Intrarenal pressure prediction method, endoscope control system, medical device, and storage medium

Abstract

The invention provides an intrarenal pressure prediction method, an endoscope control system, medical equipment and a storage medium, and relates to the technical field of data detection and calibration. Wherein the current detection data comprises the current perfusate input flow, the current negative pressure suction output flow and the current fluid resistance, and the current pressure detection value is a detection value obtained by a pressure sensor installed at a liquid inlet of an operation handle, and then a renal calyx internal pressure prediction value can be determined based on the current detection data. And the target renal calyx internal pressure is obtained based on the current pressure detection value and the renal calyx internal pressure prediction value. The current detection data and the current pressure detection value can be obtained through existing components of the endoscope, the current pressure detection value is calibrated through the predicted value of the internal pressure of the renal calyx, and the accuracy of internal pressure detection of the renal calyx can be improved while the number of the components of the endoscope is not increased.

Description

Technical Field

[0001] The present application relates to the technical field of data detection and calibration, and particularly relates to a method for predicting renal pressure, an endoscopic control system, a medical device, and a storage medium. Background Art

[0002] Currently, there are three types of renal pressure measurements. The first type is to embed a pressure sensor at the distal end of the insertion part of the endoscope, which can achieve high-precision real-time measurement, but has high costs and is difficult to produce and process. The second type is to set a pressure sensor outside the body, with the detection end extending to the insertion part, and the measurement accuracy is high. However, due to the relatively long feedback path, there is a certain delay in the detection result. In addition, if the detection end enters through the instrument channel, the use of surgical instruments will be restricted. If it is embedded inside the insertion part of the endoscope, the existing endoscope structure will be adjusted and modified, increasing the production cost and difficulty. The third type is large model prediction, which has low costs, small modifications to the endoscope, and can instantaneously calculate the current time and predict the renal pressure data after a period of time, but the prediction data accuracy is low. Summary of the Invention

[0003] The present application provides a method for predicting renal pressure, an endoscopic control system, a medical device, and a storage medium, which can improve the accuracy of renal pressure detection without adding endoscopic components.

[0004] A method for predicting renal pressure provided by the present application includes: Obtaining current detection data and a current pressure detection value; the current detection data includes the current perfusion fluid input flow rate, the current negative pressure suction output flow rate, and the current fluid resistance; the current pressure detection value is the detection value obtained by a pressure sensor installed at the liquid inlet of the operating handle; Determining a predicted renal calyx pressure value based on the current detection data; Obtaining a target renal calyx pressure based on the current pressure detection value and the predicted renal calyx pressure value.

[0005] To achieve the above object and other related objects, the present application provides an endoscopic control system, including: A data acquisition module for obtaining current detection data and a current pressure detection value; the current detection data includes the current perfusion fluid input flow rate, the current negative pressure suction output flow rate, and the current fluid resistance; the current pressure detection value is the detection value obtained by a pressure sensor installed at the liquid inlet of the operating handle; A first determination module for determining a predicted renal calyx pressure value based on the current detection data; A second determination module for obtaining a target renal calyx pressure based on the current pressure detection value and the predicted renal calyx pressure value.

[0006] To achieve the above and other related objectives, the present application also provides a medical device, including an endoscope host and an operating handle. The endoscope host includes a memory and a processor, and the processor is configured to execute program instructions stored in the memory to implement one or more of the foregoing intrarenal pressure prediction methods.

[0007] To achieve the above and other related objectives, the present application also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer is enabled to execute one or more of the foregoing intrarenal pressure prediction methods.

[0008] As described above, an intrarenal pressure prediction method, an endoscope control system, a medical device, and a storage medium provided by the present application have the following beneficial effects: An intrarenal pressure prediction method in the present application. This method obtains current detection data and a current pressure detection value. The current detection data includes the current perfusion fluid input flow rate, the current negative pressure suction output flow rate, and the current fluid resistance, and the current pressure detection value is the detection value obtained by a pressure sensor installed at the liquid inlet of the operating handle. Then, an intrarenal pressure prediction value can be determined based on the current detection data, and a target intrarenal pressure can be obtained based on the current pressure detection value and the intrarenal pressure prediction value. Both the current detection data and the current pressure detection value can be obtained through existing components of the endoscope. By calibrating the current pressure detection value with the intrarenal pressure prediction value, the accuracy of intrarenal pressure detection can be improved without adding components to the endoscope.

