WO2023207752A1

WO2023207752A1 - Surgical robot and control system therefor

Info

Publication number: WO2023207752A1
Application number: PCT/CN2023/089533
Authority: WO
Inventors: 唐建东; 周国新
Original assignee: 苏州景昱医疗器械有限公司
Priority date: 2022-04-27
Filing date: 2023-04-20
Publication date: 2023-11-02
Also published as: CN114948215A

Abstract

Provided are a surgical robot and a control system therefor. The surgical robot (100) comprises a driving assembly (120) and a control assembly (110). The control assembly (110) is configured to: acquire a first image data of a patient by using an image acquisition device (S1); on the basis of the first image data, control the driving assembly (120) to implant an electrode cable into the cranium of the patient (S2); acquire a second image data of the patient by using the image acquisition device (S3); on the basis of the first image data and the second image data, detect whether a target point corresponding to the electrode cable is offset (S4); in the case that the target point corresponding to the electrode cable is detected to be offset, control the driving assembly (120) to adjust the pose of the electrode cable, such that the pose of the electrode cable is matched with the target point corresponding to the electrode cable (S5).

Description

Surgical robots and control systems for surgical robots

This application claims priority to the Chinese patent application with application number 202210454471.4, which was submitted to the China Patent Office on April 27, 2022. The entire content of this application is incorporated into this application by reference.

Technical field

The present application relates to the technical field of deep brain stimulation therapy, for example, to surgical robots and surgical robot control systems.

Background technique

During the electrode implantation surgery, the target position of the patient's brain is first determined through a three-dimensional stereotaxic device, and then a suitable part of the skull is drilled according to the target position and the meninges are incised, and then the electrode leads are passed through the bone holes and meninges. The notch is inserted into the corresponding target position. Among them, the most critical step is how to accurately implant the electrode leads at the most effective target point.

Generally speaking, the common target of Parkinson's disease is the subthalamic nucleus, which has a volume of 4×5×6mm and is about the same size as a soybean. The diameter of the electrode lead is only 1.27mm, and up to three electrode contacts can be located in the thalamus. In the base nucleus, therefore, doctors need to locate the target and electrode leads extremely accurately, otherwise the position may be slightly different and the effect will be lost.

When the electrode lead is implanted into the corresponding target point, due to the force between the electrode lead and the brain, the brain tissue deforms, causing the target position to shift, causing the stimulation site of the electrode lead to deviate from the position of the corresponding target point. This in turn affects the implantation effect of the electrode leads.

Patent CN113797440A discloses an automatic deep brain electrode implantation system based on imaging and electrophysiological real-time positioning, including: a control center, a skull puncture unit, an electrophysiological signal acquisition unit and a mechanical transmission unit; the skull puncture unit is configured to perform puncture operations; The physiological signal acquisition unit is configured to collect deep brain electrophysiological signals; the mechanical transmission unit is configured to drive the skull puncture unit; the control center is configured to generate image targets and virtual implantation pathways based on the three-dimensional brain image, and obtain the best implantation point and implantation depth, as well as controlling the action of the mechanical delivery unit. This method does not consider that the corresponding target point may shift after the electrode leads are implanted in the brain, and the implantation effect of the electrode leads cannot be guaranteed.

Patent CN112842531A discloses a neurosurgery planning system, which includes: a three-dimensional model reconstruction module, a diffusion tensor imaging (DTI) module, a functional magnetic resonance (functional Magnetic Resonance Imaging, fMRI) module, and image registration module, surgical path planning module, and automatic blood vessel avoidance module. This method also does not consider implanting the electrode leads After entering the brain, the corresponding target point may shift, making it impossible to ensure the implantation effect of the electrode lead.

Contents of the invention

This application provides a surgical robot and a control system for the surgical robot to ensure that after the electrode lead is implanted in the skull, the position of the electrode lead matches the corresponding target point to ensure the implantation effect of the electrode lead.

The present application provides a surgical robot, which is configured to implant at least two electrode leads into a patient's skull, and the surgical robot includes a driving component and a control component;

For each electrode lead that is not implanted, the control component is configured to perform the following steps:

Using an image acquisition device to obtain the first image data of the patient;

Based on the first image data, control the driving component to implant the electrode lead into the patient's skull;

Using the image acquisition device to obtain second image data of the patient;

Based on the first image data and the second image data, detect whether the target target corresponding to the electrode lead is offset;

When it is detected that the target point corresponding to the electrode lead is offset, the driving assembly is controlled to adjust the posture of the electrode lead so that the posture of the electrode lead is consistent with the position corresponding to the electrode lead. Target target matches.

