Bone cement robot control method, robot, equipment, medium and product

Abstract

The embodiment of the invention discloses a bone cement robot control method, a robot, equipment, a medium and a product, and belongs to the field of medical equipment. The method comprises the steps that image data and process parameter data are obtained, the image data comprise preoperative image data for a preset part of a target object and an intraoperative CBCT image at the current moment, and the process parameter data comprise one of the current injection rate and the current suction rate and current injection pressure data; the image data and the process parameter data are analyzed based on a pre-training machine learning model, control parameter data and state description data are obtained, and the state description data are used for describing the operation effect of the completed operation content; according to the control parameter data, an injection mechanism is controlled to execute bone cement injection operation or bone cement suction operation on the injured vertebra; and controlling the display device to display the state description data. According to the technical scheme, the consistency of the percutaneous puncture kyphoplasty effect can be improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of medical devices, and in particular to a bone cement robot control method, robot, device, medium and product. Background Technology

[0002] In percutaneous vertebroplasty, contrast agent is injected into a balloon within the affected vertebral body to create expansion. After the contrast agent is removed and the balloon is taken out, bone cement is injected. The expansion within the balloon helps restore the height of the vertebral body or create an injection cavity. Bone cement injection requires first mixing the powdered and liquid bone cement, then injecting the mixed bone cement into the vertebral cavity using an injection device. Once the bone cement has hardened within the vertebral body, it provides support for the restored vertebral height.

[0003] Current techniques typically involve doctors operating the relevant equipment based on their clinical experience to perform contrast agent injection, bone cement mixing, and bone cement injection. However, the skill levels of different doctors vary considerably, resulting in inconsistent surgical outcomes. Summary of the Invention

[0004] This invention provides a method for determining robot control parameters, a robot, equipment, media, and products to solve the problem of poor consistency in surgical outcomes in existing percutaneous kyphoplasty.

[0005] According to one aspect of the present invention, a method for controlling a bone cement robot is provided. This method is applied to a processor of a bone cement robot, the bone cement robot further comprising an injection mechanism and a display device. The method includes:

[0006] Acquire imaging data and process parameter data. The imaging data includes preoperative imaging data for a predetermined site of the target object and intraoperative CBCT images at the current moment. The preoperative imaging data includes CT images and / or X-ray anteroposterior and lateral images for the predetermined site. The process parameter data includes one of the current injection rate and the current aspiration rate, as well as the current injection pressure data. The predetermined site includes the injured vertebra and the adjacent vertebrae of the injured vertebra.

[0007] The image data and process parameter data are analyzed based on a pre-trained machine learning model to obtain control parameter data and state description data. The state description data is used to describe the operational effect of the completed surgical procedure.

[0008] Based on the control parameter data, the injection mechanism is controlled to perform bone cement injection or bone cement aspiration operations on the injured vertebra.

[0009] Control the display device to display the status description data.

[0010] According to another aspect of the present invention, a bone cement robot control device is provided, comprising a processor disposed in a bone cement robot, the bone cement robot further comprising an injection mechanism and a display device, the device comprising:

[0011] The data acquisition module is used to acquire image data and process parameter data. The image data includes preoperative image data for a predetermined site of the target object and intraoperative CBCT images at the current time. The preoperative image data includes CT images and / or X-ray anteroposterior and lateral images for the predetermined site. The process parameter data includes one of the current injection rate and the current aspiration rate, as well as the current injection pressure data. The predetermined site includes the injured vertebra and the adjacent vertebrae of the injured vertebra.

[0012] The data analysis module is used to analyze the image data and process parameter data based on a pre-trained machine learning model to obtain control parameter data and state description data. The state description data is used to describe the operational effect of the completed surgical procedure.

[0013] The control module is used to control the injection mechanism to perform bone cement injection or bone cement aspiration operations on the injured vertebra according to the control parameter data.

[0014] The display module is used to control the display device to display the status description data.

[0015] According to another aspect of the present invention, a bone cement robot is provided, comprising:

[0016] Display device;

[0017] An injection mechanism is located at the end of the robotic arm;

[0018] The processor is configured to control the injection mechanism according to any embodiment to perform a bone cement injection operation or a bone cement aspiration operation for the injured vertebra; and to display the state description data determined in any embodiment via a display device.

[0019] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0020] One or more processors;

[0021] Storage device for storing one or more programs.

[0022] When one or more programs are executed by one or more processors, the one or more processors implement the bone cement robot control method as described in any embodiment of the present invention.

[0023] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to execute and implement the bone cement robot control method according to any embodiment of the present invention.

[0024] According to another aspect of the present invention, a computer program product is provided, which, when executed by a processor, implements the bone cement robot control method as described in any embodiment of the present invention.

