A training method, device, electronic device and medium for a magnetic wire control model

By constructing the metacosmic guidewire system and training the current rectifier model, the problem of the guidewire relying on operating experience to enter the lesion part is solved, and the precise control and efficient entry of the magnetic guidewire are achieved.

CN117563111BActive Publication Date: 2024-11-15BEIJING SIBO HUIYI TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311657773.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2023-12-05
Publication Date
2024-11-15
Estimated Expiration
2043-12-05

AI Technical Summary

Technical Problem

Traditional guidewires and magnetic guidewires rely on the experience of operators when entering human vascular lesions, resulting in insufficient accuracy and reliability. Especially for inexperienced operators, it is difficult to achieve accurate entry.

Method used

By building a metacosmic guidewire system mirrored with the magnetic guidewire system, training the current rectifier model and generating a training sample set, precise control of the magnetic guidewire system is achieved, independent of the operator's operating experience.

Benefits of technology

It realizes that magnetic guidewires accurately enter the lesion site without relying on the experience of the operator, improving the reliability and efficiency of interventional treatment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117563111B_ABST
    Figure CN117563111B_ABST
Patent Text Reader

Abstract

The present application discloses a training method, device, electronic device and medium for a magnetic wire control model. The method and device are applied to electronic devices, specifically to construct a metaverse wire system corresponding to the mirror image of the magnetic wire system, the metaverse wire system includes a meta-current and a meta-wire; based on the control current and wire action of the magnetic wire system, the model training is performed to obtain a current rectifier model; a training sample set is constructed based on the current rectifier model; based on the training sample set, the model training is performed to obtain a magnetic wire control model for controlling the magnetic wire system. When the magnetic wire control model is applied to the magnetic wire system, the magnetic wire can accurately enter the lesion without relying on the operator's operating experience.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of medical device technology, and more specifically, to a training method, device, electronic equipment and medium for a magnetic wire control model. Background Art

[0002] One of the key steps of interventional treatment is to move the guidewire along the blood vessel to the lesion site so that it can deliver treatment devices such as catheters and stents to the lesion site. Traditional guidewires have pre-bent tips so that the guidewires can be guided along arteries or veins and into different branches. When guiding the guidewire in, professionals are required to twist the direction of the tip at the proximal end to keep the guidewire moving in the correct direction. Given the irregularity of human blood vessels, this operation is extremely dependent on the operator's operating experience.

[0003] In order to reduce the dependence on operating experience, a magnetic guidewire with a magnetic tip has been proposed. The magnetic tip is driven by a magnetic field to achieve steering, which is more sensitive and predictable than traditional guidewires. However, this steering operation only converts the operator's twisting operation into an operation of the magnetic field direction and intensity, which still requires a lot of training to be competent, that is, it still needs to rely on the operator's operating experience. For inexperienced operators, it is still impossible to make the magnetic guidewire accurately enter the lesion site. Summary of the invention

[0004] In view of this, the present application provides a training method, device, electronic equipment and medium for a magnetic wire control model, which are used to enable the magnetic wire system to accurately enter the lesion site without relying on the operator's operating experience.

[0005] In order to achieve the above objectives, the proposed solution is as follows:

[0006] A training method for a magnetic wire control model is applied to electronic equipment, and the training method comprises the following steps:

[0007] Constructing a meta-universe guide wire system corresponding to the magnetic guide wire system in a mirror image, wherein the meta-universe guide wire system includes a meta-current and a meta-guide wire;

[0008] Performing model training based on the control current and wire guiding action of the magnetic wire guiding system to obtain a current rectifier model;

[0009] Constructing a training sample set based on the current rectifier model;

[0010] Model training is performed based on the training sample set to obtain a magnetic wire guide control model for controlling the magnetic wire guide box.

[0011] Optionally, the construction of a metaverse guidewire system corresponding to the mirror image of the magnetic guidewire system comprises the steps of:

[0012] Obtaining the guidewire stiffness and the guidewire magnetic susceptibility obtained by testing the guidewire of the magnetic guidewire system;

[0013] The metaverse construction is performed based on the guidewire stiffness, the guidewire magnetic susceptibility and the underlying physical laws to obtain the metaverse guidewire system.

