Positioning method based on magnetic navigation, surgical power device and surgical operation system

Abstract

The invention relates to the technical field of medical instruments, and discloses a positioning method based on magnetic navigation, a surgical power device and a surgical operating system, the method comprises the following steps: obtaining an initial calibration position of a cutter, and obtaining a real-time acceleration and a real-time angular velocity of the surgical power device through a gyroscope, the initial calibration position is obtained through a positioning magnetic field collected by the first magnetic detection part in the magnetic field; determining a real-time displacement according to the real-time acceleration, and determining a real-time rotation angle according to the real-time angular velocity; and the tool is positioned based on the real-time displacement, the real-time rotation angle and the initial calibration position. As positioning can be achieved through the first magnetic detection component and the gyroscope, compared with an existing mode of adopting an optical camera and a reflective ball, the optical mode is directly abandoned, positioning is achieved by adopting a magnetic field and arranging the gyroscope on the operation power device, optical sight is not depended on, the situation of positioning interruption is reduced, and the positioning accuracy is improved. And the user experience is improved.

Description

Technical Field

[0001] This application relates to the field of medical device technology, and in particular to a positioning method based on magnetic navigation, a surgical power device, and a surgical operating system. Background Technology

[0002] Currently, in orthopedic surgeries such as joint replacement, it is usually necessary to use cutting tools (such as oscillating saws, drills, etc.) in the surgical power unit to cut the bone. Taking the oscillating saw as an example, in order to track the precise position of the oscillating saw teeth at the end of the surgical power unit inside the human body in real time during the operation, an optical navigation system is generally used.

[0003] Specifically, before the surgery begins, the operator can place the tip of the oscillating saw at a fixed reference point known to the navigation system. While keeping the tip stationary, the system uses an optical camera to capture the position of a reflective ball mounted on the surgical power unit. Calibration is then completed based on the position of the fixed reference point and the position of the reflective ball. During the surgery, the position of the reflective ball is captured in real time, and the previously calibrated result is used to calculate the real-time position of the tip of the saw. This result is then overlaid on the patient's medical image to guide the surgeon's operation.

[0004] However, in the current surgical process, the optical camera needs to collect the position of the reflective ball in real time. When there are obstacles in the shooting path (such as the operator passing through the shooting path and causing obstruction of the shooting), it is easy to cause positioning interruption, resulting in a poor user experience. Summary of the Invention

[0005] The main purpose of this application is to provide a positioning method, surgical power device and surgical operating system based on magnetic navigation, which aims to solve the technical problem that existing positioning methods using optical cameras and reflective balls are easily blocked by obstacles, resulting in positioning interruption and poor user experience.

[0006] To achieve the above objectives, this application provides a positioning method based on magnetic navigation. The method is applied to a surgical power unit in a surgical operating system. The surgical power unit includes a cutting tool, a first magnetic detection component, and a gyroscope. The surgical operating system also includes a magnetic field emitting device for generating a magnetic field. The method includes: The initial calibration position of the cutting tool is obtained, and the real-time acceleration and real-time angular velocity of the surgical power device are obtained through the gyroscope. The initial calibration position is obtained by the positioning magnetic field collected by the first magnetic detection component in the magnetic field. The real-time displacement is determined based on the real-time acceleration, and the real-time rotation angle is determined based on the real-time angular velocity. The tool is positioned based on the real-time displacement, the real-time rotation angle, and the initial calibration position.

[0007] In one embodiment, the surgical power device further includes a device body, the cutting tool and the first magnetic detection component are disposed on the device body, and the device body drives the cutting tool to move; The step of obtaining the initial calibration position of the tool includes: During the positioning phase, the positioning magnetic field in the magnetic field is collected by the first magnetic detection component, and the device coordinates of the magnetic field emitting device are obtained. The coordinates of the first component of the first magnetic detection component are determined based on the device coordinates and the positioning magnetic field. The coordinates of the first component are transformed by a preset transformation relationship to obtain the tool coordinates, and the tool coordinates are used as the initial calibration position of the tool.

[0008] In one embodiment, the surgical operating system further includes a second magnetic detection component; Before the step of acquiring the positioning magnetic field in the magnetic field through the first magnetic detection component during the positioning phase, the method further includes: During the calibration phase, the device coordinates of the magnetic field emitting device are obtained; The first magnetic detection component acquires a first calibration magnetic field in the magnetic field, and the second magnetic detection component acquires a second calibration magnetic field in the magnetic field. The second calibration magnetic field is the current magnetic field of the tool's location in the magnetic field. The first calibration coordinates of the first magnetic detection component are determined based on the device coordinates and the first calibration magnetic field, and the second calibration coordinates of the second magnetic detection component are determined based on the device coordinates and the second calibration magnetic field. A preset transformation relationship is constructed based on the first calibration coordinate and the second calibration coordinate.

[0009] In one embodiment, the step of determining the real-time displacement based on the real-time acceleration includes: The initial velocity of the surgical power device at the initial moment is obtained, and the real-time acceleration is integrated according to the current moment and the initial moment to obtain the continuous change in velocity; The real-time speed is obtained based on the initial speed and the continuous change in speed. The initial displacement of the surgical power device at the initial moment is obtained, and the real-time velocity is integrated according to the current moment and the initial moment to obtain the continuous change of displacement; The real-time displacement is obtained based on the initial displacement and the continuous change in displacement.

[0010] In one embodiment, the step of determining the real-time displacement based on the real-time acceleration includes: The previous velocity and acceleration of the surgical power device at the previous acquisition time are obtained, and the acquisition time interval is also obtained. The velocity interval change is obtained based on the real-time acceleration, the previous acceleration, and the acquisition time interval, and the real-time velocity is obtained based on the previous velocity and the velocity interval change. The previous displacement of the surgical power device at the previous acquisition time is obtained, and the displacement interval change is obtained based on the real-time speed, the previous speed and the acquisition time interval. The real-time displacement is obtained based on the previous displacement and the change in the displacement interval.

[0011] In one embodiment, the step of determining the real-time rotation angle based on the real-time angular velocity includes: The initial rotation angle of the surgical power device at the initial moment is obtained, and the real-time angular velocity is integrated according to the current moment and the initial moment to obtain the continuous change of the angle; The real-time rotation angle is obtained based on the initial rotation angle and the continuous change of the angle.