[0025] The technical solution of this invention includes model input data comprising image data and process parameter data for percutaneous kyphoplasty of the target object. The image data includes preoperative image data of a predetermined site on the target object and intraoperative CBCT images at the current moment. The preoperative image data includes CT images and / or X-ray anteroposterior and lateral images of the predetermined site. The process parameter data includes one of the current injection rate and the current aspiration rate, as well as the current injection pressure data. The predetermined site includes the injured vertebra and its adjacent vertebrae. Therefore, the control parameter data and state description data determined by the model based on the image data and process parameter data have high accuracy. Thus, driving the robot to perform bone cement injection or aspiration operations based on the control parameter data ensures high accuracy in these operations. This guarantees a high consistency in the surgical outcome of percutaneous kyphoplasty performed by the user using the surgical robot. Furthermore, the state description data allows the user to monitor the bone cement injection or aspiration process in real time, ensuring its accuracy and further guaranteeing the consistency of the surgical outcome.

[0026] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 A flowchart illustrating the bone cement robot control method provided in an embodiment of the present invention;

[0029] Figure 2 A schematic flowchart of the model training method provided in an embodiment of the present invention;

[0030] Figure 3 This is a schematic diagram of the structure of the bone cement robot provided in an embodiment of the present invention;

[0031] Figure 4 This is a schematic diagram of the bone cement robot control device provided in an embodiment of the present invention;

[0032] Figure 5 This is a schematic diagram of the structure of the model training device provided in an embodiment of the present invention;

[0033] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0034] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0035] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0036] It should be noted that the collection, use, storage, sharing and transfer of user personal information involved in the technical solution of the present invention all comply with the provisions of relevant laws and regulations, and require notification to users and obtaining their consent or authorization. When applicable, user personal information is subjected to de-identification and / or anonymization and / or encryption technical processing.

[0037] Figure 1This is a flowchart illustrating the bone cement robot control method provided in an embodiment of the present invention. This embodiment is applicable to situations where a model-controlled bone cement robot performs bone cement injection or aspiration operations at a given injection site. The method can be executed by a bone cement robot control device, which can be implemented in hardware and / or software and can be configured in electronic devices such as computers or servers. Figure 1 As shown, the method in this embodiment includes:

[0038] S110. Acquire imaging data and process parameter data. The imaging data includes preoperative imaging data of the predetermined site of the target object and intraoperative CBCT images at the current moment. The preoperative imaging data includes CT images and / or X-ray anteroposterior and lateral images of the predetermined site. The process parameter data includes one of the current injection rate and the current aspiration rate, as well as the current injection pressure data. The predetermined site includes the injured vertebra and the adjacent vertebrae of the injured vertebra.

[0039] Injection rate and aspiration rate can be calculated from the control parameters of the drive motor, or measured through flow sensors, scale changes, etc. Current push rod pressure data can be collected in real time by a pressure sensor mounted on the injection mechanism to reflect the resistance during injection.

[0040] Preoperative imaging data refers to images taken before surgery targeting the patient's intended site, such as CT (Computed Tomography) images and / or X-ray anteroposterior and lateral images targeting the intended site.

[0041] X-ray anteroposterior and lateral views include both anteroposterior and lateral X-ray images. In an anteroposterior X-ray image, the subject faces the X-ray source, and the X-ray rays pass from the front to the back of the body, acquiring a frontal image of the predetermined area of ​​the subject. In a lateral X-ray image, the patient lies on their side facing the X-ray source, and the X-ray rays pass from one side of the body to the other, obtaining a lateral image of the predetermined area of ​​the subject. Both anteroposterior and lateral X-ray images and CT images can be used to determine the three-dimensional structure and spatial features of the injured vertebra and adjacent vertebrae.

[0042] Preoperative CT images are acquired using diagnostic CT equipment, while intraoperative CBCT (Cone Beam Computed Tomography) images are acquired using intraoperative CBCT equipment. The intraoperative CBCT equipment is positioned next to the operating table and can acquire CBCT images of predetermined locations on the target subject at any time, as needed during the surgery. Intraoperative CBCT images may include one or more of the following: anteroposterior intraoperative CBCT images, lateral intraoperative CBCT images, and oblique intraoperative CBCT images.

[0043] In this embodiment, the execution of the bone cement control method is triggered by intraoperative CBCT images. Specifically, when the processor detects a newly acquired intraoperative CBCT image, it replaces the previous intraoperative CBCT image in the image data with the newly acquired CBCT image to update the image data. Then, based on the updated image data and process parameter data, the bone cement robot control method described in this embodiment is executed again, i.e., S110-S140.

[0044] The intended site can be the neck, chest, or lower back. The injured vertebra is the vertebra that has been injured and requires percutaneous vertebroplasty.

[0045] Adjacent vertebrae include the vertebrae above and below the injured vertebrae. The upper adjacent vertebrae are those adjacent to the injured vertebrae and located between the injured vertebrae and the head of the target; the lower adjacent vertebrae are those adjacent to the injured vertebrae and located between the injured vertebrae and the feet of the target.

[0046] In one embodiment, bone cement data is acquired simultaneously with image data and process parameter data, and the combination of bone cement data, image data, and process parameter data is used as model input data. The bone cement data includes the bone cement curing time and the mixing time. In another embodiment, the bone cement data may also optionally include ambient temperature.

[0047] Bone cement is a commonly used bone implant material in orthopedic surgery, and its properties directly determine the safety and long-term efficacy of the surgery.

[0048] Bone cement property data includes physical and mechanical property data and clinical operational property data. Physical and mechanical property data includes bone cement curing time, flexural strength, etc., while clinical operational property data includes bone cement viscosity, etc. Optionally, curing time and viscosity data are required property parameters.