[0014] Optionally, the control current and wire guiding action of the magnetic wire guiding system are used to perform model training to obtain a current rectifier model, comprising the steps of:

[0015] Generate a randomly distributed control current and record the physical wire guiding action in the magnetic wire guiding system in accordance with the control current;

[0016] Simulating the current distribution and the wire guide action into the meta-universe wire guide system, and recording the meta-wire guide action of the meta-wire;

[0017] Calculating the distance loss between the entity guide wire motion and the meta guide wire motion;

[0018] Model training is performed based on the distance loss to obtain the current rectifier model.

[0019] Optionally, the step of constructing a training sample set based on the current rectifier model comprises the following steps:

[0020] Randomly generate a series of meta-control currents for creating meta-magnetic fields;

[0021] Recording the elementary control current and the elementary guide wire shape corresponding to the elementary control current;

[0022] Sample construction is performed based on the plurality of element control powers and the plurality of element guide wire shapes to obtain the training sample set.

[0023] A training device for a magnetic wire control model, applied to electronic equipment, comprising:

[0024] A metaverse construction module, configured to construct a metaverse guide wire system corresponding to the mirror image of the magnetic guide wire system, wherein the metaverse guide wire system includes a meta-current and a meta-guide wire;

[0025] A first training module is configured to perform model training based on the control current and wire guiding action of the magnetic wire guiding system to obtain a current rectifier model;

[0026] A sample set building module, configured to build a training sample set based on the current rectifier model;

[0027] The second training module is configured to perform model training based on the training sample set to obtain a magnetic wire control model for controlling the magnetic wire system.

[0028] Optionally, the metaverse building module includes:

[0029] A parameter acquisition unit is configured to acquire the guide wire stiffness and the guide wire magnetic susceptibility obtained by detecting the guide wire of the magnetic guide wire system;

[0030] The first construction unit is configured to perform metaverse construction based on the guidewire stiffness, the guidewire magnetic susceptibility and underlying physical laws to obtain the metaverse guidewire system.

[0031] Optionally, the first training module includes:

[0032] A first recording unit is configured to generate a randomly distributed control current and record a physical wire guiding action in the magnetic wire guiding system in accordance with the control current;

[0033] A second recording unit is configured to simulate the current distribution and the wire action into the meta-universe wire system, and record the meta-wire action of the meta-wire;

[0034] a distance calculation unit, configured to calculate a distance loss between the entity guide wire action and the meta guide wire action;

[0035] A training execution unit is configured to perform model training based on the distance loss to obtain the current rectifier model.

[0036] Optionally, the sample set construction module includes:

[0037] a current generating unit configured to randomly generate a series of meta-control currents for creating a meta-magnetic field;

[0038] a data recording unit configured to record the elementary control current and the elementary guide wire shape corresponding to the elementary control current;

[0039] The second construction unit is configured to perform sample construction based on the plurality of element control currents and the plurality of element guide wire shapes to obtain the training sample set.

[0040] An electronic device, comprising at least one processor and a memory connected to the processor, wherein:

[0041] The memory is used to store computer programs or instructions;

[0042] The processor is used to execute the computer program or instructions so that the electronic device implements the training method of the magnetic guidewire control module as described above.

[0043] A medium is applied to an electronic device, wherein the medium carries one or more computer programs, and the one or more computer programs can be executed by the electronic device, so that the electronic device implements the training method of the magnetic wire control model as described above.

[0044] It can be seen from the above technical solutions that the present application discloses a training method, device, electronic device and medium for a magnetic wire control model. The method and device are applied to electronic devices, specifically to construct a metaverse wire system corresponding to the mirror image of the magnetic wire system, the metaverse wire system includes a meta-current and a meta-wire; based on the control current and wire action of the magnetic wire system, the model training is performed to obtain a current rectifier model; a training sample set is constructed based on the current rectifier model; based on the training sample set, the model training is performed to obtain a magnetic wire control model for controlling the magnetic wire system. When the magnetic wire control model is applied to the magnetic wire system, the magnetic wire can accurately enter the lesion without relying on the operator's operating experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0046] Figure 1 It is a structural diagram of a magnetic wire guide system;