[0012] In one embodiment, the step of determining the real-time rotation angle based on the real-time angular velocity includes: The previous rotation angle and angular velocity of the surgical power device at the previous acquisition time are obtained, and the acquisition time interval is also obtained. The change in angle interval is obtained based on the real-time angular velocity, the previous angular velocity, and the acquisition time interval, and the real-time rotation angle is obtained based on the previous rotation angle and the change in angle interval.

[0013] In one embodiment, the step of positioning the tool based on the real-time displacement, the real-time rotation angle, and the initial calibration position includes: The target position of the tool is obtained based on the real-time displacement, the real-time rotation angle, and the initial calibration position. If the calibration time interval does not reach the preset time interval, the tool is positioned according to the target position; When the correction time interval reaches the preset time interval, the target position is corrected for error using a preset neural network model, and the tool is positioned according to the corrected target position.

[0014] In one embodiment, before the step of obtaining the initial calibration position of the tool, the method further includes: Obtain a training dataset and a validation dataset, construct a first network tensor based on the training dataset, and construct a second network tensor based on a preset learning rate parameter; A correction vector is constructed based on the real-time rotation angle, and a correction matrix is ​​obtained according to the preset correction parameters and the correction vector; The training dataset is corrected using the first network tensor, the second network tensor, and the correction matrix; The initial neural network model is trained using the modified training dataset and the validation dataset to obtain the preset neural network model.

[0015] In one embodiment, the step of correcting the training dataset using the first network tensor, the second network tensor, and the correction matrix includes: The first network tensor and the correction matrix are multiplied to obtain the multiplication result, and the multiplication result and the second network tensor are concatenated to obtain the concatenated result; The splicing result is expanded using the second network tensor to obtain an expanded result, and the dimensions of the expanded result are adjusted to obtain an adjusted result; The adjusted results are used as the corrected training dataset.

[0016] In addition, to achieve the above objectives, this application also proposes a surgical power device, which includes: a cutting tool, a first magnetic detection component, a gyroscope, a memory, a processor, and a magnetic navigation-based positioning program stored in the memory and executable on the processor. When the magnetic navigation-based positioning program is executed by the processor, it implements the steps of the magnetic navigation-based positioning method described above.

[0017] In addition, to achieve the above objectives, this application also proposes a surgical operating system, which includes a magnetic field emitting device and a surgical power device as described above.

[0018] This application provides a positioning method, surgical power unit, and surgical operating system based on magnetic navigation. The method is applied to the surgical power unit in the surgical operating system. The surgical power unit includes a cutting tool, a first magnetic detection component, and a gyroscope. The surgical operating system also includes a magnetic field emitting device for generating a magnetic field. The method includes: obtaining the initial calibration position of the cutting tool, and obtaining the real-time acceleration and real-time angular velocity of the surgical power unit through the gyroscope. The initial calibration position is obtained by the positioning magnetic field collected by the first magnetic detection component in the magnetic field; determining the real-time displacement based on the real-time acceleration, and determining the real-time rotation angle based on the real-time angular velocity; and positioning the cutting tool based on the real-time displacement, the real-time rotation angle, and the initial calibration position.

[0019] This application includes a magnetic field emitting device that generates a magnetic field, and a first magnetic detection component and a gyroscope on the surgical power unit. In actual use, the initial calibration position of the cutting tool can be obtained by first detecting the positioning magnetic field in the magnetic field by the first detection component, and simultaneously, the real-time acceleration and angular velocity of the surgical power unit can be obtained by the gyroscope. Then, the real-time displacement of the surgical power unit is determined based on the real-time acceleration, and the real-time rotation angle of the surgical power unit is determined based on the real-time angular velocity. Finally, the cutting tool can be positioned based on the real-time displacement, real-time rotation angle, and initial calibration position. Since this application can achieve positioning through the first magnetic detection component and the gyroscope, compared with the existing method of using optical cameras and reflectors, this application directly abandons the optical method and uses a magnetic field and a gyroscope set in the surgical power unit itself to achieve positioning, without relying on optical lines of sight, thereby reducing positioning interruptions and improving the user experience. Attached Figure Description

[0020] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0021] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a schematic diagram of the surgical power device structure of the hardware operating environment involved in the embodiments of this application; Figure 2 This is a flowchart illustrating the first embodiment of the positioning method based on magnetic navigation in this application; Figure 3This is a schematic diagram of the surgical power device in the first embodiment of the magnetic navigation-based positioning method of this application; Figure 4 This is a flowchart illustrating the second embodiment of the positioning method based on magnetic navigation in this application; Figure 5 This is a flowchart illustrating the third embodiment of the positioning method based on magnetic navigation in this application.

[0023] Explanation of icon numbers:

[0024] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0025] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0026] Reference Figure 1 , Figure 1 This is a schematic diagram of the surgical power device structure of the hardware operating environment involved in the embodiments of this application.

[0027] like Figure 1 As shown, the surgical power unit may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The user interface 1003 may include an interface for connecting to a display screen; optionally, the user interface 1003 may also include a standard wired interface or a wireless interface. In this application, the wired interface of the user interface 1003 may be a USB interface. The network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a Wireless-Fidelity (Wi-Fi) interface). The memory 1005 may be a high-speed random access memory (RAM) or a non-volatile memory (NVM), such as a disk storage device. The memory 1005 may also optionally be a storage device independent of the aforementioned processor 1001.

[0028] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on the surgical power unit and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0029] like Figure 1 As shown, the memory 1005, which is identified as a computer storage medium, may include an operating system, a network communication module, a user interface module, and a positioning program based on magnetic navigation.

[0030] exist Figure 1 In the surgical power device shown, the network interface 1004 is mainly used to connect to the backend server and communicate data with the backend server; the user interface 1003 is mainly used to connect to the user equipment; the surgical power device calls the magnetic navigation-based positioning program stored in the memory 1005 through the processor 1001 and executes the magnetic navigation-based positioning method provided in the embodiments of this application.