[0009] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The accompanying drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application. Obviously, the accompanying drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts. In the drawings: Figure 1 is a schematic diagram of the implementation environment of the intrarenal pressure prediction method shown in an exemplary embodiment of the present application; Figure 2 is a flowchart of the intrarenal pressure prediction method shown in an exemplary embodiment of the present application; Figure 3 is a block diagram of the structure of the endoscope control system shown in an exemplary embodiment of the present application. DETAILED DESCRIPTION

[0011] The embodiments of the present application will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be understood that the preferred embodiments are only for explaining the present application, rather than for limiting the protection scope of the present application.

[0012] It should be noted that the diagrams provided in the following embodiments only illustrate the basic concept of the present application in a schematic manner. Therefore, only the components related to the present application are shown in the diagrams, rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and ratio of each component in actual implementation can be arbitrarily changed, and the component layout type may also be more complex.

[0013] In the following description, a large number of details are explored to provide a more thorough explanation of the embodiments of the present application. However, it is obvious to those skilled in the art that the embodiments of the present application can be implemented without these specific details. In other embodiments, well-known structures and devices are shown in the form of block diagrams rather than in detail to avoid making the embodiments of the present application difficult to understand.

[0014] Please refer to Figure 1 , which is a schematic diagram of the implementation environment of the intrarenal pressure prediction method shown in an exemplary embodiment of the present application. The implementation environment may include an operating handle 110 and an endoscope host 120.

[0015] The operating handle 110 and the endoscope host 120 can be connected by wired or wireless means, Figure 1 as shown in the wired connection method. When the operating handle 110 and the endoscope host 120 are connected in a wired manner, they can be connected by optical fiber or cable. When the operating handle 110 and the endoscope host 120 are connected in a wireless manner, they can be connected to the endoscope host through wireless communication protocols such as Wi-Fi or Bluetooth.

[0016] An insertion tube 111 is connected to the operating handle 110, and a lens is provided at the front end of the insertion tube 111. The insertion tube is used to insert into the renal calyx 200, and the lens is responsible for capturing the image inside the renal calyx 200 and displaying the captured image through the display screen of the endoscope host 120. The operating handle 110 may further include an operating handle liquid inlet 112, a perfusion module 113, a pressure sensor 114, and a negative pressure suction module 115. The operating handle liquid inlet 112 can also be referred to as the instrument port.

[0017] The perfusion module 113 is connected to the liquid inlet 112 of the operating handle through a pipeline. The perfusion module 113 can be used to pump perfusion fluid into the renal calyx through the liquid inlet 112 of the operating handle and the input pipeline on the operating handle. A flow sensor and a pressure sensor can be integrated in the perfusion module 113. The flow sensor of the perfusion module 113 can be used to collect the current perfusion fluid input flow rate, and the pressure sensor of the perfusion module 113 can collect the current perfusion end pressure. The perfusion module 113 can also transmit the flow data collected by the flow sensor and the pressure data collected by the pressure sensor to the endoscope host 120.

[0018] The pressure sensor 114 can be arranged on the connecting pipeline between the perfusion module 113 and the liquid inlet 112 of the operating handle, and the pressure sensor 114 is installed at one end close to the liquid inlet 112 of the operating handle. The pressure sensor 114 can be used to collect the current pressure detection value and transmit the current pressure detection value to the endoscope host 120.

