Unicondylar arthroplasty surgical robot system and control method

Abstract

The invention provides a unicompartmental knee arthroplasty surgical robot system and a control method, and the system comprises a preoperative planning module which is used for carrying out the segmentation and reconstruction of a knee joint according to an obtained knee joint medical image, carrying out the preoperative planning, and determining a unicompartmental knee arthroplasty scheme; the positioning navigation module is used for carrying out registration on the intraoperative entity knee joint and the preoperative knee joint three-dimensional model according to the navigator and the tracer so as to map a unicompartmental knee replacement scheme and track the poses of the guide equipment and the entity knee joint in real time; and the mechanical arm control module is used for planning a path from the mechanical arm to the preparation position and controlling the mechanical arm guide equipment to move to the thighbone preparation position and the tibia preparation position. In this way, the mechanical arm can be controlled to assist in completing the osteotomy operation of unicompartmental knee arthroplasty in a pre-operation planning and intra-operation navigation mode, and the problems that the operation level is uneven and the operation effect is not expected due to different individuals in the current manual operation are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of medical devices, in particular to a single knee replacement surgery robot system and a control method. BACKGROUND

[0002] Single knee replacement is a common and complex surgical procedure used to treat knee-related diseases and injuries. Traditional single knee replacement usually requires doctors to operate based on their rich experience and visual judgment, but this approach has certain limitations and risks. In recent years, with the development of robot technology and computer-aided surgery, single knee replacement robots have gradually become a new technology, bringing great changes and progress to single knee replacement.

[0003] Currently, in the case of introducing a single knee replacement robot, the single knee replacement robot only participates in preoperative planning, and these intraoperative operations are generally performed manually. This surgical method is slow, and due to differences in surgical experience, the surgical level of doctors is uneven, and the surgical effect may not be as expected. SUMMARY

[0004] The problem solved by the present application is that the current manual surgery causes uneven surgical levels due to individual differences, and the surgical effect is not as expected.

[0005] To solve the above problems, the first aspect of the present application provides a single knee replacement surgery robot system, comprising: a preoperative planning module, a positioning and navigation module, and a mechanical arm control module; The preoperative planning module is configured to segment and reconstruct a knee joint based on acquired knee joint medical images, and to determine a single knee replacement plan based on a reconstructed three-dimensional model of the knee joint. The positioning and navigation module is configured to register the actual knee joint during surgery and the three-dimensional model of the knee joint before surgery based on a navigator and a tracer, to map the single knee replacement plan, and to track the pose of the guiding device and the actual knee joint in real time. The mechanical arm control module is configured to plan the path of the mechanical arm to the femur preparation position and the tibia preparation position, and to control the movement of the mechanical arm guiding device to the femur preparation position and the tibia preparation position.

[0006] The second aspect of the present application provides a single knee replacement surgery robot system, comprising: an upper controller, a robot, a navigator, a tracer, and a probe. The upper controller is configured to segment and reconstruct a knee joint based on acquired knee joint medical images, to determine a single knee replacement plan based on a reconstructed three-dimensional model of the knee joint, to map the single knee replacement plan during surgery, and to send the single knee replacement plan to the robot. The trackers of the femur, the trackers of the tibia and the tracker of the guiding device are respectively arranged at the femur and the tibia of the patient, the end of the mechanical arm of the robot, and cooperate with the navigator to track the poses of the femur, the tibia and the guiding device in real time; The probe and the navigator cooperate to collect bone surface contour data of the knee joint of the patient; The upper controller is connected with the navigator and the robot, and is configured to: According to the collected bone surface contour data and the preoperative three-dimensional model of the knee joint, a unicompartmental replacement scheme is mapped, and paths of the mechanical arm to the femur preparation position and the tibia preparation position are planned according to the tracked poses of the femur, the tibia and the guiding device; The robot receives the planned paths and controls the guiding device to move to the femur preparation position and the tibia preparation position.

[0007] The third aspect of the present application provides a control method of a unicompartmental replacement surgery robot system, which comprises: Segmenting and reconstructing the knee joint according to the obtained medical image of the knee joint, and determining a unicompartmental replacement scheme according to the reconstructed three-dimensional model of the knee joint; Registering the in-situ knee joint and the preoperative three-dimensional model of the knee joint according to the navigator and the tracker to map the unicompartmental replacement scheme, and tracking the poses of the guiding device and the in-situ knee joint in real time; Planning paths of the mechanical arm to the femur preparation position and the tibia preparation position, and controlling the guiding device to move to the femur preparation position and the tibia preparation position.

[0008] The fourth aspect of the present application provides an electronic device, which comprises a memory and a processor; The memory is used for storing a program; The processor is coupled to the memory and is used for executing the program, so as to: Segmenting and reconstructing the knee joint according to the obtained medical image of the knee joint, and determining a unicompartmental replacement scheme according to the reconstructed three-dimensional model of the knee joint; Registering the in-situ knee joint and the preoperative three-dimensional model of the knee joint according to the navigator and the tracker to map the unicompartmental replacement scheme, and tracking the poses of the guiding device and the in-situ knee joint in real time; Planning paths of the mechanical arm to the femur preparation position and the tibia preparation position, and controlling the guiding device to move to the femur preparation position and the tibia preparation position.

[0009] The fifth aspect of the present application provides a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the control method of the unicompartmental replacement surgery robot system.

[0010] Thus, the osteotomy surgery of unicompartmental replacement can be controlled by preoperative planning and intraoperative navigation in the manner of mechanical arm assistance, so as to solve the problems of uneven surgery level and unsatisfactory surgery effect due to individual differences in current manual surgery. BRIEF DESCRIPTION OF DRAWINGS

[0011] Figure 1 Fig. 1 is an architecture diagram of a unicompartmental replacement surgery robot system according to an embodiment of the present application; Figure 2 Fig. 2 is an architecture diagram of another unicompartmental replacement surgery robot system according to an embodiment of the present application; Figure 3 Fig. 3 is a schematic diagram of a knee three-dimensional model in a standard body posture of a unicompartmental replacement surgery robot system according to an embodiment of the present application; Figure 4 Fig. 4 is a schematic diagram of a guiding device of a unicompartmental replacement surgery robot system according to an embodiment of the present application; Figure 5 Fig. 5 is a schematic diagram of soft tissue balance of a unicompartmental replacement surgery robot system according to an embodiment of the present application; Figure 6 Fig. 6 is a flowchart of a control method of a unicompartmental replacement surgery robot system according to an embodiment of the present application; Figure 7 Fig. 7 is an architecture diagram of an electronic device according to an embodiment of the present application.

[0012] Fig. 8 is a schematic diagram of a unicompartmental replacement surgery robot system according to an embodiment of the present application. DETAILED DESCRIPTION

[0013] In order to make the above objectives, features and advantages of the present application more apparent, specific embodiments of the present application will be described in detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present application are shown in the drawings, it should be understood that the present application can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided so that the present application can be more thoroughly understood and the scope of the present application can be accurately conveyed to those skilled in the art.

[0014] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in the present application should be understood as the common meanings understood by those skilled in the art to which the present application belongs.