[0031] It should be emphasized that the above-mentioned surgical power device also includes: device body 3, blade 1, first magnetic detection component 2, second magnetic detection component, and gyroscope. The specific implementation methods of each of the above components can be referred to in the following method embodiments, and will not be elaborated upon in this embodiment.

[0032] It should be noted that currently, in orthopedic surgeries such as joint replacement, a surgical power device (such as an oscillating saw) is usually required to cut the bone. In order to track the precise position of the tooth tip of the cutting tool 1 at the end of the surgical power device within the human body in real time during the operation, an optical navigation system is generally used.

[0033] Specifically, before the surgery begins, the operator can place the tip of the cutting tool 1 on a fixed reference point known to the navigation system. While keeping the tip stationary, the system uses an optical camera to capture the position of a reflective ball mounted on the surgical power unit. Calibration is then completed based on the position of the fixed reference point and the position of the reflective ball. During the surgery, the position of the reflective ball can be captured in real time, and the previously calibrated position is used to calculate the real-time position of the tip, which is then superimposed onto the patient's medical image to guide the surgeon's operation.

[0034] However, in the current surgical process, the optical camera needs to collect the position of the reflective ball in real time. When there are obstacles in the shooting path (such as the operator passing through the shooting path and causing obstruction of the shooting), it is easy to cause positioning interruption, resulting in a poor user experience.

[0035] Therefore, to address the aforementioned shortcomings, this embodiment provides a positioning method based on magnetic navigation. This embodiment includes a magnetic field transmitting device that generates a magnetic field, and a first magnetic detection component 2 and a gyroscope mounted on the surgical power unit. In actual use, the initial calibration position of the cutting tool 1 is first obtained by collecting the positioning magnetic field in the magnetic field using the first detection component. Simultaneously, the real-time acceleration and angular velocity of the surgical power unit are acquired in real time using the gyroscope. Then, the real-time displacement of the surgical power unit is determined based on the real-time acceleration, and the real-time rotation angle is determined based on the real-time angular velocity. Finally, the cutting tool 1 is positioned based on the real-time displacement, real-time rotation angle, and initial calibration position. Since this embodiment achieves positioning using the first magnetic detection component 2 and the gyroscope, compared to existing methods using optical cameras and reflectors, this embodiment directly abandons optical methods and uses magnetic fields and a gyroscope mounted on the surgical power unit itself for positioning. This eliminates reliance on optical lines of sight, thereby reducing positioning interruptions and improving the user experience.

[0036] For ease of understanding, the following is combined with Figures 2 to 5 The positioning method based on magnetic navigation provided in the embodiments of this application will be described in detail.

[0037] Reference Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of the positioning method based on magnetic navigation of this application. The first embodiment of the positioning method based on magnetic navigation of this application is presented as follows: Figure 2 As shown, in this embodiment, the specific method includes: Step S10: Obtain the initial calibration position of the cutting tool 1, and obtain the real-time acceleration and real-time angular velocity of the surgical power device through the gyroscope. The initial calibration position is obtained by the positioning magnetic field collected by the first magnetic detection component 2 in the magnetic field.

[0038] It is understood that the method of this embodiment can be applied to any device with data processing, program execution, and positioning functions, such as the surgical power device mentioned above in a surgical operating system, and this embodiment does not limit it. However, for ease of understanding, this embodiment uses a surgical power device as the execution subject to describe this embodiment and the following embodiments.

[0039] It is also understood that the surgical operating system described above in this embodiment can be a system including a surgical power unit and a magnetic field emitting device. The surgical power unit can be any device that provides mechanical power to help the user complete the cutting. For ease of understanding, refer to... Figure 3 , Figure 3 This is a schematic diagram of the surgical power device in the first embodiment of the magnetic navigation-based positioning method of this application. Figure 3As shown, the surgical power device may include a device body 3, a cutting tool 1, a first magnetic detection component 2, and a gyroscope (not shown in the figure).

[0040] The aforementioned device body 3 can be the main structure of a surgical power device, which may include a motor, housing, handle, and control mechanism, etc., and this embodiment does not impose any limitations on this. The aforementioned blade 1 can be an actuating component installed at the end of the device body 3, and a serration (i.e.,...) can be provided at the end of the blade 1 away from the device body 3. Figure 3 (A) Then the motor in the main body 3 can be connected to the cutter 1 to drive the cutter 1 to move the saw teeth to complete the cutting of bones and other parts.

[0041] The aforementioned first magnetic detection component 2 can be any sensor that senses magnetic field strength and direction parameters, such as a magnetometer or magnetic sensor. This embodiment uses a magnetic sensor for illustration. Furthermore, as... Figure 3 As shown, in this embodiment, the first magnetic detection component 2 can be fixed on the device body 3 of the surgical power device, and the specific position can be set according to the actual situation.

[0042] The aforementioned gyroscope can be a gyroscope used to collect acceleration and angular velocity, such as a six-axis inertial measurement unit, which integrates a three-axis accelerometer and a three-axis gyroscope. Furthermore, in this embodiment, the gyroscope can be mounted on the device body 3, and its specific location can be set according to actual conditions.

[0043] The aforementioned magnetic field emitting device can be a device capable of generating a known controlled magnetic field with a specific gradient or distribution pattern in space, such as a device with a permanent magnet, etc. This embodiment does not impose any limitations on this. In this embodiment, the aforementioned magnetic field emitting device can be fixedly placed near the operating table so that the emitted magnetic field can be collected by the first magnetic detection component 2.

[0044] It should be understood that the aforementioned initial calibration position can be the precise three-dimensional coordinate position of the tip of the cutting tool 1 in the global coordinate system established by the magnetic field emitting device before the start of surgical tracking. This initial calibration position can be a known fixed position, and the specific position can be set according to the actual situation. This embodiment does not impose any restrictions on this. Before surgical tracking, the magnetic field emitting device can emit a magnetic field. At this time, the cutting tool 1 can be placed in this known fixed position. The first magnetic detection component 2 collects the magnetic field at this time (i.e., the aforementioned positioning magnetic field) to determine the position of the first magnetic detection component 2 in the magnetic field. Since the position between the first magnetic detection component 2 and the cutting tool 1 is fixed, the initial calibration position of the cutting tool 1 can be obtained by converting the position of the first magnetic detection component 2 in the magnetic field.

