Method for determining influence of magnetic field interference on navigation results of navigation system, and navigation system

Abstract

The invention provides a method for determining the influence of magnetic field interference on the navigation result of a navigation system, a corresponding computer readable storage medium, a computer program product and a control device, and a navigation system. The navigation system comprises an electromagnetic tracking device which comprises a magnetic field generator, a reference sensor and a detection sensor fixed in physical relative position relative to the reference sensor. The method comprises: an acquisition step of acquiring a sensing relative pose of a detection sensor relative to a reference sensor, wherein the sensing relative pose is determined based on sensing pose data of the reference sensor and the detection sensor; and a determination step of determining an influence of the magnetic field disturbance on a navigation result of the navigation system based on the sensed relative pose. According to the method, the magnetic field interference can be detected, whether the magnetic field interference influences the navigation result of the navigation system or not can be more directly determined, interference of different degrees can be distinguished, and direct indication can be conveniently and quickly given to an operator.

Description

Technical Field

[0001] The present invention relates to the field of medical equipment, and in particular to medical equipment using an electromagnetic navigation system. More specifically, it relates to a method for detecting electromagnetic interference in an electromagnetic navigation system and determining the impact of the electromagnetic interference on the navigation results of the navigation system, as well as a corresponding navigation system. Background Art

[0002] During surgical procedures, navigation systems are often used to guide surgeons or robotic arms to move manipulated parts, such as surgical tools or instruments, toward a desired location. Common tracking technologies employed by navigation systems include optical tracking and electromagnetic tracking. Optical tracking typically uses an optical camera and a tracker attached to the tracked component. Electromagnetic tracking utilizes an electromagnetic tracking device, including a magnetic field generator and an electromagnetic sensor attached to the tracked component.

[0003] For example, during the intramedullary nail placement operation, after the intramedullary nail is placed into the medullary cavity, a drill is needed to drill a hole to insert the distal locking screw into the distal locking hole of the intramedullary nail. However, the intramedullary nail is not visible after placement in the medullary cavity, and due to the asymmetric structure of the medullary cavity, the intramedullary nail often deforms when placed into the medullary cavity, making distal locking of the intramedullary nail difficult. Computer-guided intramedullary nail navigation can accurately guide the doctor in the placement operation while significantly reducing the radiation to the patient under C-arm fluoroscopy. In order to track the intramedullary nail for navigation, a commonly used method is to use electromagnetic tracking technology. Two electromagnetic sensors are placed in the intramedullary nail and the drill guide respectively. An external magnetic field generator is used to simultaneously track the relative posture of the intramedullary nail and the guide. The relative position and posture of the two are displayed in real time in the navigation view of the display device to guide the doctor to adjust the position of the drill guide and thus adjust the drill to aim at the locking hole.

[0004] The advantage of electromagnetic tracking is that it can effectively solve the problem of camera vision being blocked in optical tracking technology, but its disadvantage is that it is easily affected by external magnetic fields or electromagnetic interference from metal equipment.

[0005] The locking hole in the intramedullary nail is very close to the drill bit size, allowing for a very small margin of error. Therefore, navigation accuracy is critical. When metal surgical instruments come close to the magnetic field generator or the electromagnetic sensor, electromagnetic tracking accuracy is compromised. If the doctor continues to follow the navigation without being aware of the situation, the procedure often fails. Therefore, a solution is needed that can detect magnetic field interference in real time.

[0006] Current electromagnetic tracking manufacturers haven't yet implemented a viable magnetic field interference detection solution. Some manufacturers estimate errors based on the geometry of the 6DOF electromagnetic sensor, but these estimates are unreliable and don't reflect the accuracy of specific applications. Summary of the Invention

[0007] The object of the present invention is to solve at least one of the above problems and defects in the prior art as well as other technical problems.

[0008] According to one aspect of the present invention, a method for determining the impact of magnetic field interference on navigation results of a navigation system is provided. The navigation system includes an electromagnetic tracking device, which includes a magnetic field generator, a reference sensor, and a detection sensor with a fixed physical relative position relative to the reference sensor. The method includes the following steps:

[0009] Acquisition step: acquiring a sensing relative posture of the detection sensor relative to the reference sensor, wherein the sensing relative posture is determined based on sensing posture data of the reference sensor and the detection sensor; and

[0010] Impact determination step: determining the impact of magnetic field interference on the navigation result of the navigation system based on the sensed relative posture.