[0049] In the technical field of bone cement, curing time refers to the entire process from the mixing of powder and liquid to the chemical polymerization reaction and the formation of a solidified body with stable mechanical properties. This includes working time and setting time. Working time, also known as operable time, refers to the duration during which the bone cement remains injectable and malleable after mixing. During this stage, the viscosity of the bone cement is within the range suitable for surgical procedures, allowing for smooth injection and aspiration. Beyond this time, the viscosity of the bone cement increases sharply, making intraoperative shaping impossible. Percutaneous injection typically takes 3-8 minutes. Setting time, also known as complete curing time, refers to the time from the start of mixing to the near completion of the polymerization reaction, achieving clinically acceptable mechanical properties. During this stage, the bone cement gradually transforms from a paste to a solid state, reaching its design thresholds for compressive and flexural strength, and can withstand bone loads. The setting time for clinically commonly used bone cement is typically 8–15 minutes, which must be matched to the surgical rhythm. Premature curing can lead to interruption of the procedure, while delayed curing can introduce the risk of bone cement leakage.

[0050] The mixing time includes the interval between the start of mixing and the start of surgery, as well as the duration of the surgery. During actual surgery, the start time of mixing, the start time of surgery, and the current intraoperative CBCT image acquisition time are recorded. Based on these three time points, the interval between the start of mixing and the start of surgery, as well as the duration of the surgery, can be determined, or in other words, the mixing time can be directly determined.

[0051] S120. Based on the pre-trained machine learning model, the image data and process parameter data are analyzed to obtain control parameter data and state description data. The state description data is used to describe the operational effect of the completed surgical procedure.

[0052] The control parameter data are quantitative control parameters used to regulate the robot's surgical actions. For example, the direction and speed of bone cement delivery.

[0053] The direction of bone cement delivery can be selected as a direction indicator, such as using "0" to indicate bone cement injection and "1" to indicate bone cement aspiration.

[0054] Status description data includes, but is not limited to, the percentage of vertebral height recovery, bone cement dispersion uniformity, and current extravasation risk score.

[0055] The vertebral height recovery ratio is used to characterize the degree of recovery of the current anterior and / or middle height of the injured vertebra relative to the height of adjacent vertebrae and / or the preoperative estimated normal height.

[0056] Bone cement dispersion uniformity is used to characterize whether the spatial distribution of bone cement within the injured vertebra is uniform, including the coverage area of ​​bone cement within the vertebral body, the uniformity of brightness distribution, and the presence of focally highly concentrated clumps.

[0057] Extravasation risk score is used to quantify the risk of bone cement leakage toward the vertebral cortex margin, posterior vertebral margin, and vertebral venous pathway.

[0058] In one embodiment, the state description data further includes a bone cement flow map. The bone cement flow map is a dynamic visualization that visually shows the flow direction, diffusion rate, and path branches of bone cement within or around the vertebral body.

[0059] Pre-set first, second, and third risk thresholds for the percentage of vertebral height recovery, uniformity of bone cement diffusion, and current extravasation risk score, respectively. If any of these thresholds is reached or exceeded, a corresponding alert message is output.

[0060] Specifically, taking the leakage risk score as an example, when the current leakage risk score reaches or exceeds the preset leakage risk threshold, leakage warning information is generated, a corresponding prompt message is output, and / or, the conveying direction is automatically set to the suction direction, and / or, the conveying rate is automatically reduced to a preset safe rate. The prompt message corresponding to the leakage warning information includes color-coded prompts displayed on a display device, and / or, voice prompts or a pre-defined ringtone output through a speaker.

[0061] The pre-trained machine learning model can be an end-to-end model. In this case, image data and process parameter data are simultaneously input into the pre-trained machine learning model to obtain control parameter data and state description data.

[0062] Specifically, the pre-trained machine learning model is an end-to-end model, which includes a first output head and a second output head; the first output head is configured to output the state description data based on the preoperative image data, the intraoperative CBCT image, and the process parameter data; the second output head is configured to output the control parameter data based on the preoperative image data, the intraoperative CBCT image, the process parameter data, and the state description data output by the first output head.

[0063] The first output head, based on a convolutional neural network or other visual coding network, extracts spatial features corresponding to preoperative image data and intraoperative CBCT images, outputting state description data. The second output head uses temporal convolution, recurrent neural networks, or self-attention mechanisms to model the changes in bone cement diffusion time in all acquired intraoperative CBCT images, encoding numerical features such as the current delivery rate and pusher pressure to output control parameter data. In other words, the state description data is mainly estimated based on image data, while the delivery rate and pusher pressure serve as auxiliary information, focusing more on inferring the control parameter data.

[0064] S130. Based on the control parameter data, control the injection mechanism to perform bone cement injection or bone cement aspiration operations for the injured vertebra.

[0065] Since the control parameters are quantitative control parameters used to regulate the surgical actions of the bone cement robot, the injection mechanism can be controlled to perform bone cement injection or aspiration operations on the injured vertebra based on these parameters.