[0047] Figure 2 A flowchart of a training method for a magnetic wire control model according to an embodiment of the present application;

[0048] Figure 3 A block diagram of a training device for a magnetic wire control model according to an embodiment of the present application;

[0049] Figure 4 A block diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0051] The training method and device in the present application are used to train a magnetic wire control model for straightening a magnetic wire system, wherein the magnetic wire control system specifically includes a controller 100 and a plurality of solenoids 101 connected to the controller, such as Figure 1 As shown, the controller outputs different control currents to different solenoids based on the magnetic guide wire control model, so that the magnetic field generated by the solenoid controls the direction of the guide wire 200 entering the human body.

[0052] Figure 2 The present invention is a flowchart of a method for training a magnetic wire control model according to an embodiment of the present application.

[0053] Reference Figure 2 As shown, this embodiment provides a training method for a magnetic wire control model, which is applied to an electronic device to implement the training of a magnetic wire control model for controlling a magnetic wire system. The electronic device can be understood as a computer, server or embedded device with data computing and information processing capabilities. The training method includes the following steps:

[0054] S1. Construct a metaverse guidewire system that mirrors the magnetic guidewire system.

[0055] The magnetic wire guide system here refers to the physical magnetic wire guide system in the real world, that is, the control entity of the magnetic wire guide control model. The metaverse wire guide system refers to a virtual system that exists in the electronic device for mirror matching the physical magnetic wire guide system. The construction method can be implemented based on the following scheme:

[0056] Firstly, the guide wire stiffness and the guide wire magnetic susceptibility of the magnetic guide wire system are obtained. The guide wire stiffness and the guide wire magnetic susceptibility are parameters obtained by actually measuring the guide wire using corresponding equipment.

[0057] Then, based on the underlying physical laws such as electromagnetic laws, and the wire stiffness and wire magnetic susceptibility, the metaverse is constructed to obtain the metaverse wire system.

[0058] S2. Model training is performed based on the control current and wire guide action of the magnetic wire guide system.

[0059] In view of the slight differences in the behavior of the real world and the metaverse, specifically in this embodiment, there will be slight differences between the actual current flow direction of the magnetic wire guide system and the ideal simulated current of the metaverse wire guide system. In addition, there will also be slight differences between the physical solenoid of the magnetic wire guide system and the simulated solenoid of the metaverse wire guide system. Therefore, we need to train the current rectifier model to compensate for the slight differences in control behavior caused by the above differences. This application adopts the following scheme for the current rectifier model.

[0060] First, a set of randomly distributed control currents is output to multiple solenoids of the magnetic wire guide system, that is, different control currents are output to different solenoids based on a certain rule, so that the wire guide moves under the magnetic field of the solenoid. At this time, the current value of the randomly distributed control current is recorded, and the physical wire guide action of the wire guide is recorded by a camera. Here, the action can be explained by the specific physical shape of the wire guide after the corresponding action is generated.

[0061] Then, based on the record of the control current, the record is simulated into the meta-universe guide wire system, that is, the meta-current is made the same as the control current, and the meta-guide wire action of the meta-guide wire in the meta-universe guide wire system is recorded, which actually refers to the meta-guide wire shape Gmeta of the meta-guide wire.

[0062] Then, the distance loss between the entity's arrival action and the meta-wire action is calculated, or the distance L between the two shapes Greal and Gmeta.

[0063]

[0064] Where dt is the infinitesimal length of the guidewire. x(t), y(t) and z(t) are the spatial positions of the guidewire at time t.

[0065] Finally, model training is performed based on the distance loss and other parameters mentioned above, thereby obtaining the current rectifier model Mθ. The rectifier current δi is used to be added to the main current Ii and applied to the corresponding solenoid Si, based on which the present application defines δi=Mθ(Ii).

[0066] Mθ is a parameterized function that is obtained by gradient descent. → θ = [θ1, θ2, ..., θk] minimizes the distance loss L between the meta-wire and the real wire, where lr is the learning rate.