[0019] The negative pressure suction module 115 can be connected to the liquid outlet channel ( Figure 1 not shown) through a pipeline. The negative pressure suction module 115 can suck the crushed stone debris and the like together with the perfusion fluid out of the renal calyx, and at the same time ensure that the pressure in the renal calyx is maintained at a stable value to ensure the safety of the operation. A pressure sensor and a flow sensor can be integrated in the negative pressure suction module 115. The pressure sensor of the negative pressure suction module 115 can be used to collect the current negative pressure at the suction end, and the flow sensor of the negative pressure suction module 115 can be used to collect the current negative pressure suction output flow rate. The negative pressure suction module 115 can also transmit the data collected by the flow sensor and the data collected by the pressure sensor to the endoscope host 120.

[0020] It should be noted that when the endoscope is a multi-channel endoscope, the liquid outlet channel can be one of the multi-channels. When the endoscope works in cooperation with the sheath, the liquid outlet channel can be the gap between the sheath and the insertion part of the endoscope, and the liquid outlet channel can also be an independent channel on the sheath; preferably, the gap between the sheath and the insertion part of the endoscope can be used as the liquid outlet channel.

[0021] It should be noted that the arrow indicates the flow direction of the perfusion fluid. The perfusion fluid can be pumped into the renal calyx from the perfusion module 113, and the perfusion fluid can be sucked out of the renal calyx through the negative pressure suction module 115.

[0022] Please refer to Figure 2 , Figure 2 which is a flowchart of the renal pressure prediction method shown in an exemplary embodiment of the present application. The renal pressure prediction method can be applied to the Figure 1 shown implementation environment. Referring to Figure 2 it can be seen that the renal pressure prediction method can include: Step S210, obtaining the current detection data and the current pressure detection value.

[0023] Among them, the current detection data includes the current perfusion fluid input flow rate, the current negative pressure suction output flow rate, and the current fluid resistance; the current pressure detection value is the detection value obtained by the pressure sensor installed at the liquid inlet of the operation handle.

[0024] In an embodiment of the present application, the current detection data and the current pressure detection value can be obtained. The current pressure detection value can be obtained by the pressure sensor installed at the liquid inlet of the operation handle. A flow sensor can be integrated in the perfusion module, and the current perfusion fluid input flow rate can be obtained through the flow sensor of the perfusion module. A flow sensor can also be integrated in the negative pressure suction module, and the current negative pressure suction output flow rate can be obtained through the flow sensor of the negative pressure suction module.

[0025] Exemplarily, the current fluid resistance can be determined by the pressure detection value, the current perfusion fluid input flow rate, and the current negative pressure suction output flow rate. The determination formula of the current fluid resistance can be expressed as: ; Wherein, is the current fluid resistance, is the current perfusion fluid input flow rate, is the current negative pressure suction output flow rate, is the current pressure detection value.

[0026] Step S220, determining a predicted value of the renal calyx pressure based on the current detection data.

[0027] In an embodiment of the present application, the predicted value of the renal calyx pressure can be determined based on the current pressure detection data. The current detection data is the detection data related to the renal calyx pressure, and the renal calyx pressure can be estimated through the current detection data to obtain the predicted value of the renal calyx pressure.

[0028] Optionally, determining the predicted value of the renal calyx pressure based on the current detection data may include: obtaining the predicted value of the renal calyx pressure based on the current detection data and a pre-trained renal pressure prediction model.

[0029] Optionally, before obtaining the predicted value of the renal calyx pressure based on the current detection data and the pre-trained renal pressure prediction model, the method may further include: obtaining a training sample set, the training sample set includes a plurality of training sample pairs, each training sample pair includes a training sample and a sample label, the training sample includes the perfusion fluid input flow rate, the negative pressure suction output flow rate, and the fluid resistance, and the sample label includes the renal calyx pressure; training the renal pressure prediction model based on the training sample set until the training stop condition is reached.