[0066] In one embodiment, the control parameter data includes the bone cement delivery direction and the bone cement delivery rate. If the bone cement delivery direction is injection, the injection mechanism is controlled to perform a bone cement injection operation at the current injection site of the injured vertebra, and the injection rate is the same as the bone cement delivery rate. If the bone cement delivery direction is aspiration, the injection mechanism is controlled to perform a bone cement aspiration operation at the current injection site of the injured vertebra, and the aspiration rate is the same as the bone cement delivery rate. In this embodiment, the bone cement robot can automatically determine the bone cement delivery direction and speed, and complete the corresponding bone cement injection or aspiration operation according to the determined bone cement delivery direction and speed.

[0067] Specifically, the delivery direction is indicated by injection and aspiration indicators. When the control parameter data includes the injection indicator, the processor drives the piston of the injection mechanism to advance at a corresponding speed, so that the piston injects bone cement into the current injection site at a delivery speed during the forward movement. When the control parameter data includes the aspiration indicator, the processor drives the piston of the injection mechanism to retract at a corresponding speed, so that the piston aspirates bone cement from the current injection site at a delivery speed during the retraction.

[0068] S140, The control display device displays status description data.

[0069] The processor outputs all determined status description data to the display device, so that the user can understand the surgical progress through the status description data displayed on the display device.

[0070] In this embodiment, the percentage of the injured vertebral height restored to the height of the adjacent vertebra is preferably expressed as a percentage, and the measurement line segments and values ​​are superimposed on the image; the bone cement coverage area, low coverage area and possible mass area are marked by different colors or brightness to help doctors intuitively judge whether the current bone cement diffusion uniformity is ideal; the current extravasation risk score and risk level are indicated by color or text, and dangerous areas near the posterior edge of the vertebral body or venous access are marked on the image.

[0071] The display device also shows one of the injection and aspiration indicators, the current delivery rate, and whether it is in a deceleration state.

[0072] It should be noted that S130 and S140 are preferably configured to be executed in parallel.

[0073] It should be noted that, in this embodiment of the invention, after the user completes the injection site selection and inserts the injection needle into the injured vertebra, the user triggers an injection start command through the controls on the interactive interface; the processor responds to the trigger injection start command and executes the above-described S110-S140. Then, during the bone cement injection process, the control parameter data and status description data are periodically updated based on the latest CBCT image data and process parameter data.

[0074] The technical solution of this invention includes model input data comprising image data and process parameter data for percutaneous kyphoplasty of the target object. The image data includes preoperative image data of a predetermined site on the target object and intraoperative CBCT images at the current moment. The preoperative image data includes CT images and / or X-ray anteroposterior and lateral images of the predetermined site. The process parameter data includes one of the current injection rate and the current aspiration rate, as well as the current injection pressure data. The predetermined site includes the injured vertebra and its adjacent vertebrae. Therefore, the control parameter data and state description data determined by the model based on the image data and process parameter data have high accuracy. Thus, driving the robot to perform bone cement injection or aspiration operations based on the control parameter data ensures high accuracy in these operations. This guarantees a high consistency in the surgical outcome of percutaneous kyphoplasty performed by the user using the surgical robot. Furthermore, the state description data allows the user to monitor the bone cement injection or aspiration process in real time, ensuring its accuracy and further guaranteeing the consistency of the surgical outcome.

[0075] Since the updates to control parameter data and status description data are triggered by the updating of intraoperative CBCT images, these data are updated in stages. Status description data describes the operational effects of completed surgical procedures. This allows users to clearly understand the operational effects of completed surgical procedures up to the end of the previous stage based on the status description data. With reasonable settings for intraoperative CBCT image acquisition timing, users can effectively monitor the surgical progress of the target patient based on the status description data, and ensure surgical safety by taking necessary intervention measures when the status description data is abnormal.

[0076] Intraoperative CBCT images can be set to timed triggering, quantitative triggering, or triggering based on effective duration. Quantitative triggering means that when the amount of bone cement injected or aspirated reaches a predetermined threshold, the CBCT image capture operation is triggered.

[0077] Regarding the use of effective duration to trigger intraoperative CBCT image acquisition: For example, the control parameter data includes an effective duration, which is determined based on a predetermined time interval and the amount of remaining bone cement corresponding to the injection site. Specifically, if the injection time corresponding to the amount of remaining bone cement at injection site A is greater than or equal to the predetermined time interval, then after determining the control parameter data based on the current CBCT image, preoperative imaging data, and process parameter data, the effective duration in the control parameter data is the predetermined time interval. If the injection time corresponding to the amount of remaining bone cement at injection site A is less than the predetermined time interval, then after determining the control parameter data based on the current CBCT image, preoperative imaging data, bone cement data, and process parameter data, the effective duration in the control parameter data is less than the predetermined time interval. In other words, when the processor controls the injection mechanism to perform the injection operation for the effective duration, the intraoperative CBCT image is triggered, and then a new round of control parameter data and status description data prediction begins. This embodiment improves the rationality of intraoperative CBCT image acquisition by triggering intraoperative CBCT image acquisition with an effective duration.