[0015] Unicondylar replacement surgery is a common and complex surgical procedure used to treat knee-related diseases and injuries. Traditional unicondylar surgery usually requires the surgeon to operate based on rich experience and visual judgment, but this approach has certain limitations and risks. In recent years, with the development of robotic technology and computer-assisted surgery, unicondylar replacement surgery robots have gradually become a new technology, bringing great changes and progress to unicondylar replacement surgery.

[0016] Currently, in the case of introducing a unicondylar replacement surgery robot, the unicondylar replacement surgery robot only participates in preoperative planning, and these intraoperative operations are generally performed manually. Such a system is slow, and due to differences in surgical experience, the surgical level of doctors is uneven, and the surgical effect may not be as expected.

[0017] To solve the above problems, the present application provides a new unicondylar replacement surgery robot system scheme, which can control the mechanical arm to assist in completing the osteotomy surgery of unicondylar replacement through preoperative planning and intraoperative navigation, solving the problem of uneven surgical level and unexpected surgical effect caused by individual differences in current manual surgery.

[0018] For ease of understanding, the following terms that may be used are explained here: The embodiment of the present application provides a unicondylar replacement surgery robot system, and the specific scheme of the system is shown in Figures 1-5 .

[0019] Combined with Figure 1 , which is an architecture diagram of a unicondylar replacement surgery robot system according to an embodiment of the present application; wherein the unicondylar replacement surgery robot system comprises a preoperative planning module, a positioning and navigation module, and a mechanical arm control module. The preoperative planning module is configured to perform segmentation and reconstruction of the knee joint according to the obtained knee joint medical image, and perform preoperative planning according to the reconstructed three-dimensional model of the knee joint to determine a unicondylar replacement scheme. The positioning and navigation module is configured to register the entity knee joint in the operation and the three-dimensional model of the knee joint before the operation according to a navigator and a tracer, to map the unicondylar replacement scheme, and to track the pose of the guiding device and the entity knee joint in real time. The mechanical arm control module is configured to plan the path of the mechanical arm to the femur preparation position and the tibia preparation position, and to control the mechanical arm to move to the femur preparation position and the tibia preparation position.

[0020] In the present application, the mechanical arm can be controlled to assist in completing the osteotomy surgery of unicondylar replacement through preoperative planning and intraoperative navigation, solving the problem of uneven surgical level and unexpected surgical effect caused by individual differences in current manual surgery.

[0021] In an embodiment, the positioning and navigation module is at least one of the following positioning methods: infrared positioning, visible light positioning, structured light positioning, intraoperative imaging positioning, electromagnetic navigation positioning, ultrasound-guided positioning, inertial navigation positioning.

[0022] Among them, the structured light positioning is to project a specific light pattern (such as stripes, grid) to the target surface, capture the deformed pattern through the camera, and reconstruct the three-dimensional surface topography by using the principle of triangulation, so as to realize the spatial positioning.

[0023] Among them, the intraoperative imaging positioning is to obtain the image of the patient's anatomical structure by using the intraoperative real-time imaging device, and to register with the preoperative image to realize the accurate positioning of the instrument or lesion.

[0024] Among them, the electromagnetic navigation positioning is to generate a low-frequency alternating magnetic field by using an electromagnetic field generator, and the sensor probe induces a signal in the magnetic field, and the position and attitude of the sensor probe in the three-dimensional space are determined by calculating the signal strength and phase.

[0025] Among them, the ultrasound-guided positioning is to generate real-time two-dimensional or three-dimensional images by using the reflection echo of high-frequency ultrasound waves in tissues, and the doctor guides the puncture needle, catheter or surgical instrument to reach the target position according to the image.

[0026] Among them, the inertial navigation positioning is to measure the acceleration and angular velocity of the object by using an inertial measurement unit (IMU), including an accelerometer and a gyroscope, and to calculate the position and attitude changes by integration. It is often fused with other systems (such as optical, electromagnetic) to reduce cumulative error.

[0027] In an embodiment, the positioning method of the positioning and navigation module is visible light combined with infrared positioning, and the specific positioning process includes: A plurality of marker points of a specific position shape and a black and white grid pattern of a specific shape are arranged on the tracer; The optical positioning instrument (navigator) determines the specific coordinates of the tracer in the camera coordinate system based on the black and white grid pattern of a specific shape and the photographed tracer image, and determines the specific coordinates of the tracer in the infrared coordinate system based on the plurality of marker points of a specific position shape and the received infrared light of the marker points; Based on the specific coordinates of the tracer in the camera coordinate system and the specific coordinates in the infrared coordinate system, the fixed transformation relationship between the camera coordinate system and the infrared coordinate system is solved; Based on the fixed transformation relationship, the accurate positioning in the infrared view is combined with the visual image in the visible light view.

[0028] Among them, the tracer is a hybrid tracer, which is equipped with NDI infrared marker points and visible light chessboard pattern at the same time, and the relative position relationship of the NDI infrared marker points and the visible light chessboard pattern is visible.

[0029] Preferably, based on the positioning of NDI combined with visible light, an enhanced display navigation can be generated, presenting the most critical positioning information in the most natural way (directly on the real image that can be seen) to the doctor, significantly improving the intuitiveness and safety of the operation.

[0030] In an embodiment, the preoperative planning module specifically comprises: a three-dimensional bone model generation submodule, a key point labeling submodule, a unicompartmental prosthesis planning submodule, and an osteotomy surface planning submodule. The three-dimensional bone model generation submodule is configured to segment and reconstruct the knee joint based on the acquired knee joint medical images to obtain a three-dimensional bone model of the knee joint. The key point labeling submodule is configured to label the femoral key points and tibial key points of the knee joint. The unicompartmental prosthesis planning submodule is configured to plan a unicompartmental replacement prosthesis for the knee joint, and determine the prosthesis model and implant information for unicompartmental replacement. The osteotomy surface planning submodule is configured to plan multiple osteotomy surfaces of the femur and multiple osteotomy surfaces of the tibia for unicompartmental replacement based on the prosthesis model and implant information.

[0031] As shown in Figure 4 , it is a schematic diagram of unicompartmental prosthesis planning; the unicompartmental prosthesis is the planning result of the unicompartmental prosthesis planning submodule.

[0032] In an embodiment, the preoperative planning module further comprises a guide device planning configured to plan osteotomy grooves and nail placement grooves of an osteotomy guide device based on the multiple osteotomy surfaces of the femur and the multiple osteotomy surfaces of the tibia.

[0033] As shown in Figure 4 , the guide device has a base fixed at the end of the mechanical arm, and a guide part provided with osteotomy grooves and nail placement grooves, and the base and the guide part are connected and fixed by a fixed rod.

[0034] The guide device is an integrated structure, and after the osteotomy grooves and nail placement grooves of the guide device are planned, a complete guide device can be generated based on a preset template and manufactured by 3D printing or the like.

[0035] Preferably, the guide device is provided with a first osteotomy groove, a second osteotomy groove, and a third osteotomy groove perpendicular to each other, and a femoral positioning hole.

