Integrated orthopedic surgical robot

Abstract

The application discloses an integrated orthopedic surgery robot, which comprises a control device, a mechanical arm, an intelligent instrument library, a multi-modal image import module, an individualized kinematics planning system, a surgery planning and execution system, a force feedback and safety system and a graphical user interface. The integrated orthopedic surgery robot can cover various surgery scenes, reduce the cost of a single surgery, improve the work efficiency of a surgery room, overcome the limitations of a traditional single surgery robot in cost, resource utilization, operation training, surgery adaptability and technical updating, realize higher integration, standardization and intelligentization, and thus better serve diversified orthopedic surgery demands.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of medical devices, and relates to an integrated orthopedic surgery robot. BACKGROUND

[0002] In traditional orthopedic surgery, due to limited surgical precision, insufficient surgical planning, and complex instrument switching, there is a certain instability in surgical effectiveness and safety.

[0003] Traditional single-surgery robots, such as robots dedicated to spinal surgery, hip surgery, or knee surgery, while showing certain advantages in their respective fields, such as improving surgical precision, reducing trauma, and shortening recovery time, also have the following problems:

[0004] 1. High cost: The research and development, production, purchase, and maintenance costs of each type of single-surgery robot are very high. If a hospital wants to cover multiple orthopedic surgery fields, it needs to purchase multiple sets of different types of surgery robots, which is a considerable economic burden for many medical institutions.

[0005] 2. Poor technology closure and compatibility: Different types of surgery robots often use independent operating systems and accessories, which means that doctors need to learn and train specifically for each robot, and surgical instruments cannot be universal, which is not conducive to resource sharing and optimization.

[0006] 3. Limited surgical adaptability: Single-surgery robots often only target a specific part or type of surgery, and when faced with complex conditions or the need for comprehensive cross-field surgery, such robots are limited in function.

[0007] Therefore, the present application proposes an integrated orthopedic surgery robot system to solve the above problems and improve the accuracy, safety, and efficiency of surgery SUMMARY

[0008] The present application overcomes at least one deficiency of the prior art and provides an integrated orthopedic surgery robot.

[0009] To achieve the above-mentioned purpose, the present application adopts the following technical solution: an integrated orthopedic surgery robot, comprising a control device, a mechanical arm, an intelligent instrument library, a multi-modal image import module, an individualized kinematics planning system, a surgical planning and execution system, a force feedback and safety system, and a graphical user interface,

[0010] The control device is linked with the mechanical arm, and through real-time calculation and transmission of movement instructions, the movement of the mechanical arm in three-dimensional space is controlled;

[0011] The control device is linked with the intelligent instrument library, and surgical instruments are automatically allocated and called according to surgical planning, improving the efficiency of the operating room.

[0012] The control device is linked with the multi-modal image import module: the processed image data is presented in real time in front of the doctor, assisting the doctor to perform precise surgical operation;

[0013] The control device is linked with the individualized kinematics planning system: intelligent surgical path planning is performed according to individual differences;

[0014] The control device is connected with the graphical user interface for displaying the surgical path planning and serving as an interactive interface.

[0015] Further, the control device comprises a main controller composed of computer hardware, an operating system and a communication interface, and the main controller further integrates a CPU, a GPU and a storage device inside, for processing algorithms, real-time data streams and medical image data.

[0016] Further, the operating system receives and processes signals of the intelligent instrument library and the mechanical arm in real time, and is also used for executing surgical planning, navigation algorithms and human-computer interaction, the operating system embeds motion planning and control algorithms, controls the action of the mechanical arm, and can make intelligent decisions through integrated AI algorithms.

[0017] Further, the operating system comprises a motion planning and control module, an image processing and registration module, an artificial intelligence and deep learning module and a human-computer interaction module,

[0018] The motion planning and control module: the control instructions sent by the main controller are analyzed, and the motion trajectory is obtained by combining the motion planning and control algorithm to control the action of the end effector of the mechanical arm, wherein the motion planning and control algorithm is stored in the motion planning and control module;

[0019] The image processing and registration module: the preoperative image is accurately corresponded with the intraoperative real-time image by combining the image registration algorithm, guiding the positioning of the surgical instrument, wherein the image registration algorithm is stored in the image processing and registration module;

[0020] The artificial intelligence and deep learning module: the case data is learned and trained by combining the deep learning algorithm, the intelligent degree of the surgical planning is improved, and the doctor is assisted to make decisions, wherein the deep learning algorithm is stored in the artificial intelligence and deep learning module.

[0021] Further, the mechanical arm is a multi-degree-of-freedom mechanical arm, which is composed of joints with multiple degrees of freedom, and the end of the mechanical arm carries a modular end effector, and the end effector is connected with the surgical instrument.