[0078] Based on the aforementioned embodiments, the robot also includes a control terminal located outside the operating room. The control terminal includes a display device and a foot pedal control mechanism. The foot pedal control mechanism is used to generate some or all of the following: emergency stop command, injection command, aspiration command, and trigger command for intraoperative CBCT images. Different commands correspond to different foot pedal triggering methods.

[0079] For example, the foot pedal control mechanism includes a left pedal and a right pedal, each pedal corresponding to a short-pedal trigger mode and a long-pedal trigger mode. These pedal trigger modes correspond one-to-one with the aforementioned commands.

[0080] Figure 2 This is a schematic flowchart illustrating the pre-trained machine learning model method provided in an embodiment of the present invention. The technical solution of this embodiment can be combined with other embodiments; for the same or related parts, descriptions of other embodiments can be used, and will not be repeated here. Figure 2 As shown, the method in this embodiment may specifically include:

[0081] S210. Obtain the training sample set, which includes multiple samples. The samples include preoperative image data, intraoperative CBCT image sequences, process parameter data and labels for the corresponding objects. The labels include state labels for state description data and control labels for control parameter data. The state labels include state description data corresponding to each intraoperative CBCT image in the intraoperative CBCT image sequence, and the control labels include control parameter data at the corresponding time node of each intraoperative CBCT image.

[0082] A sample set is a set of samples used to train a machine learning model. This sample set includes multiple training samples, such as hundreds, thousands, or even more.

[0083] Intraoperative CBCT image sequences include all intraoperative CBCT images acquired during the procedure.

[0084] Since updates to both control parameter data and status description data can be considered to be triggered by intraoperative CBCT images, the status label includes status description data corresponding to each intraoperative CBCT image in the intraoperative CBCT image sequence, while the control label includes control parameter data at the corresponding time node for each CBCT image in the intraoperative CBCT image sequence.

[0085] The status label and control label are both determined based on the analysis results of the training samples.

[0086] S220. Based on the training sample set, the machine learning model is trained to obtain a pre-trained machine learning model.

[0087] The machine learning model is trained based on the training sample set, enabling it to learn the mapping relationship between input data and labels, thereby optimizing the model parameters and obtaining a pre-trained machine learning model.

[0088] In one embodiment, the training sample set includes a training set and a validation set. The parameters of the machine learning model are optimized based on the training set, and the parameters are adjusted based on the validation set to obtain a pre-trained machine learning model.

[0089] In one embodiment, to facilitate the application of the model, the model is integrated into a web platform based on the Shiny application.

[0090] The technical solution of this invention can complete the pre-training of a machine learning model simply and quickly while ensuring the prediction accuracy of the pre-trained machine model.

[0091] Figure 3 This is a schematic diagram of the bone cement robot provided in an embodiment of the present invention. Figure 3 As shown, the bone cement robot includes a display device 310, a robotic arm 320, an injection mechanism 330, and a processor 340. The injection mechanism 330 is disposed at the end of the robotic arm 320; the processor 340 is used to control the injection mechanism 330 according to the method described in any embodiment to perform a bone cement injection operation or a bone cement aspiration operation for the injured vertebra; and the display device 310 displays the status description data determined by the method described in any embodiment.

[0092] An injection mechanism 330 is located at the end of the robotic arm 320 and includes an injection cylinder, a piston disposed within the injection cylinder, and a drive mechanism connected to the piston's drive end. Based on the aforementioned control parameter data, the robot's injection mechanism 330 is controlled to perform either a bone cement injection operation or a bone cement aspiration operation targeting the injured vertebra. For specific control procedures, please refer to the aforementioned embodiments; these will not be elaborated upon here.

[0093] In this embodiment, the robotic arm and the injection mechanism mounted on the robotic arm are located in the operating room, while the control terminal, including the display device, is located in the control room. In the control room, the user understands the surgical progress through the status description data displayed on the display device. When necessary, the user can intervene in the surgical process through the control mechanism in the control terminal, such as pausing the surgery. The control mechanism can be a foot-operated control mechanism to reduce sterilization requirements and facilitate doctors in better responding to emergencies.

[0094] For example, the control mechanism is a foot pedal control mechanism, used to generate some or all of the following: emergency stop command, injection command, aspiration command, and trigger command for intraoperative CBCT images, with different commands corresponding to different pedal triggering methods; the processor responds to the commands generated by the foot pedal control mechanism and controls the corresponding device to perform the corresponding operation. For example, if the foot pedal control mechanism generates an intraoperative CBCT trigger command, the processor responds to the command and controls the CBCT device to acquire CBCT images of a predetermined part of the target object; if the foot pedal control mechanism generates an emergency stop command, the processor responds to the command and stops the injection or aspiration operation of the injection mechanism and / or the scanning operation of the CBCT device.

[0095] The technical solution provided by the embodiments of the present invention controls the injection mechanism to perform bone cement injection or bone cement aspiration operations on the injured vertebra through the control parameter data determined in the aforementioned embodiments, and displays the status description data determined in the aforementioned embodiments through a display device, thereby improving the accuracy and automation level of bone cement robotic surgery, reducing the dependence of percutaneous vertebroplasty on user experience, and improving the consistency of surgical results.