In some optional embodiments, the control component is configured to detect whether the target target corresponding to the electrode lead has shifted based on the first image data and the second image data in the following manner:

Obtain the first bounding box position information of each target target in the first image data;

Obtain the second bounding box position information of each target target in the second image data;

Based on the first bounding box position information and the second bounding box position information corresponding to each target target point, it is detected whether the target target point corresponding to the electrode lead is offset.

In some optional embodiments, the control component is configured to detect whether the target target corresponding to the electrode lead has shifted in the following manner:

Use the text similarity model to calculate the similarity of the first bounding box position information and the second bounding box position information corresponding to each target target, and obtain the position similarity corresponding to each target target;

When the position similarity corresponding to the target point corresponding to the electrode lead is less than the first similarity threshold, it is determined that the target target point corresponding to the electrode lead has shifted.

In some optional embodiments, the control component is configured to detect the electrical Whether the target point corresponding to the polar wire has shifted:

Based on the first bounding box position information corresponding to each target target point, intercept the first sub-image of the preset area corresponding to each target target point from the first image data;

Based on the second bounding box position information corresponding to each target target point, intercept the second sub-image of the preset area corresponding to each target target point from the second image data;

Use the image similarity model to calculate the similarity of the first sub-image and the second sub-image corresponding to each target target, and obtain the image similarity corresponding to each target target;

When the image similarity corresponding to the target point corresponding to the electrode lead is less than the second similarity threshold, it is determined that the target target point corresponding to the electrode lead is shifted.

In some optional embodiments, the control component is configured to control the driving component to position the electrode wire in the following manner when it is detected that the target point corresponding to the electrode wire has shifted. Adjust so that the posture of the electrode lead matches the target target corresponding to the electrode lead:

When it is detected that the target point corresponding to the electrode lead is offset, the driving assembly is controlled to deepen the electrode lead downward or extract it upward, so that the posture of the electrode lead is consistent with the corresponding target point. match.

When it is detected that the target point corresponding to the electrode lead has shifted, the driving assembly is controlled to remove the electrode lead from the patient's skull, and the image acquisition device is used to obtain the first image of the patient again. The step of imaging data is to control the driving component to adjust the posture of the electrode lead.

In some optional embodiments, the control component is configured to control the driving component to implant the electrode lead into the patient's skull based on the first image data in the following manner:

During the process of implanting the electrode lead using the driving assembly, the image acquisition device is used to obtain real-time image data of the patient;

Based on the patient's real-time image data, detect whether the electrode lead deviates from its corresponding reference path;

When it is detected that the electrode lead does not deviate from its corresponding reference path, re-execute the process of using the driving assembly to implant the electrode lead and using the image acquisition device to acquire the patient's image. The steps of real-time image data;

When it is detected that the electrode lead deviates from its corresponding reference path, the reference path corresponding to the electrode lead is updated based on the patient's current image data, and the process of implanting the electrode lead using the driving assembly is re-executed. During the process, the step of using the image acquisition device to obtain real-time image data of the patient.

In some optional embodiments, the control component is configured to perform the step of detecting whether the electrode lead deviates from its corresponding reference path based on the patient's real-time image data in the following manner:

Based on the real-time image data of the patient within the preset time period, obtain multiple position data corresponding to the electrode leads within the preset time period;

Based on the plurality of position data, obtain the actual path corresponding to the electrode lead;

Use a path similarity model to calculate the similarity between the actual path corresponding to the electrode wire and the reference path to obtain the path similarity corresponding to the electrode wire;

Based on the path similarity corresponding to the electrode wire, it is detected whether the electrode wire deviates from its corresponding reference path.

In some optional embodiments, the process of obtaining the reference path corresponding to the electrode wire includes:

Based on the first image data, obtain the pose information of the target target corresponding to the electrode lead;

Based on the pose information of the target point corresponding to the electrode lead, the reference path corresponding to the electrode lead is obtained.

In some optional embodiments, the control component is configured to obtain the pose information of the target target corresponding to the electrode lead in the following manner:

Generate a brain model of the patient based on the first imaging data;

Based on the patient's brain model, the pose information of the target target corresponding to each electrode lead is obtained.