[0011] In this solution of the present invention, by providing a detection sensor with a fixed physical relative position relative to a reference sensor, and positioning both sensors within the same magnetic field of a magnetic field generator, it is possible to obtain sensing pose data for both sensors relative to the magnetic field generator, thereby calculating their relative pose data, i.e., the pose of the sensed object. Once the magnetic field is disturbed, the calculated relative pose will change, deviating from the actual physical relative pose. Therefore, magnetic field disturbances can be detected by this change in relative pose. This solution not only detects magnetic field disturbances but also more directly determines, or predicts, the impact of such magnetic field disturbances on the navigation system's reliability—that is, whether the navigation system's navigation results will be affected. Different levels of disturbance can be distinguished. In cases where there is no disturbance or the disturbance is insufficient to cause navigation failure, there is no need to notify the operator. However, in cases where the disturbance is severe enough to cause navigation failure, the operator needs to be reminded to take necessary measures. This results-oriented solution provides the operator with direct and quick instructions, enabling them to quickly take measures, such as removing the disturbance, thereby improving navigation system reliability and surgical efficiency.

[0012] According to one example, the impact determination step is performed using a trained interference detection model, wherein the interference detection model is a classification model. This exemplary solution uses a trained interference detection model to achieve more reliable predictions, while the classification model is simpler and can provide more intuitive guidance to the operator.

[0013] According to one example, the classification model is a multi-layer perceptron neural network model, including an input layer, at least one hidden layer and an output layer, wherein the activation function of the output layer is a rectified linear unit ReLU.

[0014] According to one example, the classification model is a binary classification neural network, which determines that the impact of magnetic field interference on navigation results includes navigation capability and inability to navigate.

[0015] According to one example, during the training phase of the interference detection model, the data collection process of the training data set of the interference detection model and the navigation process of the navigation system are carried out simultaneously, wherein the training data set is generated based on the sensed relative posture and the corresponding navigation result of the navigation system in the presence of the sensed relative posture.

[0016] When the model is trained using this solution, the data collection process and the navigation process of the navigation system are carried out simultaneously. The data collection and annotation are automatically carried out with the help of the existing navigation system without the need for manual annotation.

[0017] According to one example, the navigation system further includes a navigation sensor, which is provided on a component requiring navigation, and the navigation sensor and the detection sensor are the same sensor, wherein during the training phase of the interference detection model, graphical navigation information is generated based on the sensing posture data of the navigation sensor and the reference sensor, and the graphical navigation information includes a navigation result indication of navigation failure or navigation success.

[0018] In this solution, since the navigation sensor and the detection sensor are the same sensor, it can be considered that the magnetic field interference detected by the detection sensor is consistent with the interference experienced by the navigation sensor, thereby improving the detection accuracy and reliability of the magnetic field interference.

[0019] According to one example, the navigation system is an intramedullary nail navigation system, the reference sensor and the detection sensor are arranged in the intramedullary nail, and the navigation sensor is arranged on the guide of the drill bit; wherein the graphical navigation information displays the positional relationship between the model of the intramedullary nail and the model of the drill bit, and displays a navigation result indication of navigation failure or navigation success.

[0020] According to one example, during the training phase of the interference detection model, the drill is placed into the intramedullary nail through the guide. If the indication on the graphical navigation information is that the navigation is successful, the navigation result in the training data set is set to 1; if the indication on the graphical navigation information is that the navigation fails, the navigation result in the training data set is set to 0.

[0021] According to an example, the training process of the interference detection model is achieved by continuously changing the relative position of the navigation system and the navigation environment to obtain the sensing posture data of the reference sensor, the detection sensor and the navigation sensor.

[0022] In the scheme of this example, during the training phase, data is collected while the entire device or surgical instrument (an exemplary interference source) is moving rather than when it is stationary, so that dynamic data is obtained, which can better reflect the distribution of positive and negative samples.

[0023] According to one example, the sensed relative posture is an array [q0, q1, q2, q3, t1, t2, t3] with a dimension of 7, including a four-dimensional array [q0, q1, q2, q3] representing the relative rotation between the reference sensor and the detection sensor and a three-dimensional vector [t1, t2, t3] representing the relative translation between the reference sensor and the detection sensor.