[0096] Based on the aforementioned embodiments, the injection mechanism is an injection cylinder, which consists of two detachable parts: a front cylinder and a rear cylinder. The front and rear cylinders can be detached via a threaded connection. The rear cylinder can be inserted into the front cylinder and is reusable. A lead screw, fixed to the piston, is located inside the rear cylinder and is driven by a motor. The piston end may also optionally be equipped with a stirring paddle. Before injecting the contrast agent using the piston, the stirring paddle can be removed from the piston end; when stirring with the paddle before injecting bone cement is required, the stirring paddle can be installed at the piston end. The piston is movably fixed to the lead screw, and a movable seal exists between the two.

[0097] The rear cylinder contains a nut, a slender lead screw passing through the nut, a piston movably fixed to one end of the lead screw and capable of moving back and forth with it, and an agitator selectively positioned at the end of the piston. The other end of the lead screw is a hollow cavity. A drive motor is located at the rear of the rear cylinder, with its motor shaft inserted into the hollow cavity of the lead screw within the rear cylinder. The nut meshing with the lead screw is fixed inside the rear cylinder. The shape of the motor shaft matches the shape of the hollow cavity of the lead screw, allowing the motor shaft to drive the lead screw to rotate forward and backward. A piston is fixed to the other end of the lead screw, and the agitator is detachably mounted at the front end of the piston. The agitator is fixed to the end of the piston by an insertion and bonding joint. The piston does not rotate with the lead screw but moves back and forth accordingly as the lead screw moves forward and backward. The piston also has two stages of sealing rings. The cross-sectional shape of the space between the motor shaft and the lead screw can be triangular, D-shaped, etc. Furthermore, the length of the cavity in the lead screw needs to be long enough to cover the length required for the motor shaft and lead screw to move forward and backward.

[0098] The drive motor includes a stepper motor, which can be used for both the propulsion and retraction of contrast agents, as well as for the mixing, injection, and aspiration of bone cement.

[0099] The process of motor-assisted injection / aspiration of contrast agent is as follows: A front cylinder containing contrast agent and sealed by an elastic membrane is threadedly installed with a rear cylinder containing a piston, lead screw, and nut. Both cylinders are fixed to a tray. The motor shaft is located inside the cavity of the lead screw in the rear cylinder. No stirring paddle is installed at the front end of the piston. Starting the motor in the forward direction injects the contrast agent, while reversing the motor aspirates the contrast agent, even emptying the injected contrast agent completely. Specifically, when the motor rotates forward, it drives the lead screw to rotate forward, while the nut remains stationary in the rear cylinder. The lead screw rotates forward under the action of the nut, which in turn moves the piston forward, pushing the elastic membrane and its sealed contrast agent into the injection process. When the motor rotates in the reverse direction, it drives the lead screw to rotate in the reverse direction, while the nut remains stationary in the rear cylinder. The lead screw rotates backward under the action of the nut, which in turn moves the piston backward, releasing the elastic membrane and initiating the pull-back process. The contrast agent is then pushed out of the front cylinder until it enters the injured vertebra. After the balloon, inflated with contrast agent, is compressed at the lesion site to create a cavity, a piston is used to pull the flexible membrane back and aspirate the contrast agent back into the pre-canister. Once the contrast agent has been completely aspirated into the pre-canister, the pre-canister containing the contrast agent is removed.

[0100] The process of motor-stirred bone cement and its injection / extraction is as follows: A front cylinder containing bone cement and solution is sealed with a rear cylinder containing a stirring paddle, piston, lead screw, and nut via threads. Both cylinders are fixed to a tray. The motor shaft is inserted into the cavity of the lead screw inside the rear cylinder, with the stirring paddle mounted at the front end of the piston. The motor is started and set to rotate forward for a few seconds and then reverse for a few seconds to fully stir the bone cement. An algorithm determines when the appropriate bone cement viscosity is reached. Once the bone cement viscosity meets the requirements, the motor is set to rotate only forward. When the motor rotates forward, it drives the lead screw to rotate forward, while the nut remains stationary in the rear cylinder. Therefore, the lead screw rotates forward under the action of the nut, which in turn moves the piston at the front end forward, injecting the bone cement into the injured vertebra. If necessary, the motor is set to rotate in reverse. In this case, the motor drives the lead screw to rotate in reverse, while the nut remains stationary in the rear cylinder. Therefore, the lead screw rotates backward under the action of the nut, which in turn moves the piston at the front end backward, achieving the bone cement aspiration operation.

[0101] Figure 4 This is a schematic diagram of the structure of a bone cement robot control device provided in an embodiment of the present invention. This bone cement robot control device can be used to control equipment. Figure 4 As shown, the bone cement robot control device includes: a data acquisition module 410, a data analysis module 420, a control module 430, and a display module 440.

[0102] The data acquisition module 410 is used to acquire image data and process parameter data. The image data includes preoperative image data for a predetermined site of the target object and intraoperative CBCT images at the current time. The preoperative image data includes CT images and / or X-ray anteroposterior and lateral images for the predetermined site. The process parameter data includes one of the current injection rate and the current aspiration rate, as well as the current injection pressure data. The predetermined site includes the injured vertebra and the adjacent vertebrae of the injured vertebra.