[0030] In one embodiment of the present application, a training sample set can be obtained. The process of obtaining the training sample set may include collecting raw data, where the raw data includes the perfusion fluid input flow rate, the negative pressure suction output flow rate, and the fluid resistance; performing preprocessing on the raw data including missing value processing, outlier detection, data standardization, and data normalization to obtain training samples; annotating the intrarenal calyx pressure corresponding to each training sample to obtain sample labels; and combining the training samples and the corresponding sample labels to obtain multiple training sample pairs, and the multiple training sample pairs constitute the training sample set. A three-dimensional model of the renal calyx can be reconstructed using CT scanning, and CFD simulation can be performed on the three-dimensional model based on simulation conditions to obtain the intrarenal calyx pressure of the sample labels.

[0031] Exemplarily, the intrarenal pressure prediction model can be a fully connected neural network (FCNN) regression model. The intrarenal pressure prediction model may include an input layer, two hidden layers, and an output layer; one of the hidden layers may include 64 neurons, which are output to the other hidden layer through the non-linear activation function ReLU and the fully connected layer; the other hidden layer may include 32 neurons, which are output to the output layer through the non-linear activation function ReLU and the fully connected layer. A loss function can be set, and the loss function can be selected as the mean square error (MSE) loss function. The training stop condition may include stopping training when the number of training rounds reaches the maximum number of training rounds.

[0032] Optionally, the current detection data may further include the current perfusion end pressure and the current suction end negative pressure. The process of determining the intrarenal calyx pressure prediction value based on the current detection data may further include: determining the intrarenal calyx pressure prediction value based on the current detection data and the intrarenal calyx pressure prediction formula. The intrarenal calyx pressure prediction formula can be expressed as: ; where, is the intrarenal calyx pressure prediction value, is the current perfusion fluid input flow rate, is the current negative pressure suction output flow rate, is the current suction end negative pressure, is the current perfusion end pressure, and R is the current fluid resistance.

[0033] It should be noted that a pressure sensor can be integrated in the perfusion module, and the value detected by the pressure sensor in the perfusion module at the current moment is the current perfusion end pressure; a pressure sensor can be integrated in the negative pressure suction module, and the value detected by the pressure sensor in the negative pressure suction module at the current moment is the current suction end negative pressure.

[0034] In one possible way, the current detection data may further include a three-dimensional model of the renal calyx, and the training sample also includes a three-dimensional model of the renal calyx. The three-dimensional model of the renal calyx can be obtained through three-dimensional reconstruction by CT scanning, and the three-dimensional model of the renal calyx can be represented as a voxelized grid. Then the training sample may include the perfusion fluid input flow rate, the negative pressure suction output flow rate, the fluid resistance, and the corresponding three-dimensional model of the renal calyx, and the three-dimensional model of the renal calyx can be the three-dimensional model of the renal calyx corresponding to the patient before surgery.

[0035] It should be noted that before using the endoscope to probe into the patient's renal calyx for surgery, the patient's renal calyx can be scanned by CT to reconstruct the corresponding three-dimensional model of the renal calyx. When actually using the current detection data and the pre-trained renal intrarenal pressure prediction model to obtain the renal intrarenal pressure prediction value, the input of the renal intrarenal pressure prediction model can be the current perfusion fluid input flow rate, the current negative pressure suction output flow rate, the current fluid resistance, and the three-dimensional model of the renal calyx. The three-dimensional models of the renal calyces of different patients are different. By inputting the three-dimensional model of the renal calyx into the renal intrarenal pressure prediction model, the pre-trained renal intrarenal pressure prediction model can extract the key features of the three-dimensional model of the renal calyx and obtain the renal intrarenal pressure prediction value based on the key features, which can improve the accuracy of the renal intrarenal pressure prediction value.

[0036] Step S230, based on the current pressure detection value and the renal intrarenal pressure prediction value, obtain the target renal intrarenal pressure.

[0037] In an embodiment of the present application, the target renal intrarenal pressure can be obtained based on the current pressure detection value and the renal intrarenal pressure prediction value. The current pressure detection value is the pressure value near the liquid inlet end. Since there is still a certain distance from the renal calyx, there may be a certain difference between the current pressure detection value and the renal intrarenal pressure. The renal intrarenal pressure prediction value is a theoretical data estimated according to the current detection data. The target renal intrarenal pressure can be obtained by fusing and correcting the current pressure detection value and the renal intrarenal pressure prediction value.