[0022] Further, the end effector is provided with a standardized interface, through which the end effector is connected and disconnected with the mechanical arm; the end effector is provided with a driving module, which is a servo motor, controlling the movement of the surgical instrument; the end effector is provided with a tool clamping system, which adopts an electrically controlled magnetic adsorber or a quick-change jaw, clamping and controlling different types of surgical instruments; the shell of the end effector is made of medical-grade stainless steel or titanium alloy and other biocompatible materials; the end effector is provided with a sensor assembly, which includes a torque sensor and a position sensor, monitoring and feeding back the force and position information of the contact between the surgical instrument and the tissue.

[0023] Further, the multi-modal image import module receives and processes various image data, performs three-dimensional reconstruction and real-time navigation using GPU, matches the three-dimensional image planned before the operation with the real-time two-dimensional image during the operation through an image registration algorithm, and obtains the position and direction of the surgical instrument.

[0024] Further, the individualized kinematic planning system includes a three-dimensional imaging and modeling module, a surgical planning module, a path planning module, and a dynamic adjustment module.

[0025] The three-dimensional imaging and modeling module uses image data to obtain a three-dimensional model of the bone, and reconstructs the three-dimensional bone model through a three-dimensional modeling algorithm.

[0026] The surgical planning module plans the operation according to the reconstructed three-dimensional bone model.

[0027] The path planning module calculates the surgical path from the initial position to the target position based on a path planning algorithm, the spatial limitations of the surgical instrument, and the safety boundary, and the path planning algorithm is stored in the path planning module.

[0028] The dynamic adjustment module receives feedback information from the sensor assembly in real time, combines with the preset safety threshold, and the system can automatically adjust or prompt the doctor to adjust the surgical path to avoid damaging the surrounding soft tissue and nerve and blood vessel structures.

[0029] Further, the three-dimensional imaging and modeling module reconstructs the three-dimensional bone model in the following steps:

[0030] 1. Image data processing: import image data and do preprocessing, and then do contrast enhancement processing on the image after preprocessing;

[0031] 2. Three-dimensional reconstruction algorithm:

[0032] Perform operations on three-dimensional volume data, map the properties of each voxel to color and transparency, and generate continuous three-dimensional images with depth perception,

[0033] Color and transparency mapping: use linear or nonlinear mapping functions to map CT values to color and transparency.

[0034] Light projection and integration: for each pixel on the final image, a ray is cast from the viewpoint through the volume data, and the attributes of the voxels are integrated along the way;

[0035] Geometry optimization and detail enhancement, as well as model smoothing: based on model smoothing-Laplacian smoothing to keep the boundaries of the model clear, including:

[0036] Constructing an adjacency matrix: for each vertex (v), construct its neighborhood vertex set (N(v)), and construct an adjacency matrix based on it, which is used to store the connection relationship between vertices;

[0037] Calculating weights: the influence of vertices (u) in (N(v)) on (v) is not necessarily the same, and different weights (w_{uv}) are given;

[0038] Iterative smoothing: multiple iterations, updating the positions of all vertices after each iteration, until the preset smoothing degree is met or the maximum number of iterations is reached.

[0039] Further, the specific operations of the path planning module are environment modeling, target setting, constraint conditions, path smoothing and optimization, and collision detection and obstacle avoidance:

[0040] The operation of environment modeling specifically includes three-dimensional model conversion, surgical space definition

[0041] The operation of three-dimensional model conversion includes:

[0042] Data input: the three-dimensional model extracted from the image data exists in the form of point cloud, voxel grid or triangular facet, and these data are stored in DICOM standard format;

[0043] Surface reconstruction: using a three-dimensional reconstruction algorithm to convert voxel data into a continuous surface model, obtaining the accurate three-dimensional shape of the patient's skeleton or other anatomical structure;

[0044] Coordinate system definition: defining a global coordinate system, as well as the local coordinate systems of surgical instruments and robots;

[0045] The operation of surgical space definition includes:

[0046] Reachability analysis: calculating the working radius, length and bendable degree of the surgical instrument to determine its reachable range in the surgical space; to determine the position and attitude of the instrument tip under a given joint configuration;

[0047] Safety boundary setting: defining the minimum safety distance of soft tissue, nerves and blood vessels around the bone, the safety boundary is a distance-based buffer zone, which is formed by setting a distance outside the surface of the anatomical structure.