[0024] According to an example, the hidden layer is one layer, and the hidden layer and the output layer are both fully connected layers.

[0025] According to one example, the method further includes an alarm step, wherein, if the impact on the navigation result of the navigation system determined in the impact determination step is that navigation is impossible, an alarm is issued to warn that the magnetic field interference is excessive. The alarm indication can be, for example, in the form of a pop-up box on the navigation view, sound, and / or light, etc., to intuitively prompt the operator.

[0026] According to another aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. The computer program includes executable instructions, and when the executable instructions are executed by a processor, the method described above is implemented.

[0027] According to yet another aspect of the present invention, a computer program product is provided, comprising a computer program, which implements the method described above when the computer program is executed by a processor.

[0028] According to yet another aspect of the present invention, a control device is provided, comprising a processor and a memory for storing executable instructions of the processor, wherein the processor is configured to execute the executable instructions to implement the method described above.

[0029] According to another aspect of the present invention, a navigation system capable of determining the impact of magnetic field interference on navigation results is proposed. The navigation system includes an electromagnetic tracking device and a processor. The electromagnetic tracking device includes a magnetic field generator, a reference sensor, and a detection sensor whose physical relative position to the reference sensor is fixed. The processor is electrically connected to the electromagnetic tracking device and executes the above method during operation.

[0030] According to one example, the navigation system also includes a display device and a navigation sensor, and the graphical navigation information of the navigation system is displayed on the display device, and the navigation sensor is arranged on the component that needs to be navigated, wherein the navigation sensor and the detection sensor are the same sensor, and the navigation system constructs graphical navigation information based on the sensing posture data of the navigation sensor and the reference sensor to navigate the operation of the component.

[0031] According to one example, the navigation system is an intramedullary nail navigation system, the reference sensor and the detection sensor are arranged in the intramedullary nail in a manner of fixing their physical relative postures, and the navigation sensor is arranged on a guide of the drill bit.

[0032] It should be understood that the above general description and the following detailed description are merely exemplary and explanatory and are not intended to limit the scope of protection of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The above and other features and advantages of the present invention will become more apparent by describing in detail exemplary embodiments thereof with reference to the following drawings.

[0034] Figure 1 FIG. 1 is a schematic diagram showing the principle of sensor arrangement of an electromagnetic tracking device of a navigation system according to an embodiment of the present invention.

[0035] Figure 2 A schematic diagram of an exemplary interference detection model for use with the navigation system of the present invention.

[0036] Figure 3 1 is a schematic diagram of thread principles of a processor of a navigation system during a training phase of an interference detection model according to an embodiment of the present invention.

[0037] Figure 4a and Figure 4b Two exemplary navigation views are shown, wherein Figure 4a shows a navigation view showing a navigation failure, Figure 4b A navigation view showing successful navigation is shown.

[0038] Figure 5 The figure is a schematic flow chart of a method for determining the influence of magnetic field interference on a navigation system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0039] The following examples and accompanying drawings further illustrate the technical solution of the present invention. The following description of the embodiments of the present invention with reference to the accompanying drawings is intended to explain the overall concept of the present invention and should not be construed as limiting the present invention.

[0040] The following describes, as a specific example, a navigation system and specific steps of a method for determining the impact of magnetic field interference on the navigation system, as one embodiment of the present invention. In the detailed description that follows, many specific details and steps are set forth in great detail and detail to provide a thorough understanding of this embodiment. However, it should be understood that one or more other embodiments may be practiced without these specific details and steps.

[0041] In this specific embodiment, the electromagnetic navigation system for intramedullary nails is used as an example for description, but those skilled in the art will appreciate that the determination method and navigation system of the present invention are not limited to applications for intramedullary nail placement, but may also be applicable to any other navigation system using electromagnetic navigation technology.

