Puncture opportunity prediction method and device, computer equipment and storage medium

Abstract

The invention relates to a puncture opportunity prediction method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: for an upcoming next period, acquiring actual breathing waveforms corresponding to a plurality of periods before the next period of a punctured object; inputting the actual breathing waveforms corresponding to the previous plurality of periods into a pre-trained breathing waveform prediction model to obtain a predicted breathing waveform corresponding to the next period; acquiring a target respiration characteristic value of the punctured object; the target respiration characteristic value is a respiration characteristic value of a punctured object when a medical scanning image used for puncture needle passage planning is collected; and in the predicted respiration waveform corresponding to the next period, determining a predicted respiration characteristic value matched with the target respiration characteristic value so as to determine the puncture opportunity in the next period. By adopting the method, the prediction accuracy of the puncture opportunity can be improved.

Description

Technical Field

[0001] The present application relates to the field of medical technology, and in particular to a method, device, computer equipment, storage medium and computer program product for predicting the timing of puncture. Background Art

[0002] Interventional surgery refers to the use of special catheters, guidewires, puncture needles and other precision instruments into the human body under the guidance of medical imaging equipment to diagnose and treat local diseases in the body. Interventional treatment has the characteristics of no surgery, less trauma, quick recovery and good results.

[0003] In the actual interventional surgery, the doctor will use medical images to determine the lesion area, then determine the target point, and determine the final puncture timing based on experience, so as to send the puncture instrument to the target point for surgical treatment. However, when the patient is under anesthesia, his breathing or other physiological activities will cause the target point to deviate from the target point planned by the actual image. Or, because there is a time lag from the imaging of the image to the final execution of the robotic arm, the actual target reached is inconsistent with the theoretical target. In other words, the judgment on the timing of puncture in the relevant technology cannot match the actual situation, resulting in the inability to accurately send the puncture instrument to the target point.

[0004] Therefore, in the related art, there is a problem of inaccurate prediction of the puncture timing during interventional surgery. Summary of the invention

[0005] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for predicting puncture timing, which can improve the prediction accuracy of puncture timing during interventional surgery, in order to address the above technical problems.

[0006] In a first aspect, the present application provides a method for predicting the timing of puncture. The method comprises:

[0007] For the next cycle to come, obtaining the actual breathing waveform of the punctured object corresponding to several cycles before the next cycle;

[0008] Inputting the actual respiratory waveforms corresponding to the first several cycles into a pre-trained respiratory waveform prediction model to obtain a predicted respiratory waveform corresponding to the next cycle;

[0009] Acquiring a target respiratory characteristic value of the punctured object; the target respiratory characteristic value is a respiratory characteristic value of the punctured object when collecting a medical scan image used for puncture needle tract planning;

[0010] In the predicted breathing waveform corresponding to the next cycle, a predicted breathing characteristic value matching the target breathing characteristic value is determined to determine the puncture timing in the next cycle.

[0011] In one embodiment, the step of inputting the actual respiratory waveforms corresponding to the first several cycles into a pre-trained respiratory waveform prediction model to obtain the predicted respiratory waveform corresponding to the next cycle includes:

[0012] Discretize the continuous actual breathing waveforms corresponding to the first several cycles to obtain discrete actual breathing waveforms corresponding to the first several cycles;

[0013] The discrete actual respiratory waveforms corresponding to the first several cycles are input into the pre-trained respiratory waveform prediction model to obtain the predicted respiratory waveform corresponding to the next cycle.

[0014] In one embodiment, the discretization processing of the continuous actual breathing waveform corresponding to the first several cycles to obtain the discrete actual breathing waveform corresponding to the first several cycles includes:

[0015] According to the actual breathing characteristic values ​​corresponding to the discrete time points on the continuous actual breathing waveforms corresponding to the first several periods, the discrete actual breathing waveforms corresponding to the first several periods are obtained.

[0016] In one embodiment, the step of inputting the discrete actual respiratory waveforms corresponding to the first several cycles into the pre-trained respiratory waveform prediction model to obtain the predicted respiratory waveform corresponding to the next cycle includes:

[0017] Inputting the discrete actual respiratory waveforms corresponding to the first several cycles into the pre-trained respiratory waveform prediction model to obtain the discrete predicted respiratory waveform corresponding to the next cycle;

[0018] Interpolation processing is performed on the discrete predicted breathing waveform corresponding to the next cycle to obtain the predicted breathing waveform corresponding to the next cycle.

[0019] In one embodiment, determining a predicted breathing characteristic value matching the target breathing characteristic value in the predicted breathing waveform corresponding to the next cycle to determine the puncture timing in the next cycle includes:

[0020] Acquire a respiratory characteristic value fluctuation range with the target respiratory characteristic value as a fluctuation reference;

[0021] The predicted breathing characteristic value in the predicted breathing waveform corresponding to the next cycle that falls within the breathing characteristic value fluctuation range is used as the predicted breathing characteristic value matching the target breathing characteristic value to determine the puncture timing in the next cycle.

[0022] In one of the embodiments, the method further includes: during the puncture process, when it is detected that the predicted breathing waveform corresponding to the next cycle at the current moment meets the preset breathing abnormality condition, sending an end-puncture instruction to the surgical robot; the end-puncture instruction is used to instruct the surgical robot to stop puncture and perform a needle withdrawal operation.

[0023] In one embodiment, when it is detected that the predicted respiratory waveform corresponding to the next cycle at the current moment meets the preset abnormal respiratory condition, sending an instruction to end the puncture to the surgical robot includes:

[0024] Determining a threshold interval of predicted characteristic values ​​of the predicted respiratory waveform representation;

[0025] When the target respiratory characteristic value is not within the predicted characteristic value threshold interval, the puncture end instruction is sent to the surgical robot.

[0026] In one embodiment, when it is detected that the predicted respiratory waveform corresponding to the next cycle at the current moment meets the preset abnormal respiratory condition, sending an instruction to end the puncture to the surgical robot includes:

[0027] Determine an actual characteristic value threshold interval of an actual respiratory waveform representation corresponding to each cycle in a plurality of cycles before the next cycle, and determine a predicted characteristic value threshold interval of a predicted respiratory waveform representation corresponding to the next cycle;

[0028] Determine the average value of the actual characteristic value threshold interval corresponding to each of the periods to obtain an average actual characteristic value threshold interval;

[0029] When the difference between the predicted characteristic value threshold interval and the average actual characteristic value threshold interval meets a preset difference condition, the puncture end instruction is sent to the surgical robot.

[0030] In one embodiment, when it is detected that the predicted respiratory waveform corresponding to the next cycle at the current moment meets the preset abnormal respiratory condition, sending an instruction to end the puncture to the surgical robot includes:

[0031] When the difference between the predicted cycle duration corresponding to the predicted respiratory waveform corresponding to the next cycle and the actual cycle duration meets a preset difference condition, the puncture end instruction is sent to the surgical robot.

[0032] In a second aspect, the present application also provides a device for predicting the timing of puncture. The device comprises:

[0033] A waveform acquisition module is used to acquire, for the next upcoming cycle, the actual breathing waveform of the punctured object corresponding to several cycles before the next cycle;

[0034] An input module, used to input the actual respiratory waveforms corresponding to the previous several cycles into a pre-trained respiratory waveform prediction model to obtain a predicted respiratory waveform corresponding to the next cycle;

[0035] A characteristic value acquisition module is used to acquire a target breathing characteristic value of the punctured object; the target breathing characteristic value is a breathing characteristic value of the punctured object when a medical scan image used for puncture needle tract planning is collected;

[0036] The determination module is used to determine the predicted breathing characteristic value matching the target breathing characteristic value in the predicted breathing waveform corresponding to the next cycle, so as to determine the puncture timing in the next cycle.