[0045] It should also be understood that the aforementioned real-time acceleration can refer to the instantaneous linear acceleration generated by motion, measured by the gyroscope when the surgical power unit is moving. The aforementioned real-time angular velocity can refer to the instantaneous angular velocity values ​​of the surgical power unit, measured by the gyroscope, around its various axes when it is rotating.

[0046] In actual use, before use, the user can place the surgical power unit (blade 1) in a known fixed position and maintain it in a fixed initial posture. At this time, the first magnetic detection component 2 will measure and collect the positioning magnetic field (i.e., the magnetic field strength and / or direction at that position point), and then calculate the initial calibration position of the blade 1 based on the positioning magnetic field. At the same time, the real-time acceleration and real-time angular velocity of the surgical power unit are collected by the gyroscope.

[0047] Step S20: Determine the real-time displacement based on the real-time acceleration, and determine the real-time rotation angle based on the real-time angular velocity.

[0048] It should be noted that the aforementioned real-time displacement can be the displacement of the surgical power unit at the current moment relative to the start time of operation. Similarly, the aforementioned real-time rotation angle can be the rotation angle of the surgical power unit at the current moment relative to the start time of operation.

[0049] In this embodiment, the real-time displacement can be obtained by numerical integration based on the obtained real-time acceleration, and the real-time rotation angle can be obtained by integration based on the real-time angular velocity.

[0050] Step S30: Position the tool 1 based on the real-time displacement, the real-time rotation angle, and the initial calibration position.

[0051] After obtaining the real-time displacement and real-time rotation angle, since the positional relationship between the gyroscope and the tool 1 is also fixed, the initial calibration position can be transformed. The initial calibration position is displaced according to the real-time displacement and rotated according to the real-time rotation angle, thereby obtaining the current position of the tool 1 and completing the positioning of the tool 1.

[0052] Therefore, since this embodiment can achieve positioning through the first magnetic detection component 2 and the gyroscope, compared with the existing method of using an optical camera and a reflective ball, this embodiment directly abandons the optical method and uses a magnetic field and a gyroscope set in the surgical power device itself to achieve positioning, without relying on optical line of sight, thereby reducing positioning interruptions and improving the user experience.

[0053] Furthermore, in order to convert the location of the first magnetic detection component 2 into the initial calibration position of the cutting tool 1, in this embodiment, the surgical power device also includes a device body 3, the cutting tool 1 and the first magnetic detection component 2 are disposed on the device body 3, and the device body 3 drives the cutting tool 1 to move. The step of obtaining the initial calibration position of the tool 1 includes: Step S11: In the positioning stage, the positioning magnetic field in the magnetic field is collected by the first magnetic detection component 2, and the device coordinates of the magnetic field emitting device are obtained.

[0054] It should be noted that the aforementioned positioning magnetic field can be the magnetic field actually measured by the first magnetic detection component 2. The aforementioned device coordinates can be the position coordinates of the magnetic field emitting device itself in the global coordinate system, and these device coordinates can be pre-set known coordinates.

[0055] In actual use, the user can place the blade 1 of the surgical power unit at a known initial calibration position. At this time, the first magnetic detection component 2 begins to collect the positioning magnetic field and simultaneously obtains the coordinates of the device where the magnetic field emitting device is located.

[0056] Step S12: Determine the first component coordinates of the first magnetic detection component 2 based on the device coordinates and the positioning magnetic field.

[0057] It is understandable that the coordinates of the first component mentioned above can be the precise three-dimensional coordinates of the first magnetic detection component 2 in the global coordinate system.

[0058] In practical use, the surgical power device can also acquire the magnetic field model of the magnetic field emitting device and compare the positioning magnetic field with the magnetic field model. Since the magnetic field model contains the distribution law of the magnetic field in space, the position of the first magnetic detection component 2 in the magnetic field can be directly obtained based on the positioning magnetic field, which can be used as the coordinates of the first component.

[0059] Step S13: Transform the coordinates of the first component using a preset transformation relationship to obtain the coordinates of the tool 1, and use the coordinates of the tool 1 as the initial calibration position of the tool 1.

[0060] It should be understood that the aforementioned preset transformation relationship can be the spatial geometric relationship between the first magnetic detection component 2 and the tooth tip of the cutting tool 1, for example, it can be a transformation matrix, which can include rotation and translation components, and can be obtained by prior measurement.

[0061] It should also be understood that the coordinates of tool 1 mentioned above can be the three-dimensional coordinates of the tooth tip of the mirror saw in the global coordinate system.

[0062] In actual use, the surgical power unit can obtain a preset conversion relationship and use the obtained coordinates of the first component as input. By using the preset conversion relationship, the coordinates of the tool 1 can be obtained as the initial calibration position mentioned above.

[0063] Furthermore, since the position between the first magnetic detection component 2 and the tooth tip of the cutter 1 is fixed, in order to obtain the above-mentioned preset conversion relationship, in this embodiment, the surgical operating system further includes a second magnetic detection component.

[0064] It should be noted that the aforementioned second magnetic detection component can be a temporary magnetic sensor used during the calibration phase, which can be used to obtain the tooth tip position of the tool 1. The aforementioned second magnetic detection component can be set in any position. It should be noted that since the tool 1 needs to be placed on the second magnetic detection component, the second magnetic detection component should be set separately from the tool 1.

[0065] Before the step of acquiring the positioning magnetic field in the magnetic field through the first magnetic detection component 2 during the positioning phase, the method further includes: Step S001: During the calibration phase, obtain the device coordinates of the magnetic field emitting device; Step S002: The first calibration magnetic field in the magnetic field is acquired by the first magnetic detection component 2, and the second calibration magnetic field in the magnetic field is acquired by the second magnetic detection component. The second calibration magnetic field is the current magnetic field of the location of the tool 1 in the magnetic field.