[0042] Figure 1 The schematic diagram of the principle of sensor arrangement of the electromagnetic tracking device of the intramedullary nail electromagnetic navigation system is shown. The intramedullary nail electromagnetic navigation system can adopt NDI's Aurora electromagnetic tracking device, for example, and can include a magnetic field generator (not shown) and a reference sensor 1 used as a reference to define a reference coordinate system. Figure 1 As shown, the reference sensor 1 is built into the intramedullary nail 3, for example, it can be installed in a probe built into the intramedullary nail 3. The navigation system also includes a navigation sensor 6, which can be set on the guide 4 of the drill bit. The magnetic field generator can simultaneously track the spatial posture of the reference sensor 1 and the navigation sensor 6. The navigation system also includes a control device (not shown in the figure). The control device can be a general-purpose computer, a special-purpose computer, an embedded processor, or any other appropriate programmable data processing device such as a single-chip microcomputer or a chip. The control device may include a processor and a memory for storing programs, but may also include only a processor, in which case the processor can be attached to a memory storing programs. In other words, the control device includes at least a processor. The processor is electrically connected to the above-mentioned electromagnetic tracking device to receive the posture information of the reference sensor 1 and the navigation sensor 6 (that is, its sensed posture data).

[0043] The navigation system may further include a display device (not shown in the figure), and the control device and the display device may be integrated into one body or provided separately. The display device may be used to display graphical navigation information (eg, a navigation view). Figure 4a and Figure 4bTwo exemplary navigation views are shown in the figure. Each view includes a model of the intramedullary nail (orange) and a drill model (red or green circular projection in the figure). Since the spatial position relationship between the drill bit and the guide (also called sleeve) is determined by machining, the spatial position relationship between the two is fixed. By setting the navigation sensor 6 on the guide, the position of the guide can be obtained based on the sensed position data of the navigation sensor 6, and then the position of the drill bit can be obtained. The position of the intramedullary nail can be obtained by the above-mentioned reference sensor 1 fixed in the intramedullary nail. Therefore, the relative position of the drill bit and the intramedullary nail can be obtained and reflected by the relative position relationship between the drill bit model and the intramedullary nail 3D model shown in the navigation view. The operator operates the drill bit and the guide under the navigation guidance of the graphical navigation information to achieve the purpose of aiming the drill bit at the locking hole of the intramedullary nail.

[0044] However, during the navigation process of an actual surgical procedure, the magnetic field of the navigation system will inevitably be subject to electromagnetic interference from the surrounding environment, such as the metal bedside of the operating table, the surgical instruments being operated, etc. Under these electromagnetic interferences, the sensing accuracy of the electromagnetic sensor and the electromagnetic tracking accuracy of the navigation system are affected. In severe cases, the navigation results may be affected, and the drill may deviate from the locking hole by more than the allowable error, i.e., navigation fails. According to the concept of the present invention, in order to detect magnetic field interference, a sensor (i.e., detection sensor 2) is added to the intramedullary nail, which is completely consistent with the navigation sensor (i.e., the electromagnetic sensor provided on the guide in this embodiment). In other words, the detection sensor 2 and the navigation sensor 6 are the same sensor. The detection sensor 2 is, for example, fixed in the intramedullary nail 3, and it also uses the reference sensor 1 in the intramedullary nail as a reference, and the relative posture of the two in physical space remains unchanged (i.e., the physical relative position of the two is fixed).

[0045] During navigation, the spatial posture of the navigation sensor 6 relative to the reference sensor 1 changes all the time, but the actual physical relative posture of the detection sensor 2 and the reference sensor 1 remains unchanged due to their fixed physical positions. However, the sensing posture of the two sensed by the magnetic field and the "sensing relative posture (this term is used to distinguish it from the physical relative posture in the actual space)" of the two calculated therefrom will be affected by magnetic field interference. In the absence of interference, the calculated relative posture should be the same as the actual physical relative posture and remain unchanged. Once the calculated relative posture, i.e., the sensing relative posture, changes, it means that the magnetic field has been interfered with. In this embodiment, the magnetic field interference detection and navigation share the same reference sensor 1 as a reference, and the detection sensor 2 and the navigation sensor 6 are of the same model. Therefore, it can be considered that the detected magnetic field interference is consistent with the interference experienced by the navigation sensor. The detected relative posture of the reference sensor 1 and the detection sensor 2 can reflect the interference experienced by the navigation process.