[0037] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0038] For the next cycle to come, obtaining the actual breathing waveform of the punctured object corresponding to several cycles before the next cycle;

[0039] Inputting the actual respiratory waveforms corresponding to the first several cycles into a pre-trained respiratory waveform prediction model to obtain a predicted respiratory waveform corresponding to the next cycle;

[0040] Acquiring a target respiratory characteristic value of the punctured object; the target respiratory characteristic value is a respiratory characteristic value of the punctured object when collecting a medical scan image used for puncture needle tract planning;

[0041] In the predicted breathing waveform corresponding to the next cycle, a predicted breathing characteristic value matching the target breathing characteristic value is determined to determine the puncture timing in the next cycle.

[0042] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0043] For the next cycle to come, obtaining the actual breathing waveform of the punctured object corresponding to several cycles before the next cycle;

[0044] Inputting the actual respiratory waveforms corresponding to the first several cycles into a pre-trained respiratory waveform prediction model to obtain a predicted respiratory waveform corresponding to the next cycle;

[0045] Acquiring a target respiratory characteristic value of the punctured object; the target respiratory characteristic value is a respiratory characteristic value of the punctured object when collecting a medical scan image used for puncture needle tract planning;

[0046] In the predicted breathing waveform corresponding to the next cycle, a predicted breathing characteristic value matching the target breathing characteristic value is determined to determine the puncture timing in the next cycle.

[0047] In a fifth aspect, the present application also provides a surgical execution device. The surgical execution device includes a medical image acquisition device, a respiratory motion acquisition device, a surgical robot and a surgical planning execution workstation; the medical image acquisition device is used to acquire a medical scan image of the punctured object and send it to the surgical planning execution workstation;

[0048] The surgical planning execution workstation is used to plan the puncture needle path according to the medical scan image;

[0049] The respiratory motion acquisition device is used to monitor the respiratory characteristic value of the punctured object when the medical image acquisition device acquires the medical scan image of the punctured object;

[0050] For the next cycle to come, the respiratory motion acquisition device is also used to collect the actual respiratory waveform of the punctured object corresponding to several cycles before the next cycle, and send it to the surgical planning execution workstation;

[0051] The surgical planning execution workstation is used to input the actual respiratory waveforms corresponding to the previous several cycles into the pre-trained respiratory waveform prediction model to obtain the predicted respiratory waveform corresponding to the next cycle;

[0052] The surgical planning execution workstation is further used to use the respiratory characteristic value of the punctured object as the target respiratory characteristic value when acquiring the medical scan image of the punctured object, and determine the predicted respiratory characteristic value matching the target respiratory characteristic value in the predicted respiratory waveform corresponding to the next cycle, so as to determine the puncture timing in the next cycle;

[0053] The surgical planning execution workstation is further used to send a puncture instruction to the surgical robot when the puncture opportunity arrives;

[0054] The surgical robot is used to control the robotic arm to perform the puncture operation according to the puncture instruction.

[0055] In one embodiment, the surgical planning execution workstation is also used to execute the steps of implementing the above method.

[0056] The above-mentioned prediction method, device, computer equipment, storage medium and surgical execution equipment for puncture timing, since the most intuitive feature for predicting breathing is the breathing waveform, therefore, for the upcoming next cycle, the actual breathing waveforms corresponding to the previous several cycles of the next cycle of the punctured object are obtained; then, the actual breathing waveforms corresponding to the previous several cycles are input into the pre-trained breathing waveform prediction model, so that the predicted breathing waveform corresponding to the next cycle can be obtained more accurately; then, the target breathing characteristic value of the punctured object is obtained; wherein the target breathing characteristic value is the breathing characteristic value of the punctured object when the medical scanning image used for puncture needle track planning is collected; then, the target breathing characteristic value is compared with the predicted breathing characteristic value in the predicted breathing waveform corresponding to the next cycle. By matching the eigenvalues, a predicted respiratory eigenvalue matching the target respiratory eigenvalue can be determined to determine the puncture timing in the next cycle. In this way, since the punctured object is in a steady breathing state when the medical scanning image used for puncture needle track planning is collected, that is, the target respiratory eigenvalue is the respiratory eigenvalue of the punctured object in a steady breathing state, therefore, when the puncture timing is predicted by the predicted respiratory eigenvalue matching the target respiratory eigenvalue, the respiratory state of the punctured object is closer to the steady breathing state, so that when the puncture object is punctured according to the puncture timing, the target point actually reached by the interventional instrument can be closer to the target target point. Therefore, predicting the puncture timing by the above method can effectively improve the prediction accuracy of the puncture timing. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 A schematic diagram of a flow chart of a method for predicting puncture timing in one embodiment;

[0058] Figure 2 is a schematic diagram of a respiratory motion state waveform diagram in one embodiment;

[0059] Figure 3 A schematic diagram of the structure of a BP neural network model in one embodiment;

[0060] Figure 4 A schematic diagram of a training process of a BP neural network model in an embodiment;

[0061] Figure 5 A schematic diagram of a flow chart of a method for predicting puncture timing in another embodiment;

[0062] Figure 6 It is a structural schematic diagram of a surgical execution device in one embodiment;

[0063] Figure 7 A schematic diagram of a flow chart of another method for predicting puncture timing in one embodiment;

[0064] Figure 8It is a structural block diagram of a device for predicting puncture timing in one embodiment;

[0065] Fig. 9 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0066] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0067] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of devices and methods consistent with some aspects of the present disclosure as detailed in the appended claims.

[0068] In one embodiment, Figure 1 As shown, a method for predicting the timing of puncture is provided. This embodiment uses the method applied to a computer device as an example for illustration. It is understandable that the method can also be applied to a server. The computer device can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers, etc. The server can be implemented as an independent server or a server cluster composed of multiple servers. In this embodiment, the method includes the following steps:

[0069] Step S110, for the upcoming next cycle, obtain the actual breathing waveform of the punctured object corresponding to several cycles before the next cycle.

[0070] The upcoming next cycle is based on the current moment, and the duration of a breathing cycle experienced after the current moment can be used as the upcoming next cycle. For example, the current moment is 4.1s (seconds), the duration of the breathing cycle is 1s, and the upcoming next cycle is 4.1s~5.1s. Then, the first three cycles of the punctured object in the next cycle can be 3.1s~4.1s, 2.1s~3.1s, and 1.1s~2.1s. It can be understood that the number of the first several cycles is not limited to three, and can also be other numbers.

[0071] In the specific implementation, the most intuitive feature for predicting breathing is the respiratory waveform. During the operation, the respiratory waveform of the punctured object can be collected in real time through the respiratory movement acquisition device, and the respiratory waveform is sent to the computer device. In this way, for the upcoming next cycle, the computer device can obtain the respiratory waveform of the punctured object corresponding to the previous several cycles of the next cycle as the actual respiratory waveform corresponding to the previous several cycles.

[0072] Step S120, inputting the actual respiratory waveforms corresponding to the previous several cycles into the pre-trained respiratory waveform prediction model to obtain the predicted respiratory waveform corresponding to the next cycle.

[0073] In a specific implementation, the computer device can input the actual breathing waveforms corresponding to the first several cycles into a pre-trained breathing waveform prediction model, so as to predict the breathing waveform corresponding to the next cycle as the predicted breathing waveform corresponding to the next cycle.

