area. If the pixel gray value meets the preset blood vessel threshold, it is marked as the blood vessel area. If the pixel gray value meets the preset nerve threshold, it is marked as the nerve area to generate the three-dimensional anatomical model including the blood vessel distribution and the nerve distribution. According to the three-dimensional anatomical model, use the stereoscopic projection algorithm to perform projection transformation on the tibia area, femur area, and the residual stump area of the posterior cruciate ligament to obtain the transformed projection dataset. Through the projection dataset, determine the initial surgical planning area.

[0085] More specifically, when obtaining the original three-dimensional structure data from the nuclear magnetic resonance imaging data, the T2-weighted imaging technology can be used to scan the knee joint area to generate a high-resolution three-dimensional stereoscopic dataset with a resolution of up to 0.5mm×0.5mm×1mm. The stereomicroscope algorithm generates a continuous three-dimensional structure including the tibia, femur, and the residual stump of the posterior cruciate ligament through voxel interpolation and surface reconstruction. This method can retain the boundary details of soft tissues and bones, which helps with subsequent accurate positioning.

[0086] In a possible implementation, for the preliminary positioning of the tibia, femur, and posterior cruciate ligament stump regions, regional marking and geometric feature extraction can be combined. Due to the tubular bone structure of the tibia region, it can be positioned through gradient analysis in the long-axis direction; due to the spherical joint characteristics of the femur region, it can be identified through curvature analysis; due to the fibrous structure of the posterior cruciate ligament stump, it can be preliminarily marked through texture features. This positioning method can effectively distinguish different anatomical regions and improve the accuracy of subsequent segmentation. When processing the three-dimensional structure dataset using the threshold segmentation algorithm, the bone gray-scale threshold can be set to 2000 HU (Hounsfield unit), and the pixels above this value are marked as the bone region.

[0087] It should be noted that the threshold needs to be calibrated according to the specific device and scanning parameters to avoid misjudging soft tissue as bone. The separated bone region dataset can clearly show the contours of the tibia and femur, providing a basis for subsequent blood vessel and nerve segmentation. Based on the bone region dataset, when the region growing algorithm expands outward from the bone boundary, the blood vessel gray-scale threshold can be set to 800 - 1200 HU, and the nerve gray-scale threshold can be set to 300 - 600 HU. Starting from the outer boundary of the tibia, if the gray-scale of a certain pixel is 900 HU, it is marked as a blood vessel; if the gray-scale is 400 HU, it is marked as a nerve. This method uses the gray-scale difference to achieve accurate classification, and the generated three-dimensional anatomical model containing the blood vessel and nerve distribution can intuitively display the anatomical relationship of the knee joint, which is helpful for surgical planning.

[0088] In one embodiment, when the stereoscopic projection algorithm performs projection transformation on the tibia, femur, and posterior cruciate ligament stump regions, the orthogonal projection method can be adopted to generate a two-dimensional projection dataset. For the posterior cruciate ligament stump, it can be projected from the anterior-posterior and lateral directions to retain its spatial position information. The transformed projection dataset can highlight the relative positions of key anatomical structures and reduce the complexity of surgical planning.

[0089] When determining the initial surgical planning area through the projection dataset, anatomical landmark points and lesion locations can be combined. If there is a tear in the posterior cruciate ligament stump, the coordinates of the tear site can be marked in the projection dataset, and combined with the projection contours of the tibia and femur, the surgical incision and repair path can be planned. This method can improve surgical accuracy, reduce intraoperative adjustment time, and significantly improve the repair effect. The overall process of the above technical solution can ensure seamless connection from image data to surgical planning. Especially in posterior cruciate ligament reconstruction surgery, it can avoid intraoperative damage through accurate blood vessel and nerve distribution information and improve the postoperative recovery effect.

[0090] As an implementation method in this embodiment, the process of generating the optimal guide needle puncture path includes:

[0091] Analyze the geometric constraints of the connection region between the tibia positioning point and the femur;

[0092] Combined with the vascular and nerve distribution data, a node coordinate sequence is generated by avoiding high-risk areas through the A* path planning algorithm.

[0093] The cubic spline interpolation method is used to smooth the node coordinate sequence.

[0094] Specifically, in step S102, for the three-dimensional anatomical model, an artificial intelligence path planning algorithm is adopted. By analyzing the geometric constraints of the tibia positioning point and the femoral connection area, combined with the vascular and nerve distribution data, an optimal guide needle puncture path is generated, and a three-dimensional coordinate sequence of the planned path is obtained.

[0095] More specifically, coordinate data of the tibia positioning point and the femoral connection area are obtained from the three-dimensional anatomical model. The coordinate data includes the three-dimensional coordinates of the tibia positioning point and the boundary point coordinates of the femoral connection area. Using the spatial geometry calculation method, for the three-dimensional coordinates of the tibia positioning point and the boundary point coordinates of the femoral connection area, the distance between the two areas is calculated. If the distance is greater than the preset threshold, it is marked as an effective connection area, and a coordinate data set of the effective connection area is obtained. According to the coordinate data set of the effective connection area, combined with the coordinate data of the vascular distribution and the nerve distribution, using the region segmentation algorithm, for the coordinate points of the vascular distribution and the nerve distribution, if the distance between the coordinate point and the boundary of the effective connection area is less than the preset threshold, it is marked as a high-risk area, and a coordinate data set of the high-risk area is obtained. Through the coordinate data set of the high-risk area, using the A path planning algorithm, for the path search from the tibia positioning point to the femoral connection area, the constraint condition of avoiding the high-risk area is set for the path points, the optimal path is calculated, and the node coordinate sequence of the optimal path is obtained. According to the node coordinate sequence of the optimal path, using the cubic spline interpolation method, the node coordinate sequence is smoothed to generate a continuous guide needle puncture path, and a three-dimensional coordinate sequence of the guide needle puncture path is obtained.

[0096] Exemplarily, when obtaining the coordinate data of the tibia positioning point and the femoral connection area from the three-dimensional anatomical model, the voxel marking method can be used. The tibia positioning point is usually selected as the center of the tibial plateau. By scanning the flat area at the upper end of the tibia in the three-dimensional model, the point with the highest voxel density is determined as the center coordinate, such as the coordinate (50, 30, 20). The boundary points of the femoral connection area can be obtained through curvature analysis, identifying the edge points of the lower femoral articular surface to form a boundary point set, such as (60, 35, 25), (62, 34, 24), etc. This method can accurately capture anatomical features and facilitate subsequent calculations.

[0097] In a possible implementation, for the distance calculation between the tibia positioning point and the femoral connection area, the Euclidean distance formula can be used. Assume the coordinates of the tibia positioning point are (50, 30, 20), and a boundary point of the femoral connection area is (60, 35, 25). Calculate the distance between the two points through spatial geometry. If the preset threshold is 15 mm, and the calculation result is greater than 15 mm, then mark the area to which the boundary point belongs as the effective connection area. This screening method can ensure the anatomical rationality of the connection area and provide a reliable basis for path planning.