[0046] The degree of impact of magnetic field interference on navigation accuracy varies. Some magnetic field interference, even if it has an impact, is within the range allowed by navigation accuracy, while some magnetic field interference will seriously damage navigation accuracy, and measures must be taken to remove the interference source, otherwise it will cause navigation failure. Therefore, it is necessary to distinguish these different levels of interference. In the case of no interference or interference not enough to cause navigation failure, there is no need to notify the doctor. In the case of interference that is serious enough to cause navigation failure, the doctor needs to be reminded to take necessary measures. The method and navigation system provided by the present invention can not only detect magnetic field interference in real time, but also determine whether such interference will cause navigation failure, and will also provide an alarm when it is predicted that it will cause navigation failure.

[0047] Specifically, if Figure 5 As shown, the method for determining the impact of magnetic field interference on a navigation system provided by the present invention may include the following steps:

[0048] Acquisition step: Acquiring the sensed relative pose of reference sensor 1 and detection sensor 2; this acquisition can be directly calculated by the processor based on the pose data of sensor 1 and sensor 2 obtained from the system control unit (SCU) of the electromagnetic tracking device, or it can be directly acquired from other control devices, such as the electromagnetic tracking device. For example, as an exemplary electromagnetic tracking device, the calculation of the sensed relative pose of reference sensor 1 and detection sensor 2 can be performed by the electronic tracking device, which directly transmits the calculated sensed relative position to the processor. As an example, the processor of the control device in this embodiment can obtain the sensed pose of reference sensor 1 represented by an array with a dimension of 7 and the sensed pose of detection sensor 2 represented by an array with a dimension of 7 from the system control unit (SCU) of the electromagnetic tracking device, and compare them to obtain the sensed relative pose of the two. The array with a dimension of 7 includes a four-dimensional array representing rotation and a three-dimensional vector representing translation.

[0049] Impact determination step: determining the impact of the magnetic field interference on the navigation result of the navigation system based on the sensed relative posture.

[0050] The impact determination step can be implemented by a trained interference detection model, the input of which is the relative position of the reference sensor 1 and the detection sensor 2, and the interference detection model is trained to output the impact of the magnetic field interference on the navigation result of the navigation system based on the relative position of the reference sensor 1 and the detection sensor 2. Preferably, in this embodiment, the interference detection model is Figure 2The neural network shown in FIG. 7 includes an input layer 71, at least one hidden layer 72, and an output layer 73. The input of the input layer is the above-mentioned relative position sensing, and the output of the output layer is the above-mentioned impact on the navigation result. In this specific embodiment, the neural network is a binary classification neural network. The input of its input layer, i.e., the relative position sensing between the reference sensor 1 and the detection sensor 2, is an array of 7 dimensions [q0, q1, q2, q3, t1, t2, t3], including a four-dimensional array [q0, q1, q2, q3] representing the relative rotation between the two sensors and a three-dimensional vector [t1, t2, t3] representing the relative translation between the two sensors, corresponding to Figure 2 The input is [x1,x2,x3,x4,x5,x6,x7] shown in Figure 1. The hidden layer is used to model the complex changes between the input features. The activation function of the output layer is the rectified linear unit (ReLU).

[0051] The output impact result is a binary classification, with 1 indicating navigation is possible and 0 indicating navigation is not possible. Therefore, in this embodiment, the relative position (i.e., sensed relative position) between the detection sensor 2 for detecting magnetic field interference and the reference sensor 1 serving as a reference is obtained (e.g., calculated) and used as input to the neural network. The neural network then directly outputs the impact result of whether navigation is possible under the electromagnetic interference. When the impact result is 0, indicating navigation is not possible, an alarm step can be entered to warn the user of excessive magnetic field interference, so that the user can take measures such as removing the object causing the magnetic field interference.

[0052] The neural network used in this embodiment is a multi-layer perceptron network with one hidden layer. The hidden layer and the output layer are both fully connected layers. Figure 2 The full connection corresponding to the input nodes x2 to x6 is not drawn.

[0053] It should be noted that, although in this specific embodiment, the impact on the navigation result determined by the method is a binary classification of whether navigation is possible, the solution of the present invention is not limited to this. For example, the impact can also be divided into various levels such as weak impact, medium-strong impact, and strong impact, and can include a further step of indicating the determined impact to the user. Moreover, although a binary classification neural network is used in this embodiment to implement the impact determination step, other types of neural networks or no neural network can also be used. For example, when the sensed relative posture exceeds a predetermined threshold, the impact on the navigation system is determined to be unable to navigate. In other words, those skilled in the art can understand that there are multiple implementation methods to determine the impact on the navigation result, and are not limited to the method described in this specific embodiment.