[0036] The guiding device, the first osteotomy groove, the second osteotomy groove and the third osteotomy groove are perpendicular to each other, in the application, the plane where the base is located is the relative plane, and the continuous line between the two holes shown in the base is the relative line; the first osteotomy groove is considered as the osteotomy groove parallel to the relative plane, the second osteotomy groove is considered as the osteotomy groove parallel to the relative line, and the third osteotomy groove is considered as the osteotomy groove perpendicular to the relative line.

[0037] The single-cone osteotomy surface includes a front femur osteotomy surface, a rear femur oblique osteotomy surface, a tibia sagittal osteotomy surface, a tibia horizontal osteotomy surface, a femur distal osteotomy surface and a femur posterior condyle osteotomy surface.

[0038] The first osteotomy groove is used for guiding osteotomy on the front femur osteotomy surface and the rear femur oblique osteotomy surface; the second osteotomy groove is used for guiding osteotomy on the tibia sagittal osteotomy surface; the third osteotomy surface is used for guiding osteotomy on the tibia horizontal osteotomy surface, the femur distal osteotomy surface and the femur posterior condyle osteotomy surface; and the femur positioning hole is used for guiding the installation hole of the prosthesis on the femur.

[0039] Preferably, the fixed rod of the guiding device has a curvature.

[0040] In the application, the guiding device itself has no power, but is installed on a mechanical arm, and is accurately positioned to a predetermined position by the mechanical arm, so as to guide the doctor to perform osteotomy.

[0041] The design method of the guiding device includes: obtaining a preoperative CT image of any object, and constructing a three-dimensional bone model of the knee joint; correcting the three-dimensional bone model of the knee joint based on a bone correction model, and determining a three-dimensional bone model in a standard posture; labeling key points of the three-dimensional bone model in the standard posture, and determining osteotomy surface planning information of single-cone replacement based on the key points; obtaining knee posture data of the object; generating a guiding device based on the knee posture data and the osteotomy surface planning information.

[0042] In the application, the three-dimensional model in the standard posture is generated to obtain accurate osteotomy surface planning, and then the knee posture data is combined, so that the generated single-cone replacement navigation positioning device is completely adapted to the individual, and the osteotomy accuracy and the surgical effect of the single-cone replacement are improved.

[0043] In one embodiment, the design method of the guiding device includes: obtaining historical medical data of a single-cone osteotomy object; generating a knee statistical morphology model based on the historical medical data; generating a predetermined guiding device based on the knee statistical morphology model.

[0044] In the present application, a knee statistical morphology model is generated based on historical medical data, and then a guide device is generated based on the statistical morphology model, so that the generated guide device is adapted to the individual, and the bone cutting accuracy and surgical effect of unicompartmental arthroplasty are improved.

[0045] In an embodiment, generating a knee statistical morphology model based on historical medical data comprises: generating a knee three-dimensional model based on historical medical data; identifying key points of the knee three-dimensional model; mapping the knee three-dimensional model based on the key points of the knee model; determining a knee statistical morphology model based on the knee three-dimensional model after mapping.

[0046] In an embodiment, the guide device design method further comprises: obtaining intraoperative bone cutting data of the unicompartmental bone cutting object; performing bone cutting simulation on the predetermined guide device based on the intraoperative bone cutting data; determining the specific structure of the guide device based on the result of the bone cutting simulation.

[0047] In this way, a perfectly simulated guide device is finally determined.

[0048] In an embodiment, the knee medical image is an anteroposterior X-ray image, or a CT image, or an MRI image, or includes a first image and a second image, and the first image and the second image are any two of the anteroposterior X-ray image, the CT image, and the MRI image.

[0049] In an embodiment, the mechanical arm control module specifically comprises: a mechanical arm femur path planning submodule, a first control submodule, a mechanical arm tibia path planning submodule, and a second control submodule. The mechanical arm femur path planning submodule determines the relative position between the current pose of the mechanical arm guide device and the tibia preparation position based on the navigator, the tracker installed on the mechanical arm guide device, the tracker installed on the femur, and the mapped femur preparation position, and plans a mechanical arm femur path. The first control submodule controls the mechanical arm to move to the mapped femur preparation position along the planned mechanical arm femur path. The mechanical arm tibia path planning submodule determines the relative position between the current pose of the mechanical arm guide device and the tibia preparation position based on the navigator, the tracker installed on the mechanical arm guide device, the tracker installed on the tibia, and the mapped tibia preparation position, and plans a mechanical arm tibia path. The second control sub-module controls the robot arm to move to the mapped tibia preparation position along the planned robot arm tibia path.

[0050] In an embodiment, the first control sub-module controls the robot arm to move to the mapped femur preparation position along the planned robot arm femur path, specifically comprising: obtaining a robot arm femur path, the robot arm femur path comprising a first path from a current position to a cache position, and a second path from the cache position to the femur preparation position; the cache position and the femur preparation position are at the same bone cutting surface; controlling the robot arm to move along the first path until reaching the cache position; controlling the robot arm to move along the second path until reaching the femur preparation position; the second path is a straight line.

[0051] In an embodiment, the tibia preparation position is multiple, and the robot arm tibia path planning sub-module is specifically configured to: obtaining multiple target positions of the mapped tibia preparation positions and the order of the target positions; determining the relative position between the current pose of the robot arm end guiding device and the first tibia preparation position based on the navigator, the tracker installed on the robot arm end guiding device, the tracker installed on the tibia, the mapped first tibia preparation position, and planning a robot arm first tibia path; In response to receiving a next preparation position signal, planning a robot arm short tibia path with the current position as the initial position and the target position of the next preparation position as the end position.

[0052] In an embodiment, the response to the received next preparation position signal, planning a robot arm short tibia path with the current position as the initial position and the target position of the next preparation position as the end position, comprises: determining the robot arm pose and the end tool centroid of the current position; determining the robot arm pose and the end tool centroid of the target position; planning a robot arm short tibia path according to the end tool centroid of the current position and the end tool centroid of the target position; planning a robot arm end rotation action of the initial position / end position of the robot arm short tibia path according to the robot arm pose of the current position and the robot arm pose of the target position.

[0053] Wherein, the robot arm short tibia path is a path with very close initial position and end position. By kinematic constraint, it is split into a simple path + robot arm rotation action; in this way, by splitting, the constraint consideration of path planning is greatly simplified, so that simple path planning can be realized, and the planning difficulty and execution difficulty are greatly reduced.

[0054] Wherein, the minimal path can be a straight line or a micro-arc line + a rounded corner transition. The straight line or micro-arc line herein can be a line segment movement corresponding to the rotation of a joint, so as to greatly simplify the control problem of the mechanical arm (the conventional control is to move six axes together, and the present application can only move one axis).

[0055] In an embodiment, the first control sub-module controls the mechanical arm to move to the mapped femur preparation position along the planned mechanical arm femur path, and specifically comprises: Obtaining an intraoperative image of the binocular camera; Generating an intraoperative three-dimensional map based on the intraoperative image; Mapping the mechanical arm femur path to the intraoperative three-dimensional map for correction; Controlling the mechanical arm to move according to the corrected mechanical arm femur path.

[0056] Wherein, in the step of mapping the mechanical arm femur path to the intraoperative three-dimensional map for correction, for each path sampling point / path segment, the safety distance from the obstacle is queried, and if the safety distance is less than the safety distance, the correction is performed.