[0098] Specifically, when marking high-risk areas based on the coordinate data set of the effective connection area and combining vascular and nerve distribution data, distance field analysis can be used. Assume the vascular coordinate point is (58, 33, 23), the nerve coordinate point is (59, 34, 24), the boundary point of the effective connection area is (60, 35, 25), and the preset distance threshold is 2 mm. If the distance between a vascular point and the boundary point is less than 2 mm, then mark it as a high-risk area. This method can effectively identify areas close to key anatomical structures and reduce the surgical risk.

[0099] When using the A* path planning algorithm to search for the optimal path from the tibia positioning point to the femoral connection area, the high-risk area can be set as a no-go zone. In the path search from (50, 30, 20) to (60, 35, 25), the algorithm preferentially selects nodes that avoid the high-risk area, such as detouring to (55, 32, 22). This path planning method can ensure the safety of the guide needle puncture path and at the same time maintain the optimal path length.

[0100] In one embodiment, when performing cubic spline interpolation on the node coordinate sequence of the optimal path, the node coordinate sequence such as (50, 30, 20), (55, 32, 22), (60, 35, 25) can be input into the interpolation model to generate a smooth guide needle puncture path. The path coordinate points after interpolation are continuous and have no acute angle changes. For example, new coordinate points (52, 31, 21) are generated. This smoothing process can ensure the stability of the guide needle during puncture and improve the fluency of the surgical operation.

[0101] It can be understood that each step of the above method is closely centered around the precise positioning of the knee joint anatomical structure and the safe path planning. Through the accurate acquisition of coordinate data, the reasonable screening of distance calculation, the detailed marking of high-risk areas, and the optimization and smoothing of the path, the whole process forms a tight logical chain, providing reliable technical support for surgical planning.

[0102] As an implementation method in this embodiment, the process of real-time capturing the three-dimensional position coordinates and attitude angles of the guide needle includes:

[0103] Calculating the relative distance between the front end of the guide needle and the electromagnetic receiver array through the triangulation algorithm of the electromagnetic field signal strength;

[0104] The real-time three-dimensional coordinates of the guide needle are determined based on the geometric layout of the receiver array.

[0105] Specifically, in step S103, a micro electromagnetic transmitter is integrated at the front end of the guide needle, and an electromagnetic receiver array is arranged outside the body. Through the triangulation positioning algorithm of the electromagnetic field signal strength, the position coordinates and posture angles of the guide needle in three-dimensional space are captured in real time to obtain the real-time motion trajectory data of the guide needle.

[0106] More specifically, electromagnetic signal data is acquired from a miniature electromagnetic transmitter at the front end of the guide needle, and valid signals with field strength values greater than a preset threshold are marked to obtain a field strength dataset of the valid signals. The strength of the valid signals is measured using multiple electromagnetic receivers in a receiving array, and the relative distance between the receivers and the front end of the guide needle is calculated to obtain the distance dataset. Based on the distance dataset, a triangulation algorithm is used to calculate the position coordinates of the guide needle front end in three-dimensional space, based on the geometric layout of the receiving array, to obtain the position coordinate dataset.

[0107] For example, when acquiring electromagnetic signal data from a miniature electromagnetic transmitter at the tip of a guide needle, valid signals can be filtered by setting a field strength threshold. The electromagnetic transmitter operates by generating electromagnetic waves of a specific frequency, with signal strength attenuating with distance. Assuming a threshold of 0.5 mT, signals below this value are considered noise. In actual operation, the signals emitted by the guide needle tip are captured by a receiving array, and signals with field strengths of, for example, 0.8 mT or 0.6 mT are recorded as valid signals, forming a field strength dataset. This screening method ensures data reliability and facilitates subsequent positioning calculations.

[0108] In one possible implementation, multiple electromagnetic receivers in a receiving array measure effective signal strength and calculate the relative distance to the guide needle tip. The receivers are typically arranged at known coordinates in three-dimensional space, such as four receivers at (0,0,0), (10,0,0), (0,10,0), and (0,0,10). Using a signal strength attenuation model, distance can be estimated: a field strength of 0.8 mT corresponds to a distance of 5 mm, and 0.6 mT to 6 mm. This method leverages the propagation characteristics of electromagnetic waves to ensure the accuracy of the distance dataset and provide a foundation for positioning.

[0109] Specifically, when using triangulation to calculate the three-dimensional coordinates of the guide needle tip, the geometric layout of the receiving array must be considered. Triangulation is based on multi-point ranging, inferring the spatial position of the transmitter using the receiver coordinates and the distance data set. Assuming the distance data set is 5mm, 6mm, 5.5mm, and 6.2mm, combined with the receiver coordinates, the guide needle tip coordinates can be determined as (4, 3, 2). To improve accuracy, a weighted averaging method can be introduced, prioritizing receiver data with higher signal strength. This method effectively mitigates signal interference and improves the stability of positioning results.

[0110] When dealing with complex anatomical environments, the triangulation algorithm can further improve accuracy through iterative optimization. For example, in knee surgery, the guide pin needs to avoid bones and soft tissues, and the receiving array may be interfered by metal implants. The iterative algorithm can exclude abnormal distance data through multiple calculations and generate a more reliable coordinate dataset, such as optimizing from the initial estimate (4.1, 3.2, 2.1) to (4, 3, 2). This method can adapt to the dynamic environment during surgery and ensure real-time tracking of the guide pin position. The position coordinate dataset can be used to guide the real-time adjustment of the guide pin. Assuming the surgical target point is (5, 4, 3) and the current front-end coordinate of the guide pin is (4, 3, 2), the system can prompt the adjustment direction and distance. This real-time feedback mechanism can help doctors precisely control the guide pin path and improve the fluency of surgical operations.

[0111] It can be understood that the above method closely revolves around electromagnetic signal processing and three-dimensional positioning. From signal screening to distance calculation and then to triangulation, each step takes data accuracy as the core, forming a complete logical chain. This method has high applicability in knee guide pin positioning and can effectively support the requirements of surgical navigation.

[0112] As an implementation manner in this embodiment, the implementation process of the dynamic path calibration algorithm includes:

[0113] Using the least squares method to fit the coordinate sequences of the real-time trajectory and the planned path;

[0114] Calculating the angle between the current traveling direction of the guide pin and the corrected path direction;

[0115] If the angle exceeds the preset angle threshold, generate a direction adjustment parameter and update the guide pin motion control parameter.

[0116] Specifically, in step S104, if the deviation between the real-time motion trajectory data of the guide pin and the three-dimensional coordinate sequence of the planned path exceeds the preset threshold, the dynamic path calibration algorithm is adopted to fit the real-time trajectory and the planned path by the least squares method, generate a corrected path coordinate sequence, and determine the adjusted traveling direction of the guide pin.