[0103] The data analysis module 420 is used to analyze the image data and the process parameter data based on a pre-trained machine learning model to obtain control parameter data and state description data. The state description data is used to describe the operational effect of the completed surgical procedure.

[0104] The control module 430 is used to control the injection mechanism to perform a bone cement injection operation or a bone cement aspiration operation for the injured vertebra according to the control parameter data.

[0105] The display module 440 is used to control the display device to display the status description data.

[0106] The technical solution of this invention includes model input data comprising image data and process parameter data for percutaneous kyphoplasty of the target object. The image data includes preoperative image data of a predetermined site on the target object and intraoperative CBCT images at the current moment. The preoperative image data includes CT images and / or X-ray anteroposterior and lateral images of the predetermined site. The process parameter data includes one of the current injection rate and the current aspiration rate, as well as the current injection pressure data. The predetermined site includes the injured vertebra and its adjacent vertebrae. Therefore, the control parameter data and state description data determined by the model based on the image data and process parameter data have high accuracy. Thus, driving the robot to perform bone cement injection or aspiration operations based on the control parameter data ensures high accuracy in these operations. This guarantees a high consistency in the surgical outcome of percutaneous kyphoplasty performed by the user using the surgical robot. Furthermore, the state description data allows the user to monitor the bone cement injection or aspiration process in real time, ensuring its accuracy and further guaranteeing the consistency of the surgical outcome.

[0107] In one embodiment, the robot includes a robotic arm, the injection mechanism is disposed at the end of the robotic arm, and the control parameter data includes the bone cement delivery direction and the bone cement delivery rate; the control module 430 is used for:

[0108] If the bone cement delivery direction is injection, then the injection mechanism is controlled to perform bone cement injection operation on the current injection site of the injured vertebra, and the injection rate is the bone cement delivery rate.

[0109] If the bone cement delivery direction is suction, then the injection mechanism is controlled to perform a bone cement suction operation on the current injection site of the injured vertebra, and the suction rate is the same as the bone cement delivery rate.

[0110] In one embodiment, the status description data includes the current percentage of vertebral height recovery, the current uniformity of bone cement dispersion, and the current extravasation risk score.

[0111] In one embodiment, the device further includes a prompting module, which is used for:

[0112] When the current extravasation risk score reaches or exceeds the preset extravasation risk threshold, an extravasation warning message is generated and displayed on the display device, and / or the delivery direction is automatically set to the suction direction, and / or the delivery rate is automatically reduced to a preset safe rate.

[0113] In one embodiment, the pre-trained machine learning model is an end-to-end model, which includes a first output head and a second output head;

[0114] The first output head is configured to output the status description data based on the preoperative image data, the intraoperative CBCT image, and the process parameter data;

[0115] The second output head is configured to output the control parameter data based on the preoperative image data, the intraoperative CBCT image, the process parameter data, and the status description data output by the first output head.

[0116] In one embodiment, a training module is further included, which is used for:

[0117] A training sample set is obtained, which includes multiple samples. The samples include the preoperative image data, intraoperative CBCT image sequence, process parameter data and labels of the corresponding object. The labels include state labels about the state description data and control labels about the control parameters. The state labels include the state description data corresponding to each intraoperative CBCT image in the intraoperative CBCT image sequence. The control labels include the control parameter data at the time node corresponding to each CBCT image in the intraoperative CBCT image sequence.

[0118] The machine learning model is trained based on the training sample set to obtain a pre-trained machine learning model.

[0119] The bone cement robot control device provided in the embodiments of the present invention can execute the bone cement robot control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0120] It is worth noting that the various units and modules included in the above-mentioned bone cement robot control device are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the protection scope of the embodiments of the present invention.

[0121] Figure 5 This is a schematic diagram of the structure of a model training device provided in an embodiment of the present invention. This model training device can be used to train a machine learning model. Figure 5 As shown, the model training device includes a sample set acquisition module 510 and a training module 520.

[0122] The sample set acquisition module 510 is used to acquire a training sample set, which includes multiple samples. The samples include the preoperative image data, intraoperative CBCT image sequence, process parameter data and labels of the corresponding object. The labels include state labels about the state description data and control labels about the control parameter data. The state labels include state description data corresponding to each intraoperative CBCT image in the intraoperative CBCT image sequence. The control labels include control parameter data at the corresponding time node of each intraoperative CBCT image.

[0123] The training module 520 is used to train the machine learning model based on the training sample set to obtain a pre-trained machine learning model.

[0124] The technical solution of this invention can complete the pre-training of a machine learning model simply and quickly while ensuring the prediction accuracy of the pre-trained machine model.

[0125] Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the embodiments of the invention described and / or claimed herein.

[0126] like Figure 6 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 may also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0127] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0128] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as bone cement robot control methods.

[0129] In some embodiments, the bone cement robot control method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 10 via read-only memory (ROM) 12 and / or communication unit 19. When the computer program is loaded into random access memory (RAM) 13 and executed by processor 11, one or more steps of the bone cement robot control method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the bone cement robot control method by any other suitable means (e.g., by means of firmware).