This application also provides a control system for a surgical robot configured to control the surgical robot to implant each unimplanted electrode lead into the patient's skull;

The system includes:

A first image data acquisition device configured to acquire first image data of the patient using an image acquisition device;

a driving component control device configured to control the driving component of the surgical robot to implant the electrode lead into the patient's skull based on the first image data;

The second image data acquisition device is configured to use the image acquisition device to acquire the patient's second image data;

A target target point detection device configured to detect whether the target target point corresponding to the electrode lead is offset based on the first image data and the second image data;

The electrode lead adjustment device is configured to control the driving assembly to adjust the posture of the electrode lead when it detects that the target target point corresponding to the electrode lead is offset, so that the posture of the electrode lead is adjusted. Matches its corresponding target target.

Description of the drawings

Figure 1 is a schematic flowchart of a control method for a surgical robot provided by an embodiment of the present application;

Figure 2 is a schematic flowchart of detecting whether a target target point has shifted according to an embodiment of the present application;

Figure 3 is a schematic flowchart of adjusting the position and posture of electrode leads provided by an embodiment of the present application;

Figure 4 is a schematic flow chart of implanting electrode leads provided by an embodiment of the present application;

Figure 5 is a structural block diagram of a surgical robot provided by an embodiment of the present application;

Figure 6 is a structural block diagram of a control system for a surgical robot provided by an embodiment of the present application.

Detailed ways

The present application will be described below with reference to the accompanying drawings and embodiments. On the premise that there is no conflict, multiple embodiments or multiple technical features described below can be arbitrarily combined to form new embodiments.

Briefly describe the application fields of this application.

Implantable medical equipment is an implantable programmable multi-program medical equipment, which can be an implanted nerve electrical stimulation device, an implantable cardiac electrical stimulation system (also known as a pacemaker), or an implantable drug infusion Any one of the Implantable Drug Delivery System (IDDS) and the lead adapter device. Implantable neuroelectric stimulation devices include, for example, Deep Brain Stimulation (DBS) system, Implantable Cortical Nerve Stimulation (CNS) system, and Implantable Spinal Cord Stimulation (SCS) system. system, implantable sacral nerve stimulation (Sacral Nerve Stimulation, SNS) system, implantable vagus nerve stimulation (Vagus Nerve Stimulation, VNS) system, etc. The implantable medical device is, for example, a stimulator. The stimulator includes an Implantable Pulse Generator (IPG), extension wires, and electrode wires. The IPG is placed in the patient's body and relies on a sealed battery and circuit to provide controllable Electrical pulse stimulation provides one or two controllable specific electrical pulse stimulations to specific areas of biological tissue through implanted extension wires and electrode wires. The extension lead is used in conjunction with the IPG as a pulse transmission medium to deliver the stimulation pulse generated by the IPG to the electrode lead. The electrode lead transmits the electrical stimulation generated by the IPG to the living body through multiple electrode contacts. A specific area of the tissue; the implantable medical device has one or more electrode leads on one or both sides. Multiple electrode contacts are provided on the electrode leads. The electrode contacts can be arranged evenly or non-uniformly. Arranged in the circumferential direction of the electrode lead, for example, the electrode contacts are arranged in an array of 4 rows and 3 columns (a total of 12 electrode contacts) in the circumferential direction of the electrode lead.

In one embodiment of the present application, the stimulated biological tissue can be the patient's brain tissue, and the stimulated site can be a specific part of the brain tissue. When the patient's disease type is different, the stimulated site is generally Different, the number of stimulation contacts used (single source or multiple sources), the use of one or more channels (single channel or multiple channels) of specific electrical pulse stimulation, and stimulation parameter data are also different. This application does not limit the applicable disease types. The disease types can be those applicable to deep brain stimulation (DBS), spinal cord stimulation (SCS), pelvic stimulation, gastric stimulation, peripheral nerve stimulation, and functional electrical stimulation. Among them, the types of diseases that DBS can be used to treat or manage include: spastic diseases (such as epilepsy), pain, migraine, mental illness (such as major depressive disorder (Major Depressive Disorder, MDD)), bipolar disorder, anxiety disorder , post-traumatic stress disorder, mild depression, obsessive-compulsive disorder (OCD), behavioral disorders, mood disorders, memory disorders, mental status disorders, movement disorders (such as essential tremor or Parkinson's disease ), Huntington's disease, Alzheimer's disease, substance addiction disorders, autism, or other neurological or psychiatric diseases and impairments. When DBS is used to treat patients with drug addiction, it can help drug addicts detoxify and improve their happiness and quality of life.