[0074] It is understandable that, because the duration of the breathing cycle of the punctured object actually varies to a certain extent, the duration of the breathing cycle is not fixed. For example, if the current time is 4.5s, the first three cycles of the punctured object in the next cycle may be 0s-1.6s, 1.6s-3.1s, and 3.1s-4.5s, and the predicted cycle duration (duration of the breathing cycle) corresponding to the predicted breathing waveform corresponding to the next cycle predicted by the model is 1.5s, that is, the next cycle predicted by the model is 4.5s-6s.

[0075] Step S130, obtaining the target breathing characteristic value of the punctured object.

[0076] The target respiratory characteristic value is the respiratory characteristic value of the punctured object when the medical scan image used for puncture needle tract planning is collected.

[0077] The breathing characteristic value includes a value that can represent breathing, that is, a value that can truly reflect the breathing waveform. The breathing waveform corresponding to the breathing characteristic value is a sine wave. The breathing characteristic value may include, but is not limited to, a breathing pressure value, a breathing flow rate value, and the like.

[0078] The medical scan images may include but are not limited to CT (Computed Tomography) images, MR (Magnetic Resonance) images, ultrasonic images and other medical images.

[0079] Among them, medical scanning images can also be named as preoperative images in practical applications.

[0080] In a specific implementation, before the operation, the computer device can obtain the respiratory characteristic value of the punctured object when collecting the medical scanning image used for the puncture needle tract planning for the puncture object, as the target respiratory characteristic value of the punctured object. Specifically, the respiratory characteristic value of the punctured object during the preoperative image scan can be collected by the respiratory motion acquisition device. During the preoperative image scan, the punctured object will be required to hold his breath, that is, the punctured object is in a stable breathing state at this time. At this time, the respiratory characteristic value measured by the respiratory motion acquisition device is recorded as the target respiratory characteristic value. For different punctured objects or different scanning devices, this target respiratory characteristic value is not a fixed value, but it is necessary to ensure that the target respiratory characteristic value during the preoperative image scan matches the respiratory characteristic value during the puncture.

[0081] In actual application, when the punctured subject inhales and holds his breath in a normal state, the amount of air inhaled is the maximum value (that is, the respiratory pressure value is the maximum value, and this maximum respiratory pressure value is the maximum pressure of the chest pressure strap when collecting data), and the respiratory flow rate value is 0 when the punctured subject exhales all the air and inhales fully. The target respiratory characteristic value used to predict the puncture timing obtained by the puncture timing prediction method can theoretically be any value under the stable breathing state.

[0082] After the computer device obtains the medical scan image through the preoperative image scan, the user can make a surgical plan on the medical scan image and use the surgical plan as a reference during the operation. The surgical plan can be the planning of the puncture needle tract in surgical procedures such as puncture biopsy and particle implantation. After the planning is completed, the surgical process can begin.

[0083] Step S140, determining the predicted breathing characteristic value matching the target breathing characteristic value in the predicted breathing waveform corresponding to the next cycle, so as to determine the puncture timing in the next cycle.

[0084] In a specific implementation, during the operation, the computer device can match the target breathing characteristic value with the predicted breathing characteristic value in the predicted breathing waveform corresponding to the next cycle, so that the predicted breathing characteristic value that matches the target breathing characteristic value can be determined in the predicted breathing waveform corresponding to the next cycle, and then the puncture timing can be determined in the next cycle through the time point corresponding to the matched predicted breathing characteristic value in the next cycle, so that when the current moment is the puncture timing, the puncture instruction is sent to the surgical robot to start the puncture.

[0085] In the above-mentioned prediction method of puncture timing, since the most intuitive feature for predicting breathing is the breathing waveform, for the upcoming next cycle, the actual breathing waveforms corresponding to the previous several cycles of the next cycle of the punctured object are obtained; then, the actual breathing waveforms corresponding to the previous several cycles are input into the pre-trained breathing waveform prediction model, so that the predicted breathing waveform corresponding to the next cycle can be obtained more accurately; then, the target breathing characteristic value of the punctured object is obtained; wherein the target breathing characteristic value is the breathing characteristic value of the punctured object when the medical scanning image used for puncture needle track planning is collected; wherein, when the medical scanning image used for puncture needle track planning is collected, the punctured object is in a stable breathing state; then, the target breathing characteristic value is compared with the predicted breathing waveform corresponding to the next cycle. By matching the predicted breathing characteristic value in the shape, the predicted breathing characteristic value matching the target breathing characteristic value can be determined to determine the puncture timing in the next cycle. In this way, since the punctured object is in a steady breathing state when the medical scanning image used for puncture needle track planning is acquired, that is, the target breathing characteristic value is the breathing characteristic value of the punctured object in the steady breathing state, therefore, when the puncture timing is predicted by the predicted breathing characteristic value matching the target breathing characteristic value, the breathing state of the punctured object is closer to the steady breathing state, so that when the punctured object is punctured according to the puncture timing, the target point actually reached by the interventional instrument can be closer to the target target point. Therefore, predicting the puncture timing by the above method can effectively improve the prediction accuracy of the puncture timing.

[0086] In one embodiment, the actual breathing waveforms corresponding to the first several cycles are input into a pre-trained breathing waveform prediction model to obtain a predicted breathing waveform corresponding to the next cycle, including: discretizing the continuous actual breathing waveforms corresponding to the first several cycles to obtain discrete actual breathing waveforms corresponding to the first several cycles; inputting the discrete actual breathing waveforms corresponding to the first several cycles into a pre-trained breathing waveform prediction model to obtain a predicted breathing waveform corresponding to the next cycle.

[0087] The continuous actual breathing waveform can be represented by a breathing motion state waveform diagram, where the horizontal axis of the breathing motion state waveform diagram is time and the vertical axis is the breathing characteristic value. Figure 2 A schematic diagram of a respiratory motion state waveform diagram is provided when the respiratory characteristic value is the respiratory pressure value. Figure 2 The respiratory pressure value corresponding to the dotted line in is the respiratory pressure value of the punctured object when collecting the medical scan image, that is, the target respiratory pressure value.

[0088] In a specific implementation, when the computer device inputs the actual breathing waveform corresponding to the previous several cycles into the pre-trained breathing waveform prediction model to obtain the predicted breathing waveform corresponding to the next cycle, the computer device can discretize the continuous actual breathing waveform corresponding to the previous several cycles to obtain the discrete actual breathing waveform corresponding to the previous several cycles. Specifically, after discretizing the corresponding continuous actual breathing waveform for a certain cycle in the previous several cycles, each discrete time point and the actual breathing characteristic value corresponding to each discrete time point on the continuous actual breathing waveform can be obtained. Therefore, a group of discrete time points and actual breathing characteristic values ​​corresponding to the cycle will be used as the discrete actual breathing waveform of the cycle. In this way, by the same method, the continuous actual breathing waveform corresponding to each cycle in the previous several cycles is discretized to obtain the discrete actual breathing waveform corresponding to each cycle in the previous several cycles, so as to obtain the discrete actual breathing waveform corresponding to the previous several cycles.

[0089] For example, assuming that the current moment is 2.5s, the duration of the breathing cycle is 1s, a certain cycle is 1.5s to 2.5s, and one cycle is discretized into 11 discrete time points (the number of discrete time points can also be other numbers, which is not specifically limited here), then, after discretization of the continuous actual breathing waveform corresponding to the cycle, we can obtain discrete time points such as 1.5s, 1.6s, 1.7s, 1.8s, 1.9s, 2.0s, 2.1s, 2.2s, 2.3s, 2.4s, and 2.5s, as well as the actual breathing characteristic values ​​corresponding to these discrete time points on the continuous actual breathing waveform corresponding to the cycle of 1.5s to 2.5s. Then, the above discrete time points and the corresponding actual breathing characteristic values ​​will be used as the discrete actual breathing waveform of the cycle of 1.5s to 2.5s.