[0054] The method for determining the impact of magnetic field interference on the navigation system of this embodiment also includes a process of training and testing the neural network before use. During the training process, data can be automatically collected and annotated based on the navigation system. Specifically, in this embodiment, in order to correctly determine the reliability of navigation, the data collection process is combined with the navigation process. Figure 3 As shown, the processor may include a navigation module and a detection module, wherein the detection module includes the above-mentioned neural network. Figure 3 On the left is the navigation module, which calculates the relative pose of the navigation sensor and reference sensor based on their pose data. This relative pose is displayed on the navigation view by displaying the positional relationship between the drill bit model and the intramedullary nail model. The navigation module also determines and indicates the navigation result, i.e., whether the navigation was successful. This determination is used as a label to calibrate the output of the neural network's training dataset. Figure 3 The right side of the figure is the detection module in the training phase, which calculates the relative pose between the detection sensor and the reference sensor and uses it as the input of the neural network.

[0055] During the data collection process during the training of the neural network, the intramedullary nail is not inserted into the intramedullary cavity as in a real operation. Instead, the drill bit is placed into the locking hole of the intramedullary nail through the guide and remains in the intramedullary nail during the subsequent data collection process. This means that the drill bit is accurately placed in the locking hole. In this state, if there is no electromagnetic interference, the navigation view should show that the navigation is successful, as shown in the figure below. Figure 4b In the case shown in FIG, the projection model of the drill bit is located in the distal locking hole of the intramedullary nail model, and the navigation module indicates that the navigation is successful, which is achieved by displaying the projection of the drill bit in green, as shown in FIG. Figure 4b In the case of electromagnetic interference, due to the interference of the magnetic field, the sensing accuracy of the electromagnetic sensor is reduced, the relative position of the navigation sensor and the reference sensor calculated by the navigation module and the relative position relationship between the drill model and the intramedullary nail model on the graphical navigation information generated thereby are not accurate, which may cause Figure 4a In the case of unsuccessful navigation, the navigation module prompts that the navigation is unsuccessful, which is achieved, for example, by displaying the projection of the drill bit in red. Figure 4a shown.

[0056] During the data collection process, the data collection thread of the detection module runs in parallel with the navigation thread of the navigation module. The data collection process includes automatically calculating the relative position of the detection sensor 2 and the reference sensor 1, storing it in an array of 7 dimensions as the input of the neural network; and obtaining the navigation result corresponding to the current relative position of the navigation system (the navigation result is represented by Figure 3The output label is 0 or 1. When the current corresponding navigation result is successful, the output label is set to 1, indicating that navigation is possible, that is, the sample is a positive sample. When the current corresponding navigation result is failed, the output label is set to 0, indicating that navigation is not possible, that is, the sample is a negative sample.

[0057] The following describes the data collection process as an example. The entire apparatus (including the magnetic field generator, intramedullary nail, guide, and drill bit, with reference sensor 1 and detection sensor 2 fixed to the intramedullary nail, and navigation sensor 6 installed on the guide) is placed on a surgical table used for intramedullary nail navigation. The center section of the table is non-metallic for C-arm fluoroscopy, while the sides contain metal.

[0058] First, place the entire device in a clean, interference-free environment. The drill is placed in the locking hole of the intramedullary nail through the guide, and the navigation view and navigation results are displayed on the display device. If the projection of the drill on the navigation view is completely within the locking hole of the intramedullary nail, it means there is no interference, and the drill is displayed in green, indicating that the navigation is successful. Figure 4b If the magnetic field is disturbed to a certain extent, the drill projection deviates from the locking hole to a certain extent, for example, exceeds the allowable error, and the drill projection is displayed in red, as shown. Figure 4a The data collection thread automatically sets the label to 1 when the drill head projection turns green, indicating successful navigation under the current magnetic field conditions (corresponding to the current relative position of reference sensor 1 and detection sensor 2); and automatically sets the label to 0 when the drill head projection turns red, indicating a navigation failure under the current magnetic field conditions.