[0048] In summary, the present application has the advantages of:

[0049] The present application can cover various surgical scenarios, reduce the cost of a single surgery, improve the work efficiency of the operating room, and overcome the limitations of traditional single surgical robots in cost, resource utilization, operation training, surgical adaptability and technical updating, realize higher integration, standardization and intelligentization, and better serve diversified orthopedic surgery needs. BRIEF DESCRIPTION OF DRAWINGS

[0050] Figure 1 A schematic diagram of the integrated orthopedic surgery robot of the present application. DETAILED DESCRIPTION

[0051] The advantages and effects of the present application can be easily understood by those skilled in the art from the disclosure herein. The present application can also be implemented or applied in other different specific embodiments, and the details in the specification can be modified or changed based on different views and applications without departing from the spirit of the present application. It should be noted that the following examples and features in the examples can be combined with each other without conflict.

[0052] It should be noted that the diagrams provided in the following examples only illustrate the basic concept of the present application in a schematic manner, and only show the components related to the present application in the diagrams, not the number, shape and size of the components when actually implemented. The actual implementation of each component may be arbitrarily changed in type, number and proportion, and the layout pattern of the components may be more complex.

[0053] All directional indications in the embodiments of the present application, such as up, down, left, right, front, back, transverse, longitudinal, etc., are only used to explain the relative positional relationship, movement condition, etc. between components in a certain specific posture, and if the specific posture changes, the directional indications will also change accordingly.

[0054] Due to installation errors and other reasons, the parallel relationship referred to in the embodiments of the present application may actually be an approximate parallel relationship, and the vertical relationship may actually be an approximate vertical relationship.

[0055] Example 1:

[0056] For example, Figure 1The illustrated individualized orthopedic surgery robot includes a control device, a mechanical arm, an intelligent instrument library, a multi-modal image import module, an individualized kinematics planning system, a surgery planning and execution system, a force feedback and safety system, and a graphical user interface.

[0057] The control device is linked with the mechanical arm to control the movement of the mechanical arm in three-dimensional space by real-time calculation and transmission of movement instructions.

[0058] The control device is linked with the intelligent instrument library to automatically allocate and call surgical instruments according to the surgery plan, improving the efficiency of the operating room.

[0059] The control device is linked with the multi-modal image import module to present the processed image data to the doctor in real time, assisting the doctor in precise surgical operation.

[0060] The control device is linked with the individualized kinematics planning system to plan an intelligent surgery path according to individual differences, ensuring the surgery effect.

[0061] The control device is connected with the graphical user interface, which is used to display the surgery path planning and provide an interface for interactive surgery planning and control.

[0062] The control device includes a main controller, which is the core component of the surgery robot, used to coordinate and control the entire surgery process, with high intelligence and human-computer interaction function, supporting the doctor to plan, monitor and intervene in real time through touch screen or voice command and other interactive methods.

[0063] The main controller is composed of computer hardware, operating system (RTOS), and communication interface. The computer hardware is industrial or even military grade to ensure stable and efficient operation in complex surgical environment. The main controller also integrates CPU, GPU, and large-scale storage devices for processing complex algorithms, real-time data streams, and high-definition medical image data.

[0064] The operating system has high professionalization and intelligence. It can not only receive and process signals from various sensors, intelligent instrument library, mechanical arm, and other components in real time, but also execute surgery planning, navigation algorithms, and human-computer interaction programs. The operating system is embedded with advanced motion planning and control algorithms to accurately control each movement of the mechanical arm and make intelligent decisions through integrated AI algorithms.

[0065] The operating system can ensure that the surgery robot can respond to various operation commands and external events in time under harsh time requirements, avoiding surgery errors caused by delays.

[0066] The operating system includes a motion planning and control module, an image processing and registration module, an artificial intelligence and deep learning module, and a human-computer interaction module.

[0067] The motion planning and control module parses the control instructions sent by the main controller and obtains the motion trajectory control of the end effector of the robot arm by combining the motion planning and control algorithm, wherein the motion planning and control algorithm is stored in the motion planning and control module.

[0068] The image processing and registration module accurately corresponds the preoperative image and the real-time intraoperative image by combining the image registration algorithm, thereby guiding the accurate positioning of the surgical instrument, wherein the image registration algorithm is stored in the image processing and registration module.

[0069] The artificial intelligence and deep learning module learns and trains a large amount of case data by combining the deep learning algorithm, thereby improving the intelligent degree of surgical planning and assisting the doctor to make a better decision, wherein the deep learning algorithm is stored in the artificial intelligence and deep learning module.

[0070] The human-computer interaction module uses touch screen, voice recognition and other interaction methods to simplify the operation process of the doctor and improve the comfort and efficiency of the surgery.

[0071] The control device controls the surgical robot in real time, making the surgical process more accurate, stable and efficient. The main controller can accurately convey the surgical planning of the doctor, control the robot arm to execute the preset surgical path through the operating system, thereby reducing the surgical risk and complications. In addition, through real-time image registration and force feedback control, the doctor can clearly understand the actual contact between the instrument and the tissue, avoiding excessive cutting or damaging the important structures nearby.