[0117] More specifically, obtain the real-time motion trajectory data of the guide needle to obtain a three-dimensional coordinate sequence of the real-time trajectory. For the preset three-dimensional coordinate sequence of the planned path, calculate the Euclidean distance between the three-dimensional coordinate sequence of the real-time trajectory and the three-dimensional coordinate sequence of the planned path. If the Euclidean distance is greater than the preset deviation threshold, determine the trajectory segment dataset to be calibrated. Use the least squares method to fit the real-time trajectory and the planned path in the trajectory segment dataset to obtain a three-dimensional coordinate dataset of the corrected path. According to the three-dimensional coordinate dataset of the corrected path, calculate the angle between the current traveling direction of the guide needle and the direction of the corrected path. If the angle is greater than the preset angle threshold, generate a direction adjustment parameter to obtain an adjusted traveling direction dataset. Update the motion control parameters of the guide needle through the traveling direction dataset to obtain an updated three-dimensional coordinate sequence of the real-time trajectory.

[0118] Exemplarily, when obtaining the real-time motion trajectory data of the guide needle, the displacement signal at the front end of the guide needle can be captured by an in vitro arranged sensor array to form a three-dimensional coordinate sequence. The sensor array usually adopts optical or electromagnetic positioning technology to record the position of the guide needle in the surgical space in real time. In knee surgery, the coordinates of the front end of the guide needle are recorded every 0.1 second to form a sequence such as (2, 3, 4), (2.1, 3.2, 4.1). This high-frequency sampling ensures the continuity of the trajectory data and provides a reliable basis for subsequent deviation analysis.

[0119] In a possible implementation, when calculating the Euclidean distance between the real-time trajectory and the planned path, it is necessary to preset the coordinate sequence of the planned path, such as (2, 3, 5), (2.2, 3.3, 5.2). By comparing the differences between the real-time coordinates and the planned coordinates, the Euclidean distance can be obtained. The distance between the real-time point (2.1, 3.2, 4.1) and the planned point (2.2, 3.3, 5.2) is approximately 1.1 mm. If the preset deviation threshold is 0.5 mm, this distance exceeds the standard, indicating that the trajectory deviates and this section of the trajectory needs to be calibrated. This method can quickly identify the deviation section and facilitate precise adjustment.

[0120] Specifically, when using the least squares method to fit the deviation trajectory segment, the coordinate points of the real-time trajectory can be curve-fitted with the planned path. The real-time trajectory segment contains points (2.1, 3.2, 4.1), (2.3, 3.4, 4.3), and the planned path segment is (2.2, 3.3, 5.2), (2.4, 3.5, 5.4). Through the least squares method, a smooth corrected path is generated, and the output coordinates are such as (2.15, 3.25, 4.8). This fitting method can smooth the trajectory fluctuations and generate corrected data that is more consistent with the planned path.

[0121] When calculating the angle between the advancing direction of the guide needle and the corrected path direction, the direction vector can be derived based on the coordinate sequence of the corrected path. The corrected path goes from (2.15, 3.25, 4.8) to (2.4, 3.5, 5.0), and the direction vector is (0.25, 0.25, 0.2). If the current direction vector of the guide needle is (0.2, 0.3, 0.1), the angle is approximately 15 degrees. If the preset angle threshold is 10 degrees, the direction needs to be adjusted. This vector analysis method is intuitive and efficient, ensuring that the guide needle advances in the correct direction.

[0122] In one embodiment, when generating the direction adjustment parameters, the adjustment angle and step size can be calculated according to the size of the angle. The 15-degree angle can be decomposed into the adjustment amounts in the horizontal and vertical directions, generating parameters such as "rotate 8 degrees to the right and adjust 5 degrees upward". These parameters form a data set of the advancing direction and are directly used to update the motion control of the guide needle. This parametric adjustment method can precisely control the movement of the guide needle. After updating the motion control parameters of the guide needle, a new trajectory coordinate sequence can be generated through a real-time feedback mechanism. After adjustment, the guide needle moves from (2.3, 3.4, 4.3) to (2.35, 3.45, 4.7), getting closer to the planned path. This closed-loop control method can continuously optimize the trajectory and ensure that the guide needle precisely fits the surgical requirements.

[0123] It should be noted that the above method takes data-driven as the core, forming a complete logical chain from trajectory acquisition to direction adjustment, and is applicable to high-precision scenarios such as knee surgery. Each step aims at real-time and accuracy, supporting the continuity and reliability of surgical navigation.

[0124] As an implementation manner in this embodiment, in step S105, according to the real-time motion trajectory data of the guide needle and the corrected path coordinate sequence, using virtual reality rendering technology, the three-dimensional anatomical model, the planned path, and the current position of the guide needle are superimposed and displayed to generate a dynamic image sequence including a stereoscopic vision navigation interface, obtaining intuitive guide needle advancing guidance information.

[0125] Specifically, obtain the three-dimensional coordinate sequence of the real-time trajectory of the guide pin, the three-dimensional coordinate sequence of the correction path, and the pre-established three-dimensional anatomical model data. Align the three-dimensional coordinate sequence of the real-time trajectory, the three-dimensional coordinate sequence of the correction path, and the three-dimensional anatomical model data in a virtual reality environment through data overlay technology to obtain an initial three-dimensional rendering data set. Use virtual reality rendering technology to perform lighting processing and texture mapping on the initial three-dimensional rendering data set to generate a sequence of rendering images. If the frame rate of the sequence of rendering images is lower than a preset threshold, supplement intermediate frames through an interpolation algorithm to obtain a sequence of dynamic images. According to the sequence of dynamic images, calculate the relative position deviation between the current position of the guide pin and the three-dimensional coordinate sequence of the correction path to obtain deviation data. Superimpose the deviation data and the sequence of dynamic images on the navigation interface through visual feedback technology to generate a travel guidance data set. If the deviation data is greater than a preset threshold, generate a highlighted prompt message and determine dynamic navigation guidance information.

[0126] Exemplarily, when obtaining the three-dimensional coordinate sequence of the real-time trajectory of the guide pin, the position data of the guide pin in the surgical space can be captured by an electromagnetic positioning system. During knee surgery, the coordinates of the front end of the guide pin are recorded every 0.05 seconds to form a sequence such as (1.5, 2.8, 3.6), (1.6, 2.9, 3.7). The three-dimensional coordinate sequence of the correction path can be generated by a path planning algorithm, such as (1.7, 3.0, 3.8), (1.8, 3.1, 3.9). The three-dimensional anatomical model data is generated based on preoperative CT scans and includes the spatial structures of the knee joint bones and soft tissues. This multi-source data acquisition method ensures the accuracy of subsequent data overlay.

[0127] In a possible implementation, data overlay technology aligns the real-time trajectory, the correction path, and the three-dimensional anatomical model in a virtual reality environment.

[0128] A coordinate transformation method based on feature points can be used to unify the coordinate systems of the three. For example, select the anatomical landmark points of the femur and tibia of the knee joint as references, and achieve coordinate alignment through matrix transformation to generate an initial three-dimensional rendering data set. This method can ensure the spatial consistency of different data sources and provide a reliable basis for rendering.

[0129] Furthermore, when the virtual reality rendering technology processes the initial three-dimensional rendering data set, the Phong lighting model can be used to simulate the light and shadow effects, and surface details of bones and soft tissues can be added to the anatomical model through texture mapping.