[0059] In an interference-free state, data collection and automatic labeling begins. Since the system is in an interference-free environment at the beginning, the label value is 1. Intraoperative magnetic field interference can come from the surrounding environment, such as the metal bedside of the operating table, as well as from the surgical instruments being operated. After starting the data collection process, slowly move the entire device closer to / away from the bedside. The whole process takes about 30 seconds, and the time when the indicator on the navigation view turns red and turns green is controlled to be as close as possible. This is to make the distribution of positive and negative samples as consistent as possible. After collecting data close to / away from the bedside, fix the entire device and move the metal instrument so that it is close to / away from the device, that is, close to / away from each sensor. Also collect data for about 30 seconds, and make the positive and negative samples as balanced as possible.

[0060] In this embodiment, data is collected while the device or instrument is moving rather than while stationary. This produces dynamic data that better reflects the distribution of positive and negative samples. In this specific embodiment, NDI's Aurora electromagnetic tracking device is used, with a data acquisition frequency of 40 Hz. Therefore, the data generated in 30 seconds is 40 x 30 = 1200 frames. This dataset size is suitable for a simple binary classification neural network. After the neural network is trained, it can also be tested.

[0061] During the surgical procedure of intramedullary nail implantation according to the navigation system of an embodiment of the present invention, after the intramedullary nail is placed into the medullary cavity, since the reference sensor 1 and the detection sensor 2 are fixed in the intramedullary nail, the processor of the control device can obtain the detected positions of the sensor 1 and the sensor 2 represented by the array of 7 dimensions from the system control unit (SCU) of the electromagnetic tracking device, and compare them to obtain the relative position of the two (corresponding to Figure 5 The processor processes the sensed relative position using a neural network and outputs a conclusion as to whether navigation is possible (corresponding to the impact determination step). This determination determines the impact of the magnetic field interference on the navigation system's navigation results. If navigation is not possible, an alarm may be displayed to warn that excessive magnetic field interference may result in a navigation failure. This alarm may be displayed, for example, as a pop-up box on the navigation view, or in the form of sound and / or light.

[0062] It should be noted that, although the navigation module and the detection module included in the processor are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the present invention, the features and functions of the two modules described above can be concretized in one module or unit. Conversely, the features and functions of a module described above can also be further divided into multiple modules or units for concretization. The components of the module may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the present invention. Those of ordinary skill in the art can understand and implement it without paying any creative work.

[0063] In an exemplary embodiment of the present invention, a computer-readable storage medium is further provided, on which a computer program is stored, the program including executable instructions that, when executed by a processor, can implement the steps of the above-described method. In some possible implementations, various aspects of the present invention can also be implemented in the form of a program product, which includes a computer program that, when executed by a processor, causes the processor to perform the steps described in the method of the present invention according to various exemplary embodiments of the present invention.

[0064] According to an embodiment of the present invention, a program product for implementing the above method can be a portable compact disc read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0065] The program product may be implemented in any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (a non-exhaustive list) of readable storage media include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0066] The computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, wherein the readable program code is carried. The data signal propagated may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, device, or component. The program code contained on the readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination thereof.

[0067] The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, and the like, as well as conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0068] In an exemplary embodiment of the present invention, a control device is further provided, which may include a processor and a memory for storing executable instructions of the processor. The processor is configured to execute the executable instructions to perform the method for determining the impact of magnetic field interference on a navigation system and the steps of the navigation method in any of the above-mentioned embodiments.

[0069] Those skilled in the art will appreciate that various aspects of the present invention may be implemented as systems, methods, or program products. Therefore, various aspects of the present invention may be implemented in the following forms: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software implementations, which may be collectively referred to herein as "circuits," "modules," or "systems."

[0070] Those skilled in the art will readily appreciate other embodiments of the present invention after considering the specification and practicing what is disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the invention and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, and the true scope and spirit of the invention are indicated by the appended claims.

Claims

1. A method for determining the influence of magnetic field interference on navigation results of a navigation system, wherein the navigation system comprises an electromagnetic tracking device, the device comprising a magnetic field generator, a reference sensor (1), and a detection sensor (2) having a fixed physical relative position relative to the reference sensor (1), wherein the method comprises the following steps: Acquisition step: acquiring a sensing relative posture of the detection sensor (2) relative to the reference sensor (1), wherein the sensing relative posture is determined based on sensing posture data of the reference sensor (1) and the detection sensor (2); and Impact determination step: determining the impact of magnetic field interference on the navigation result of the navigation system based on the sensed relative posture.