[0130] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0131] Computer programs for implementing the bone cement robot control method of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0132] This invention provides a computer-readable storage medium storing computer instructions for causing a processor to execute a bone cement robot control method, including:

[0133] Acquire imaging data and process parameter data. The imaging data includes preoperative imaging data for a predetermined site of the target object and intraoperative CBCT images at the current moment. The preoperative imaging data includes CT images and / or X-ray anteroposterior and lateral images for the predetermined site. The process parameter data includes one of the current injection rate and the current aspiration rate, as well as the current injection pressure data. The predetermined site includes the injured vertebra and the adjacent vertebrae of the injured vertebra.

[0134] The image data and process parameter data are analyzed based on a pre-trained machine learning model to obtain control parameter data and state description data. The state description data is used to describe the operational effect of the completed surgical procedure.

[0135] Based on the control parameter data, the injection mechanism is controlled to perform bone cement injection or bone cement aspiration operations on the injured vertebra.

[0136] Control the display device to display the status description data.

[0137] In the context of embodiments of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0138] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0139] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0140] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0141] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0142] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the bone cement robot control method according to any embodiment of the invention.

[0143] In implementing the computer program product, computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. Programming languages ​​include object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone 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 remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0144] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0145] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for controlling a bone cement robot, characterized in that, A processor for use in a bone cement robot, the bone cement robot further comprising an injection mechanism and a display device, the method comprising: Acquire imaging data and process parameter data. The imaging data includes preoperative imaging data for a predetermined site of the target object and intraoperative CBCT images at the current moment. The preoperative imaging data includes CT images and / or X-ray anteroposterior and lateral images for the predetermined site. The process parameter data includes one of the current injection rate and the current aspiration rate, as well as the current injection pressure data. The predetermined site includes the injured vertebra and the adjacent vertebrae of the injured vertebra. The image data and process parameter data are analyzed based on a pre-trained machine learning model to obtain control parameter data and state description data. The state description data is used to describe the operational effect of the completed surgical procedure. Based on the control parameter data, the injection mechanism is controlled to perform bone cement injection or bone cement aspiration operations on the injured vertebra. Control the display device to display the status description data.

2. The method according to claim 1, characterized in that, The robot includes a robotic arm, and the injection mechanism is disposed at the end of the robotic arm. The control parameter data includes the bone cement delivery direction and the bone cement delivery rate. The step of controlling the injection mechanism to perform a bone cement injection or aspiration operation targeting the injured vertebra based on the control parameter data includes: If the bone cement delivery direction is injection, then the injection mechanism is controlled to perform bone cement injection operation on the current injection site of the injured vertebra, and the injection rate is the bone cement delivery rate. If the bone cement delivery direction is suction, then the injection mechanism is controlled to perform a bone cement suction operation on the current injection site of the injured vertebra, and the suction rate is the same as the bone cement delivery rate.

3. The method according to claim 2, characterized in that, The status description data includes the current percentage of vertebral height recovery, the current uniformity of bone cement dispersion, and the current extravasation risk score.

4. The method according to claim 3, characterized in that, Also includes: When the current extravasation risk score reaches or exceeds the preset extravasation risk threshold, an extravasation warning message is generated, a prompt message corresponding to the extravasation warning message is output, and / or, the delivery direction is automatically set to the suction direction, and / or, the delivery rate is automatically reduced to a preset safe rate.

5. The method according to claim 1, characterized in that, The pre-trained machine learning model is an end-to-end model, which includes a first output head and a second output head; The first output head is configured to output the status description data based on the preoperative image data, the intraoperative CBCT image, and the process parameter data; The second output head is configured to output the control parameter data based on the preoperative image data, the intraoperative CBCT image, the process parameter data, and the status description data output by the first output head.

6. The method according to claim 1, characterized in that, The training of the pre-trained machine learning model is completed through the following steps: A training sample set is obtained, which includes multiple samples. The samples include the preoperative image data, intraoperative CBCT image sequence, process parameter data and labels of the corresponding object. The labels include state labels about the state description data and control labels about the control parameter data. The state labels include the state description data corresponding to each intraoperative CBCT image in the intraoperative CBCT image sequence. The control labels include the control parameter data at the corresponding time node of each intraoperative CBCT image. The machine learning model is trained based on the training sample set to obtain a pre-trained machine learning model.

7. A bone cement robot, characterized in that, include: Display device; robotic arm; An injection mechanism is located at the end of the robotic arm; A processor is configured to control the injection mechanism according to any one of claims 1-6 to perform a bone cement injection operation or a bone cement aspiration operation for the injured vertebra; and to display state description data determined by the method according to any one of claims 1-6 via a display device.

8. The robot according to claim 7, characterized in that, The robot also includes a control terminal located outside the operating room, the control terminal including the display device and the foot pedal control mechanism; The foot pedal control mechanism is used to generate some or all of the emergency stop command, injection command, aspiration command, and trigger command for intraoperative CBCT images, and different commands correspond to different foot pedal triggering methods. The processor responds to the instructions generated by the foot pedal control mechanism and controls the corresponding device to perform the corresponding operation.

9. An electronic device, characterized in that, The electronic device includes: One or more processors; Storage device for storing one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the bone cement robot control method as described in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the bone cement robot control method according to any one of claims 1-6.

Images