[0090] Then, the computer device inputs the discrete actual breathing waveforms corresponding to the previous several cycles into the pre-trained breathing waveform prediction model, and can obtain the predicted breathing waveform corresponding to the next cycle.

[0091] The technical solution of this embodiment is to obtain discrete actual breathing waveforms corresponding to the first several cycles by discretizing the continuous actual breathing waveforms corresponding to the first several cycles; the discrete actual breathing waveforms corresponding to the first several cycles are input into a pre-trained breathing waveform prediction model, which can quickly and accurately predict the predicted breathing waveform corresponding to the next cycle based on the historical breathing waveform data.

[0092] In one embodiment, the discrete actual breathing waveforms corresponding to the first several cycles are input into a pre-trained breathing waveform prediction model to obtain a predicted breathing waveform corresponding to the next cycle, including: inputting the discrete actual breathing waveforms corresponding to the first several cycles into a pre-trained breathing waveform prediction model to obtain a discrete predicted breathing waveform corresponding to the next cycle; interpolating the discrete predicted breathing waveform corresponding to the next cycle to obtain a predicted breathing waveform corresponding to the next cycle.

[0093] In a specific implementation, when a computer device inputs the discrete actual breathing waveforms corresponding to the previous several cycles into a pre-trained breathing waveform prediction model to obtain a predicted breathing waveform corresponding to the next cycle, the computer device can input the discrete actual breathing waveforms corresponding to the previous several cycles into a pre-trained breathing waveform prediction model to obtain a discrete predicted breathing waveform corresponding to the next cycle. Then, the computer device can interpolate the discrete predicted breathing waveform corresponding to the next cycle to obtain a complete continuous breathing waveform as the predicted breathing waveform corresponding to the next cycle.

[0094] The technical solution of this embodiment is to input the discrete actual breathing waveforms corresponding to the previous several cycles into a pre-trained breathing waveform prediction model to obtain a discrete predicted breathing waveform corresponding to the next cycle; interpolation processing is performed on the discrete predicted breathing waveform corresponding to the next cycle to obtain a predicted breathing waveform corresponding to the next cycle; in this way, a complete continuous breathing waveform corresponding to the next cycle can be obtained, so that the puncture timing can be more accurately determined in the complete continuous breathing waveform corresponding to the next cycle.

[0095] In one embodiment, in the predicted breathing waveform corresponding to the next cycle, a predicted breathing characteristic value that matches the target breathing characteristic value is determined to determine the puncture timing in the next cycle, including: obtaining a breathing characteristic value fluctuation range with the target breathing characteristic value as a fluctuation reference; using the predicted breathing characteristic value that falls within the breathing characteristic value fluctuation range in the predicted breathing waveform corresponding to the next cycle as the predicted breathing characteristic value that matches the target breathing characteristic value to determine the puncture timing in the next cycle.

[0096] In a specific implementation, the computer device determines the predicted breathing characteristic value that matches the target breathing characteristic value in the predicted breathing waveform corresponding to the next cycle, so as to determine the puncture timing in the next cycle. The computer device can obtain the breathing characteristic value fluctuation range with the target breathing characteristic value as the fluctuation benchmark, and use the predicted breathing characteristic value that falls into the breathing characteristic value fluctuation range in the predicted breathing waveform corresponding to the next cycle as the predicted breathing characteristic value that matches the target breathing characteristic value, so as to determine the puncture timing in the next cycle through the matched predicted breathing characteristic value, and when the current moment is the puncture timing, the computer device sends a puncture instruction to the surgical robot to start the puncture.

[0097] The technical solution of this embodiment is to obtain a respiratory characteristic value fluctuation range with the target respiratory characteristic value as the fluctuation reference; then, the predicted respiratory characteristic value that falls within the respiratory characteristic value fluctuation range in the predicted respiratory waveform corresponding to the next cycle is used as the predicted respiratory characteristic value that matches the target respiratory characteristic value. In this way, a predicted respiratory characteristic value that is consistent with the target respiratory characteristic value corresponding to the punctured object in a stable breathing state can be determined in the predicted respiratory waveform corresponding to the next cycle, so that the puncture timing can be determined in the next cycle according to the time point corresponding to the predicted respiratory characteristic value in the next cycle, so that when the punctured object is punctured according to the predicted puncture timing, the breathing state of the punctured object is closer to the stable breathing state, thereby reducing the impact of organ deformation caused by breathing during puncture, making the puncture more accurate.

[0098] In one embodiment, the method also includes: during the puncture process, when it is detected that the predicted breathing waveform corresponding to the next cycle meets the preset breathing abnormality condition, sending an end-puncture instruction to the surgical robot; the end-puncture instruction is used to instruct the surgical robot to stop puncture and perform the needle withdrawal operation.

[0099] In the specific implementation, the doctor usually takes certain fixed measures on the punctured object to prevent the displacement of the punctured object during the operation, which affects the accuracy of the operation and ensures the safety of the operation. However, it does not rule out the possibility that the punctured object may experience violent coughing and pain caused by accidents. Therefore, during the puncture, the respiratory motion acquisition device will still collect the respiratory waveform and send it to the computer device to perform dynamic and real-time respiratory waveform prediction, that is, the computer device will predict the respiratory waveform of the next cycle at each moment. When there is a drastic respiratory change that causes a strong inconsistency between the actual respiratory characteristic value and the predicted respiratory waveform, the computer device will determine that the predicted respiratory waveform corresponding to the next cycle meets the preset respiratory abnormality condition, that is, the puncture abnormality occurs, and the computer device will send an end puncture instruction to the surgical robot, and instruct the surgical robot to stop puncture and perform the needle withdrawal operation through the end puncture instruction.

[0100] The technical solution of this embodiment is to send a puncture end instruction to the surgical robot when it is detected that the predicted breathing waveform corresponding to the next cycle meets the preset breathing abnormality condition during the puncture process; the puncture end instruction is used to instruct the surgical robot to stop puncture and perform the needle withdrawal operation; in this way, the safety of the puncture process can be improved.

[0101] In one embodiment, when it is detected that the predicted respiratory waveform corresponding to the next cycle at the current moment meets the preset respiratory abnormality condition, an instruction to end the puncture is sent to the surgical robot, including: determining a predicted characteristic value threshold interval represented by the predicted respiratory waveform; when the target respiratory characteristic value is not within the predicted characteristic value threshold interval, sending an instruction to end the puncture to the surgical robot.

[0102] In a specific implementation, when the computer device detects that the predicted breathing waveform corresponding to the next cycle at the current moment meets the preset breathing abnormality condition, while sending an end-puncture instruction to the surgical robot, the computer device can determine the predicted characteristic value threshold interval represented by the predicted breathing waveform according to the maximum predicted breathing characteristic value and the minimum predicted breathing characteristic value in the predicted breathing waveform corresponding to the next cycle during the puncture process, and when the target breathing characteristic value is not within the predicted characteristic value threshold interval, it is determined that there is a strong inconsistency between the actual breathing characteristic value and the predicted breathing waveform, that is, when it is detected that the predicted breathing waveform corresponding to the next cycle meets the preset breathing abnormality condition, the computer device sends an end-puncture instruction to the surgical robot.