[0067]

[0068] The rectifier model Mθ can be a linear function, a polynomial function or a multi-layer neural network. If it is a linear function, it can make δi=Mθ(Ii)=θi×Ii+bi, where θi and bi can be optimized; the expression form of the polynomial function is Mθ( → I)= → ao+ → a1· → I+ → a2· → I2+....

[0069] Based on this rectifier model, the current sent to the solenoid is:

[0070]

[0071] S3. Construct a training sample set based on the current rectifier model.

[0072] The current rectifier model can be used as the controller of the Metaverse wire guide system, that is, it is used to output the analog control current of the solenoid. Based on this, a training sample set for model training is constructed. The specific scheme is as follows:

[0073] First, a random current pattern is generated based on the current rectifier model →c1=(I1, I2, ...Ik), that is, a randomly distributed analog control current is generated in the metaverse magnetic wire system. The control current will generate a virtual magnetic field, which will act on the meta-wire to make it move, that is, it will be twisted into a specific shape →s1=(x(t), y(t), z(t)).

[0074] Then, by continuously generating and recording operations, multiple simulated control currents and corresponding element guide wire shapes can be obtained, Dl = {(→ci,→si)|→ci∈Rk,→si∈(x(t),y(t),z(t)), where t∈[0,l]} and l is the length of the guide wire.

[0075] Finally, the above-mentioned control current and element guide wire shape are recorded to form a training sample set in this application, which includes a training set and a test set.

[0076] S4. Perform model training based on the training sample set to obtain a magnetic wire control model.

[0077] After obtaining the above training sample set, model training is performed based on the training sample set to obtain a magnetic guidewire notification model.

[0078] In the first training step based on the training sample set D1, many shapes that do not conform to the actual situation will be generated. After the first training is completed, a set of realistic shapes S*1 will be generated based on a set of rules, such as the curvature of each point of the guide wire does not exceed the preset maximum value and the twisted guide wire does not exceed the magnetic specified compound ROI, etc., and the shape is passed through M1 to generate its corresponding current C2=M1(S*1), and it is run through the simulator to obtain the corresponding shape S2.

[0079] Then we further fine-tune model M2 based on (S2, C2).

[0080] By repeating the above operations, we converge to a final model guidewire shape that performs well in various realistic situations, and determine the model as the magnetic guidewire control model.

[0081] It can be seen from the above technical solution that this embodiment provides a training method for a magnetic wire control model, which is applied to electronic equipment, specifically to construct a metaverse wire system corresponding to the mirror image of the magnetic wire system, the metaverse wire system includes a meta-current and a meta-wire; based on the control current and wire action of the magnetic wire system, the model training is performed to obtain a current rectifier model; a training sample set is constructed based on the current rectifier model; based on the training sample set, the model training is performed to obtain a magnetic wire control model for controlling the magnetic wire system. When the magnetic wire control model is applied to the magnetic wire system, the magnetic wire can accurately enter the lesion without relying on the operator's operating experience.

[0082] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0083] Although operations are depicted in a particular order, this should not be understood as requiring that the operations be performed in the particular order shown or in a sequential order.Multitasking and parallel processing may be advantageous under certain circumstances.

[0084] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0085] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages ​​or a combination thereof, including, but not limited to, object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as C or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer.

[0086] Figure 3 This is a block diagram of a training device for a magnetic wire control model according to an embodiment of the present application.

[0087] Reference Figure 3 As shown, this embodiment provides a training device for a magnetic wire control model, which is applied to an electronic device for training a magnetic wire control model for controlling a magnetic wire system. The electronic device can be understood as a computer, server or embedded device with data computing and information processing capabilities. The training device includes a metaverse construction module 10, a first training module 20, a sample set construction module 30 and a second training module 40.

[0088] The metaverse construction module is used to construct a metaverse guidewire system that mirrors the magnetic guidewire system.

[0089] The magnetic wire guide system here refers to a physical magnetic wire guide system in the real world, that is, the control entity of the magnetic wire guide control model. The metaverse wire guide system refers to a virtual system that exists in an electronic device for mirror matching the physical magnetic wire guide system. The construction module specifically includes a parameter acquisition unit and a first construction unit.