[0066] Before positioning, the surgical power device can be calibrated. During the calibration stage, the user can first place the tip of the blade 1 of the surgical positioning device close to the second magnetic detection component (preferably, the blade 1 can be placed perpendicular to the second magnetic detection component, and the center of the tip of the blade 1 is close to the second magnetic detection component). Figure 3 (Point A in the middle), then the surgical power device can first obtain the device coordinates of the magnetic field emitting device, and simultaneously obtain the magnetic field collected by the first magnetic detection component 2 as the first calibration magnetic field, and obtain the magnetic field collected by the second magnetic detection component as the second calibration magnetic field. Since the second magnetic detection component is close to the center of the tooth tip of the cutter 1 at this time, the second calibration magnetic field can be used as the current magnetic field of the location of the cutter 1 in the magnetic field.

[0067] Step S003: Determine the first calibration coordinates of the first magnetic detection component 2 based on the device coordinates and the first calibration magnetic field, and determine the second calibration coordinates of the second magnetic detection component based on the device coordinates and the second calibration magnetic field; Step S004: Construct a preset transformation relationship based on the first calibration coordinates and the second calibration coordinates.

[0068] It is understood that the first calibration coordinates mentioned above can be the coordinates of the position of the first magnetic detection component 2 in the global coordinate system, and the second calibration coordinates mentioned above can be the coordinates of the position of the second magnetic detection component in the global coordinate system.

[0069] In practical use, based on the calculation principle of magnetic navigation, the first calibration coordinates of the first magnetic detection component 2 can be obtained according to the device coordinates and the first calibration magnetic field, and the second calibration coordinates of the second magnetic detection component can be obtained according to the device coordinates and the second calibration magnetic field. Finally, since the first and second calibration coordinates are now known, vector operations can be performed on them to construct a preset transformation relationship.

[0070] This embodiment provides a positioning method based on magnetic navigation. This embodiment includes a magnetic field transmitting device that generates a magnetic field, and a first magnetic detection component 2 and a gyroscope on the surgical power unit. In actual use, the initial calibration position of the cutting tool 1 is obtained by first collecting the positioning magnetic field in the magnetic field through the first detection component. Simultaneously, the real-time acceleration and angular velocity of the surgical power unit are obtained in real time through the gyroscope. Then, the real-time displacement of the surgical power unit is determined based on the real-time acceleration, and the real-time rotation angle of the surgical power unit is determined based on the real-time angular velocity. Finally, the cutting tool 1 is positioned based on the real-time displacement, real-time rotation angle, and initial calibration position. Since this embodiment achieves positioning through the first magnetic detection component 2 and the gyroscope, compared to existing methods using optical cameras and reflectors, this embodiment directly abandons optical methods and uses magnetic fields and a gyroscope built into the surgical power unit itself for positioning. It does not rely on optical lines of sight, thereby reducing positioning interruptions and improving the user experience.

[0071] It should also be emphasized that, compared with the method of positioning using a pure magnetic field, since there can be interference in the magnetic field that causes instability, this embodiment can rely on the gyroscope itself to complete the acquisition of displacement and rotation angle, thereby completing the positioning and further improving the stability of positioning.

[0072] Reference Figure 4 , Figure 4 This is a flowchart illustrating the second embodiment of the positioning method based on magnetic navigation of this application. Based on the first embodiment described above, the second embodiment of the positioning method based on magnetic navigation of this application is proposed.

[0073] To obtain real-time displacement, such as Figure 4 As shown, in this embodiment, the step of determining the real-time displacement based on the real-time acceleration includes: Step S21: Obtain the initial velocity of the surgical power device at the initial moment, and integrate the real-time acceleration according to the current moment and the initial moment to obtain the continuous change in velocity.

[0074] It should be noted that the initial time mentioned above can be the time when positioning begins, that is, the time after calibration ends, which can be denoted as t0. The initial velocity mentioned above can be the velocity collected by the gyroscope at the initial time, which can be denoted as v(t0). The continuous change in velocity mentioned above can be the total change in velocity caused by the accumulation of all real-time accelerations (denoted as a(t)) from the initial time to the current time (denoted as t), which can be denoted as Δv = .

[0075] Step S22: Obtain the real-time speed based on the initial speed and the continuous change in speed.

[0076] After obtaining the continuous change in velocity, it can be summed with the initial velocity to obtain the real-time velocity, denoted as v(t) = v(t0) + .

[0077] Step S23: Obtain the initial displacement of the surgical power device at the initial moment, and integrate the real-time velocity according to the current moment and the initial moment to obtain the continuous change in displacement.

[0078] Understandably, the initial displacement mentioned above can be the displacement at the initial moment, denoted as s(t0). Since the initial moment is generally a static state, s(t0) = 0. The continuous change in displacement mentioned above can be the total change in displacement caused by the accumulation of all real-time velocities from the initial moment to the current moment, denoted as Δs = .

[0079] Step S24: Obtain the real-time displacement based on the initial displacement and the continuous change in displacement.

[0080] After obtaining the continuous change in displacement, it can be summed with the initial displacement to obtain the real-time displacement, denoted as s(t) = s(t0) + .

[0081] Furthermore, in addition to using an integral method, a discrete method can also be used. Specifically, the step of determining the real-time displacement based on the real-time acceleration includes: Step S21': Obtain the previous velocity and acceleration of the surgical power device at the previous acquisition time, and obtain the acquisition time interval.

[0082] It should be noted that the aforementioned "previous acquisition time" can be the most recent time the gyroscope acquired data before the current time. In this embodiment, the gyroscope can acquire data according to the aforementioned acquisition time interval, which can be denoted as Δt. For example, if the current time is k, then the previous acquisition time can be t(k-1). The aforementioned "previous velocity" can be the velocity calculated at the previous acquisition time, denoted as v(k-1), and the aforementioned "previous acceleration" can be the real-time acceleration acquired at the previous moment, denoted as a(k-1).

[0083] In actual use, the surgical power device can obtain real-time acceleration and calculate real-time velocity after each acquisition, so that the previous velocity and acceleration obtained in the previous calculation can be retrieved at the current moment.

[0084] Step S22': Obtain the velocity interval change based on the real-time acceleration, the previous acceleration, and the acquisition time interval, and obtain the real-time velocity based on the previous velocity and the velocity interval change.

[0085] It should also be noted that the above real-time acceleration can be the acceleration at the current moment, denoted as a(k), and the above velocity interval change can be the velocity change between the previous moment and the current moment, which can be obtained by 1 / 2*(a(k-1)+a(k))*△t.