[0103] The technical solution of this embodiment is to determine the predicted characteristic value threshold interval of the predicted respiratory waveform representation; when the target respiratory characteristic value is not within the predicted characteristic value threshold interval, send an end-puncture instruction to the surgical robot; in this way, by comparing with the target respiratory characteristic value, it is possible to accurately determine whether the punctured object has abnormal breathing, and thus send an end-puncture instruction in an abnormal situation to effectively improve the safety of the puncture process.

[0104] In one embodiment, when it is detected that the predicted breathing waveform corresponding to the next cycle at the current moment meets the preset breathing abnormality condition, an instruction to end the puncture is sent to the surgical robot, including: determining the actual characteristic value threshold interval of the actual breathing waveform representation corresponding to each cycle in the first several cycles of the next cycle, and determining the predicted characteristic value threshold interval of the predicted breathing waveform representation corresponding to the next cycle; determining the average value of the actual characteristic value threshold interval corresponding to each cycle to obtain the average actual characteristic value threshold interval; when the difference between the predicted characteristic value threshold interval and the average actual characteristic value threshold interval meets the preset difference condition, sending an instruction to end the puncture to the surgical robot.

[0105] In a specific implementation, when the computer device detects that the predicted breathing waveform corresponding to the next cycle at the current moment meets the preset breathing abnormality condition, while sending the puncture end instruction to the surgical robot, the computer device can determine the actual characteristic value threshold interval of the actual breathing waveform representation corresponding to each cycle in the first several cycles of the next cycle during the puncture process, and determine the predicted characteristic value threshold interval of the predicted breathing waveform representation corresponding to the next cycle; then, according to the average value of the actual characteristic value threshold interval corresponding to each cycle in the first several cycles, determine the average actual characteristic value threshold interval; then, compare the predicted characteristic value threshold interval with the average actual characteristic value threshold interval, and when the difference between the predicted characteristic value threshold interval and the average actual characteristic value threshold interval meets the preset difference condition, it is determined that the actual breathing characteristic value is strongly inconsistent with the predicted breathing waveform, that is, it is detected that the predicted breathing waveform corresponding to the next cycle meets the preset breathing abnormality condition, and then send the puncture end instruction to the surgical robot.

[0106] The technical solution of this embodiment is to determine the actual characteristic value threshold interval of the actual breathing waveform characterization corresponding to each cycle in the first several cycles of the next cycle, and determine the predicted characteristic value threshold interval of the predicted breathing waveform characterization corresponding to the next cycle; determine the average value of the actual characteristic value threshold interval corresponding to each cycle to obtain the average actual characteristic value threshold interval; when the difference between the predicted characteristic value threshold interval and the average actual characteristic value threshold interval meets the preset difference condition, send an end puncture instruction to the surgical robot; in this way, when the predicted breathing waveform obtained based on the actual breathing waveform corresponding to the first several cycles has a large difference from the actual breathing waveform corresponding to the first several cycles, it is determined that the puncture object has abnormal breathing, and then send an end puncture instruction to effectively improve the safety of the puncture process.

[0107] In one embodiment, when it is detected that the predicted breathing waveform corresponding to the next cycle at the current moment meets the preset breathing abnormality condition, an instruction to end the puncture is sent to the surgical robot, including: when the difference between the predicted cycle duration corresponding to the predicted breathing waveform corresponding to the next cycle and the actual cycle duration meets the preset difference condition, an instruction to end the puncture is sent to the surgical robot.

[0108] In a specific implementation, when the computer device detects that the predicted breathing waveform corresponding to the next cycle at the current moment meets the preset breathing abnormality condition, while sending an end-puncture instruction to the surgical robot, the computer device can determine the predicted cycle duration corresponding to the predicted breathing waveform corresponding to the next cycle. When the difference between the predicted cycle duration corresponding to the next cycle and the actual cycle duration meets the preset difference condition, it is determined that there is a strong mismatch between the actual breathing characteristic value and the predicted breathing waveform, that is, when it is detected that the predicted breathing waveform corresponding to the next cycle meets the preset breathing abnormality condition, the end-puncture instruction is sent to the surgical robot.

[0109] Specifically, when the difference between the predicted cycle duration corresponding to the next cycle and the actual cycle duration is greater than a preset cycle change threshold, it is determined that the difference between the predicted cycle duration and the actual cycle duration meets the preset difference condition.

[0110] For example, if the current moment is 4.5s, the first several cycles of the punctured object in the next cycle can be 0s-1.6s, 1.6s-3.1s, 3.1s-4.5s. If the actual respiratory waveforms corresponding to the first several cycles are input into the pre-trained respiratory waveform prediction model, the predicted next cycle is 4.5-6s. If the next cycle is 4.5-5.5s in reality, then the predicted cycle duration corresponding to the next cycle is 1.5s, and the actual cycle duration corresponding to the next cycle is 1s. The difference between the predicted cycle duration and the actual cycle duration is 1.5s-1s=0.5s. If the preset cycle change threshold is 0.3s, since the difference of 0.5s is greater than 0.3s, it is determined that the difference between the above-mentioned predicted cycle duration and the actual cycle duration meets the preset difference condition, that is, it is detected that the predicted respiratory waveform corresponding to the next cycle meets the preset respiratory abnormality condition, and the puncture end instruction is sent to the surgical robot.

[0111] The technical solution of the present embodiment sends a puncture end instruction to the surgical robot when the difference between the predicted cycle duration corresponding to the predicted respiratory waveform corresponding to the next cycle and the actual cycle duration meets the preset difference condition; in this way, by comparing the predicted cycle duration obtained based on the historical respiratory waveform data with the actual cycle duration, it is possible to accurately determine whether the punctured object has abnormal breathing, and thus send a puncture end instruction in an abnormal situation to effectively improve the safety of the puncture process.

[0112] In one embodiment, the method also includes: using the period corresponding to the actual breathing sample waveform used as a label as the label period; training the breathing waveform prediction model to be trained according to the actual breathing sample waveforms corresponding to the first several periods of the label period and the actual breathing sample waveforms corresponding to the label period to obtain a pre-trained breathing waveform prediction model.

[0113] The respiratory waveform prediction model to be trained may be a BP neural network model.

[0114] In a specific implementation, before predicting the puncture timing, the computer device may obtain actual breathing waveforms of several punctured sample objects as actual breathing sample waveforms to form an actual breathing sample waveform set. Then, the computer device may use the actual breathing sample waveform set as the period corresponding to the actual breathing sample waveform of the label as the label period, and train the breathing waveform prediction model to be trained according to the actual breathing sample waveforms corresponding to the first several periods of the label period and the actual breathing sample waveform corresponding to the label period to obtain a pre-trained breathing waveform prediction model.

[0115] Among them, the structure diagram of a typical three-layer BP neural network model is as follows Figure 3 As shown, X1, X2, X3, X4 are input layer neurons, W1, W2, W3, W4 are hidden layer neurons, and Y1 is the output.

[0116] When designing a BP neural network model, the accuracy of the results and the prediction time of the model should be taken into account. Therefore, the following aspects need to be considered:

[0117] 1. Selection and preprocessing of input features. The validity of the input feature values ​​determines the accuracy of the model to a certain extent. Although a large number of input features will improve the accuracy, it will inevitably reduce the prediction efficiency of the model. Therefore, it is necessary to find the most suitable effective input features. Sometimes such features are not obvious. At this time, it is necessary to preprocess the original data to obtain more effective features.

[0118] 2. During training, the number of training times needs to be controlled to avoid overfitting of the neural network model caused by too many training times for the current data set and underfitting of the neural network model caused by too few training times for the data set.