[0072] The control device realizes the intelligentization, accuracy and humanization of surgical operation through precise design and efficient cooperation, which is of great significance to improve the quality of surgery, reduce the risk of surgery and improve the rehabilitation effect.

[0073] The robot arm is a multi-degree-of-freedom robot arm composed of joints with multiple degrees of freedom, driven by a servo motor and a precision harmonic reducer to achieve high-precision motion. The robot arm can be flexibly adjusted and positioned according to the surgical requirements, and its end carries a modular end effector, which connects the surgical instrument to ensure accurate control of the surgical instrument.

[0074] The end effector is provided with a standardized interface, which is an ISO 11064 standard interface, capable of quickly and safely connecting and disconnecting with the end of the robot arm.

[0075] The end effector is equipped with a drive module, which is a high-precision servo motor, such as the UltraDrive-SM12 model. Through a precision transmission mechanism (such as a harmonic reducer or ball screw), the rotational motion of the motor is converted into linear or rotational motion to accurately control the advancement, rotation, and other actions of the surgical instrument.

[0076] The end effector is equipped with a tool clamping system that uses an electrically controlled magnetic force adsorber or quick-change jaw to securely hold and accurately control different types of surgical instruments, such as bone drills, forceps, electric saws, etc.

[0077] The end effector's shell is made of medical-grade stainless steel or titanium alloy and other biocompatible materials, and the surface is specially treated for easy cleaning and disinfection. For example, using medical-grade stainless steel 316L material ensures safety when in contact with the human body.

[0078] The end effector is equipped with a sensor assembly, including torque sensors and position sensors, such as the ForceSense-FS100 force feedback sensor, which monitors and feeds back real-time force and position information when the surgical instrument contacts the tissue, ensuring the precision and safety of surgical operations.

[0079] The working principle of the modular end effector is based on the instructions of the main controller and sensor feedback. The main controller generates accurate motion instructions through calculations and transmits them to the end effector through a high-speed communication interface. The drive module acts according to the instructions and drives the surgical instrument to perform the pre-set surgical action through the transmission mechanism. At the same time, the sensor monitors and feeds back real-time torque and position information, and the main controller adjusts in a timely manner based on these feedbacks to ensure that the surgical instrument is always in a safe and effective state throughout the operation process.

[0080] The modular end effector greatly improves the surgical precision, safety, and work efficiency of orthopedic surgery robots by flexibly replacing different surgical instruments, accurately controlling the movement of surgical instruments, and real-time feedback of force and position information, providing strong technical support for achieving precise, minimally invasive, and personalized orthopedic surgery.

[0081] The intelligent instrument library integrates RFID tag identification and automatic grabbing technology, which can automatically manage and deploy surgical instruments. During the operation process, according to the operation plan and progress, the required surgical instruments are accurately delivered to the operation area through the mechanical arm.

[0082] The multi-modal image import module can receive and process CT, MRI, X-ray, and other multi-modal image data, and use high-performance GPUs for three-dimensional reconstruction and real-time navigation. Through advanced image registration algorithms, the preoperative three-dimensional image is accurately matched with the intraoperative real-time two-dimensional image, helping doctors accurately understand the position and direction of the surgical instrument.

[0083] The personalized kinematic planning system plans the optimal prosthesis position and parameters for hip and knee replacement surgeries based on individual-specific parameters. Through unique surgical planning and postoperative kinematic target constraint and feedback algorithms, it ensures the accuracy and safety of surgical planning.

[0084] The individualized kinematic planning system includes a three-dimensional imaging and modeling module, a surgical planning module, a path planning module, and a dynamic adjustment module.

[0085] 3D imaging and modeling module: Use CT, MRI and other imaging data to obtain a 3D bone model, and reconstruct the 3D bone model through a 3D modeling algorithm;

[0086] The steps for the 3D imaging and modeling module to reconstruct a 3D bone model are as follows:

[0087] 1. Image data processing: import image data and perform preprocessing, and then perform contrast enhancement on the image after preprocessing;

[0088] Image data preprocessing includes DICOM data parsing and filtering and denoising.

[0089] DICOM data parsing: DICOM formatted data contains metadata such as image pixel values, patient information, and scan parameters. This information, particularly the pixel array and related scan parameters (such as pixel pitch and slice thickness), must be read during import for subsequent processing. This step typically involves parsing the file using specialized DICOM libraries (such as DCMTK or GDCM).

[0090] Median filter denoising: For salt and pepper noise, each pixel value is replaced by the median of the pixel values ​​in its neighborhood.