[0057] Wherein, in the step of controlling the mechanical arm to move according to the corrected mechanical arm femur path, comprising: Real-time monitoring of the closest distance from the current posture to the obstacle; in the case that the closest distance is less than the safety distance, the mechanical arm speed is scaled proportionally, and the mechanical arm path is quickly re-planned; Through an end approach strategy, when the distance from the end of the "femur preparation position" is less than a preset distance, switching to a small force threshold force control or visual servoing is performed to ensure that the end position error and posture error are less than a preset value.

[0058] Preferably, when the over-force / collision trigger / registration mismatch (threshold out-of-bound) occurs, a soft emergency stop is performed and the mechanical arm is retreated to the nearest safe intermediate position.

[0059] In an embodiment, the first control sub-module controls the mechanical arm to move to the mapped femur preparation position along the planned mechanical arm femur path, and further comprises: Constructing a twin space based on the real-time intraoperative image of the binocular camera; Generating a twin mechanical arm in the twin space based on the real-time posture of the mechanical arm; Performing motion simulation on the twin mechanical arm based on the corrected mechanical arm femur path, wherein the running time of the motion simulation is earlier than the running time of the mechanical arm Based on the motion simulation result, the mechanical arm femur path is corrected in real time.

[0060] In an embodiment, the mechanical arm control module further comprises a virtual simulation submodule for constructing a virtual space based on the intraoperative surgical environment; simulating the mechanical arm femur path and the mechanical arm tibia path in the virtual space and making corrections.

[0061] The virtual simulation submodule can be the simulation module of the twin space or a new simulation module.

[0062] In an embodiment, the positioning and navigation module is further configured to track the flexion and extension movement of the knee joint in real time after the installation of the prosthesis model based on the navigator and the femur and tibia with installed trackers. The preoperative planning module is further configured to plan soft tissue balance of the knee joint according to the unicompartmental replacement scheme, determine postoperative soft tissue balance through the tracked flexion and extension movement of the knee joint, and compare and display the planned soft tissue balance and the postoperative soft tissue balance.

[0063] As shown in Figure 5 , which is a schematic diagram of the comparison of soft tissue balance and postoperative soft tissue balance.

[0064] In this application, based on the comparison result, the knee joint soft tissue is released or tightened; or the prosthesis position is fine-tuned to make the intraoperative kinematic data as close as possible to the preoperative data reference range, thereby achieving the best soft tissue balance.

[0065] In this way, instead of relying only on the surgeon's sense, the preoperative-intraoperative data curve comparison is used for quantitative judgment; the patient's own preoperative knee joint movement pattern is used as a reference to achieve the best soft tissue balance.

[0066] In an embodiment, in the soft tissue balance, not only the preoperative and intraoperative flexion and extension kinematic curves are obtained, but also: The soft tissue tension and ligament length extracted from imaging (MRI / CT); the joint space pressure recorded by the mechanical sensor; and the real-time force feedback data during the surgeon's operation are obtained.

[0067] In an embodiment, the key point labeling submodule is configured to label the femur key points and the tibia key points of the knee joint, specifically including: performing two-dimensional mapping on the three-dimensional bone model to obtain a two-dimensional mapping diagram; performing multiple rounds of embedding and convolution attention processing on the two-dimensional mapping diagram to obtain multiple levels of attention maps; performing gate sequence fusion processing on the multiple levels of attention maps to obtain multiple levels of fusion maps; After the up-convolution processing of the attention map of the current level / decoding map of the current level, the up-convolution map is added to the fusion map of the previous level to obtain a sum map, the sum map is subjected to linear mapping and activation processing to obtain an activation map, the activation map is multiplied with the sum map to obtain a multiplication map, the multiplication map is subjected to convolution processing, linear processing and activation processing to obtain a second activation map, the second activation map is multiplied with the multiplication map to obtain the decoding map of the previous level. Based on the inverse mapping of the two-dimensional mapping, the femur key points and the tibia key points in the two-dimensional mapping are mapped to the three-dimensional bone model.

[0068] In an embodiment, the up-convolution processing of the attention map of the current level / decoding map of the current level, and the merging convolution of the fusion map of the previous level, to obtain the decoding map of the previous level, comprises: The attention map of the bottom level / decoding map of the current level is subjected to up-convolution processing to obtain an up-convolution map; The up-convolution map and the fusion map of the previous level are added to obtain a sum map; The sum map is subjected to linear mapping and activation processing to obtain an activation map; The activation map and the sum map are multiplied to obtain a multiplication map; The multiplication map is subjected to convolution processing, linear processing and activation processing to obtain a second activation map; The second activation map and the multiplication map are multiplied, and after normalization, the decoding map of the previous level is obtained.

[0069] In an embodiment, the gate sequence fusion processing of the attention maps of multiple levels to obtain the fusion maps of multiple levels comprises: A plurality of convolution branches are constructed, each convolution branch is input by the attention maps of at least two levels, and an output map of a preset level is obtained after fusion, and the output map is output after a gate function; the gate function is a function controlled by a gate sequence; A gate sequence is constructed to control the output of the convolution branch based on the gate function; if the number in the gate sequence is 1, the corresponding gate function allows the convolution branch to output, and if the number in the gate sequence is 0, the corresponding gate function does not allow the convolution branch to output; The output maps of the same preset level and output are merged as the fusion map of the preset level.

[0070] The application further provides a single knee replacement surgery robot system, and a specific scheme of the system is shown in Figures 2-5 .

[0071] Combined with Figure 2 , which is an architecture diagram of a single knee replacement surgery robot system according to an embodiment of the application; wherein the single knee replacement surgery robot system comprises an upper controller, a robot, a navigator, a tracer and a probe. The upper controller performs segmentation and reconstruction of the knee joint according to the acquired knee joint medical image, performs preoperative planning according to the reconstructed three-dimensional model of the knee joint, determines the unicompartmental replacement scheme, and maps the unicompartmental replacement scheme during the operation and sends the unicompartmental replacement scheme to the robot; The trackers of the femur, the trackers of the tibia and the trackers of the guiding device are respectively arranged at the femur and the tibia of the patient and the end of the mechanical arm of the robot, and cooperate with the navigator to track the poses of the femur, the tibia and the guiding device in real time; The probe and the navigator cooperate to collect bone surface contour data of the knee joint of the patient; The upper controller is connected with the navigator and the robot, and is configured to: According to the collected bone surface contour data and the three-dimensional model of the knee joint before the operation, the unicompartmental replacement scheme is mapped, and the path of the mechanical arm to the femur preparation position and the path of the mechanical arm to the tibia preparation position are planned according to the tracked poses of the femur, the tibia and the guiding device in real time; The robot receives the planned path and controls the movement of the mechanical arm and the guiding device to the femur preparation position and the tibia preparation position.

[0072] In an embodiment, the guiding device is provided with a first osteotomy groove, a second osteotomy groove intersecting the first osteotomy groove, and / or a third osteotomy groove, and the osteotomy grooves are used to accommodate the osteotomy tool.