[0086] The real-time speed mentioned above can be the speed at the current moment, which can be denoted as v(k). After obtaining the speed interval change, it can be obtained by v(k) = v(k-1) + 1 / 2 * (a(k-1) + a(k)) * Δt.

[0087] Step S23': Obtain the previous displacement of the surgical power device at the previous acquisition time, and obtain the displacement interval change based on the real-time speed, the previous speed and the acquisition time interval; Step S24': Obtain the real-time displacement based on the previous displacement and the change in displacement interval.

[0088] Understandably, the aforementioned previous displacement can be the displacement at the previous acquisition time, which can be denoted as s(k-1). The aforementioned displacement interval change can be the change in displacement from the previous time to the current time, which can be obtained by 1 / 2*(v(k-1)+v(k))*△t.

[0089] It is also understandable that the above real-time displacement can be the displacement at the current moment, which can be written as s(k) = s(k-1) + 1 / 2 * (v(k-1) + v(k)) * Δt.

[0090] Furthermore, in order to obtain the real-time rotation angle, in this embodiment, the step of determining the real-time rotation angle based on the real-time angular velocity includes: Step S25: Obtain the initial rotation angle of the surgical power device at the initial moment, and integrate the real-time angular velocity according to the current moment and the initial moment to obtain the continuous change of angle; Step S26: Obtain the real-time rotation angle based on the initial rotation angle and the continuous change of the angle.

[0091] It should be noted that the aforementioned initial rotation angle can be the attitude angle of the surgical power device relative to its own reference coordinate system at the initial moment, denoted as θ(t0). Since the surgical power device is in the initial calibration position at the initial moment, the initial rotation angle can be initially set to (0, 0, 0), or it can be other values. This embodiment does not limit this.

[0092] It should also be noted that the aforementioned real-time angular velocity can be the instantaneous velocity of the surgical power device rotating around the X, Y, and Z axes, which can be denoted as w(t). The aforementioned continuous change in angle can be the total change in rotation angle caused by the accumulation of all real-time angular velocities from the initial moment to the current moment, which can be obtained through... get.

[0093] After obtaining the continuous change in angular velocity, it can be summed with the initial angle to obtain the real-time rotation angle, denoted as θ(t), θ(t) = θ(t0) + .

[0094] Furthermore, in addition to using an integral method, a discrete method can also be used. Specifically, the step of determining the real-time rotation angle based on the real-time angular velocity includes: Step S25': Obtain the previous rotation angle and angular velocity of the surgical power device at the previous acquisition time, and obtain the acquisition time interval; Step S26': Obtain the angle interval change based on the real-time angular velocity, the previous angular velocity, and the acquisition time interval, and obtain the real-time rotation angle based on the previous rotation angle and the angle interval change.

[0095] Similarly, the aforementioned previous rotation angle can be the attitude angle of the surgical power device calculated at the previous acquisition moment, and can be denoted as θ(k-1). The aforementioned previous angular velocity can be the angular velocity acquired by the gyroscope at the previous acquisition moment, and can be denoted as w(k-1).

[0096] The aforementioned angular interval change can be the angle of rotation of the surgical power device from the previous acquisition time to the current time, which can be obtained by 1 / 2*(w(k-1)+w(k))*△t.

[0097] After obtaining the change in angular interval, the previous rotation angle can be summed to obtain the real-time rotation angle, denoted as θ(k), which can be obtained by θ(k) = θ(k-1) + 1 / 2 * (w(k-1) + w(k)) * Δt.

[0098] Reference Figure 5 , Figure 5 This is a flowchart illustrating the third embodiment of the positioning method based on magnetic navigation of this application. Based on the above embodiments, the third embodiment of the positioning method based on magnetic navigation of this application is proposed.

[0099] Furthermore, considering that the positioning in the above embodiments is obtained through sensor data acquisition and calculation, errors can easily accumulate over long periods of use, leading to significant positioning deviations. Therefore, to improve the accuracy of the positioning results, such as... Figure 5 As shown, in this embodiment, the step of positioning the tool 1 based on the real-time displacement, the real-time rotation angle, and the initial calibration position includes: Step S31: Obtain the target position of the tool 1 based on the real-time displacement, the real-time rotation angle, and the initial calibration position.

[0100] It should be noted that the aforementioned target position can be the real-time position of the uncorrected tip of the tool 1, calculated through pure inertial navigation. In this embodiment, the initial calibration position can be calculated based on the real-time displacement and real-time rotation angle to obtain the target position of tool 1 at the current moment.

[0101] Step S32: If the calibration time interval does not reach the preset time interval, position the tool 1 according to the target position.

[0102] It is understood that the aforementioned correction time interval can be the time interval between the current moment and the last error correction. The aforementioned preset time interval can be a pre-set time interval for error correction, and the specific time can be set according to the actual situation. This embodiment does not impose any restrictions on this.

[0103] In actual use, if the calibration time interval does not reach the preset time interval, it indicates that the error of the positioning result is within an acceptable range, and the target position can be directly used as the position of tool 1.

[0104] Step S33: When the correction time interval reaches the preset time interval, the target position is corrected by a preset neural network model, and the tool 1 is positioned according to the corrected target position.

[0105] It should be understood that the aforementioned preset neural network model can be a pre-trained model that can learn errors and compensate for them. When the correction time interval reaches the preset time interval, it indicates that the error is large. In this case, the target position can be input into the preset neural network model, and the corresponding compensated target position can be output, which can then be used as the position of tool 1.

[0106] Furthermore, in order to obtain the aforementioned preset neural network model, in this embodiment, before the step of obtaining the initial calibration position of the tool 1, the following steps are also included: Step S301: Obtain the training dataset and the validation dataset, construct a first network tensor based on the training dataset, and construct a second network tensor based on the preset learning rate parameter.

[0107] It should be noted that the training dataset mentioned above can be a dataset used to train the initial neural network model, denoted as data[:,1:8], indicating that there can be 8 sets of data, from group 1 to group 8. The validation dataset mentioned above can be a dataset used to validate the initial neural network model, denoted as data[:,9:12], indicating that there can be 4 sets of data, from group 9 to group 12. Of course, the number of training and validation datasets can be set according to the actual situation, and this embodiment does not impose any restrictions on this.