Referring to Figure 1, an embodiment of the present application provides a method for controlling a surgical robot. The surgical robot is configured to implant at least two electrode leads into a patient's skull. The surgical robot includes a driving component and a control component.

For each electrode lead that is not implanted, the method includes steps S1 to S5.

S1: Use image acquisition equipment to obtain the first image data of the patient.

S2: Based on the first image data, control the driving component to implant the electrode lead into the patient's skull.

S3: Use the image acquisition device to obtain the second image data of the patient.

S4: Based on the first image data and the second image data, detect whether the target target corresponding to the electrode lead is offset.

S5: When it is detected that the target point corresponding to the electrode lead is offset, control the driving component to adjust the posture of the electrode lead so that the posture of the electrode lead is consistent with the position of the electrode lead. The corresponding target targets match.

Therefore, before implanting each electrode lead, the first image data is acquired, and the electrode lead is implanted into the patient's skull using the first image data as a reference. After the implantation is completed, the second image data is acquired, and the second image data is compared with the first image data. Based on the comparison results of the first image data and the second image data, it is detected whether the target point corresponding to the electrode lead has shifted, and the posture of the electrode lead with the offset target point is adjusted to ensure that the position of the electrode lead is consistent with the electrode lead. Corresponding target target matches.

The related technology only acquires image data once before implanting the electrode lead, and does not consider the deviation of the target point after the electrode lead is implanted. However, this application needs to acquire image data before and after implanting the electrode lead, and the electrode lead is implanted. The first image data is obtained before the electrode lead is implanted, and the second image data is obtained after the electrode lead is implanted. The first image data is used as a reference when the electrode lead is implanted, and the second image data is combined with the first image data as a target. The basis for judging whether the target point has shifted is that when it is detected that the target point has shifted, the posture of the electrode lead that has shifted the target point is adjusted so that the stimulation site of the electrode lead does not deviate from the corresponding position of the electrode lead. The position of the target ensures the implantation effect of the electrode lead.

This application does not limit at least two of the "at least two electrode wires", which may be a preset value, such as 2, 6, 8 or 11.

In some embodiments, the surgical robot needs to implant 8 electrode leads into the patient's skull. After completing the implantation of 1 of them, the 7 electrode leads that have not yet been implanted are used to control the 7 electrode leads as described above. The electrode leads are implanted into the patient's skull one by one.

The embodiment of the present application does not limit the structure of the surgical robot, and any surgical robot disclosed in CN111631815A, CN111419400A, CN108066011A or CN114098971A can be used.

The driving assembly may include a power mechanism that provides power, a puncture actuator that performs the puncture operation, and a transmission mechanism that drives the electrode lead to complete the implantation operation. The power mechanism may include a motor, a cylinder, etc., and the puncture mechanism may include a puncture needle and a sleeve.

The control function of the control component can be controlled by a microprocessor (Microprocessor Unit, MPU), a microcontroller unit (MCU), a Digital Signal Processor (DSP), a field programmable gate array (Field Programmable Gate Array, FPGA) or other Any combination can be achieved.

The embodiments of the present application do not limit the image acquisition equipment. The image acquisition equipment may be any one of computerized tomography (CT) scanning equipment, magnetic resonance scanner, and ultrasonic scanner. When the image acquisition device is an MRI scanner, the surgical robot is made of magnetic resonance (Magnetic Resonance, MR) compatible materials.

The image data acquired by the image acquisition equipment may include one or more of CT scan images, Magnetic Resonance Imaging (MRI), radiological images, and ultrasound images.

The basic idea of DBS is to use electrodes to stimulate specific locations in the brain, called targets. The selection of target plays an important role in the effectiveness of treatment.

For different diseases or symptoms, specific targets need to be selected. For example, commonly used by Parkinson’s patients Treatment targets are the subthalamic nucleus and the medial part of the globus pallidus, while a common target in patients with tremor is the ventromedial nucleus of the thalamus.

The target target of this application is the target corresponding to the patient's implantation surgery.

Referring to Figure 2, in some optional embodiments, step S4 may include steps S41 to S43.

Step S41: Obtain the first bounding box position information of each target point in the first image data.

Step S42: Obtain the second bounding box position information of each target point in the second image data.

Step S43: Based on the first bounding box position information and the second bounding box position information corresponding to each target target point, detect whether the target target point corresponding to the electrode lead is offset.