[0038] The intracalyceal pressure refers to the liquid pressure inside the renal calyx of the kidney and is one of the urodynamic parameters, usually reflecting the pressure state of urine accumulation in the renal calyx.

[0039] Optionally, the process of S230 obtaining the target renal intrarenal pressure based on the current pressure detection value and the renal intrarenal pressure prediction value may include steps S231 to S233.

[0040] Step S231, perform a fast Fourier transform on the current pressure detection value to obtain the pressure data to be processed.

[0041] In an embodiment of the present application, the current pressure detection value can be subjected to a fast Fourier transform to obtain the pressure data to be processed. The fast Fourier transform can transform the current pressure detection value from a time-domain signal into a frequency-domain signal, and the frequency distribution of the signal can be intuitively viewed through a spectrogram, which is convenient for identifying periodic or abnormal frequency components.

[0042] Step S232: When the pressure data to be processed is greater than a preset threshold, generate a prompt message.

[0043] Among them, the prompt message is used to prompt the user that the current pressure detection is abnormal.

[0044] In an embodiment of the present application, when the pressure data to be processed is greater than a preset threshold, the current pressure detection value is abnormal data, and a prompt message can be generated. After generating the prompt message, the prompt message can be displayed through the voice module of the endoscope host, and the prompt message can also be displayed through the display screen of the endoscope host. When the pressure data to be processed is greater than the preset threshold, it indicates that the pressure signal oscillates at a high frequency, which may be caused by factors such as pipeline bubbles. At this time, the current pressure detection value is not accurate. The prompt message can be used to prompt the user that the pipeline is abnormal, and the endoscope host can determine the predicted value of the renal calyx pressure as the target renal calyx pressure, which can be used for detecting the connection stability of the instrument port pipeline.

[0045] Exemplarily, the preset threshold can be 10Hz.

[0046] Step S233: When the pressure data to be processed is less than or equal to the preset threshold, perform fusion correction on the current pressure detection value and the predicted value of the renal calyx pressure to obtain the target renal calyx pressure.

[0047] In an embodiment of the present application, when the pressure data to be processed is less than or equal to the preset threshold, the current pressure detection value is normal data, and the current pressure detection value and the predicted value of the renal calyx pressure can be subjected to fusion correction to obtain the target renal calyx pressure.

[0048] Optionally, performing fusion correction on the current pressure detection value and the predicted value of the renal calyx pressure to obtain the target renal calyx pressure includes: using the extended Kalman filter method to perform fusion correction on the current pressure detection value and the predicted value of the renal calyx pressure to obtain the target renal calyx pressure.

[0049] In an embodiment of the present application, the extended Kalman filter method can be used to perform fusion correction on the current pressure detection value and the predicted value of the renal calyx pressure to obtain the target renal calyx pressure.

[0050] Exemplarily, the process of using the extended Kalman filter method to perform fusion correction on the current pressure detection value and the predicted value of the renal calyx pressure to obtain the target renal calyx pressure can include: 1) Obtain state variables and observation variables. The state variables can be expressed as: , where is the state variable at the k-th moment, is the target renal calyx pressure, is the fluid resistance, is the pipeline delay compensation factor, which can be used to correct sensor hysteresis; the observed variable can be expressed as , where is the observed variable, is the current pressure detection value, is the predicted value of the renal calyx pressure.

[0051] 2) Design the state equation to describe the physical law of the evolution of the state variable over time: ; where is the system input, including the current perfusion fluid input flow rate and the current negative pressure suction output flow rate ; is the process noise, and the process noise obeys the Gaussian distribution , is the process noise covariance, is the first function. The state equation can be expressed as: ; where C is the renal calyx compliance, is the sampling time interval.

[0052] 3) Design the observation equation to map the state variable to the observed value: ; where is the observation noise, and the observation noise obeys the Gaussian distribution , is the observation noise covariance, is the second function. The observation equation can be expressed as: ; where is the current pressure detection value at the k-th moment, is the predicted value of the renal calyx pressure at the k-th moment.