[0130] The guide pin trajectory is rendered as a red line, the correction path as a green line, and the anatomical model is shown as a semi-transparent skeletal structure. If the rendering frame rate is lower than a preset threshold such as 60 frames per second, intermediate frames can be generated through a linear interpolation algorithm. Interpolate the transition coordinates (1.7, 3.0, 3.8) between two frame coordinates (1.6, 2.9, 3.7) and (1.8, 3.1, 3.9) to form a smooth dynamic image sequence. This processing improves visual continuity.

[0131] It can be understood that when calculating the relative position deviation between the current position of the guide pin and the correction path, the distance between the real-time coordinates and the correction path coordinates can be compared. The current position of the guide pin is (1.6, 2.9, 3.7), and the correction path point is (1.7, 3.0, 3.8). The deviation distance is approximately 0.17 mm. If the preset threshold is 0.1 mm, then the deviation exceeds the standard. This deviation analysis provides a quantitative basis for navigation.

[0132] In one embodiment, the visual feedback technology superimposes the deviation data on the navigation interface. In a virtual reality headset, the deviation data is displayed as yellow numbers next to the guide pin trajectory, and the dynamic image sequence updates the relative position of the guide pin and the anatomical model in real time. If the deviation is greater than 0.1 mm, a highlighted prompt is generated, such as a red flashing arrow indicating the correction direction. This intuitive feedback facilitates the surgeon to quickly adjust the position of the guide pin.

[0133] It should be noted that the generation of the travel guidance dataset depends on the fusion of the deviation data and the dynamic image sequence. The navigation interface shows that the guide pin should move 0.1 mm to the right and adjust 0.05 mm downward, while highlighting the correction path direction. This closed-loop guidance method improves the accuracy and real-time performance of surgical navigation.

[0134] As an implementation manner in this embodiment, in step S106, if the position of the guide pin in the dynamic image sequence deviates from the correction path by more than the preset safety threshold, the deviation area is detected through an image processing algorithm, a deviation vector is generated and mapped to the three-dimensional coordinate space, and the precise adjustment angle and distance of the guide pin are determined.

[0135] Obtain the real-time three-dimensional coordinate data of the guide pin and the three-dimensional coordinate sequence of the correction path in the dynamic image sequence. Perform region segmentation on the dynamic image sequence through an image processing algorithm, identify the deviation region between the current position of the guide pin and the correction path, and generate the first deviation data set. If the deviation value in the first deviation data set exceeds the preset safety threshold, then use the vector calculation method to extract the deviation direction and distance from the first deviation data set to generate the first deviation vector data. Through the coordinate mapping algorithm, convert the first deviation vector data into the three-dimensional coordinate space, combine it with the three-dimensional coordinate sequence of the correction path, calculate the adjustment angle and adjustment distance of the guide pin, and obtain the first adjustment parameter data set. According to the first adjustment parameter data set, use the image rendering algorithm to process the navigation interface, superimpose the adjustment angle and adjustment distance on the dynamic image sequence, and generate a navigation guidance image sequence with real-time feedback.

[0136] Exemplarily, when obtaining the real-time three-dimensional coordinate data of the guide pin, the motion trajectory of the guide pin in the surgical space can be captured by an optical positioning system. During knee surgery, the coordinates of the front end of the guide pin are recorded every 0.1 second to form a sequence such as (2.0, 3.5, 4.0), (2.1, 3.6, 4.1). The three-dimensional coordinate sequence of the correction path is generated based on preoperative planning, such as (2.2, 3.7, 4.2), (2.3, 3.8, 4.3). The optical positioning system tracks the marker points on the guide pin through an infrared camera to ensure coordinate accuracy. This method provides a reliable data basis for subsequent deviation analysis.

[0137] In a possible implementation, when the image processing algorithm performs region segmentation on the dynamic image sequence, the edge detection method can be used to identify the contours of the guide pin and the correction path. The position area of the guide pin is extracted through the Canny edge detection algorithm to generate a binary image, and then compared with the preset area of the correction path to identify the deviation area. Assuming that the current position of the guide pin is (2.1, 3.6, 4.1) and the correction path point is (2.2, 3.7, 4.2), the deviation area is manifested as a set of pixels where the guide pin deviates from the path. This method facilitates the generation of the first deviation data set.

[0138] It should be noted that if the deviation value in the first deviation data set exceeds the preset safety threshold, such as 0.15 mm, the deviation vector calculation can be triggered.

[0139] Specifically, the vector calculation method extracts the deviation direction and distance by comparing the coordinates of the guide pin with the coordinates of the correction path. The deviation direction of the guide pin coordinates (2.1, 3.6, 4.1) and the path point (2.2, 3.7, 4.2) is along the positive directions of the X, Y, and Z axes, and the distance is approximately 0.17 mm, generating the first deviation vector data. This quantitative analysis provides a basis for calculating the adjustment parameters.

[0140] As an implementation, when the coordinate mapping algorithm converts the first deviation vector data into a three-dimensional coordinate space, an affine transformation method can be adopted. The deviation vector is mapped to the correction path coordinate system through matrix operations, and it is calculated that the guide needle needs to be adjusted by 0.1 mm along the X-axis, 0.1 mm along the Y-axis, and the rotation angle is 5 degrees, generating the first adjustment parameter data set. This method ensures the spatial consistency of the adjustment parameters.

[0141] In one embodiment, when the image rendering algorithm processes the navigation interface, a texture overlay technique can be used to visualize the adjustment parameters. In the navigation interface, the adjustment angle is displayed as a blue arrow, and the adjustment distance is marked with green numbers, overlaid on the dynamic image sequence. The rendering process maintains 60 frames per second to ensure the smoothness of the navigation guidance image sequence. This intuitive presentation facilitates the surgeon to quickly understand the adjustment requirements.

[0142] It can be understood that the navigation guidance image sequence with real-time feedback forms a closed-loop guidance mechanism by dynamically updating the adjustment parameters. After the guide needle is adjusted, the new coordinate sequence is compared with the correction path, and the deviation is reduced to 0.05 mm, and a green confirmation flag is displayed on the interface. This mechanism improves the real-time performance and accuracy of surgical navigation.

[0143] As an implementation in this embodiment, in step S107, according to the deviation vector and the correction path coordinate sequence, an inverse kinematics algorithm is used to calculate the rotation angle and the advancement distance required for the guide needle adjustment, generate a control signal, and transmit it to the guide needle driving device through an electromagnetic feedback system to obtain an automatic adjustment instruction for the guide needle.

[0144] Specifically, a dynamic image sequence is acquired, and an image processing algorithm is used to perform region segmentation on the dynamic image sequence to obtain the real-time three-dimensional coordinate data of the guide needle and the three-dimensional coordinate sequence of the correction path. According to the real-time three-dimensional coordinate data of the guide needle and the three-dimensional coordinate sequence of the correction path, the deviation is calculated to generate the first deviation data set. If the deviation value in the first deviation data set exceeds the preset safety threshold, the deviation direction and distance are extracted through a vector calculation method to obtain the first deviation vector data. An inverse kinematics algorithm is used to calculate the rotation angle and the advancement distance of the guide needle according to the first deviation vector data and the three-dimensional coordinate sequence of the correction path, generating the first adjustment parameter data set. According to the first adjustment parameter data set, a control signal is generated and transmitted to the driving device through an electromagnetic feedback system to obtain an automatic adjustment instruction for the guide needle. According to the automatic adjustment instruction, the movement trajectory of the guide needle is adjusted to generate the corrected three-dimensional coordinate data of the guide needle.