[0073] In an embodiment, the upper controller is further configured to: generate a safety boundary of the selected osteotomy surface; monitor the real-time position of the osteotomy tool of the user; when the osteotomy tool of the user exceeds the safety boundary, generate a stop instruction and send it to the robot.

[0074] The safety boundary is a three-dimensional safety space or volume generated around the planned selected osteotomy surface to prevent accidental deviation of the surgical tool and damage to the surrounding key tissues.

[0075] The safety boundary is generated by automatically offsetting a preset safety distance (for example, 2-3 mm) from the osteotomy position, depth and angle marked by the doctor on the three-dimensional model, and is slightly larger than the actual osteotomy area.

[0076] The execution part of the safety mechanism is a real-time closed-loop control process: the system continuously tracks the pose of the tip and the entire saw blade of the osteotomy tool (such as a swing saw) through an optical positioning system such as NDI; as soon as it is detected that any part of the tool penetrates the safety boundary, the system will immediately trigger the safety protocol, generate a stop instruction and send it to the lower controller of the robot. This instruction has the highest priority and usually: Immediately stop the power output of all motors, so that the mechanical arm is instantaneously kept stationary. At the same time, send a clear audio-visual alarm (such as screen flashing red, sounding an alarm) to the console to remind the doctor.

[0077] In an embodiment, the femoral tracker, the tibial tracker, and the navigation device are further configured to track, in real time, pose change data of the knee joint flexion and extension movement after the installation of the prosthesis model; The upper controller is further configured to: According to the single-cone replacement scheme, the soft tissue balance of the knee joint is planned, the postoperative soft tissue balance is determined through the tracked pose change data of the knee joint flexion and extension movement, and the planned soft tissue balance and the postoperative soft tissue balance are compared and displayed.

[0078] In an embodiment, at least one console is further included, and the console is disposed at a preset location different from the upper controller to generate control instructions; The upper controller is in communication connection with the console and is configured to: In response to the control instructions of the console, the motion path of the mechanical arm is planned according to the mapped single-cone replacement scheme based on the tracked poses of the femur, the tibia, and the end tool; The motion path of the mechanical arm is sent to the mechanical arm and is synchronously sent to the console.

[0079] The planned motion path is sent back to the console in real time, achieving visualization and real-time monitoring, as well as safety verification and human intervention.

[0080] In this way, remote control of the osteotomy surgery is achieved.

[0081] In an embodiment, the upper controller is further configured to: Construct a virtual space based on the intraoperative surgical environment; Simulate the motion path of the mechanical arm in the virtual space and make corrections.

[0082] The specific process can be: Based on the real-time intraoperative image of the binocular camera, a virtual space is constructed; Based on the real-time pose of the mechanical arm, a simulated mechanical arm is generated in the virtual space; Based on the motion path of the mechanical arm, the simulated mechanical arm is subjected to motion simulation, and the running time of the motion simulation is earlier than the running time of the mechanical arm; Based on the motion simulation result, the motion path of the mechanical arm is corrected in real time.

[0083] In an embodiment, the selected osteotomy surface is one of an anterior femoral osteotomy surface, a posterior femoral oblique osteotomy surface, a tibial sagittal osteotomy surface, a tibial horizontal osteotomy surface, a distal femoral osteotomy surface, and a posterior femoral condyle osteotomy surface.

[0084] The anterior femoral osteotomy surface, the posterior femoral oblique osteotomy surface, the distal femoral osteotomy surface, and the posterior femoral condyle osteotomy surface are osteotomy surfaces planned on the femur and correspond to four attachment surfaces of a femoral prosthesis. The tibial sagittal osteotomy surface and the tibial horizontal osteotomy surface are osteotomy surfaces planned on the tibia and correspond to two attachment surfaces (one bottom surface and one side surface) of a tibial prosthesis.

[0085] In an embodiment, the human-computer interaction device includes a display screen. When the trackers of the femur, the trackers of the tibia, and the trackers of the end tool are tracked in real time by the navigator to determine the poses of the femur, the tibia, and the end tool, the display screen displays the poses of the femur, the tibia, and the end tool in real time.

[0086] In this way, the abstract spatial data obtained by the navigation system is converted into an intuitive graphical interface and presented to the surgeon.

[0087] In an embodiment, the navigator receives visible light reflected by the trackers of the femur, the trackers of the tibia, and the trackers of the end tool, and / or infrared light. The upper controller is in communication connection with the navigator and is configured to: According to the received visible light and / or infrared light, the poses of the trackers of the femur, the trackers of the tibia, and the trackers of the end tool are determined.

[0088] In an embodiment, the single-knee replacement surgery robot navigation positioning system further includes a human-computer interaction device that obtains manual operation instructions or knee joint medical images and displays a single-knee replacement scheme. The upper controller is in communication connection with the human-computer interaction device and is configured to: According to the obtained knee joint medical images, the knee joint is segmented and reconstructed to obtain a three-dimensional bone model of the knee joint. Key points of the femur and key points of the tibia of the knee joint are labeled. A unicompartmental replacement prosthesis of the knee joint is planned to determine the prosthesis type and implant information of the unicompartmental replacement. Based on the prosthesis type and implant information, multiple osteotomy surfaces of the femur and multiple osteotomy surfaces of the tibia of the single-knee replacement are planned, and the single-knee replacement scheme is sent to the human-computer interaction device for display.

[0089] In an embodiment, the knee medical image is a frontal lateral X-ray image, or a CT image, or an MRI image, or includes a first image and a second image, and the first image and the second image are any two of the frontal lateral X-ray image, the CT image, and the MRI image.

[0090] It should be noted that the unicompartmental replacement surgery robot system and the unicompartmental replacement surgery robot system described above are different forms of definition and description of the same content, and the description of the specific definition and advantages therein can be mutually referred to. The present application will not be described again.

[0091] The embodiment of the present application provides a control method of the unicompartmental replacement surgery robot system described above, for controlling the unicompartmental replacement surgery robot system described above, and the specific scheme of the method is as follows Figure 6 The control method of the unicompartmental replacement surgery robot system will be described in detail below.

[0092] In combination with Figure 6 The control method of the unicompartmental replacement surgery robot system includes the following steps. S101, segmenting and reconstructing the knee according to the acquired knee medical image, and performing preoperative planning according to the reconstructed knee three-dimensional model to determine a unicompartmental replacement scheme; S102, registering the entity knee in surgery and the knee three-dimensional model before surgery according to the navigator and the tracer to map the unicompartmental replacement scheme, and tracking the poses of the guiding device and the entity knee in real time; S103, planning the paths of the mechanical arm to the femur preparation position and the tibia preparation position, and controlling the mechanical arm guiding device to move to the femur preparation position and the tibia preparation position.

[0093] In this way, the mechanical arm can be controlled to assist in completing the unicompartmental replacement osteotomy surgery through preoperative planning and intraoperative navigation, and the problem that the surgical level is uneven and the surgical effect is not as expected due to individual differences in current manual surgery can be solved.