[0090] The parameter acquisition unit is used to acquire the guide wire stiffness and the guide wire magnetic susceptibility of the magnetic guide wire system. The guide wire stiffness and the guide wire magnetic susceptibility are parameters obtained by actually measuring the guide wire through corresponding equipment.

[0091] The first construction unit is used to construct the metaverse based on the underlying physical laws such as electromagnetic laws, and the wire stiffness and wire magnetic susceptibility to obtain the metaverse wire system.

[0092] The first training module is used to perform model training based on the control current and guidewire action of the magnetic guidewire system.

[0093] In view of the slight differences in the behavior of the real world and the metaverse, specifically in this embodiment, there will be slight differences between the actual current flow direction of the magnetic wire guide system and the ideal simulated current of the metaverse wire guide system. In addition, there will also be slight differences between the physical solenoid of the magnetic wire guide system and the simulated solenoid of the metaverse wire guide system. Therefore, we need to train the current rectifier model to compensate for the slight differences in control behavior caused by the above differences. The first training module of the present application includes a first recording unit, a second recording unit, a distance calculation unit, and a training execution unit.

[0094] The first recording unit is used to output a set of randomly distributed control currents to multiple solenoids of the magnetic guide wire system, that is, different control currents are output to different solenoids based on a certain rule, so that the guide wire moves under the magnetic field of the solenoid, and the current value of the randomly distributed control current is recorded at this time, and the physical guide wire movement of the guide wire is recorded by a camera, where the explanation of the movement can be the specific physical shape of the guide wire after the corresponding movement is generated.

[0095] The second recording unit is used to simulate the record of the control current into the meta-universe guide wire system based on the record of the control current, that is, to make the meta-current the same as the control current, and to record the meta-guide wire action of the meta-guide wire in the meta-universe guide wire system, which actually refers to the meta-guide wire shape Gmeta of the meta-guide wire.

[0096] The distance calculation unit is used to calculate the distance loss between the entity's arrival action and the meta-wire action, or the distance L between the two shapes Greal and Gmeta.

[0097]

[0098] Where dt is the infinitesimal length of the guidewire. x(t), y(t) and z(t) are the spatial positions of the guidewire at time t.

[0099] The training execution unit is used to perform model training based on the distance loss and other parameters mentioned above, so as to obtain the current rectifier model Mθ. The rectifier current δi is used to be added to the main current Ii and applied to the corresponding solenoid Si, based on which the present application defines δi=Mθ(Ii).

[0100] Mθ is a parameterized function that is obtained by gradient descent. → θ = [θ1, θ2, ..., θk] minimizes the distance loss L between the meta-wire and the real wire, where lr is the learning rate.

[0101]

[0102] The rectifier model Mθ can be a linear function, a polynomial function or a multi-layer neural network. If it is a linear function, it can make δi=Mθ(Ii)=θi×Ii+bi, where θi and bi can be optimized; the expression form of the polynomial function is Mθ( → I)= → ao+ → a1· → I+ → a2· → I2+....

[0103] Based on this rectifier model, the current sent to the solenoid is:

[0104]

[0105] The sample set building module is used to build a training sample set based on the current rectifier model.

[0106] The current rectifier model can be used as a controller of the metaverse wire guide system, that is, used to output the analog control current of the solenoid. Based on this, a training sample set for model training is constructed. The module includes a current generation unit, a data recording unit and a second construction unit.

[0107] The current generating unit is used to generate a random current pattern based on the current rectifier model → c1=(I1,I2,...Ik), that is, a randomly distributed simulated control current is generated in the metaverse magnetic wire system. The control current will generate a virtual magnetic field, which will act on the metawire to make it move, that is, it will be twisted into a specific shape→s1=(x(t),y(t),z(t)).

[0108] The data recording unit is used to obtain multiple simulated control currents and corresponding element guide wire shapes by continuously generating and recording operations, Dl = {(→ci, →si)|→ci∈Rk, →si∈(x(t), y(t), z(t)), where t∈[0,l]}, and l is the length of the guide wire.

[0109] The second construction unit is used to record the above-mentioned control current and element guide wire shape to form a training sample set in the present application, and the training sample set includes a training set and a test set.