[0145] Exemplarily, when acquiring the dynamic image sequence, a high-speed infrared camera system can be used to capture the movement of the guide needle in the surgical space to form a high-resolution dynamic image sequence.

[0146] It should be noted that such a system usually combines optical marking technology. Specific reflective marks are attached to the surface of the guide pin, and the camera records the mark positions at a frequency of 100 frames per second, ensuring that the captured image sequence has high temporal resolution. During knee replacement surgery, every tiny displacement of the guide pin can be accurately recorded, forming a continuous image data stream, providing a reliable basis for subsequent processing.

[0147] In a possible implementation, when the image processing algorithm performs region segmentation on the dynamic image sequence, a deep learning-based segmentation method can be adopted.

[0148] Specifically, a pre-trained convolutional neural network model is used to identify the feature regions of the guide pin and the correction path. The network model is trained with preoperative annotation data and can distinguish the metal contour of the guide pin from the boundary of the surrounding soft tissue. The guide pin region is segmented into a set of white pixels, and the correction path region is a set of green pixels. The real-time three-dimensional coordinates of the guide pin are output, such as 2.3, 3.8, 4.4, and the correction path coordinates are such as 2.4, 3.9, 4.5. This method improves the robustness of the segmentation.

[0149] It can be understood that when calculating the deviation, a first deviation data set can be generated by comparing the real-time coordinates of the guide pin with the correction path coordinates. The difference between the guide pin coordinates 2.3, 3.8, 4.4 and the path coordinates 2.4, 3.9, 4.5 indicates that the deviation direction is the positive direction of the X, Y, and Z axes, and the deviation distance is about 0.2 mm. If the preset safety threshold is 0.15 mm, subsequent processing is triggered. This axis-by-axis comparison method ensures the comprehensiveness of the deviation analysis.

[0150] In one embodiment, when generating the first deviation vector data, a vector projection method can be used to extract the deviation direction and distance. The deviation vector is constructed from the coordinate differences, the direction points to the correction path, and the distance is approximated by the Euclidean distance. The deviation vector shows that the guide pin needs to move 0.1 mm in the positive direction of the X axis and 0.1 mm in the positive direction of the Y axis. This quantization method provides a clear basis for calculating the adjustment parameters.

[0151] Specifically, when the inverse kinematics algorithm is used to calculate the rotation angle and the advancement distance of the guide pin, it can be iteratively optimized based on the joint parameters of the robotic arm. The algorithm analyzes the angle between the deviation vector and the correction path, determines that the guide pin needs to rotate 6 degrees and advance 0.15 mm, and generates a first adjustment parameter data set. This method ensures that the adjustment instructions are consistent with the geometric constraints of the surgical space. When generating the control signal, the adjustment parameters can be converted into electrical signals of the electromagnetic feedback system through a digital-to-analog converter. Specifically, the signal drives the servo motor of the robotic arm to adjust the attitude of the guide pin.

[0152] In one embodiment, the electromagnetic feedback system transmits signals with a millisecond-level delay to ensure the real-time nature of the instructions. After the guide pin receives the instruction to rotate 6 degrees, it quickly adjusts to the target angle.

[0153] It is understandable that after adjusting the movement trajectory of the guide needle, the calibration effect can be verified by collecting coordinates again. After adjustment, the coordinates of the guide needle become 2.4, 3.9, 4.5, which is consistent with the calibration path, indicating that the trajectory calibration is successful. This closed-loop verification mechanism improves the reliability of navigation.

[0154] As an implementation manner in this embodiment, the process of verifying the positioning accuracy of the guide needle includes:

[0155] Comparing the position data of the guide needle after adjustment with the coordinate sequence of the calibration path;

[0156] Calculating the average deviation distance through an error analysis algorithm;

[0157] If the average deviation distance is less than the sub-millimeter-level threshold, it is determined that the positioning accuracy meets the standard.

[0158] Specifically, in step S108, the position and attitude data of the guide needle after adjustment are obtained from the execution result of the guide needle driving device. Through comparison with the coordinate sequence of the calibration path, the positioning accuracy is calculated using an error analysis algorithm to determine whether the guide needle meets the requirement of sub-millimeter-level accuracy.

[0159] More specifically, the position and attitude data of the guide needle after adjustment are obtained from the execution result of the guide needle driving device. A data parsing algorithm is used to extract the three-dimensional coordinates and direction angles of the guide needle, obtaining a first position data set and a first attitude data set. According to the first position data set and the first attitude data set, data comparison is performed with a preset coordinate sequence of the calibration path, and a vector difference calculation method is used to calculate the deviation of the position and attitude of the guide needle, obtaining a first deviation data set. For the first deviation data set, a least squares algorithm is used for error analysis to calculate the average deviation distance between the position of the guide needle and the calibration path, obtaining a positioning accuracy value. If the positioning accuracy value exceeds the preset sub-millimeter-level threshold, a signal indicating that the accuracy does not meet the standard is generated; if the positioning accuracy value is within the threshold range, a signal indicating that the accuracy meets the standard is generated. According to the signal indicating that the accuracy meets the standard or the signal indicating that the accuracy does not meet the standard, the positioning state of the guide needle is determined.

[0160] Exemplarily, when obtaining the execution result of the guide needle driving device, the real-time position and attitude data of the guide needle can be collected through a high-precision sensor system.

[0161] Specifically, the sensors include a laser rangefinder and a gyroscope, which are respectively used to capture the three-dimensional coordinates and direction angles of the guide needle. During knee surgery, the laser rangefinder records the position of the tip of the guide needle at a frequency of 200 times per second, generating coordinate data such as 2.5, 3.7, 4.3; the gyroscope records the tilt angle of the guide needle relative to the Z-axis, such as 5 degrees. This high-frequency acquisition method ensures the real-time nature and accuracy of the data, providing reliable input for subsequent analysis.

[0162] In a possible implementation, the data parsing algorithm can adopt filtering techniques to extract valid coordinates and angles.

[0163] As an implementation, the Kalman filtering algorithm is used to process sensor noise and smooth the three-dimensional coordinates and direction angles of the guide needle. The original coordinates 2.5, 3.7, 4.3 are optimized to 2.51, 3.72, 4.29 after filtering, and the angle is corrected from 5 degrees to 4.8 degrees. Such a processing method improves the accuracy of the first position data set and the first attitude data set, laying a foundation for deviation analysis.

[0164] It should be noted that when comparing with the calibrated path coordinate sequence, data alignment can be performed through a point-by-point matching method.

[0165] Specifically, the calibrated path coordinates such as 2.6, 3.8, 4.4 are compared with the guide needle coordinates 2.51, 3.72, 4.29 axis by axis, and the vector difference is calculated. The deviation of the X axis is 0.09, the Y axis is 0.08, and the Z axis is 0.11. This axis-by-axis analysis method ensures the comprehensiveness of deviation calculation, and the generated first deviation data set clearly reflects the deviation direction of the guide needle.