[0091] Wiener filtering denoising: For Gaussian noise, the weight of each pixel is adaptively determined according to the local variance of the image and the noise power spectrum for weighted averaging.

[0092] Contrast enhancement is performed based on histogram equalization, adaptive contrast stretching, image registration, rigid transformation, and affine transformation.

[0093] Histogram equalization: changes the grayscale distribution of an image to make the probability distribution of pixel values ​​as uniform as possible.

[0094] Adaptive contrast stretching: Like CLAHE (Contrast Limited Adaptive H i stogram Equalization), histogram equalization is performed in small blocks and the intensity of contrast enhancement is limited to prevent artifacts caused by over-enhancement. For each small block, a calculation similar to histogram equalization is applied, but with a contrast cap.

[0095] 2. Three-dimensional reconstruction algorithm

[0096] The three-dimensional volume data is operated to map the properties of each voxel to color and transparency, and then generate a continuous three-dimensional image with depth perception.

[0097] Color and transparency mapping: CT values (Hounsfield Unit, HU) are mapped to color and transparency, usually using linear or nonlinear mapping functions. For example, for the CT value range [-1000, 2000], the low value area (such as soft tissue outside the bone) can be set to a lower transparency and a specific color, while the high value area (such as bone) is set to a high transparency and another color.

[0098] Ray casting and integration: To calculate each pixel on the final image, a ray is cast from the viewpoint through the volume data, and the properties of the voxels (color and transparency) are integrated according to the properties of the voxels (color and transparency). The integration takes into account the attenuation of light along the path.

[0099] Geometry optimization and detail enhancement, and model smoothing:

[0100] Model smoothing - Laplacian smoothing: reduces model surface noise while maintaining the clear boundaries of the model as much as possible, including:

[0101] Constructing an adjacency matrix: for each vertex (v), construct its neighborhood vertex set (N(v)) and construct an adjacency matrix based on it, which is used to store the connection relationship between vertices.

[0102] Calculate the weight: in practical applications, the influence of the vertices (u) in (N(v)) on (v) is not necessarily the same, and different weights (w_{uv}) can be given by distance or other criteria;

[0103] Iterative smoothing: usually requires multiple iterations of the above formula, and updates the position of all vertices after each iteration until the preset smoothing degree is met or the maximum number of iterations is reached.

[0104] Through the above method, the three-dimensional imaging and modeling module can accurately construct the three-dimensional model of the patient's bone from the original image data, providing an accurate basis for subsequent surgical planning and execution.

[0105] Surgical planning module: preoperative planning based on the reconstructed three-dimensional bone model, such as the knee replacement robot, the preoperative planning is used to determine the size of the prosthesis, the angle and position of the prosthesis.

[0106] A path planning module that calculates an optimal surgical path from the initial position to the target position based on a path planning algorithm, which takes into account the spatial limitations of the surgical instruments and safety boundaries, is stored with the path planning module.

[0107] The path planning algorithm utilizes advanced algorithmic techniques such as graph search algorithms, Probabilistic Roadmap Methods (PRMs), Rapidly-exploring Random Trees (RRTs), or Model Predictive Control (MPC) to ensure the optimality and safety of the surgical path.

[0108] The specific operations of the path planning module include environment modeling, goal setting, constraint conditions, path smoothing and optimization, and collision detection and obstacle avoidance. The path planning module ensures that the surgical robot can safely and efficiently navigate from the initial position to the target position while minimizing surgical risks and complications and improving surgical quality.

[0109] Environment modeling is the foundation of the entire path planning process, involving the conversion of complex anatomical structures and surgical environments into mathematical models for algorithmic processing. This includes:

[0110] a. Three-dimensional model conversion

[0111] Data input: First, the three-dimensional models extracted from CT, MRI, and other imaging data exist in the form of point clouds, voxel grids, or triangular facets. These data are usually stored in the DICOM (Digital Imaging and Communications in Medicine) standard format.

[0112] Surface reconstruction: Use three-dimensional reconstruction algorithms such as the Marching Cubes algorithm to convert voxel data into continuous surface models, obtaining the precise three-dimensional shape of the patient's bones or other anatomical structures.

[0113] Coordinate system definition: Define a global coordinate system (usually a standardized form of anatomical coordinates) and local coordinate systems for surgical instruments and robots to facilitate subsequent calculations and transformations.

[0114] b. Surgical space definition

[0115] Reachability analysis: Determine the reachability of surgical instruments within the surgical space by calculating their working radius, length, and flexibility. This involves inverse kinematics (IK) calculations to determine the position and attitude of the instrument's end in a given joint configuration.