[0108] It should also be noted that the first network tensor mentioned above can be a tensor constructed from the training dataset, which can represent the features collected from the first magnetic sensor. For example, the training dataset obtained after the first magnetic sensor is collected may have X=-182.3, Y=0.1, Z=-5.2, then the first network tensor mentioned above can be written as {tensor([-182.3]), tensor([0.1]), tensor([-5.2])}.

[0109] The aforementioned preset learning rate can be a preset parameter used for model learning. In this embodiment, X, Y, and Z can all be described as 0.01, and thus the aforementioned second network tensor can be denoted as {tensor([0.01]), tensor([0.01]), tensor([0.01])}. This second network tensor can be used to represent the learning rate in deep learning.

[0110] Step S302: Construct a correction vector based on the real-time rotation angle, and obtain a correction matrix according to the preset correction parameters and the correction vector.

[0111] Understandably, the aforementioned correction vector can be a vector composed of real-time rotation angles. Since the real-time rotation angle can be represented in quaternion form (i.e., [w, x, y, z]), where w is the weight, x is the X-axis, y is the Y-axis, and z is the Z-axis, x, y, and z can be the values ​​of the three axes in the real-time rotation angle. The aforementioned weights can be set according to the actual situation, and this embodiment does not impose any restrictions on them.

[0112] It is also understood that the aforementioned correction matrix can be a 3×3 matrix obtained by rearranging the aforementioned correction vectors, i.e., a standard rotation matrix derived from quaternions. The aforementioned preset correction parameters can be parameters used for rearrangement and can be obtained by the user in advance through experimentation.

[0113] In practical use, the surgical power unit can first construct a correction vector based on the real-time rotation angle to obtain [w,x,y,z]. Then, it transforms the correction vector using preset correction parameters, specifically [1-2(y²+z²),2(xy-zw),2(xz+yw),2(xy+zw),1-2(x²+z²),2(yz-xw),2(xz-yw),2(yz+xw),1-2(x²+y²)], thereby obtaining a 3×3 correction matrix. Here, 1 and 2 are the aforementioned preset correction parameters.

[0114] Step S303: Correct the training dataset using the first network tensor, the second network tensor, and the correction matrix; Step S304: Train the initial neural network model using the corrected training dataset and the validation dataset to obtain the preset neural network model.

[0115] After obtaining the correction matrix, the training dataset can be corrected using the first network tensor and the second network tensor. The corrected training dataset is then input into the initial neural network model for training, and validated using the validation dataset to obtain the preset neural network model.

[0116] Furthermore, in order to correct the training dataset, in this embodiment, the step of correcting the training dataset using the first network tensor, the second network tensor, and the correction matrix includes: Step S3031: Multiply the first network tensor and the correction matrix to obtain the multiplication result, and concatenate the multiplication result and the second network tensor to obtain the concatenation result.

[0117] In practical use, multiplication can be achieved first using torch.matmul, i.e., the result of multiplication = torch.matmul(first network tensor, correction matrix). Specifically, if the first network tensor is denoted as A = [[-182.3], [0.1], [-5.2]], and the correction matrix is ​​denoted as M, assuming a rotation of θ (θ = 90°) around the Z-axis, then the quaternion [w, x, y, z] = [0.707, 0.707, 0, 0]. After calculation according to the preset correction parameters, the correction matrix is ​​obtained. The matrix can be M = tensor([[1-2*(0+0),2*(0-0),2*(0+0)],[2*(0+0),1-2*(0.5+0),2*(0-0.707)],[2*(0-0),2*(0+0.707),1-2*(0.5+0)]]) = tensor([[1,0,0],[0,0,-1.414],[0,1.414,0]]) ≈[1,0,0,0,0,-1,0,1,0], which is a 3×3 matrix. Next, we multiply them. The first network tensor can be regarded as a 3×1 tensor A=[-182.3,0.1,-5.2], and the second network tensor can be regarded as a 3×1 tensor B=[0.01,0.01,0.01].

[0118] The result of the multiplication is torch.matmul(M, A) = [-182.3, 5.2, 0.1], which means that the original [-182.3, 0.1, -5.2] is rotated to become [-182.3, 5.2, 0.1].

[0119] Next, concatenation is performed, which can be achieved using torch.concat, i.e., concatenation result = torch.concat(multiplication result, second network tensor). Continuing with the example above, since the shape of the multiplication result is 3 and the shape of the second network tensor is 3, a richer concatenation result with 6 features can be obtained, i.e., concatenation result = [-182.3, 5.2, 0.1, 0.01, 0.01, 0.01].

[0120] Step S3032: Expand the splicing result using the second network tensor to obtain an expanded result, and adjust the dimensions of the expanded result to obtain an adjusted result; Step S3033: Use the adjustment result as the corrected training dataset.

[0121] After obtaining the splicing result, the splicing result can be copied and expanded using the second network tensor. Specifically, this can be achieved using delta.repeat, and the specific number of copies and expansions can be set according to the actual situation. For example, copying twice to form a 2×6 matrix would result in the expanded result = [[-182.3,5.2,0.1,0.01,0.01,0.01],[-182.3,5.2,0.1,0.01,0.01,0.01]].

[0122] Considering the potential changes in dimensions after expansion, dimensional adjustments can be made to meet the model's input requirements. For example, adding a batch dimension at the beginning would transform the expanded shape (2, 6) into (1, 2, 6), which is the adjusted result. After obtaining the adjusted result, it can be used as the corrected training dataset and transmitted to the initial neural network model for training.

[0123] In addition, to achieve the above objectives, this application also provides a surgical operating system, which may include a magnetic field emitting device and a surgical power device as described above.

[0124] Since the surgical power device in this embodiment can be implemented in accordance with the specific implementation of the above method embodiment, the specific implementation of the surgical operating system in this embodiment and the beneficial effects thereon can be referred to the above method embodiment. This embodiment will not elaborate on this further.