[0119] 3. When adjusting parameters, use methods such as grid search to adjust hyperparameters such as learning rate, number of hidden layers, activation function, etc., and find the optimal hyperparameter configuration under the current input characteristics while avoiding underfitting and overfitting.

[0120] 4. Finally, when evaluating the design of a neural network, it is necessary to consider the accuracy of the model, as well as the prediction time and computer resource usage, which are very important for real-time systems. In addition, there are factors such as training costs that need to be considered. Taking all of the above into consideration, the optimal input features and the optimal hyperparameter configuration under the input features are obtained.

[0121] The selection of input features and the adjustment of hyperparameters of the BP neural network algorithm not only ensure the time efficiency of the algorithm, but also save surgical time. In addition, the simplification of parameters can greatly reduce its occupation of computer resources.

[0122] Wherein, according to the actual breathing sample waveform corresponding to the first several cycles of the label cycle and the actual breathing sample waveform corresponding to the label cycle, the breathing waveform prediction model to be trained is trained to obtain the pre-trained breathing waveform prediction model, including: the computer device inputs the actual breathing sample waveform corresponding to the first several cycles of the label cycle into the breathing waveform prediction model to be trained for forward propagation to obtain the predicted breathing sample waveform corresponding to the label cycle; according to the difference between the predicted breathing sample waveform corresponding to the label cycle and the corresponding actual breathing sample waveform, the model parameters of the breathing waveform prediction model to be trained are updated by back propagation to obtain the pre-trained breathing waveform prediction model. Wherein, when the model parameters are updated, the weights (weights) of the connections between each neuron are updated.

[0123] In order to facilitate the understanding of those skilled in the art, Figure 4 A training process diagram of a BP neural network model is provided, such as Figure 4 As shown, the actual breathing sample waveform is a discrete actual breathing sample waveform. The computer device can use the discrete actual breathing sample waveforms corresponding to the first several periods of the label period, such as the discrete actual breathing sample waveforms corresponding to the first three periods (including one-to-one corresponding discrete time points and actual breathing sample feature values) as the input features of the BP neural network. The output of the BP neural network is the discrete predicted breathing sample waveform corresponding to the label period. The discrete predicted breathing sample waveform is interpolated to obtain a complete predicted breathing waveform corresponding to the label period as the predicted breathing sample waveform corresponding to the label period. According to the difference between the predicted breathing sample waveform corresponding to the label period and the corresponding actual breathing sample waveform, back propagation is used to determine the response error of the hidden layer and the output layer of the BP neural network. The weights of each neuron of the BP neural network are updated through back propagation. Finally, the training is stopped when the training requirements are met to obtain a pre-trained breathing waveform prediction model.

[0124] Among them, the input features may not be limited to the discrete actual breathing sample waveforms corresponding to the first three cycles, but more input features will lead to lower efficiency of the neural network, and it is necessary to find a balance between the number of input features and the efficiency of the neural network.

[0125] In actual applications, when a computer device is determining an actual breathing sample waveform as a label, the computer device can obtain discrete original breathing sample waveforms corresponding to several punctured sample objects acquired by a respiratory motion acquisition device; then, the discrete original breathing sample waveforms are screened to obtain an actual breathing sample waveform set; then, the computer device can determine the actual breathing sample waveform as a label in the actual breathing sample waveform set.

[0126] Among them, in the process of the computer device screening the discrete original breathing sample waveform to obtain the actual breathing sample waveform set, the computer device can screen out the sample waveform that meets the data invalidity condition in the discrete original breathing sample waveform to obtain the screened discrete original breathing sample waveform; for example, invalid sample waveform data caused by incorrect wearing of the respiratory movement acquisition device can be screened out; then, the computer device can pre-process the screened discrete original breathing sample waveform (such as data shearing processing) to obtain the processed discrete original breathing sample waveform; then, the computer device can classify the processed discrete original breathing sample waveform according to the sample waveform acquisition scenario, and obtain the actual breathing sample waveform set based on the classified discrete original breathing sample waveform for training the BP neural network model.

[0127] The processed discrete raw breathing sample waveforms can be classified into different scenarios such as normal conditions and surgical conditions, making the distribution of training data more reasonable. When training the model, a part of the data set will be selected for training. When there is too much data in the normal condition, the model will have a poor prediction effect on the surgical condition, and vice versa. Therefore, it is necessary to classify the scenarios and obtain a balance of input data.

[0128] Among them, during the training process, the actual breathing sample waveform set can be reasonably divided into a training set, a test set and a validation set. After the actual breathing sample waveform set is reasonably divided into a training set, a test set and a validation set, the computer equipment can design a suitable BP neural network model based on the actual situation. Roughly confirm the hyperparameters such as the input layer neurons, the number of hidden layer neurons, the number of hidden layer layers and the learning rate of the model. Then, use the training set to train the model, and use the test set to test the training results. According to the test results, adjust the hyperparameters to obtain the best test results. Then, use the validation set to verify the model obtained in the previous step, and obtain the accuracy, time consumption and other evaluation criteria under the validation set to evaluate the model. Finally, integrate the final neural network model into the application to predict the timing of puncture.

[0129] The technical solution of this embodiment uses the BP neural network to predict the optimal puncture time in real time, changing the traditional puncture timing judgment method from the doctor's subjective judgment to the actual respiratory waveform collected by the respiratory motion acquisition device by the surgical robot for active prediction, completing the prerequisite for the automation of the puncture process of the interventional surgical robot. The application of the BP neural network learning algorithm can quickly, accurately and robustly predict the optimal puncture time based on the actual respiratory waveform corresponding to the previous several cycles. By predicting the puncture time in advance, not only can the precision and accuracy of the puncture be improved, but also the foundation can be laid for the automation of the puncture action process.

[0130] In another embodiment, Figure 5 As shown, a method for predicting the timing of puncture is provided, which is described by taking the method applied to a computer device as an example, and includes the following steps:

[0131] Step S502, for the next cycle to come, obtaining the continuous actual breathing waveforms corresponding to the first several cycles of the next cycle of the punctured object;

[0132] Step S504, discretizing the continuous actual breathing waveforms corresponding to the first several cycles to obtain discrete actual breathing waveforms corresponding to the first several cycles;

[0133] Step S506, inputting the discrete actual breathing waveforms corresponding to the previous several cycles into the pre-trained breathing waveform prediction model to obtain the discrete predicted breathing waveform corresponding to the next cycle;

[0134] Step S508, interpolating the discrete predicted breathing waveform corresponding to the next cycle to obtain the predicted breathing waveform corresponding to the next cycle;

[0135] Step S510, obtaining a respiratory characteristic value fluctuation range of a target respiratory characteristic value of the punctured subject as a fluctuation reference;

[0136] Step S512, taking the predicted breathing characteristic value in the predicted breathing waveform corresponding to the next cycle that falls within the breathing characteristic value fluctuation range as the predicted breathing characteristic value that matches the target breathing characteristic value, so as to determine the puncture timing in the next cycle.

[0137] It should be noted that the specific limitations of the above steps can refer to the specific limitations of a method for predicting the timing of puncture mentioned above.