[0053] 4) Execute the prediction step, state prediction: ; Error covariance prediction: ; where is the first Jacobian matrix, and the first Jacobian matrix is the partial derivative matrix of the state equation with respect to the state variables. For a linear state equation, the first Jacobian matrix can be expressed as: ; where is the first Jacobian matrix at the (k - 1)-th moment.

[0054] 5) Execute the update step to calculate the Kalman gain: ; where is the second Jacobian matrix, and the second Jacobian matrix is the partial derivative matrix of the observation equation with respect to the state variables. The second Jacobian matrix can be expressed as: ; State update: ; Covariance update: ; where is the identity matrix, and the dimension of is the same as the dimension of the state vector.

[0055] It should be noted that the process noise covariance and the observation noise covariance can be initialized, and the initial values of the state variables and the covariance can be set.

[0056] Exemplarily, after determining the fluid resistance at the (k - 1)-th moment in the state variables, the fluid resistance at the (k - 1)-th moment can be determined as the fluid resistance at the k-th moment, and the predicted value of the intrarenal pelvis pressure at the k-th moment can be determined based on the fluid resistance at the k-th moment, the perfusion fluid input flow rate at the k-th moment, and the negative pressure suction output flow rate at the k-th moment.

[0057] Optionally, based on the current pressure detection value and the predicted value of the intrarenal pelvis pressure for fusion correction to obtain the target intrarenal pelvis pressure, including: the mean value of the current pressure detection value and the predicted value of the intrarenal pelvis pressure can be determined as the target intrarenal pelvis pressure. By averaging the current pressure detection value and the predicted value of the intrarenal pelvis pressure to obtain their mean value, the random noise in both can be partially offset, making the target intrarenal pelvis pressure closer to the true value and further improving the accuracy of the target intrarenal pelvis pressure.

[0058] It should be noted that the intrarenal pressure prediction method provided in the embodiments of the present application can be executed by an endoscope host.

[0059] Figure 3 is a block diagram of an endoscope control system shown in an exemplary embodiment of the present application. As Figure 3As shown, the exemplary endoscopic control system 300 includes: A data acquisition module 310 for acquiring current detection data and a current pressure detection value; the current detection data includes a current perfusion fluid input flow rate, a current negative pressure suction output flow rate, and a current fluid resistance; the current pressure detection value is the detection value acquired by a pressure sensor installed at the liquid inlet of the operation handle.

[0060] A first determination module 320 for determining a predicted value of the intrarenal calyx pressure based on the current detection data.

[0061] A second determination module 330 for obtaining a target intrarenal calyx pressure based on the current pressure detection value and the predicted value of the intrarenal calyx pressure.

[0062] It should be noted that the endoscopic control system provided in the above embodiment and the intrarenal pressure prediction method provided in the above embodiment belong to the same concept. The specific manners in which each module and unit perform operations have been described in detail in the method embodiment and will not be elaborated here. In practical applications, the endoscopic control system provided in the above embodiment can, according to needs, allocate the above functions to different functional modules, that is, divide the internal structure of the system into different functional modules to complete all or part of the functions described above, and this will not be limited here either.

[0063] An embodiment of the present application further provides a medical device, including an endoscopic host and an operation handle. The endoscopic host includes a memory and a processor. The processor is configured to execute program instructions stored in the memory to implement the intrarenal pressure prediction method provided in any one of the above embodiments.

[0064] On the other hand, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor of a computer, the computer is enabled to execute the intrarenal pressure prediction method provided in each of the above embodiments. The computer-readable storage medium may be included in the electronic device described in the above embodiment, or may exist alone without being assembled into the electronic device.

[0065] On the other hand, the present application further provides a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the intrarenal pressure prediction method provided in each of the above embodiments.

[0066] In the embodiments of the present application, the terms "first" and "second" are only used for descriptive purposes and should not be construed as indicating or implying relative importance. The terms "comprising" and "including" mentioned throughout the specification and claims are open-ended terms and should be interpreted as "including but not limited to".