2. The method according to claim 1, characterized in that The impact determination step is performed using a trained interference detection model, wherein the interference detection model is a classification model.

3. The method according to claim 2, characterized in that The classification model is a multi-layer perceptron neural network model, comprising an input layer (71), at least one hidden layer (72) and an output layer (73), wherein the activation function of the output layer is a rectified linear unit (ReLU).

4. The method according to claim 3, characterized in that The classification model is a binary classification neural network, which determines whether the impact of magnetic field interference on navigation results is able to navigate or not.

5. The method according to claim 4, characterized in that During the training phase of the interference detection model, the data collection process of the training data set of the interference detection model and the navigation process of the navigation system are carried out simultaneously, wherein the training data set is generated based on the sensed relative posture and the corresponding navigation result of the navigation system in the presence of the sensed relative posture.

6. The method according to claim 5, characterized in that The navigation system also includes a navigation sensor, which is arranged on a component that requires navigation, and the navigation sensor and the detection sensor are the same sensor. During the training phase of the interference detection model, graphical navigation information is generated based on the sensing posture data of the navigation sensor and the reference sensor, and the graphical navigation information includes a navigation result indication of navigation failure or navigation success.

7. The method according to claim 6, characterized in that The navigation system is an intramedullary nail navigation system, wherein the reference sensor and the detection sensor are arranged in the intramedullary nail (3), and the navigation sensor is arranged on the guide (4) of the drill bit; wherein the graphical navigation information displays the positional relationship between the model of the intramedullary nail and the model of the drill bit, and displays a navigation result indication of navigation failure or navigation success.

8. The method according to claim 7, characterized in that In the training phase of the interference detection model, the drill is placed into the intramedullary nail through the guide (4). If the indication on the graphical navigation information is that the navigation is successful, the navigation result in the training data set is set to 1; if the indication on the graphical navigation information is that the navigation fails, the navigation result in the training data set is set to 0.

9. The method according to claim 6, characterized in that The training process of the interference detection model is realized by continuously changing the relative position of the navigation system and the navigation environment to obtain the sensing posture data of the reference sensor, the detection sensor and the navigation sensor.

10. The method according to any one of claims 2 to 4, characterized in that The sensed relative pose is an array of dimension 7 [q0, q1, q2, q3, t1, t2, t3], including a four-dimensional array [q0, q1, q2, q3] representing the relative rotation between the reference sensor and the detection sensor and a three-dimensional vector [t1, t2, t3] representing the relative translation between the reference sensor and the detection sensor.

11. The method according to claim 3, characterized in that The hidden layer is one layer, and both the hidden layer and the output layer are fully connected layers.

12. The method according to any one of claims 1 to 9 and 11, characterized in that The method further comprises an alarm step, wherein when the impact on the navigation result of the navigation system determined in the impact determination step is that navigation is impossible, an alarm is issued to warn that the magnetic field interference is too large.

13. A computer-readable storage medium having a computer program stored thereon, the computer program comprising executable instructions, and when the executable instructions are executed by a processor, the method according to any one of claims 1 to 12 is implemented.

14. A computer program product comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 12.

15. A control device, characterized in that: include: processor; as well as a memory for storing executable instructions of the processor; The processor is configured to execute the executable instructions to implement the method according to any one of claims 1 to 12.

16. A navigation system capable of determining the impact of magnetic field interference on navigation results, characterized in that: The navigation system includes: An electromagnetic tracking device comprises a magnetic field generator, a reference sensor (1), and a detection sensor (2) whose physical relative posture to the reference sensor is fixed, and A processor is electrically connected to the electromagnetic tracking device and executes the method according to any one of claims 1 to 12 when the processor is running.

17. The navigation system according to claim 16, characterized in that The navigation system further includes: a display device, on which graphical navigation information of the navigation system is displayed; and A navigation sensor is provided on a component requiring navigation, wherein the navigation sensor and the detection sensor are the same sensor, and wherein the navigation system constructs the graphical navigation information based on the sensed posture data of the navigation sensor and the reference sensor to navigate the operation of the component.

18. The navigation system according to claim 17, wherein: The navigation system is an intramedullary nail navigation system, the reference sensor and the detection sensor are arranged in the intramedullary nail in a manner of fixing their physical relative postures, and the navigation sensor is arranged on a guide of a drill bit.

Images