[0166] In an embodiment, when using the least squares method to analyze the first deviation data set, the average deviation distance can be calculated by fitting the deviation point set. The deviation data collected multiple times shows that the average distance between the guide needle position and the calibrated path is 0.12 millimeters. If the preset sub-millimeter threshold is 0.1 millimeter, the positioning accuracy value of 0.12 millimeters triggers a signal indicating that the accuracy is not up to standard. This analysis method quantifies the positioning error and provides a basis for subsequent adjustments.

[0167] When generating the accuracy signal, the analysis result can be converted into an input of the control system through a signal encoder. A signal indicating that the accuracy is not up to standard may prompt that the guide needle needs further fine-tuning, while a signal indicating that the accuracy meets the standard confirms that the current positioning state is reliable.

[0168] Specifically, the signal indicating that the accuracy meets the standard can be directly transmitted to the navigation system to instruct the guide needle to continue advancing along the current path. This signal generation method improves the automation level of the system.

[0169] It can be understood that when determining the positioning state of the guide needle, trend analysis can be performed in combination with historical deviation data.

[0170] As an implementation, if the deviation is within 0.05 millimeters for three consecutive signals indicating that the accuracy meets the standard, it is confirmed that the guide needle is stably on the target path; if the signal indicating that the accuracy is not up to standard appears repeatedly, it may indicate a problem with the robotic arm calibration. In a stable state, the guide needle coordinates continuously match the calibrated path, indicating that the positioning system is operating well. This trend analysis enhances the robustness of state determination and provides a reliable guarantee for surgical navigation.

[0171] As an implementation method in this embodiment, in step S109, if the positioning accuracy meets the preset threshold, the superimposed display of the guide needle position and the three-dimensional anatomical model is updated through the virtual reality interface to generate the final navigation image sequence, and the real-time guidance data for the surgical path is determined to complete the full-process closed-loop control of the guide needle positioning.

[0172] Specifically, the guide needle position data and the three-dimensional anatomical model data are obtained from the virtual reality interface. The coordinate transformation algorithm is used to map the guide needle position data to the reference coordinate system of the three-dimensional anatomical model to obtain the first superimposed data set. According to the first superimposed data set, the image rendering algorithm is used to generate the navigation image including the guide needle position and the three-dimensional anatomical structure to obtain the first image sequence. For the first image sequence and the preset surgical path data, the vector matching algorithm is used to calculate the deviation between the guide needle position and the surgical path data to obtain the first deviation data. It is judged whether the first deviation data is within the preset threshold range to obtain the first path guidance data. If the first path guidance data meets the preset threshold, the closed-loop control algorithm is used to update the motion parameters of the guide needle to obtain the real-time guidance data. According to the real-time guidance data, the final surgical navigation path is determined.

[0173] Exemplarily, when obtaining the guide needle position data and the three-dimensional anatomical model data from the virtual reality interface, it can be realized through the head-mounted display device and the motion tracking system.

[0174] Specifically, the head-mounted display device is built-in with a high-resolution camera to capture the optical markers on the guide needle to generate position data, such as coordinates 3.2, 4.1, 5.0; the three-dimensional anatomical model data is generated from the preoperative CT scan and includes the bone and soft tissue structures of the knee joint. This method ensures the real-time nature of the data source and the accuracy of the anatomical structure, providing a basis for subsequent mapping.

[0175] In a possible implementation method, the coordinate transformation algorithm is used to map the guide needle position data to the reference coordinate system of the three-dimensional anatomical model.

[0176] It should be noted that the coordinate transformation is based on the principle of rigid body transformation, and the guide needle coordinates and the model coordinates are aligned through the rotation matrix and the translation vector. The guide needle coordinates 3.2, 4.1, 5.0 are mapped to 3.25, 4.08, 4.95 after transformation to form the first superimposed data set. This mapping method ensures the spatial consistency of the two sets of data and is convenient for subsequent image generation.

[0177] Specifically, the image rendering algorithm can be based on the principle of a stereomicroscope to convert the first superimposed data set into a navigation image.

[0178] In one embodiment, the rendering algorithm utilizes GPU acceleration to generate a real-time image sequence that includes the position of the guide pin and the knee joint structure. The tip of the guide pin is displayed marked in red, and the bones are rendered in gray transparency to generate the first image sequence. This visualization method intuitively presents the relative position of the guide pin and the anatomical structure, facilitating intraoperative navigation.

[0179] As an implementation, the vector matching algorithm is used to calculate the deviation between the position of the guide pin and the preset surgical path. The surgical path data is 3.3, 4.2, 5.1, and the guide pin position is 3.25, 4.08, 4.95. After comparing axis by axis, the deviation 0.05, 0.12, 0.15 is obtained to form the first deviation data. This point-by-point analysis method clearly quantifies the deviation direction and provides a basis for path guidance.

[0180] In one embodiment, when determining whether the first deviation data is within the threshold range, the preset threshold is 0.1 millimeter. The deviations 0.05, 0.12, 0.15 indicate that the Y-axis and Z-axis exceed the threshold, generating the first path guidance data and prompting that the direction of the guide pin needs to be adjusted. This judgment method improves the accuracy of navigation.

[0181] It can be understood that the closed-loop control algorithm updates the movement parameters of the guide pin through the deviation data. Based on the deviations 0.12 and 0.15, the algorithm adjusts the rotation angle and the propulsion speed of the robotic arm to generate real-time guidance data. This closed-loop mechanism ensures that the guide pin dynamically follows the target path. When determining the final surgical navigation path, the real-time guidance data is compared with the surgical path data. If the deviation continues to be less than 0.1 millimeter, the path is confirmed to be reliable. This method verifies through multi-dimensional data to ensure the stability of the navigation path and provides reliable guidance for the surgery.

[0182] Based on this, an electromagnetic-sensing-based guide pin path navigation method provided by an embodiment of the present invention is used to assist in the precise positioning of medical devices in the knee joint area. The system analyzes the patient's preoperative magnetic resonance imaging to generate a three-dimensional anatomical model including the distribution of blood vessels and nerves, and uses an intelligent algorithm to plan the movement path of the guide pin. During the positioning process, the spatial position of the guide pin is captured in real time through electromagnetic positioning technology, combined with a dynamic path calibration algorithm and virtual reality display to generate navigation guidance information. When the guide pin deviates from the preset path, the system automatically calculates the adjustment parameters and performs precise adjustment through electromagnetic feedback to achieve sub-millimeter positioning accuracy. The present invention significantly improves the positioning accuracy and operation safety of the device by integrating electromagnetic sensing, dynamic calibration, and virtual reality technologies.

[0183] Embodiment 2

[0184] In this embodiment, a computer terminal device is provided, including:

[0185] One or more processors;

[0186] A memory, coupled to the processor, for storing one or more programs;

[0187] When the one or more programs are executed by the one or more processors, the one or more processors implement the methods in the above embodiments.