[0094] In an embodiment, the control method of the unicompartmental replacement surgery robot system further includes the following steps. After installing the prosthesis model, the knee flexion and extension movement is tracked in real time according to the navigator and the femur and tibia with the installed tracer; The soft tissue balance of the knee is planned according to the unicompartmental replacement scheme, the postoperative soft tissue balance is determined through the tracked knee flexion and extension movement, and the planned soft tissue balance and the postoperative soft tissue balance are compared and displayed.

[0095] In an implementation, the medical image is a CT image, and the S101 includes segmenting and reconstructing the knee joint according to the acquired knee joint medical image, and performing preoperative planning according to the reconstructed knee joint three-dimensional model to determine a unicompartmental replacement scheme, including: segmenting and reconstructing the knee joint CT image, and then correcting the reconstructed knee joint three-dimensional bone model to obtain a knee joint three-dimensional bone model in a standard posture; annotating the femoral key points and tibial key points of the knee joint; planning a unicompartmental replacement prosthesis, and determining the model and implant information of the unicompartmental replacement prosthesis; planning the multiple osteotomy surfaces of the femur and the multiple osteotomy surfaces of the tibia for unicompartmental replacement according to the model and implant information of the unicompartmental prosthesis.

[0096] It should be noted that unicompartmental replacement is a replacement of part of the knee joint (for example, only replacing part of the tibial plateau while retaining another part of the tibial plateau), and since part of the knee joint is retained, the accuracy requirement for unicompartmental replacement is higher (compared with total knee replacement). With the same accuracy, total knee replacement may fully meet the standard, while unicompartmental replacement may cause complications due to uneven replacement of the tibial plateau or slight deviation of the force line.

[0097] In addition, unicompartmental replacement itself is a surgery for treating unilateral compartmental lesions of the knee joint, which means that there must be a certain deformation between the preoperative three-dimensional bone models, and this deformation is also a major cause of the lack of accuracy in unicompartmental replacement.

[0098] In this application, the three-dimensional bone model of the knee joint before the operation is corrected to obtain a three-dimensional bone model in a standard posture, and then the preoperative planning scheme for unicompartmental replacement is completed based on the three-dimensional bone model in the standard posture, thereby greatly improving the accuracy of the planning of unicompartmental replacement to further improve the surgical accuracy of unicompartmental replacement.

[0099] In an implementation, the S101 includes segmenting and reconstructing the knee joint according to the acquired knee joint medical image, and performing preoperative planning according to the reconstructed knee joint three-dimensional model to determine a unicompartmental replacement scheme, and further including: planning the osteotomy groove and the nail slot of the osteotomy guide device according to the multiple osteotomy surfaces of the femur and the multiple osteotomy surfaces of the tibia.

[0100] In an implementation, the S103 includes planning the paths of the mechanical arm to the femoral preparation position and the tibial preparation position, and controlling the mechanical arm guide device to move to the femoral preparation position and the tibial preparation position, including: determining a relative position between the current pose of the robotic arm end guide device and the tibia preparation site based on the navigator, the tracker mounted on the robotic arm end guide device, the tracker mounted on the tibia, and the mapped tibia preparation site, and planning a robotic arm tibia path; controlling the robotic arm to move along the planned robotic arm tibia path to the mapped tibia preparation site. determining a relative position between the current pose of the robotic arm end guide device and the tibia preparation site based on the navigator, the tracker mounted on the robotic arm end guide device, the tracker mounted on the tibia, and the mapped tibia preparation site, and planning a robotic arm tibia path; controlling the robotic arm to move along the planned robotic arm tibia path to the mapped tibia preparation site.

[0101] In one embodiment, the controlling the robotic arm to move along the planned robotic arm femur path to the mapped femur preparation site specifically comprises: obtaining a robotic arm femur path, the robotic arm femur path comprising a first path from a current position to a cache position, and a second path from the cache position to the femur preparation site; the cache position and the femur preparation site being at the same osteotomy plane; controlling the robotic arm to move along the first path until reaching the cache position; controlling the robotic arm to move along the second path until reaching the femur preparation site; the second path being a straight line.

[0102] In one embodiment, the controlling the robotic arm to move along the planned robotic arm femur path to the mapped femur preparation site specifically comprises: obtaining an intraoperative image of the binocular camera; generating an intraoperative three-dimensional map based on the intraoperative image; mapping the robotic arm femur path into the intraoperative three-dimensional map for correction; controlling the robotic arm to move according to the corrected robotic arm femur path.

[0103] In one embodiment, the control method further comprises: constructing a virtual space based on the intraoperative surgical environment; simulating the robotic arm femur path and the robotic arm tibia path in the virtual space, and correcting.

[0104] In one embodiment, the controlling the robotic arm to move along the planned robotic arm femur path to the mapped femur preparation site further comprises: constructing a twin space based on real-time intraoperative images of the binocular camera; generating a twin robotic arm in the twin space based on real-time poses of the robotic arm; motion simulation of the twin robot arm based on the corrected femur path of the robot arm, the motion simulation having an earlier run time than the robot arm correcting the femur path of the robot arm in real time based on the motion simulation result.

[0105] In an embodiment, the tibia preparation positions are multiple, the relative position between the current pose of the robot arm end guiding device and the tibia preparation positions is determined based on the navigator, the tracker mounted on the robot arm end guiding device, the tracker mounted on the tibia, the mapped tibia preparation positions, and the robot arm tibia path is planned; comprising: obtaining multiple target positions of the mapped tibia preparation positions and the order of the target positions; determining the relative position between the current pose of the robot arm end guiding device and the first tibia preparation position based on the navigator, the tracker mounted on the robot arm end guiding device, the tracker mounted on the tibia, the mapped first tibia preparation position, and planning the robot arm first tibia path; In response to the received next preparation position signal, the robot arm short tibia path is planned with the current position as the initial position and the target position of the next preparation position as the end position.

[0106] In an embodiment, the robot arm short tibia path is planned with the current position as the initial position and the target position of the next preparation position as the end position in response to the received next preparation position signal, comprising: determining the robot arm pose and the end tool mass center of the current position; determining the robot arm pose and the end tool mass center of the target position; planning the robot arm short tibia path according to the end tool mass center of the current position and the end tool mass center of the target position; planning the robot arm end rotation action of the initial position / end position of the robot arm short tibia path according to the robot arm pose of the current position and the robot arm pose of the target position.

[0107] In an embodiment, the femur key points and the tibia key points of the knee joint are labeled, comprising: performing two-dimensional mapping on the three-dimensional bone model to obtain a two-dimensional mapping graph; performing multiple rounds of embedding and convolution attention processing on the two-dimensional mapping graph to obtain multiple levels of attention graphs; performing gate sequence fusion processing on the multiple levels of attention graphs to obtain multiple levels of fusion graphs; after performing up-convolution processing on the current level of attention graph / decoding graph of the current level, merging convolution is performed with the fusion graph of the previous level to obtain the decoding graph of the previous level; the decoding graph of the highest level is the two-dimensional mapping graph with the key points labeled; Based on the inverse mapping of two-dimensional mapping, the femoral key points and tibial key points in the two-dimensional mapping map are mapped to the three-dimensional skeletal model.

[0108] In this application, key point recognition in three dimensions is achieved by mapping a three-dimensional skeletal model to two dimensions, performing feature recognition, and then mapping the recognized key points back to (inverse mapping) the three-dimensional skeletal model.