Therefore, by respectively obtaining the first bounding box position information and the second bounding box position information corresponding to each target target point, the bounding box position of each target target point in the first image data and the second image data can be compared. The position of the bounding box, and based on the comparison result of the position of the bounding box, detect whether the target target has shifted.

Compared with the method of manually detecting whether the target point has shifted, this method of automatically detecting whether the target point has shifted using the bounding box position information is more efficient and has smaller errors.

In target detection, bounding boxes are usually used to describe the spatial location of target objects. When the bounding box is a rectangle, the position of the bounding box can be determined by the abscissa and ordinate of the upper left corner of the rectangle and the abscissa and ordinate of the lower right corner of the rectangle. Alternatively, the position of the bounding box can also be determined using the abscissa and ordinate of the center of the bounding box and the width and height of the bounding box.

In some optional embodiments, step S43 may include:

Therefore, the text similarity model can be used to directly calculate the similarity between the first bounding box position information and the second bounding box position information to obtain the position similarity corresponding to each target target. This calculation method calculates the similarity between the text. The similarity between them is small, and the detection efficiency is high.

This application does not limit the text similarity model, which can adopt any text similarity model disclosed in CN113723070A, CN111353033A, and CN111626039A.

This application does not limit the size of the first similarity threshold. The first similarity threshold may be, for example, 70%, 85% or 90%.

In some optional embodiments, step S43 may include:

Thus, after obtaining the first bounding box position information, the first sub-image of the preset area corresponding to each target target point is intercepted from the first image data, and after obtaining the second bounding box position information, the first sub-image of the preset area corresponding to each target target is obtained from the second image data. The second sub-image of the preset area corresponding to each target target is intercepted from the image data. The size of the preset area can correspond to the size of the bounding box. After obtaining the first sub-image and the second sub-image, the image can be used The similarity model calculates the image similarity corresponding to each target target. This calculation method calculates the similarity between images and has higher detection accuracy.

This application does not limit the image similarity model, which can adopt any image similarity model disclosed in CN114140664A, CN112052868A, CN1926575A, and CN112633420A.

The preset area may be a preset area. This application does not limit the size of the preset area. The size may be 4×4 mm, 4×5 mm or 6×8 mm.

This application does not limit the size of the second similarity threshold. The second similarity threshold may be, for example, 70%, 85% or 90%.

In some optional embodiments, step S5 may include:

Therefore, generally speaking, the actual implantation site of the electrode lead may deviate slightly from the expected implantation site due to the accuracy of the driving assembly of the surgical robot. For example, the driving assembly may include a cylinder, a puncture needle, and a sheath. tubes, etc., and the accuracy of the cylinder may be only 1mm, which results in a certain deviation between the actual implantation site of the electrode lead and the expected implantation site. At this time, there is no need to make major adjustments, and you only need to move the electrode lead along its preset By slightly deepening or extracting the predetermined reference path upward, the posture of the electrode lead can be matched with its corresponding target point. This method does not require re-planning of the path and Re-performing the puncture will cause less harm to the patient, is safer, and the operation time is short, which improves the doctor's treatment efficiency and enables the doctor to serve more patients.

Referring to Figure 3, in some optional embodiments, step S5 may include:

When it is detected that the target point corresponding to the electrode lead has shifted, the driving component is controlled to remove the electrode lead from the patient's skull, and step S1 is re-executed to control the driving component to move the target point corresponding to the electrode lead. Adjust the posture of the electrode lead.

Therefore, when the target point corresponding to the electrode lead has a large deviation and the target point cannot be matched by deepening downward or extracting upward, the electrode lead can be removed first and step S1 can be performed again, so that Complete the loop operation of steps S1 to S5 until the posture of the electrode lead matches the target point corresponding to the electrode lead, then the cycle ends. By resetting the path corresponding to the electrode lead, and by re-implantation This method makes the position of the electrode lead match the target point corresponding to the electrode lead, ensuring the implantation effect of the electrode lead.

In some optional embodiments, the method may further include:

After all the electrode leads are implanted into the patient's skull, use the image acquisition device to obtain the third image data of the patient;

Based on the first image data and the third image data, detect whether the target target points corresponding to all the electrode leads are offset;

When the target point corresponding to at least one electrode lead is offset, the electrode lead with the offset target point is recorded as the electrode lead to be adjusted, and the driving assembly is controlled to deepen the electrode lead to be adjusted downward or extract it upward. ;

When the target point corresponding to the electrode lead to be adjusted has a large deviation, and the target point cannot be matched by deepening downward or extracting upward, you can first remove the electrode lead to be adjusted, then execute S1, and restart Plan the path and perform operations such as puncture and drilling.