[0110] The second training module is used to perform model training based on the training sample set to obtain a magnetic wire control model.

[0111] After obtaining the above training sample set, model training is performed based on the training sample set to obtain a magnetic guidewire notification model.

[0112] In the first training step based on the training sample set D1, many shapes that do not conform to the actual situation will be generated. After the first training is completed, a set of realistic shapes S*1 will be generated based on a set of rules, such as the curvature of each point of the guide wire does not exceed the preset maximum value and the twisted guide wire does not exceed the magnetic specified compound ROI, etc., and the shape is passed through M1 to generate its corresponding current C2=M1(S*1), and it is run through the simulator to obtain the corresponding shape S2.

[0113] Then we further fine-tune model M2 based on (S2, C2).

[0114] By repeating the above operations, we converge to a final model guidewire shape that performs well in various realistic situations, and determine the model as the magnetic guidewire control model.

[0115] It can be seen from the above technical solution that this embodiment provides a training device for a magnetic wire control model, which is applied to electronic equipment, specifically to construct a metaverse wire system corresponding to the mirror image of the magnetic wire system, the metaverse wire system includes a meta-current and a meta-wire; based on the control current and wire action of the magnetic wire system, the model training is performed to obtain a current rectifier model; a training sample set is constructed based on the current rectifier model; based on the training sample set, the model training is performed to obtain a magnetic wire control model for controlling the magnetic wire system. When the magnetic wire control model is applied to the magnetic wire system, the magnetic wire can accurately enter the lesion without relying on the operator's operating experience.

[0116] The units involved in the embodiments described in the present disclosure may be implemented by software or hardware. The name of a unit does not limit the unit itself in some cases. For example, the first acquisition unit may also be described as a "unit for acquiring at least two Internet Protocol addresses".

[0117] The functions described above herein may be performed at least in part by one or more hardware logic components. For example, without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), and the like.

[0118] Figure 4 A block diagram of an electronic device according to an embodiment of the present application.

[0119] refer to Figure 4As shown, it shows a schematic diagram of the structure of an electronic device suitable for implementing the embodiments of the present disclosure. The terminal device in the embodiments of the present disclosure may include but is not limited to mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. The electronic device is only an example and should not bring any limitations to the functions and scope of use of the embodiments of the present disclosure.

[0120] The electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 401, which can perform various appropriate actions and processes according to a program stored in a read-only memory ROM 402 or a program loaded from an input device 406 into a random access memory RAM 403. In the RAM, various programs and data required for the operation of the electronic device are also stored. The processing device, ROM, and RAM are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0121] Typically, the following devices may be connected to the I / O interface: input devices including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 407 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 408 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 409. The communication device 409 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows an electronic device with various devices, it should be understood that it is not required to implement or have all the devices shown. More or fewer devices may be implemented or have alternatively.

[0122] The present application also provides a computer-readable medium embodiment, which is applied to an electronic device and carries one or more computer programs. When the one or more computer programs are executed by the electronic device, the electronic device constructs a metaverse guidewire system corresponding to the magnetic guidewire system, and the metaverse guidewire system includes a meta-current and a meta-wire; performs model training based on the control current and guidewire action of the magnetic guidewire system to obtain a current rectifier model; constructs a training sample set based on the current rectifier model; performs model training based on the training sample set to obtain a magnetic guidewire control model for controlling the magnetic guidewire system. When the magnetic guidewire control model is applied to the magnetic guidewire system, the magnetic guidewire can accurately enter the lesion without relying on the operator's operating experience.

[0123] It should be noted that the computer-readable medium disclosed above may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer 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 of the above.

[0124] In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0125] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0126] Although the preferred embodiments of the present invention have been described, those skilled in the art may make additional changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the embodiments of the present invention.

[0127] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or terminal device including the elements.