[0109] In this application, a gate sequence fusion processing module is set up to randomly process and fuse input maps of multiple levels, and output output maps of multiple levels. In this way, the fusion range during the training process is expanded through random fusion, so as to improve the accuracy of key point recognition.

[0110] In this application, the convolutional attention processing can specifically be downsampling convolution, or it can be downsampling processing weighted by channel attention processing and spatial attention processing.

[0111] In one implementation, as shown in the figure, the step of performing an up-convolution on the attention map / decoding map of the current level and then merging it with the fusion map of the previous level to obtain the decoding map of the previous level includes: Perform upconvolution on the lowest level attention map / the current level decoding map to obtain an upconvolution map; Add the upper convolutional image and the fused image of the previous level to obtain the summed image; Linear mapping and activation processing are performed on the additive graph to obtain the activated graph; The activation graph and the addition graph are multiplied together to obtain the multiplication graph; The multiplication graph is subjected to convolution, linear processing, and activation processing to obtain the second activation graph. The second activation graph and the multiplication graph are multiplied together and normalized to obtain the decoding graph of the next level.

[0112] In this application, after performing upconvolution on the attention map / decoding map of the current level, it is then merged and convolved with the fusion map of the previous level to obtain the decoding map of the previous level; this is an overview of the upsampling process across multiple rounds, which may specifically include: After performing an up-convolution on the lowest-level attention map, it is merged and convolved with the fusion map of the previous level to obtain the decoding map of the previous level. After performing an upconvolution on the current level's decoded graph, it is merged and convolved with the fused graph of the previous level to obtain the decoded graph of the previous level; this step is repeated until the decoded graph of the highest level is obtained.

[0113] In this application, a summed image is obtained by adding the upper convolutional image and the fusion image of the previous level; the summed image is then linearly mapped and activated to obtain an activation image; the activation image and the summed image are multiplied to obtain a multiplied image, thereby enhancing skip connections through the processing of the summed image; furthermore, the multiplied image is subjected to convolution, linear processing, and activation processing to obtain a second activation image, achieving a second residual processing to further enhance skip connections; thus, by enhancing skip connections through refined feature fusion, more refined features are provided for the upsampling process, improving the overall recognition accuracy.

[0114] In one implementation, the step of performing gate sequence fusion processing on attention maps of multiple levels to obtain a fused map of multiple levels includes: Multiple convolutional branches are constructed, each receiving at least two levels of attention maps as input. These are then fused to obtain a preset-level output map, which is then passed through a gate function before being output. The gate function is a function controlled by a gate sequence. Construct a gate sequence to control the output of the convolutional branch based on the gate function; if the number in the gate sequence is 1, the corresponding gate function allows the convolutional branch to output, and if the number in the gate sequence is 0, the corresponding gate function does not allow the convolutional branch to output. The output images of the same preset level are merged to form a fusion image of that preset level.

[0115] In this application, the number of convolutional branches is more than five times the number of layers to ensure that a fusion graph of multiple layers is output (if a fusion graph of 4 layers is to be output, the number of convolutional branches is set to at least 20).

[0116] In this application, the size of the attention map input in each convolutional branch is different, and it can be unified to a preset layer size before processing.

[0117] In this application, the processing procedure for each convolutional branch includes: receiving multiple input attention maps; performing size processing on the attention maps to obtain multiple attention maps of the corresponding size for this convolutional branch; performing fusion processing on multiple attention maps of the same size to obtain an output map; obtaining the gate sequence number of the convolutional branch; if the number is 1, then the output map is used as the fusion map output by the convolutional branch; if the number is 0, then no output is made, or an empty convolutional map is output.

[0118] In this application, the gate sequence is a sequence composed of digits 0 and 1. During the training phase of gate sequence fusion processing, the gate sequence can be randomly generated to improve the diversity of training, and the gate sequence is trained synchronously during the training phase; after training, the gate sequence with the best processing effect is taken as the final gate sequence.

[0119] In this application, by setting up gate sequence fusion processing, and utilizing gate sequences and gate functions, attention maps at multiple levels are randomly fused, thereby granting attention maps similar fusion permissions. This allows attention maps to be fused according to preferences during training (during large-scale data training, exhaustive combinations of downsampling fusions are explored, similar to attention maps having preferences), thus achieving a more intelligent training effect.

[0120] In this application, multiple convolutional branches are constructed randomly, ensuring that different users construct different convolutional branches. Since the final training result includes gate sequences, only these gate sequences need to be retained to achieve confidentiality of the entire model, thus providing strong security. Furthermore, the gate sequences consume very little data and are easily saved and transmitted through various channels, greatly facilitating decryption and security.

[0121] In addition, random construction greatly enhances the diversity and randomness of gate sequence fusion processing, thereby approximately improving the level of intelligence.

[0122] The control method of the unicompartmental replacement surgery robot system provided in the above embodiments of this application corresponds to the unicompartmental replacement surgery robot system provided in the embodiments of this application. Therefore, the specific content of the method corresponds to the unicompartmental replacement surgery robot system. The specific content can be referred to the records in the unicompartmental replacement surgery robot system, which will not be repeated in this application.

[0123] The control method of the unicompartmental replacement surgical robot system provided in the above embodiments of this application is based on the same inventive concept as the unicompartmental replacement surgical robot system provided in the embodiments of this application, and has the same beneficial effects as the methods adopted, run or implemented by the application stored therein.

[0124] Based on the same inventive concept, another embodiment of the present invention provides an electronic device for implementing the control method of the unicompartmental arthroplasty surgical robot system described in the above embodiments. For example... Figure 7 As shown, the electronic device includes a memory 301 and a processor 303.

[0125] Memory 301 can be configured to store a program.

[0126] Additionally, memory 301 can also be configured to store various other data to support operation on the electronic device. Examples of this data include instructions for any application or method used to operate on the electronic device, contact data, phonebook data, messages, pictures, videos, etc.

[0127] Memory 301 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. Processor 303, coupled to memory 301, is used to execute programs in memory 301 for: Based on the acquired medical images of the knee joint, the knee joint is segmented and reconstructed, and preoperative planning is carried out based on the reconstructed three-dimensional model of the knee joint to determine the unicompartmental replacement plan. The navigator and tracker are used to register the intraoperative physical knee joint and the preoperative three-dimensional model of the knee joint to map the unicompartmental knee replacement scheme, and the position and pose of the guiding device and the physical knee joint are tracked in real time. Plan the path of the robotic arm to the femoral preparation position and the path of the robotic arm to the tibial preparation position, and control the robotic arm guide device to move to the femoral preparation position and the tibial preparation position.

[0128] In this application, Figure 7 The diagram only shows some components and does not mean that the electronic device includes only these components. Figure 7 The components shown.

[0129] The electronic device provided in this embodiment is based on the same inventive concept as the force-optimized robotic arm osteotomy control method provided in the embodiments of this application, and has the same beneficial effects as the methods adopted, run or implemented by the application stored therein.