[0188] In this embodiment, a computer-readable storage medium is further provided, on which a computer program is stored. When the computer program is executed by a processor, the methods in the above embodiments are implemented.

[0189] In this embodiment, an electronic device is further provided, including a memory and a processor. A computer program is stored in the memory, and the processor is configured to run the computer program to execute the methods in the above embodiments.

[0190] The above programs can run in a processor or can also be stored in a memory (or referred to as a computer-readable medium). The computer-readable medium includes permanent and non-permanent, removable and non-removable media and can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0191] These computer programs can also be loaded onto a computer or other programmable data processing device, so that a series of operation steps are executed on the computer or other programmable device to generate computer-implemented processing. Thus, the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in a process Figure 1 a process or multiple processes and / or blocks Figure 1 The steps corresponding to different steps can be implemented by different modules.

[0192] In this embodiment, such a device or system is provided. The system is called an electromagnetic sensing-based guide needle path navigation system, including:

[0193] A three-dimensional structure information acquisition module, configured to acquire three-dimensional knee joint structure information from preoperative magnetic resonance imaging data of a patient and generate a three-dimensional anatomical model including blood vessel and nerve distributions;

[0194] An artificial intelligence path planning module for generating a three-dimensional coordinate sequence of an optimal guide needle puncture path for the three-dimensional anatomical model;

[0195] An electromagnetic positioning module for capturing the three-dimensional position coordinates and attitude angles of the guide needle in real time through a micro electromagnetic transmitter integrated at the front end of the guide needle and an electromagnetic receiver array arranged outside the body;

[0196] A dynamic path calibration module for generating a corrected path coordinate sequence when the deviation between the real-time movement trajectory of the guide needle and the planned path exceeds a preset threshold;

[0197] A virtual reality navigation module for generating a dynamic image sequence containing guide needle travel guidance information based on the real-time movement trajectory and the corrected path coordinate sequence;

[0198] A deviation detection module for generating a deviation vector and mapping it to a three-dimensional coordinate space when the position of the guide needle in the dynamic image sequence deviates from the corrected path by more than a preset safety threshold;

[0199] A guide needle adjustment control module for generating a control signal to adjust the travel direction of the guide needle according to the deviation vector and the corrected path coordinate sequence;

[0200] A positioning accuracy verification module for verifying whether the positioning accuracy of the adjusted guide needle meets the sub-millimeter level requirement;

[0201] A navigation image update module for updating the navigation image sequence in the virtual reality interface when the positioning accuracy meets the standard to complete the closed-loop control.

[0202] As an implementation manner in this embodiment, the three-dimensional structure information acquisition module includes:

[0203] An image segmentation unit for separating the tibia, femur, and posterior cruciate ligament stump regions from the nuclear magnetic resonance imaging data;

[0204] A bone marking unit for marking the bone region through a threshold segmentation algorithm;

[0205] A vascular and nerve marking unit for expanding and marking the vascular region and the nerve region from the boundary of the bone region by using a region growing algorithm.

[0206] As an implementation manner in this embodiment, the artificial intelligence path planning module includes:

[0207] A geometric constraint analysis unit for analyzing the geometric constraints of the tibia positioning point and the femoral connection region;

[0208] A path obstacle avoidance unit for avoiding high-risk regions and generating a node coordinate sequence through the A* path planning algorithm in combination with the vascular and nerve distribution data;

[0209] A path smoothing unit for smoothing the node coordinate sequence by using the cubic spline interpolation method.

[0210] As an implementation manner in this embodiment, the electromagnetic positioning module includes:

[0211] A signal strength calculation unit for calculating the relative distance between the front end of the guide needle and the electromagnetic receiver array through the triangulation algorithm of the electromagnetic field signal strength;

[0212] A coordinate analysis unit for determining the real-time three-dimensional coordinates of the guide needle based on the geometric layout of the receiver array.

[0213] As an implementation manner in this embodiment, the dynamic path calibration module includes:

[0214] A trajectory fitting unit for fitting the coordinate sequences of the real-time trajectory and the planned path by using the least squares method;

[0215] A direction deviation calculation unit for calculating the included angle between the current traveling direction of the guide needle and the direction of the corrected path;

[0216] A parameter generation unit for generating a direction adjustment parameter and updating the motion control parameter of the guide needle when the included angle exceeds a preset angle threshold.

[0217] As an implementation manner in this embodiment, the positioning accuracy verification module includes:

[0218] A data comparison unit for comparing the adjusted guide needle position data with the coordinate sequence of the corrected path;

[0219] An error calculation unit for calculating the average deviation distance through an error analysis algorithm;

[0220] A determination unit for determining that the positioning accuracy meets the standard when the average deviation distance is less than the sub-millimeter level threshold.

[0221] This system or device is used to implement the functions of the method in the above embodiment. Each module in this system or device corresponds to each step in the method. Those that have been described in the method will not be repeated here.

[0222] Through the above implementation manner, the problem of guide needle path navigation based on electromagnetic sensing in the related technology is solved, so as to ensure that the problems existing in the prior art can be solved.

[0223] Embodiment III

[0224] Based on the same general inventive concept, the present invention also provides a needle guiding path navigation system based on electromagnetic sensing. The needle guiding path navigation system based on electromagnetic sensing provided by the present invention is described below. The needle guiding path navigation system based on electromagnetic sensing described below can be correspondingly referred to the needle guiding path navigation method based on electromagnetic sensing described above. For example, Figure 4 As shown, the system includes:

[0225] A three-dimensional structure information acquisition module, configured to acquire three-dimensional knee joint structure information from the preoperative magnetic resonance imaging data of the patient, separate the tibia, femur, and posterior cruciate ligament stump regions by using an image segmentation algorithm, generate a three-dimensional anatomical model including vascular and nerve distributions, and determine an initial surgical planning area;

[0226] An artificial intelligence path planning module, configured to, for the three-dimensional anatomical model, adopt an artificial intelligence path planning algorithm, generate an optimal needle puncture path by analyzing the geometric constraints of the tibia positioning point and the femoral connection region, and combining the vascular and nerve distribution data, and obtain a three-dimensional coordinate sequence of the planned path;

[0227] An electromagnetic positioning module, configured to integrate a micro electromagnetic transmitter at the front end of the needle, arrange an electromagnetic receiver array outside the body, and capture the position coordinates and attitude angles of the needle in the three-dimensional space in real time through a triangulation algorithm of the electromagnetic field signal intensity, and obtain real-time motion trajectory data of the needle;

[0228] A dynamic path calibration module, configured to, if the deviation between the real-time motion trajectory data of the needle and the three-dimensional coordinate sequence of the planned path exceeds a preset threshold, adopt a dynamic path calibration algorithm, fit the real-time trajectory and the planned path by the least squares method, generate a corrected path coordinate sequence, and determine the adjusted needle advancing direction;

[0229] A virtual reality navigation module, configured to, according to the real-time motion trajectory data of the needle and the corrected path coordinate sequence, adopt virtual reality rendering technology, superimpose and display the three-dimensional anatomical model, the planned path, and the current position of the needle, generate a dynamic image sequence including a stereoscopic vision navigation interface, and obtain intuitive needle advancing guiding information;

[0230] A deviation detection module, configured to, if the position of the needle in the dynamic image sequence deviates from the corrected path by more than a preset safety threshold, detect the deviation area through an image processing algorithm, generate a deviation vector and map it to the three-dimensional coordinate space, and determine the precise adjustment angle and distance of the needle;

[0231] A needle adjustment control module, configured to calculate the rotation angle and the advancing distance required for needle adjustment according to the deviation vector and the corrected path coordinate sequence by using an inverse kinematics algorithm, generate a control signal, and transmit it to the needle driving device through an electromagnetic feedback system to obtain an automatic adjustment instruction for the needle;

[0232] The positioning accuracy verification module is used to obtain the adjusted guide pin position and attitude data from the execution results of the guide pin driving device. By comparing with the calibration path coordinate sequence, an error analysis algorithm is used to calculate the positioning accuracy and determine whether the guide pin meets the requirement of sub-millimeter accuracy.