[0128] The technical solution provided by the present invention is introduced in detail above. Specific examples are used in this article to illustrate the principle and implementation mode of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation mode and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A training method for a magnetic wire control model, applied to electronic equipment, It is characterized in that The training method comprises the steps of: Constructing a metaverse wire guide system corresponding to the mirror image of the magnetic wire guide system, wherein the metaverse wire guide system includes a meta-current and a meta-wire guide; the metaverse wire guide system refers to a virtual system used to match the mirror image of the physical magnetic wire guide system in an electronic device; Performing model training based on the control current and wire guiding action of the magnetic wire guiding system to obtain a current rectifier model; Constructing a training sample set based on the current rectifier model; Performing model training based on the training sample set to obtain a magnetic wire control model for controlling the magnetic wire system; The control current and wire guiding action based on the magnetic wire guiding system are used to perform model training to obtain a current rectifier model, including the steps of: Generate a randomly distributed control current and record the physical wire guiding action in the magnetic wire guiding system in accordance with the control current; Simulating the current distribution and the wire action into the meta-universe wire system, and recording the meta-wire action of the meta-wire; Calculating the distance loss between the entity guide wire motion and the meta guide wire motion; Performing model training based on the distance loss to obtain the current rectifier model; The step of constructing a training sample set based on the current rectifier model comprises the following steps: Randomly generate a series of meta-control currents for creating meta-magnetic fields; Recording the elementary control current and the elementary guide wire shape corresponding to the elementary control current; Sample construction is performed based on the plurality of element control currents and the plurality of element guide wire shapes to obtain the training sample set.

2. The training method according to claim 1, It is characterized in that The method of constructing a metaverse guide wire system corresponding to the mirror image of the magnetic guide wire system comprises the steps of: Obtaining the guidewire stiffness and the guidewire magnetic susceptibility obtained by testing the guidewire of the magnetic guidewire system; The metaverse construction is performed based on the guidewire stiffness, the guidewire magnetic susceptibility and the underlying physical laws to obtain the metaverse guidewire system.

3. A training device for a magnetic wire control model, applied to electronic equipment, It is characterized in that The training device comprises: A metaverse construction module is configured to construct a metaverse guide wire system corresponding to the mirror image of the magnetic guide wire system, wherein the metaverse guide wire system includes a meta-current and a meta-guide wire; the metaverse guide wire system refers to a virtual system used to match the mirror image of the physical magnetic guide wire system in the electronic device; A first training module is configured to perform model training based on the control current and wire guiding action of the magnetic wire guiding system to obtain a current rectifier model; A sample set building module, configured to build a training sample set based on the current rectifier model; A second training module is configured to perform model training based on the training sample set to obtain a magnetic wire control model for controlling the magnetic wire system; The first training module includes: A first recording unit is configured to generate a randomly distributed control current and record a physical wire guiding action in the magnetic wire guiding system related to the control current; A second recording unit is configured to simulate the current distribution and the wire action into the meta-universe wire system, and record the meta-wire action of the meta-wire; a distance calculation unit, configured to calculate a distance loss between the entity guide wire action and the meta guide wire action; A training execution unit, configured to execute model training based on the distance loss to obtain the current rectifier model; The sample set construction module includes: a current generating unit configured to randomly generate a series of meta-control currents for creating a meta-magnetic field; a data recording unit configured to record the elementary control current and the elementary guide wire shape corresponding to the elementary control current; The second construction unit is configured to perform sample construction based on the plurality of element control currents and the plurality of element guide wire shapes to obtain the training sample set.

4. The training device according to claim 3, It is characterized in that The metaverse building blocks include: A parameter acquisition unit is configured to acquire the guide wire stiffness and the guide wire magnetic susceptibility obtained by detecting the guide wire of the magnetic guide wire system; The first construction unit is configured to perform metaverse construction based on the guidewire stiffness, the guidewire magnetic susceptibility and underlying physical laws to obtain the metaverse guidewire system.

5. An electronic device, It is characterized in that The electronic device comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs or instructions; The processor is used to execute the computer program or instruction so that the electronic device implements the training method of the magnetic wire control model as described in any one of claims 1 to 2.

6. A medium used in electronic equipment, It is characterized in that The medium carries one or more computer programs, and the one or more computer programs can be executed by the electronic device, so that the electronic device implements the training method of the magnetic wire control model as described in any one of claims 1 to 2.