[0125] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system 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, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0126] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0127] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as a read-only memory image (ROM) / random access memory (RAM), magnetic disk, optical disk), and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0128] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method of localization based on magnetic navigation, characterized in that, The method is applied to a surgical power unit in a surgical operating system. The surgical power unit includes a cutting tool, a first magnetic detection component, and a gyroscope. The surgical operating system also includes a magnetic field emitting device for generating a magnetic field. The method includes: The initial calibration position of the cutting tool is obtained, and the real-time acceleration and real-time angular velocity of the surgical power device are obtained through the gyroscope. The initial calibration position is obtained by the positioning magnetic field collected by the first magnetic detection component in the magnetic field. The real-time displacement is determined based on the real-time acceleration, and the real-time rotation angle is determined based on the real-time angular velocity. The tool is positioned based on the real-time displacement, the real-time rotation angle, and the initial calibration position.

2. The method of claim 1, wherein, The surgical power unit also includes a device body, the cutting tool and the first magnetic detection component are disposed on the device body, and the device body drives the cutting tool to move; The step of obtaining the initial calibration position of the tool includes: During the positioning phase, the positioning magnetic field in the magnetic field is collected by the first magnetic detection component, and the device coordinates of the magnetic field emitting device are obtained. The coordinates of the first component of the first magnetic detection component are determined based on the device coordinates and the positioning magnetic field. The coordinates of the first component are transformed by a preset transformation relationship to obtain the tool coordinates, and the tool coordinates are used as the initial calibration position of the tool.

3. The method of claim 2, wherein, The surgical operating system also includes a second magnetic detection component; Before the step of acquiring the positioning magnetic field in the magnetic field through the first magnetic detection component during the positioning phase, the method further includes: During the calibration phase, the device coordinates of the magnetic field emitting device are obtained; The first magnetic detection component acquires a first calibration magnetic field in the magnetic field, and the second magnetic detection component acquires a second calibration magnetic field in the magnetic field. The second calibration magnetic field is the current magnetic field of the tool's location in the magnetic field. The first calibration coordinates of the first magnetic detection component are determined based on the device coordinates and the first calibration magnetic field, and the second calibration coordinates of the second magnetic detection component are determined based on the device coordinates and the second calibration magnetic field. A preset transformation relationship is constructed based on the first calibration coordinate and the second calibration coordinate.

4. The method as described in claim 1, characterized in that, The step of determining the real-time displacement based on the real-time acceleration includes: The initial velocity of the surgical power device at the initial moment is obtained, and the real-time acceleration is integrated according to the current moment and the initial moment to obtain the continuous change in velocity; The real-time speed is obtained based on the initial speed and the continuous change in speed. The initial displacement of the surgical power device at the initial moment is obtained, and the real-time velocity is integrated according to the current moment and the initial moment to obtain the continuous change of displacement; The real-time displacement is obtained based on the initial displacement and the continuous change in displacement.

5. The method as described in claim 1, characterized in that, The step of determining the real-time displacement based on the real-time acceleration includes: The previous velocity and acceleration of the surgical power device at the previous acquisition time are obtained, and the acquisition time interval is also obtained. The velocity interval change is obtained based on the real-time acceleration, the previous acceleration, and the acquisition time interval, and the real-time velocity is obtained based on the previous velocity and the velocity interval change. The previous displacement of the surgical power device at the previous acquisition time is obtained, and the displacement interval change is obtained based on the real-time speed, the previous speed and the acquisition time interval. The real-time displacement is obtained based on the previous displacement and the change in the displacement interval.

6. The method as described in claim 1, characterized in that, The step of determining the real-time rotation angle based on the real-time angular velocity includes: The initial rotation angle of the surgical power device at the initial moment is obtained, and the real-time angular velocity is integrated according to the current moment and the initial moment to obtain the continuous change of the angle; The real-time rotation angle is obtained based on the initial rotation angle and the continuous change of the angle.

7. The method as described in claim 1, characterized in that, The step of determining the real-time rotation angle based on the real-time angular velocity includes: The previous rotation angle and angular velocity of the surgical power device at the previous acquisition time are obtained, and the acquisition time interval is also obtained. The change in angle interval is obtained based on the real-time angular velocity, the previous angular velocity, and the acquisition time interval, and the real-time rotation angle is obtained based on the previous rotation angle and the change in angle interval.

8. The method as described in claim 1, characterized in that, The step of positioning the tool based on the real-time displacement, the real-time rotation angle, and the initial calibration position includes: The target position of the tool is obtained based on the real-time displacement, the real-time rotation angle, and the initial calibration position. If the calibration time interval does not reach the preset time interval, the tool is positioned according to the target position; When the correction time interval reaches the preset time interval, the target position is corrected for error using a preset neural network model, and the tool is positioned according to the corrected target position.

9. The method as described in claim 8, characterized in that, Before the step of obtaining the initial calibration position of the tool, the method further includes: Obtain a training dataset and a validation dataset, construct a first network tensor based on the training dataset, and construct a second network tensor based on a preset learning rate parameter; A correction vector is constructed based on the real-time rotation angle, and a correction matrix is ​​obtained according to the preset correction parameters and the correction vector; The training dataset is corrected using the first network tensor, the second network tensor, and the correction matrix; The initial neural network model is trained using the modified training dataset and the validation dataset to obtain the preset neural network model.

10. The method as described in claim 9, characterized in that, The step of correcting the training dataset using the first network tensor, the second network tensor, and the correction matrix includes: The first network tensor and the correction matrix are multiplied to obtain the multiplication result, and the multiplication result and the second network tensor are concatenated to obtain the concatenated result; The splicing result is expanded using the second network tensor to obtain an expanded result, and the dimensions of the expanded result are adjusted to obtain an adjusted result; The adjusted results are used as the corrected training dataset.

11. A surgical power device, characterized in that, The surgical power unit includes: a cutting tool, a first magnetic detection component, a gyroscope, a memory, a processor, and a magnetic navigation-based positioning program stored in the memory and executable on the processor. When the magnetic navigation-based positioning program is executed by the processor, it implements the steps of the magnetic navigation-based positioning method as described in any one of claims 1 to 10.

12. A surgical operating system, characterized in that, The surgical operating system includes a magnetic field emitting device and a surgical power device as described in claim 11.

Images