[0130] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-readable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0131] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1One or more processes and / or boxes Figure 1 The computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0132] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0133] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory. Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0134] This application also provides a computer-readable storage medium corresponding to the force-optimized robotic arm osteotomy control method provided in the foregoing embodiments, wherein a computer program (i.e., a program product) is stored thereon. When the computer program is run by a processor, it executes the interactive image analysis assistance method for 3D aerial imaging provided in any of the foregoing embodiments.

[0135] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, 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, optical disc read-only memory (CDROM), digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0136] The computer-readable storage medium provided in the above embodiments of this application and the control method of the unicompartmental replacement surgical robot system provided in the embodiments of this application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0137] It should be noted that numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this application may be practiced without these specific details. In some instances, well-known structures and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0138] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, system, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, system, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, system, article, or apparatus that includes said element.

[0139] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A unicompartmental replacement surgery robotic system, characterized by, The knee arthroplasty system comprises a preoperative planning module, a positioning and navigation module, and a mechanical arm control module. The preoperative planning module is configured to segment and reconstruct a knee joint according to acquired medical images of the knee joint, and to determine a unicompartmental replacement scheme according to a reconstructed three-dimensional model of the knee joint. The positioning and navigation module is configured to register an in-situ knee joint and the three-dimensional model of the knee joint according to a navigator and a tracer, to map the unicompartmental replacement scheme, and to track the poses of a guiding device and the in-situ knee joint in real time. The mechanical arm control module is configured to plan a path of the mechanical arm to a femur preparation position and a path of the mechanical arm to a tibia preparation position, and to control the mechanical arm to move to the femur preparation position and the tibia preparation position. The mechanical arm control module specifically comprises a mechanical arm femur path planning submodule, a first control submodule, a mechanical arm tibia path planning submodule, and a second control submodule.

2. The unicompartmental replacement surgery robot system according to claim 1, characterized in that, The mechanical arm femur path planning submodule is configured to determine the relative position between the current pose of the mechanical arm guiding device and the tibia preparation position based on the navigator, the tracer installed on the mechanical arm guiding device, the tracer installed on the femur, and the mapped femur preparation position, and to plan a mechanical arm femur path. The first control submodule is configured to control the mechanical arm to move to the mapped femur preparation position along the planned mechanical arm femur path. The mechanical arm tibia path planning submodule is configured to determine the relative position between the current pose of the mechanical arm guiding device and the tibia preparation position based on the navigator, the tracer installed on the mechanical arm guiding device, the tracer installed on the tibia, and the mapped tibia preparation position, and to plan a mechanical arm tibia path. The second control submodule is configured to control the mechanical arm to move to the mapped tibia preparation position along the planned mechanical arm tibia path. The mechanical arm control module further comprises a virtual simulation submodule configured to construct a virtual space based on the in-situ surgical environment, simulate the mechanical arm femur path and the mechanical arm tibia path in the virtual space, and correct the mechanical arm femur path and the mechanical arm tibia path.

3. The unicompartmental replacement surgery robot system according to claim 2, characterized in that, The first control submodule is configured to control the mechanical arm to move to the mapped femur preparation position along the planned mechanical arm femur path, and specifically comprises the following steps:

4. The unicompartmental replacement surgery robot system of claim 2, wherein, obtaining a mechanical arm femur path, wherein the mechanical arm femur path comprises a first path from a current position to a cache position, and a second path from the cache position to the femur preparation position; the cache position and the femur preparation position are located on the same osteotomy surface; controlling the mechanical arm to move along the first path until the cache position is reached; controlling the mechanical arm to move along the second path until the femur preparation position is reached; the second path is a straight line. The knee arthroplasty system comprises an upper controller, a robot, a navigator, a tracer, and a probe.

5. A unicompartmental replacement surgical robotic system, characterized in that, The upper controller is configured to segment and reconstruct a knee joint according to acquired medical images of the knee joint, to determine a unicompartmental replacement scheme according to a reconstructed three-dimensional model of the knee joint, to map the unicompartmental replacement scheme during surgery, and to send the unicompartmental replacement scheme to the robot. The tracers of the femur, the tibia, and the guiding device are respectively arranged at the femur and the tibia of a patient and the end of the mechanical arm of the robot, and cooperate with the navigator to track the poses of the femur, the tibia, and the guiding device in real time. The probe and the navigator cooperate to collect bone surface profile data of the knee joint of the patient. ​ ​ The upper controller is connected with the navigator and the robot, and is configured to: According to the collected bone surface profile data and the preoperative knee three-dimensional model, registration is performed, and a unicompartmental replacement scheme is mapped; according to the real-time tracked poses of the femur, tibia and guiding device, a path of the mechanical arm to the femur preparation position and the tibia preparation position is planned; The robot receives the planned path and controls the movement of the mechanical arm guiding device to the femur preparation position and the tibia preparation position.

6. The unicompartmental replacement surgery robot system according to claim 5, characterized in that, The guiding device is provided with a first osteotomy groove, a second osteotomy groove intersecting the first osteotomy groove, and / or a third osteotomy groove, and the osteotomy grooves are used to accommodate the osteotomy tool.

7. The unicompartmental replacement surgery robot system according to claim 5, wherein, The trackers of the femur and the trackers of the tibia also cooperate with the navigator, and after the installation of the prosthesis model, real-time tracking of the pose change data of the knee flexion and extension movement is performed; The upper controller is also configured to: According to the unicompartmental replacement scheme, the soft tissue balance of the knee joint is planned, the postoperative soft tissue balance is determined through the tracked pose change data of the knee flexion and extension movement, and the planned soft tissue balance and the postoperative soft tissue balance are compared and displayed.

8. A control method of a unicompartmental replacement surgery robot system for controlling the unicompartmental replacement surgery robot system according to claims 1 to 4, or the unicompartmental replacement surgery robot system according to claims 5 to 7, characterized in that, It comprises: According to the obtained knee medical image, the knee is segmented and reconstructed, and according to the reconstructed knee three-dimensional model, preoperative planning is performed to determine a unicompartmental replacement scheme; According to the navigator and the tracker, the in-situ knee joint and the preoperative knee three-dimensional model are registered to map the unicompartmental replacement scheme, and the poses of the guiding device and the in-situ knee joint are tracked in real time; The path of the mechanical arm to the femur preparation position and the tibia preparation position is planned, and the movement of the mechanical arm guiding device to the femur preparation position and the tibia preparation position is controlled.

9. An electronic device, comprising: It comprises: A memory and a processor; The memory is used to store programs; The processor is coupled to the memory and is used to execute the programs for: According to the obtained knee medical image, the knee is segmented and reconstructed, and according to the reconstructed knee three-dimensional model, preoperative planning is performed to determine a unicompartmental replacement scheme; According to the navigator and the tracker, the in-situ knee joint and the preoperative knee three-dimensional model are registered to map the unicompartmental replacement scheme, and the poses of the guiding device and the in-situ knee joint are tracked in real time; The path of the mechanical arm to the femur preparation position and the tibia preparation position is planned, and the movement of the mechanical arm guiding device to the femur preparation position and the tibia preparation position is controlled.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The programs executed by the processor realize the control method of the unicompartmental replacement surgery robot system of claim 8.

Images