[0138] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0139] Based on the same inventive concept, the embodiment of the present application also provides a surgical execution device for implementing the above-mentioned puncture timing prediction method. Figure 6 As shown, the surgical execution equipment includes a medical image acquisition device, a respiratory motion acquisition device, a surgical robot and a surgical planning execution workstation;

[0140] Medical image acquisition equipment, used to acquire medical scan images of the punctured object and send them to the surgical planning execution workstation;

[0141] The surgical planning execution workstation is used to plan the puncture needle path according to the medical scan image; specifically, the medical scan image is used for the user to plan the puncture needle path to determine the puncture path, target point and other information as a reference during the operation;

[0142] A respiratory motion acquisition device is used to monitor the respiratory motion state of the punctured object when the medical image acquisition device acquires the medical scan image of the punctured object, so as to obtain a target respiratory characteristic value of the punctured object;

[0143] For the next cycle to come, the respiratory motion acquisition device is also used to collect the actual respiratory waveforms of the punctured object corresponding to the first several cycles of the next cycle, and send them to the surgical planning execution workstation;

[0144] The surgical planning execution workstation is used to input the actual respiratory waveforms corresponding to the previous several cycles into the pre-trained respiratory waveform prediction model to obtain the predicted respiratory waveform corresponding to the next cycle;

[0145] The surgical planning execution workstation is further used to use the respiratory characteristic value of the punctured object as the target respiratory characteristic value when acquiring the medical scan image of the punctured object, and determine the predicted respiratory characteristic value matching the target respiratory characteristic value in the predicted respiratory waveform corresponding to the next cycle, so as to determine the puncture timing in the next cycle;

[0146] The surgical planning and execution workstation is also used to send puncture instructions to the surgical robot when the puncture time comes;

[0147] The surgical robot is used to control the robotic arm to perform the puncture operation according to the puncture instruction, and report the relevant status of the punctured object during the puncture process to the surgical planning and execution workstation.

[0148] The surgical planning execution workstation is also used to execute the steps of the above-mentioned puncture timing prediction method.

[0149] In addition, during the operation, the respiratory motion acquisition device is also used to obtain the real-time phase and respiratory motion state of the punctured object to obtain the actual respiratory waveform of the punctured object during the operation.

[0150] In practical applications, the surgical planning execution workstation may be a computer device having surgical planning execution software.

[0151] In order to facilitate technical understanding in this field, Figure 7 A flowchart of a method for predicting the timing of puncture using the above-mentioned surgical execution device is provided. The respiratory pressure value is used as the respiratory characteristic value, and a preoperative image is obtained by scanning with a CT device. In this embodiment, the method includes the following steps:

[0152] 1. The punctured subject wears a respiratory motion acquisition device with a pressure sensor for a preoperative CT scan. During the scan, the respiratory motion acquisition device synchronously records the pressure value at this time as the target respiratory pressure value, and sends the above target respiratory pressure value to the surgical planning execution workstation.

[0153] 2. The user uses the preoperative image to plan the puncture needle path in the surgical planning execution workstation, and enters the surgical process after the planning is completed.

[0154] 3. During the operation, the surgical planning execution workstation runs the pre-trained respiratory waveform prediction model, predicts the respiratory waveform of the next cycle through the actual respiratory waveform obtained in real time by the respiratory motion acquisition device, and finds the puncture time according to the target respiratory pressure value when scanning the preoperative image. If the current time is the puncture time, the puncture command is sent to the robot to start the puncture. In actual applications, without affecting the normal breathing of the punctured object, the respiratory pressure value range measured by the chest belt is set to between 1kpa-5kpa.

[0155] 4. During puncture, the respiratory motion acquisition device will still collect respiratory waveforms and send them to the surgical planning execution workstation for respiratory waveform prediction. When the surgical planning execution work determines that the puncture is abnormal, it will send a puncture end instruction to the surgical robot to execute the needle withdrawal operation. In this way, it can provide protection for unexpected situations such as coughing during surgery that change the human body state, thereby simplifying the entire surgical process, improving surgical accuracy, and reducing patient trauma and postoperative recurrence rate.

[0156] Based on the same inventive concept, the embodiment of the present application also provides a device for predicting puncture timing for implementing the method for predicting puncture timing involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the embodiments of one or more devices for predicting puncture timing provided below can refer to the limitations of a method for predicting puncture timing above, and will not be repeated here.

[0157] In one embodiment, Figure 8 As shown, a device for predicting puncture timing is provided, comprising: a waveform acquisition module 810, an input module 820, a feature value acquisition module 830 and a determination module 840, wherein:

[0158] The waveform acquisition module 810 is used to acquire the actual breathing waveform of the punctured object corresponding to several cycles before the next cycle.

[0159] The input module 820 is used to input the actual respiratory waveforms corresponding to the previous several cycles into the pre-trained respiratory waveform prediction model to obtain the predicted respiratory waveform corresponding to the next cycle.

[0160] The characteristic value acquisition module 830 is used to acquire the target breathing characteristic value of the punctured object; the target breathing characteristic value is the breathing characteristic value of the punctured object when the medical scanning image used for puncture needle track planning is collected.

[0161] The determination module 840 is used to determine the predicted breathing characteristic value matching the target breathing characteristic value in the predicted breathing waveform corresponding to the next cycle, so as to determine the puncture timing in the next cycle.

[0162] In one embodiment, the input module 820 is specifically used to discretize the continuous actual breathing waveform corresponding to the first several cycles to obtain the discrete actual breathing waveform corresponding to the first several cycles; the discrete actual breathing waveform corresponding to the first several cycles is input into the pre-trained breathing waveform prediction model to obtain the predicted breathing waveform corresponding to the next cycle.

[0163] In one embodiment, the input module 820 is specifically used to obtain the discrete actual breathing waveforms corresponding to the first several periods according to the actual breathing characteristic values ​​corresponding to the continuous actual breathing waveforms corresponding to the first several periods at discrete time points.

[0164] In one embodiment, the input module 820 is specifically used to input the discrete actual breathing waveforms corresponding to the previous several cycles into the pre-trained breathing waveform prediction model to obtain the discrete predicted breathing waveform corresponding to the next cycle; and to interpolate the discrete predicted breathing waveform corresponding to the next cycle to obtain the predicted breathing waveform corresponding to the next cycle.

[0165] In one embodiment, the determination module 840 is specifically used to obtain a respiratory characteristic value fluctuation range with the target respiratory characteristic value as a fluctuation benchmark; and use the predicted respiratory characteristic value that falls within the respiratory characteristic value fluctuation range in the predicted respiratory waveform corresponding to the next cycle as the predicted respiratory characteristic value that matches the target respiratory characteristic value, so as to determine the puncture timing in the next cycle.

[0166] In one embodiment, the device also includes: an abnormality detection module, which is used to send an end-puncture instruction to the surgical robot when it is detected that the predicted breathing waveform corresponding to the next cycle at the current moment meets the preset breathing abnormality condition during the puncture process; the end-puncture instruction is used to instruct the surgical robot to stop puncture and perform the needle withdrawal operation.

[0167] In one of the embodiments, the abnormality detection module is specifically used to determine the predicted characteristic value threshold interval of the predicted respiratory waveform representation; when the target respiratory characteristic value is not within the predicted characteristic value threshold interval, the puncture end instruction is sent to the surgical robot.

[0168] In one embodiment, the abnormality detection module is specifically used to determine the actual characteristic value threshold interval of the actual respiratory waveform representation corresponding to each cycle in the first several cycles of the next cycle, and determine the predicted characteristic value threshold interval of the predicted respiratory waveform representation corresponding to the next cycle; determine the average value of the actual characteristic value threshold interval corresponding to each of the cycles to obtain the average actual characteristic value threshold interval; when the difference between the predicted characteristic value threshold interval and the average actual characteristic value threshold interval meets the preset difference condition, send the puncture end instruction to the surgical robot.

[0169] In one of the embodiments, the abnormality detection module is specifically used to send the end puncture instruction to the surgical robot when the difference between the predicted cycle duration corresponding to the predicted respiratory waveform corresponding to the next cycle and the actual cycle duration meets a preset difference condition.