[0116] Safety Margin: Define minimum safe distances to surrounding soft tissues, nerves, and blood vessels. These safety margins are distance-based buffers formed by expanding outward from the surface of anatomical structures by a certain distance

[0117] c. Mathematical Representation

[0118] Geometric Representation: Anatomical structures and surgical spaces can be mathematically represented in the following ways:

[0119] Point Cloud: P = {p_i = (x_i, y_i, z_i)}, where (p_i) is a point in space, (x_i, y_i, z_i) are spatial coordinates, i is the point's index, and P is the point set.

[0120] Triangular Mesh: Composed of a set of vertices V, edges E, and faces F, each face is typically composed of three vertices.

[0121] Voxel Grid: A three-dimensional array where each element represents the state of a volume unit in space (e.g., whether it belongs to the bone).

[0122] Constraint Region: Define safety and limit regions using inequalities or equations.

[0123] Goal Setting is a critical step in path planning, related to the accuracy and success rate of surgical operations, including:

[0124] a. Data Acquisition and Labeling

[0125] Image Data Labeling: Use medical image processing software such as ITK-SNAP or 3D Slicer to accurately label the surgical target positions on the three-dimensional reconstructed anatomical structure model. For example, in orthopedic surgery, label the prosthesis installation points or screw entry and exit positions on the CT scan three-dimensional model.

[0126] Coordinate Transformation: Convert the image coordinates of the labeled points to the working coordinate system of the surgical robot through registration algorithms to ensure accurate positioning of the target points in the physical world.

[0127] b. Goal Node Definition

[0128] Node Coordinates: Each target position is defined as a node (G = {g_1, g_2,..., g_m}), where (g_i = (x_i, y_i, z_i)) represents the three-dimensional coordinates of the (i)th target point in the robot's coordinate system.

[0129] Path Planning Goals: These goal nodes become the end points of the path planning algorithm, i.e., the algorithm needs to find the optimal path from the starting position of the surgery to each goal node.

[0130] c. Specific Calculation Methods

[0131] Target Priority: In multi-target surgeries, target priorities are set according to the surgical procedure or surgeon preference. This is achieved by assigning each target node a weight value (w_i), which in turn influences the decision-making process of path planning.

[0132] Target Constraints: For certain special surgical operations, target points may also come with specific constraint conditions, such as screw angle and depth requirements.

[0133] Constraints are an important part of ensuring that the surgical path is both feasible and safe, mainly including kinematic constraints, dynamic constraints, and safety constraints, which include:

[0134] a. Kinematic Constraints

[0135] Joint Angle Limitations: For surgical instruments with multiple degrees of freedom, the range of rotation or movement for each joint is limited. Let the joint angle range be ([\theta_{min},\theta_{max}]), then for the (i)th joint, its angle (\theta_i) must satisfy:

[0136] [\theta_{min,i} < \theta_i < \theta_{max,i}]

[0137] End Effector Reachability: The position and pose of the surgical instrument's end effector in space is limited by its structure, which can be solved analytically or numerically through inverse kinematics to ensure that the planned path is within the instrument's workspace.

[0138] b. Dynamic Constraints

[0139] Operating Force Limitation: Avoid applying excessive force to the surgical area to prevent tissue damage. Let the maximum allowed operating force be (F_{max}), and for the expected operating force (F) at any point along the path, it should satisfy: [F < F_{max}]. The dynamic model can be established based on Newton-Euler equations or Lagrange equations to calculate the expected force and torque.

[0140] c. Safety Constraints

[0141] Collision Avoidance: Collision detection usually involves calculating the minimum distance (d_{min}) from a point on the path to all obstacles (such as bones, soft tissue boundaries), and ensuring that the distance is greater than a safety threshold (d_{safe}) : [d_{min}(p) > d_{safe}], where (d_{min}(p)) is the distance from the path point (p) to the nearest obstacle.

[0142] Soft tissue pressure distribution: For operations requiring contact with soft tissue, the pressure distribution on the tissue surface must also be considered to avoid excessive pressure that could cause damage. By calculating the stress distribution on the contact surface, it can be ensured that the maximum pressure does not exceed a safety threshold.

[0143] Collision detection and obstacle avoidance specifically includes:

[0144] Distance calculation: For each path point (P_i), calculate its nearest distance to all obstacle surfaces.

[0145] Continuous path detection: In addition to checking individual path points, it is also necessary to check whether the line segment formed by adjacent points on the path intersects with obstacles. This is achieved through intersection tests between line segments and triangular surfaces or polyhedrons, such as using ray casting or using plane equations to determine whether a line segment passes through an obstacle surface.

[0146] Obstacle avoidance strategy adopts one of the following methods:

[0147] Local re-planning: When a collision risk is detected at a point or line segment on the path, local path re-planning is required. A variant of RRTs is used to randomly generate new candidate paths near the collision point of the current path, and only those new path segments that do not collide with any obstacles are retained to gradually build a new collision-free path.