[0067] The above embodiments are only used to exemplarily illustrate the principles and effects of the present application, rather than to limit the present application. Any person familiar with this technology can modify or change the above embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by those with ordinary knowledge in the technical field without departing from the spirit and technical idea disclosed by the present application should still be covered by the claims of the present application.

Claims

1. A method for predicting intrarenal pressure, characterized in that: include: Get the current detection data and current pressure detection value; The current detection data includes the current perfusion fluid input flow, the current negative pressure suction output flow and the current fluid resistance; the current pressure detection value is the detection value obtained by the pressure sensor installed at the liquid inlet of the operating handle; Determine the predicted value of renal calyx pressure based on current test data; The target renal calyx pressure is obtained based on the current pressure detection value and the predicted renal calyx pressure.

2. The method for predicting intrarenal pressure according to claim 1, characterized in that: Determine the predicted value of renal calyceal pressure based on the current test data, including: Based on the current detection data and the pre-trained intrarenal pressure prediction model, the predicted value of the renal calyx pressure is obtained.

3. The method for predicting intrarenal pressure according to claim 2, characterized in that: Before obtaining the predicted value of the renal calyx pressure based on the current detection data and the pre-trained renal intra-pressure prediction model, the method further includes: Acquire a training sample set, the training sample set includes a plurality of training sample pairs, each training sample pair includes a training sample and a sample label, the training sample includes a perfusion fluid input flow, a negative pressure suction output flow, and a fluid resistance, and the sample label includes a renal calyx intra-pressure; The intrarenal pressure prediction model is trained based on the training sample set until the training stop condition is reached.

4. The method for predicting intrarenal pressure according to claim 3, characterized in that: The current detection data also includes a three-dimensional model of renal calyx, and the training sample also includes a three-dimensional model of renal calyx.

5. The method for predicting intrarenal pressure according to claim 1, characterized in that: Based on the current pressure detection value and the predicted value of the renal calyx pressure, the target renal calyx pressure is obtained, including: Performing fast Fourier transform on the current pressure detection value to obtain pressure data to be processed; When the pressure data to be processed is greater than a preset threshold, a prompt message is generated; the prompt message is used to remind the user that the current pressure detection is abnormal; When the pressure data to be processed is less than or equal to a preset threshold, the current pressure detection value and the predicted value of the renal calyx pressure are fused and corrected to obtain the target renal calyx pressure.

6. The method for predicting intrarenal pressure according to claim 5, characterized in that: Based on the current pressure detection value and the predicted value of the renal calyx pressure, a fusion correction is performed to obtain the target renal calyx pressure, including: The extended Kalman filter method is used to fuse and correct the current pressure detection value and the predicted value of renal calyx pressure to obtain the target renal calyx pressure.

7. The method for predicting intrarenal pressure according to claim 5, characterized in that: Based on the current pressure detection value and the predicted value of the renal calyx pressure, a fusion correction is performed to obtain the target renal calyx pressure, including: The average of the current pressure detection value and the predicted renal calyx pressure is determined as the target renal calyx pressure.

8. An endoscope control system, characterized in that: include: A data acquisition module is used to obtain current detection data and current pressure detection value; The current detection data includes the current perfusion fluid input flow, the current negative pressure suction output flow and the current fluid resistance; the current pressure detection value is the detection value obtained by the pressure sensor installed at the liquid inlet of the operating handle; A first determination module, used to determine a predicted value of renal calyx pressure based on current detection data; The second determination module is used to obtain the target renal calyx pressure based on the current pressure detection value and the renal calyx pressure prediction value.

9. A medical device, characterized in that: The endoscope comprises an endoscope host and an operating handle, wherein the endoscope host comprises a memory and a processor, and the processor is used to execute program instructions stored in the memory to implement the method for predicting intrarenal pressure according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor of a computer, the computer is caused to execute the method for predicting intrarenal pressure according to any one of claims 1 to 7.

Images