[0170] Each module in the above-mentioned puncture timing prediction device can be implemented in whole or in part by software, hardware or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0171] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for predicting the timing of puncture is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0172] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0173] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0174] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0175] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0176] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant laws, regulations and standards of relevant countries and regions.

[0177] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0178] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0179] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for predicting the timing of puncture. It is characterized in that The method comprises: For the next cycle to come, obtaining the actual breathing waveform of the punctured object corresponding to several cycles before the next cycle; Inputting the actual respiratory waveforms corresponding to the first several cycles into a pre-trained respiratory waveform prediction model to obtain a predicted respiratory waveform corresponding to the next cycle; Acquiring a target respiratory characteristic value of the punctured object; the target respiratory characteristic value is a respiratory characteristic value of the punctured object when collecting a medical scan image used for puncture needle tract planning; In the predicted breathing waveform corresponding to the next cycle, a predicted breathing characteristic value matching the target breathing characteristic value is determined to determine the puncture timing in the next cycle.

2. The method according to claim 1, It is characterized in that The step of inputting the actual respiratory waveforms corresponding to the first several cycles into the pre-trained respiratory waveform prediction model to obtain the predicted respiratory waveform corresponding to the next cycle includes: Discretize the continuous actual breathing waveforms corresponding to the first several cycles to obtain discrete actual breathing waveforms corresponding to the first several cycles; The discrete actual respiratory waveforms corresponding to the first several cycles are input into the pre-trained respiratory waveform prediction model to obtain the predicted respiratory waveform corresponding to the next cycle.

3. The method according to claim 2, It is characterized in that The step of discretizing the continuous actual breathing waveform corresponding to the first several cycles to obtain the discrete actual breathing waveform corresponding to the first several cycles includes: According to the actual breathing characteristic values ​​corresponding to the discrete time points on the continuous actual breathing waveforms corresponding to the first several periods, the discrete actual breathing waveforms corresponding to the first several periods are obtained.

4. The method according to claim 2, It is characterized in that The step of inputting the discrete actual respiratory waveforms corresponding to the first several cycles into the pre-trained respiratory waveform prediction model to obtain the predicted respiratory waveform corresponding to the next cycle includes: Inputting the discrete actual respiratory waveforms corresponding to the first several cycles into the pre-trained respiratory waveform prediction model to obtain the discrete predicted respiratory waveform corresponding to the next cycle; Interpolation processing is performed on the discrete predicted breathing waveform corresponding to the next cycle to obtain the predicted breathing waveform corresponding to the next cycle.

5. The method according to claim 1, It is characterized in that Determining a predicted breathing characteristic value matching the target breathing characteristic value in the predicted breathing waveform corresponding to the next cycle, so as to determine the puncture timing in the next cycle, includes: Acquire a respiratory characteristic value fluctuation range with the target respiratory characteristic value as a fluctuation reference; The predicted breathing characteristic value in the predicted breathing waveform corresponding to the next cycle that falls within the breathing characteristic value fluctuation range is used as the predicted breathing characteristic value matching the target breathing characteristic value to determine the puncture timing in the next cycle.

6. The method according to claim 1, It is characterized in that The method further comprises: During the puncture process, when it is detected that the predicted breathing waveform corresponding to the next cycle at the current moment meets the preset breathing abnormality condition, an end-puncture instruction is sent to the surgical robot; the end-puncture instruction is used to instruct the surgical robot to stop puncture and perform the needle withdrawal operation.

7. The method according to claim 6, It is characterized in that When it is detected that the predicted respiratory waveform corresponding to the next cycle at the current moment meets the preset respiratory abnormality condition, sending an instruction to end the puncture to the surgical robot includes: Determining a threshold interval of predicted characteristic values ​​of the predicted respiratory waveform representation; When the target respiratory characteristic value is not within the predicted characteristic value threshold interval, the puncture end instruction is sent to the surgical robot.

8. The method according to claim 6, It is characterized in that When it is detected that the predicted respiratory waveform corresponding to the next cycle at the current moment meets the preset respiratory abnormality condition, sending an instruction to end the puncture to the surgical robot includes: Determine an actual characteristic value threshold interval of an actual respiratory waveform representation corresponding to each cycle in a plurality of cycles before the next cycle, and determine a predicted characteristic value threshold interval of a predicted respiratory waveform representation corresponding to the next cycle; Determine the average value of the actual characteristic value threshold interval corresponding to each of the periods to obtain an average actual characteristic value threshold interval; When the difference between the predicted characteristic value threshold interval and the average actual characteristic value threshold interval meets a preset difference condition, the puncture end instruction is sent to the surgical robot.

9. The method according to claim 6, It is characterized in that When it is detected that the predicted respiratory waveform corresponding to the next cycle at the current moment meets the preset respiratory abnormality condition, sending an instruction to end the puncture to the surgical robot includes: When the difference between the predicted cycle duration corresponding to the predicted respiratory waveform corresponding to the next cycle and the actual cycle duration meets a preset difference condition, the puncture end instruction is sent to the surgical robot.

10. A device for predicting the timing of puncture, It is characterized in that The device comprises: A waveform acquisition module is used to acquire, for the next upcoming cycle, the actual breathing waveform of the punctured object corresponding to several cycles before the next cycle; An input module, used to input the actual respiratory waveforms corresponding to the previous several cycles into a pre-trained respiratory waveform prediction model to obtain a predicted respiratory waveform corresponding to the next cycle; A characteristic value acquisition module is used to acquire a target breathing characteristic value of the punctured object; the target breathing characteristic value is a breathing characteristic value of the punctured object when a medical scan image used for puncture needle tract planning is collected; The determination module is used to determine the predicted breathing characteristic value matching the target breathing characteristic value in the predicted breathing waveform corresponding to the next cycle, so as to determine the puncture timing in the next cycle.

11. A computer device comprising a memory and a processor, wherein the memory stores a computer program. It is characterized in that When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

12. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 9 are implemented.

13. A surgical device, It is characterized in that The equipment includes a medical image acquisition device, a respiratory motion acquisition device, a surgical robot and a surgical planning execution workstation; The medical image acquisition device is used to acquire medical scan images of the punctured object and send them to the surgical planning execution workstation; The surgical planning execution workstation is used to plan the puncture needle path according to the medical scan image; The respiratory motion acquisition device is used to monitor the respiratory characteristic value of the punctured object when the medical image acquisition device acquires the medical scan image of the punctured object; For the next cycle to come, the respiratory motion acquisition device is also used to collect the actual respiratory waveform of the punctured object corresponding to several cycles before the next cycle, and send it to the surgical planning execution workstation; The surgical planning execution workstation is used to input the actual respiratory waveforms corresponding to the previous several cycles into the pre-trained respiratory waveform prediction model to obtain the predicted respiratory waveform corresponding to the next cycle; The surgical planning execution workstation is further used to use the respiratory characteristic value of the punctured object as the target respiratory characteristic value when acquiring the medical scan image of the punctured object, and determine the predicted respiratory characteristic value matching the target respiratory characteristic value in the predicted respiratory waveform corresponding to the next cycle, so as to determine the puncture timing in the next cycle; The surgical planning execution workstation is further used to send a puncture instruction to the surgical robot when the puncture opportunity arrives; The surgical robot is used to control the robotic arm to perform the puncture operation according to the puncture instruction.

14. The device according to claim 13, It is characterized in that The surgical planning execution workstation is also used to execute the steps of implementing any one of claims 1 to 9.

Images