[0148] Potential field method: Use the potential field method, where obstacles are considered as sources generating repulsive forces, and the target position generates attractive forces. By calculating the total force (vector sum of attractive and repulsive forces) at each path point, the path is guided to deviate towards obstacle-free areas.

[0149] Obstacle avoidance path optimization: Apply smoothing algorithms such as B-spline interpolation to optimize the new path, ensuring its continuity and feasibility for surgical operations.

[0150] Dynamic adjustment module: Real-time receive feedback information from sensor components, combined with pre-set safety thresholds, the system can automatically adjust or prompt the doctor to adjust the surgical path to avoid damaging surrounding soft tissue and neural and vascular structures.

[0151] Surgical path planning includes manual planning mode, automatic planning mode, and hybrid planning mode.

[0152] Manual planning mode: The doctor can directly set key points and paths on the three-dimensional bone model, and the path planning module will generate a surgical path based on the settings.

[0153] Automatic planning mode: The path planning module automatically matches a suitable surgical path based on typical cases in the database.

[0154] Mixed planning mode: After the system proposes a preliminary suggestion, the doctor can further fine-tune to ensure that the surgical path meets individual needs. In actual operation, the doctor selects the corresponding planning mode in the system interface according to the type of surgery, individual differences, and personal experience. The system displays the planning results through the graphical user interface (GUI), and the doctor confirms the accuracy and sends it to the surgical robot control device, which accurately executes the pre-planned surgical steps.

[0155] The individualized kinematic planning system realizes the refinement, intelligence, and individualization of orthopedic surgery by integrating cutting-edge image processing, computer-aided design, and intelligent algorithm technology, greatly improving surgical efficiency and treatment effectiveness.

[0156] Surgical planning and execution system: precise surgical path planning is performed through the individualized kinematic planning system, and the robot strictly follows the planning during the operation. At the same time, the system has real-time monitoring function, which can dynamically adjust the surgical planning according to the actual situation when necessary, realizing closed-loop management of the surgical process.

[0157] Force feedback and safety system: used to sense and control the operating force in real time to prevent accidental damage to tissues during surgery. The force feedback and safety system has built-in anti-collision detection module and safety locking module to ensure that the mechanical arm stops moving in time when encountering abnormal situations.

[0158] Graphical user interface, doctors can use touch screens or handles for surgical planning and control.

[0159] In summary, the integrated orthopedic platform surgical robot realizes precise positioning, intelligent navigation, flexible switching of surgical instruments, real-time monitoring and adjustment of surgical plans, and other functions through the close cooperation of each component, effectively improving the precision, safety, and efficiency of orthopedic surgery.

[0160] Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor should belong to the scope of protection of the present application.

Claims

1. Integrated orthopedic surgical robot, characterized by: It includes control device, robotic arm, intelligent instrument library, multimodal imaging import module, individualized kinematic planning system, surgical planning and execution system, force feedback and safety system and graphical user interface. The control device is linked to the robotic arm to control the movement of the robotic arm in three-dimensional space by real-time calculation and transmission of motion instructions; The control device is linked with the intelligent instrument library to automatically allocate and call surgical instruments according to the surgical plan, improving the efficiency of the operating room; The control device is linked to the multimodal image import module: the processed image data is presented to the doctor in real time, assisting the doctor in performing precise surgical operations; The linkage between the control device and the individualized kinematic planning system: intelligent surgical path planning based on individual differences; The control device is connected to a graphical user interface for displaying the surgical path planning and serving as an interactive interface; The individualized kinematic planning system includes a three-dimensional imaging and modeling module, a surgical planning module, a path planning module, and a dynamic adjustment module; 3D imaging and modeling module: uses image data to obtain a 3D bone model and reconstructs the 3D bone model using a 3D modeling algorithm; Surgical planning module: preoperative planning based on the reconstructed 3D bone model; Path planning module, which calculates the surgical path from the initial position to the target position based on the path planning algorithm, the spatial limitations of the surgical instruments and the safety margin, and the path planning algorithm storage and path planning module; Dynamic Adjustment Module: Receives real-time feedback from sensor components and, based on preset safety thresholds, the system automatically adjusts or prompts the surgeon to adjust the surgical path to avoid damage to surrounding soft tissue and neurovascular structures. The steps of reconstructing the three-dimensional skeleton model by the three-dimensional imaging and modeling module are as follows: Image data processing: import image data and perform preprocessing, and then perform contrast enhancement on the image after preprocessing; 3D reconstruction algorithm: Operate on 3D volume data, map the attributes of each voxel to color and transparency, and generate a continuous 3D image with a sense of depth. Color and transparency mapping: Use linear or nonlinear mapping functions to map CT values ​​to color and transparency; Ray casting and integration: To calculate each pixel on the final image, the ray is passed from the viewpoint through the volume data and integrated according to the properties of the voxel; Geometry optimization, detail enhancement, and model smoothing: Based on model smoothing - Laplacian smoothing, the model boundaries are kept clear, including: Construct an adjacency matrix: For each vertex (v), construct its neighborhood vertex set (N(v)), and construct an adjacency matrix based on this to store the connection relationship between vertices; Calculate weights: The influence of vertices (v) in the vertex set (N(v)) on the adjacency matrix (u) is not necessarily the same, so different weights (w_{uv}) are assigned. Iterative smoothing: multiple iterations, updating the positions of all vertices after each iteration until the preset smoothness is met or the maximum number of iterations is reached.