Referring to Figure 4, in some optional embodiments, step S2 may include steps S21 to S24.

S21: During the process of implanting the electrode lead using the driving assembly, use the image acquisition device to obtain real-time image data of the patient.

S22: Based on the patient's real-time image data, detect whether the electrode lead deviates from its corresponding reference path.

S23: When it is detected that the electrode wire does not deviate from its corresponding reference path, perform S21 again.

S24: When it is detected that the electrode lead deviates from its corresponding reference path, update the reference path corresponding to the electrode lead based on the current image data of the patient, and re-execute S21.

Therefore, considering that the electrode leads may deviate from the preset reference path during the implantation process, the patient's real-time image data is obtained during the implantation of each electrode lead, and the real-time image data shall prevail. Detect whether the electrode lead deviates from its corresponding reference path. When the electrode lead does not deviate from its corresponding reference path, continue to execute S21. When the electrode lead deviates from its corresponding reference path, update the reference according to the patient's current image data. Path, execute S21. This method is based on real-time image data to realize adaptive updating of the path of the electrode lead. During the implantation process, the posture of the electrode lead can be adjusted to ensure the implantation effect of the electrode lead.

In some optional embodiments, step S22 may include:

Thus, multiple position data corresponding to the electrode lead can be obtained based on multiple real-time image data within a preset time period. Based on these multiple position data, the actual path corresponding to the electrode lead can be obtained, and the path similarity model can be used to compare the actual path and Calculate the similarity using the reference path to obtain the path similarity corresponding to the electrode wires. This method has higher detection accuracy. Moreover, when there are enough real-time image data within the preset time period, for example, one hundred, the actual path obtained is more consistent with the path of the actual electrode lead implantation process.

The preset duration may be a preset duration. This application does not limit the preset duration. The preset duration may be 1 minute, 3 minutes or 5 minutes.

This application does not limit the form of the path similarity model, which can be trained using a machine learning model, a deep learning model, a reinforcement learning model, etc.

In some implementations, the training process of the path similarity model may include:

Acquire multiple similarity training data, each of which includes a sample reference path used for training, a sample actual path, and the annotated similarity between the two;

A plurality of the similarity training data are used to train a preset deep learning model to obtain a path similarity model.

In some embodiments, when the path similarity corresponding to the electrode lead is less than a third similarity threshold, it is determined that the electrode lead deviates from its corresponding reference path;

When the path similarity corresponding to the electrode lead is not less than the third similarity threshold, it is determined that the electrode lead has not deviated from its corresponding reference path.

This application does not limit the size of the third similarity threshold. The third similarity threshold may be, for example, 70%, 85% or 90%.

Thus, the pose information of the target point corresponding to the electrode lead can be obtained based on the first image data, and the reference path corresponding to the electrode lead can be automatically planned based on the pose information of the target point corresponding to the electrode lead, without the need for manual path planning. And the pose information of the target target can be used for visual display.

In some optional embodiments, obtaining the pose information of the target target corresponding to the electrode lead may include:

Generate a brain model of the patient based on the first imaging data;

As a result, the patient's brain model is automatically generated based on the first image data. Through the patient's brain model, the pose information of the target point corresponding to each electrode lead is obtained, and each electrode can be intuitively displayed on the brain model. The position and attitude of the target target corresponding to each electrode lead.

In some embodiments, the cranial model may be a three-dimensional model of the brain. The method of generating the brain model can adopt the method disclosed in CN112669938A.

Pose information can be used to indicate position and attitude. After the brain model is generated, the position and posture of the target target can be automatically determined with the help of artificial intelligence and machine learning technology.

Taking the subthalamic nucleus as the target as an example, the brain model is processed by artificial intelligence (AI) to automatically identify the level where the largest cross-section of the red nucleus is located, and the midpoint of the subthalamic nucleus in the horizontal section at the front edge of the red nucleus is As the target target, the position of the target can be confirmed by fine-tuning based on the center of gravity of the subthalamic nucleus.

Referring to FIG. 5 , an embodiment of the present application also provides a surgical robot 100 , the implementation of which is consistent with the implementation and technical effects achieved described in the embodiment of the above control method, and part of the content will not be described again.