[0233] The navigation image update module is used to, if the positioning accuracy meets the preset threshold, update the superimposed display of the guide pin position and the three-dimensional anatomical model through the virtual reality interface, generate the final navigation image sequence, determine the real-time guidance data for the surgical path, and complete the full-process closed-loop control of the guide pin positioning.

[0234] It should be understood that a guide pin path navigation system based on electromagnetic sensing provided by an embodiment of the present invention has all the advantages of the guide pin path navigation method based on electromagnetic sensing provided by the above embodiment.

[0235] The above are only the preferred specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for guiding the needle path based on electromagnetic sensing, characterized in that, Including the following steps: Obtain the three-dimensional structure information of the knee joint from the preoperative magnetic resonance imaging data of the patient, and generate a three-dimensional anatomical model including the distribution of blood vessels and nerves; For the three-dimensional anatomical model, use an artificial intelligence path planning algorithm to generate a three-dimensional coordinate sequence of the optimal guide needle puncture path; Integrate a micro electromagnetic emitter at the front end of the guide needle, and use an electromagnetic receiver array arranged outside the body to capture the three-dimensional position coordinates and attitude angles of the guide needle in real time; If the deviation between the real-time movement trajectory of the guide needle and the planned path exceeds the preset threshold, use a dynamic path calibration algorithm to generate a corrected path coordinate sequence; According to the real-time movement trajectory and the corrected path coordinate sequence, use virtual reality rendering technology to generate a dynamic image sequence including the guide needle travel guidance information; If the position of the guide needle in the dynamic image sequence deviates from the corrected path by more than the preset safety threshold, use an image processing algorithm to generate a deviation vector and map it to the three-dimensional coordinate space to determine the adjustment angle and distance of the guide needle; According to the deviation vector and the corrected path coordinate sequence, use an inverse kinematics algorithm to generate a control signal to adjust the travel direction of the guide needle; Verify whether the positioning accuracy of the adjusted guide needle meets the sub-millimeter level requirement. If it meets, update the navigation image sequence in the virtual reality interface to complete the closed-loop control.

2. The method according to claim 1, wherein The process of generating the three-dimensional anatomical model includes: Separate the tibia, femur and posterior cruciate ligament stump regions from the magnetic resonance imaging data; Mark the bone region by a threshold segmentation algorithm; Use a region growing algorithm to expand from the boundary of the bone region and mark the blood vessel region and the nerve region.

3. The method according to claim 1, characterized in that The process of generating the optimal guide needle puncture path includes: Analyze the geometric constraints of the tibia positioning point and the femoral connection region; Combined with the blood vessel and nerve distribution data, use the A* path planning algorithm to avoid high-risk regions and generate a node coordinate sequence; Use the cubic spline interpolation method to smooth the node coordinate sequence.

4. The method according to claim 1, wherein The process of capturing the three-dimensional position coordinates and attitude angles of the guide needle in real time includes: Calculate the relative distance between the front end of the guide needle and the electromagnetic receiver array by a triangulation algorithm based on the electromagnetic field signal intensity; Determine the real-time three-dimensional coordinates of the guide needle based on the geometric layout of the receiver array.

5. The method according to claim 1, wherein The implementation process of the dynamic path calibration algorithm includes: Use the least squares method to fit the coordinate sequences of the real-time trajectory and the planned path; Calculate the angle between the current travel direction of the guide needle and the corrected path direction; If the angle exceeds the preset angle threshold, generate a direction adjustment parameter and update the guide needle movement control parameters.

6. The method according to claim 1, wherein The process of verifying the positioning accuracy of the guide needle includes: Compare the adjusted guide needle position data with the corrected path coordinate sequence; Calculate the average deviation distance by an error analysis algorithm; If the average deviation distance is less than the sub-millimeter level threshold, determine that the positioning accuracy meets the standard.

7. A needle guiding path navigation system based on electromagnetic sensing, characterized in that, The system includes: A three-dimensional structure information acquisition module for obtaining the three-dimensional structure information of the knee joint from the preoperative magnetic resonance imaging data of the patient and generating a three-dimensional anatomical model including the distribution of blood vessels and nerves; An artificial intelligence path planning module for generating a three-dimensional coordinate sequence of the optimal guide needle puncture path for the three-dimensional anatomical model; An electromagnetic positioning module, which is used to capture the three-dimensional position coordinates and attitude angles of the guide needle in real time through a micro electromagnetic emitter integrated at the front end of the guide needle and an electromagnetic receiver array arranged outside the body; A dynamic path calibration module, which is used to generate a corrected path coordinate sequence when the deviation between the real-time movement trajectory of the guide needle and the planned path exceeds a preset threshold; A virtual reality navigation module, which is used to generate a dynamic image sequence containing guide needle travel guidance information according to the real-time movement trajectory and the corrected path coordinate sequence; A deviation detection module, which is used to generate a deviation vector and map it to a three-dimensional coordinate space when the position of the guide needle in the dynamic image sequence deviates from the corrected path by more than a preset safety threshold; A guide needle adjustment control module, which is used to generate a control signal to adjust the travel direction of the guide needle according to the deviation vector and the corrected path coordinate sequence; A positioning accuracy verification module, which is used to verify whether the positioning accuracy of the adjusted guide needle meets the sub-millimeter level requirement; A navigation image update module, which is used to update the navigation image sequence in the virtual reality interface when the positioning accuracy meets the standard, and complete the closed-loop control.

8. The system according to claim 7, wherein The three-dimensional structure information acquisition module includes: An image segmentation unit, which is used to separate the tibia, femur and posterior cruciate ligament stump regions from the nuclear magnetic resonance imaging data; A bone marking unit, which is used to mark the bone region through a threshold segmentation algorithm; A blood vessel and nerve marking unit, which is used to expand from the boundary of the bone region and mark the blood vessel region and nerve region by using a region growing algorithm.

9. A computer terminal device, characterized in that, Including: One or more processors; A memory, which is coupled to the processor and used to store one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the electromagnetic sensing-based guide needle path navigation method according to any one of claims 1-6.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the electromagnetic sensing-based guide needle path navigation method according to any one of claims 1-6.

Images