2. The integrated orthopedic surgical robot according to claim 1, characterized in that: The control device includes a main controller, which is composed of computer hardware, an operating system, and a communication interface. The main controller also integrates a CPU, a GPU, and a storage device for processing algorithms, real-time data streams, and medical imaging data.

3. The integrated orthopedic surgical robot according to claim 2, characterized in that: The operating system receives and processes signals from the intelligent instrument library and robotic arms in real time, and is also used to execute surgical planning, navigation algorithms, and human-computer interaction. The operating system has built-in motion planning and control algorithms to control the movements of the robotic arms, and can make intelligent decisions through integrated AI algorithms.

4. The integrated orthopedic surgical robot according to claim 2, characterized in that: The operating system includes a motion planning and control module, an image processing and registration module, an artificial intelligence and deep learning module, and a human-computer interaction module. Motion planning and control module: parses the control instructions sent by the main controller and combines the motion planning and control algorithm to obtain the motion trajectory to control the action of the end effector of the robot arm. The motion planning and control algorithm is stored in the motion planning and control module. Image processing and registration module: Combines image registration algorithms to accurately match preoperative images with real-time intraoperative images, guiding the positioning of surgical instruments. The image registration algorithms are stored in the image processing and registration module. Artificial Intelligence and Deep Learning Module: Combines deep learning algorithms to study and train case data, improves the intelligence of surgical planning, and assists doctors in making decisions. The deep learning algorithms are stored in the Artificial Intelligence and Deep Learning Module.

5. The integrated orthopedic surgical robot according to claim 1, characterized in that: The robotic arm is a multi-degree-of-freedom robotic arm, which is composed of joints with multiple degrees of freedom. The end of the robotic arm carries a modular end effector, and the end effector is connected to the surgical instrument.

6. The integrated orthopedic surgical robot according to claim 5, characterized in that: The end effector is provided with a standardized interface, through which the end effector is connected and disconnected from the end of the robotic arm; the end effector is provided with a drive module, which is a servo motor, and controls the movement of the surgical instrument; the end effector is provided with a tool clamping system, which uses an electrically controlled magnetic adsorber or quick-change claws to clamp and control different types of surgical instruments; the shell of the end effector is made of biocompatible materials such as medical-grade stainless steel or titanium alloy; the end effector is provided with a sensor assembly, which includes a torque sensor and a position sensor, and monitors and feeds back the force and position information of the contact between the surgical instrument and the tissue.

7. The integrated orthopedic surgical robot according to claim 1, characterized in that: The multimodal image import module receives and processes multiple image data, uses the GPU to perform three-dimensional reconstruction and real-time navigation, and uses an image registration algorithm to match the preoperative planned three-dimensional image with the real-time two-dimensional image during the operation to obtain the position and direction of the surgical instrument.

8. The integrated orthopedic surgical robot according to claim 1, characterized in that: The specific operations of the path planning module include environment modeling, goal setting, constraint conditions, path smoothing and optimization, and collision detection and obstacle avoidance: The operations of environmental modeling include 3D model conversion, surgical space definition, The operations for 3D model conversion include: Data input: The 3D model extracted from the image data exists in the form of point cloud, voxel mesh or triangular facets, and these data are stored in the DICOM standard format; Surface reconstruction: Use 3D reconstruction algorithms to convert voxel data into a continuous surface model to obtain the precise 3D shape of the patient's bones or other anatomical structures; Coordinate system definition: Define a global coordinate system and local coordinate systems for surgical instruments and robots; Procedures to define the surgical space include: Reachability analysis: Calculate the working radius, length, and bendability of surgical instruments to determine their reach within the surgical space; determine the position and posture of the instrument end in a given joint configuration; Safety Margin Settings: Defines the minimum safe distance for soft tissue, nerves, and blood vessels around bones. The safety margin is a distance-based buffer zone formed by expanding the set distance on the surface of the anatomical structure.

Images