The surgical robot 100 is configured to implant at least two electrode leads into the patient's skull, and the surgical robot 100 includes a driving component 120 and a control component 110;

For each electrode lead that is not implanted, the control component 110 is configured to perform the following steps:

S2: Based on the first image data, control the driving component 120 to implant the electrode lead into the patient's skull.

S5: When it is detected that the target point corresponding to the electrode lead deviates, control the driving component 120 to adjust the posture of the electrode lead so that the posture of the electrode lead is consistent with the corresponding target. target matches.

In some optional embodiments, the control component 110 is configured to perform step S4 in the following manner:

In some optional embodiments, the control component 110 is configured to detect whether the target target corresponding to the electrode lead has shifted in the following manner:

When the image similarity corresponding to the target point corresponding to the electrode lead is less than the second similarity threshold When, it is determined that the target target corresponding to the electrode lead is shifted.

In some optional embodiments, the control component 110 is configured to perform step S5 in the following manner:

When it is detected that the target point corresponding to the electrode lead is offset, the driving assembly 120 is controlled to deepen the electrode lead downward or extract it upward, so that the posture of the electrode lead is consistent with the corresponding target point. points match.

When it is detected that the target point corresponding to the electrode lead has shifted, the driving component 120 is controlled to remove the electrode lead from the patient's skull, and step S1 is re-executed to control the driving component 120 Adjust the posture of the electrode lead.

In some optional embodiments, the control component 110 is configured to perform step S2 in the following manner:

S21: During the process of implanting the electrode lead using the driving assembly 120, use the image acquisition device to acquire real-time image data of the patient.

In some optional embodiments, the control component 110 is configured to perform step S22 in the following manner:

In some optional embodiments, the control component 110 is configured to obtain the pose information of the target target corresponding to the electrode lead in the following manner:

Generate a brain model of the patient based on the first imaging data;

Embodiments of the present application also provide a control system for a surgical robot, the implementation manner of which is consistent with the implementation manner and technical effects achieved described in the embodiments of the above control method, and part of the content will not be described again. Figure 6 is a structural block diagram of a control system for a surgical robot provided by an embodiment of the present application.

The system is configured to control the surgical robot to implant each unimplanted electrode lead into the patient's skull;

The system includes:

The first image data acquisition device 210 is configured to acquire the first image data of the patient using an image acquisition device;

The driving component control device 220 is configured to control the driving component of the surgical robot to implant the electrode lead into the patient's skull based on the first image data;

The second image data acquisition device 230 is configured to acquire the second image data of the patient using the image acquisition device;

The target target point detection device 240 is configured to detect whether the target target point corresponding to the electrode lead is offset based on the first image data and the second image data;

The electrode lead adjustment device 250 is configured to control the driving assembly to adjust the posture of the electrode lead when it detects that the target target point corresponding to the electrode lead is offset, so that the position of the electrode lead is adjusted. The pose matches its corresponding target point.

Claims

A surgical robot, wherein the surgical robot is configured to implant at least two electrode leads into the patient's skull, the surgical robot including a driving component and a control component;

For each lead that is not implanted, the control component is configured to perform:

Using an image acquisition device to obtain the first image data of the patient;

Based on the first image data, control the driving component to implant the electrode lead into the patient's skull;

Using the image acquisition device to obtain second image data of the patient;

Based on the first image data and the second image data, detect whether the target target corresponding to the electrode lead is offset;

When it is detected that the target point corresponding to the electrode lead is offset, the driving component is controlled to adjust the posture of the electrode lead so that the posture of the electrode lead is consistent with the position of the electrode lead. The corresponding target targets match.
The surgical robot according to claim 1, wherein the control component is configured to detect whether the target target point corresponding to the electrode lead is deflected based on the first image data and the second image data in the following manner: shift:

Obtain the first bounding box position information of each target target in the first image data;

Obtain the second bounding box position information of each target target in the second image data;

Based on the first bounding box position information and the second bounding box position information corresponding to each target target point, it is detected whether the target target point corresponding to the electrode lead is offset.
The surgical robot according to claim 2, wherein the control component is configured to detect whether the target target corresponding to the electrode lead is offset in the following manner:

Use the text similarity model to calculate the similarity of the first bounding box position information and the second bounding box position information corresponding to each target target, and obtain the position similarity corresponding to each target target;

When the position similarity corresponding to the target point corresponding to the electrode lead is less than the first similarity threshold, it is determined that the target target point corresponding to the electrode lead is shifted.
The surgical robot according to claim 2, wherein the control component is configured to detect whether the target target corresponding to the electrode lead is offset in the following manner:

Based on the first bounding box position information corresponding to each target target point, intercept the first sub-image of the preset area corresponding to each target target point from the first image data;

Based on the second bounding box position information corresponding to each target target point, intercept the second sub-image of the preset area corresponding to each target target point from the second image data;

Use the image similarity model to calculate the similarity of the first sub-image and the second sub-image corresponding to each target target, and obtain the image similarity corresponding to each target target;

When the image similarity corresponding to the target point corresponding to the electrode lead is less than the second similarity threshold, it is determined that the target target point corresponding to the electrode lead is shifted.
The surgical robot according to claim 1, wherein the control component is configured to control the driving component to control the electrode when detecting a deviation of the target target corresponding to the electrode lead in the following manner: The posture of the lead is adjusted so that the posture of the electrode lead matches the target target corresponding to the electrode lead:

When it is detected that the target target point corresponding to the electrode lead is offset, the driving assembly is controlled to deepen the electrode lead downward or extract it upward, so that the posture of the electrode lead is consistent with the electrode lead. The corresponding target targets match.
The surgical robot according to claim 1, wherein the control component is configured to control the driving component to control the electrode when detecting a deviation of the target target corresponding to the electrode lead in the following manner: The posture of the lead is adjusted so that the posture of the electrode lead matches the target target corresponding to the electrode lead:

When it is detected that the target target corresponding to the electrode lead is shifted, the driving assembly is controlled to remove the electrode lead from the patient's skull, and the image acquisition device is used to obtain the patient's image again. The first image data is used to control the driving component to adjust the posture of the electrode lead.
The surgical robot according to claim 1, wherein the control component is configured to control the driving component to implant the electrode lead into the patient's skull based on the first image data in the following manner:

During the process of implanting the electrode lead using the driving assembly, the image acquisition device is used to obtain real-time image data of the patient;

Based on the patient's real-time image data, detect whether the electrode lead deviates from the reference path corresponding to the electrode lead;

When it is detected that the electrode lead does not deviate from the reference path corresponding to the electrode lead, re-execute the process of using the driving assembly to implant the electrode lead and using the image acquisition device to acquire the patient real-time image data;

When it is detected that the electrode lead deviates from the reference path corresponding to the electrode lead, the reference path corresponding to the electrode lead is updated based on the patient's current image data, and the implantation using the driving assembly is re-executed. During the process of conducting the electrode lead, the image acquisition device is used to obtain real-time image data of the patient.
The surgical robot according to claim 7, wherein the control component is configured to detect whether the electrode lead deviates from the reference path corresponding to the electrode lead based on the patient's real-time image data in the following manner:

Based on the real-time image data of the patient within the preset time period, obtain multiple position data corresponding to the electrode leads within the preset time period;

Based on the plurality of position data, obtain the actual path corresponding to the electrode lead;

Use a path similarity model to calculate the similarity between the actual path corresponding to the electrode wire and the reference path to obtain the path similarity corresponding to the electrode wire;

Based on the path similarity corresponding to the electrode wire, it is detected whether the electrode wire deviates from the reference path corresponding to the electrode wire.
The surgical robot according to any one of claims 7 or 8, wherein the control component is configured to obtain the reference path corresponding to the electrode lead in the following manner:

Based on the first image data, obtain the pose information of the target target corresponding to the electrode lead;

Based on the pose information of the target point corresponding to the electrode lead, the reference path corresponding to the electrode lead is obtained.
The surgical robot according to claim 9, wherein the control component is configured to obtain the pose information of the target target corresponding to the electrode lead in the following manner:

Generate a brain model of the patient based on the first imaging data;

Based on the patient's brain model, the pose information of the target target corresponding to each electrode lead is obtained.
A control system for a surgical robot configured to control the surgical robot to implant each unimplanted electrode lead into the patient's skull;

The system includes:

A first image data acquisition device configured to acquire first image data of the patient using an image acquisition device;

a driving component control device configured to control the driving component of the surgical robot to implant the electrode lead into the patient's skull based on the first image data;

a second image data acquisition device configured to acquire second image data of the patient using the image acquisition device;

A target target point detection device configured to detect whether the target target point corresponding to the electrode lead is offset based on the first image data and the second image data;

The electrode lead adjustment device is configured to detect an occurrence of a target point corresponding to the electrode lead. In the case of offset, the driving assembly is controlled to adjust the posture of the electrode lead so that the posture of the electrode lead matches the target target point corresponding to the electrode lead.