A method and apparatus for monitoring perfusion pressure

Abstract

The application provides a perfusion pressure monitoring method and device, which is suitable for the technical field of data processing. The method comprises the following steps: performing feature extraction processing on biliary tract perfusion image information based on a preset biliary tract perfusion state feature extraction model to generate biliary tract perfusion state feature information; and generating biliary tract perfusion pressure prediction information according to biliary tract pipeline pressure monitoring information, biliary tract pipeline environment temperature monitoring information, perfusion pipeline fluid fluctuation monitoring information, suction pipeline environment temperature monitoring information, the biliary tract perfusion state feature information and a preset biliary tract perfusion pressure prediction model. The application is used for realizing millisecond-level dynamic monitoring and accurate prediction of intraoperative biliary tract perfusion pressure, effectively avoiding intraoperative complications caused by biliary tract high pressure and pipeline blockage, and greatly improving the safety and intelligent level of perfusion regulation and control of hard choledochoscope surgery.

Description

Technical Field

[0001] This application belongs to the field of data processing technology, and in particular relates to a method and apparatus for monitoring injection pressure. Background Technology

[0002] Percutaneous transhepatic cholangioscopic lithotripsy and gallbladder-preserving lithotripsy, among other minimally invasive diagnostic and treatment techniques using rigid cholangioscopy, have become the mainstream minimally invasive surgical methods for the clinical treatment of intrahepatic bile duct stones and common bile duct stones. With advantages such as minimal trauma, rapid postoperative recovery, and high stone clearance rates, they are widely used in hepatobiliary surgery. During the procedure, to ensure a clear surgical field, flush out stone fragments and blood clots, and dilate narrowed bile ducts, continuous irrigation and negative pressure suction must be performed in tandem.

[0003] Currently, the equipment for irrigation and suction in clinical cholangioscopy has achieved basic widespread availability, enabling continuous fluid irrigation and routine waste fluid suction. This largely meets the irrigation and drainage needs of routine cholangioscopy. Throughout the procedure, medical staff manually adjust the irrigation flow rate and negative pressure suction intensity based on clinical experience, the equipment's preset flow rate, and changes in the intraoperative visual field, relying on subjective judgment to achieve the matching and control of irrigation and suction. However, in the current technical approach, it is impossible to collect real-time, quantitative data on the actual pressure inside the bile duct during the procedure, resulting in blind spots in pressure monitoring. Summary of the Invention

[0004] In view of this, the present application provides a perfusion pressure monitoring method and device, which aims to solve the problems existing in the prior art, such as the lack of real-time accurate pressure and flow monitoring in split perfusion and aspiration devices, poor accuracy of manual subjective control, high risk of complications from biliary hypertension, delayed treatment of pipeline blockage, and weak controllability of surgical safety.

[0005] A first aspect of this application provides a method for monitoring perfusion pressure, including:

[0006] Acquire information on biliary tubing pressure monitoring, biliary tubing ambient temperature monitoring, infusion tubing fluid fluctuation monitoring, suction tubing ambient temperature monitoring, and multiple biliary perfusion images.

[0007] Based on a preset biliary perfusion status feature extraction model, feature extraction processing is performed on the multiple biliary perfusion image information to generate multiple biliary perfusion status feature information.

[0008] Based on the biliary tract pressure monitoring information, biliary tract ambient temperature monitoring information, infusion pipeline fluid fluctuation monitoring information, suction pipeline ambient temperature monitoring information, multiple biliary tract infusion status characteristic information, and a preset biliary tract infusion pressure prediction model, multiple biliary tract infusion pressure prediction information are generated.

[0009] A second aspect of this application provides an infusion pressure monitoring device, comprising:

[0010] The information acquisition module is used to acquire biliary tubing pressure monitoring information, biliary tubing ambient temperature monitoring information, perfusion tubing fluid fluctuation monitoring information, suction tubing ambient temperature monitoring information, and multiple biliary perfusion images.

[0011] The biliary perfusion status feature information generation module is used to perform feature extraction processing on the multiple biliary perfusion image information based on a preset biliary perfusion status feature extraction model, and generate multiple biliary perfusion status feature information.

[0012] The biliary perfusion pressure prediction information generation module is used to generate multiple biliary perfusion pressure prediction information based on the biliary tubing pressure monitoring information, biliary tubing ambient temperature monitoring information, perfusion tubing fluid fluctuation monitoring information, suction tubing ambient temperature monitoring information, multiple biliary perfusion state characteristic information, and a preset biliary perfusion pressure prediction model.

[0013] A third aspect of this application provides a terminal device, the terminal device including a memory and a processor, the memory storing a computer program executable on the processor, the processor executing the computer program to implement the steps of the perfusion pressure monitoring method described in the first aspect above.

[0014] A fourth aspect of this application provides a computer-readable storage medium, comprising: storing a computer program, which, when executed by a processor, implements the steps of the perfusion pressure monitoring method described in the first aspect above.

[0015] The beneficial effects of this application embodiment compared with the prior art are as follows: This application effectively solves the technical defects of existing biliary perfusion pressure monitoring that rely solely on a single sensor to collect data, such as low monitoring accuracy, pressure drift lag, and abnormality identification lag. It achieves millisecond-level dynamic monitoring and accurate prediction of intraoperative biliary perfusion pressure, effectively avoids intraoperative complications caused by biliary hypertension and tubing blockage, and significantly improves the safety and intelligence level of perfusion control in rigid cholangioscopy surgery, providing accurate data support for intraoperative intelligent pressure adjustment, automatic backflushing, and risk warning. Attached Figure Description

[0016] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0017] Figure 1 This is a schematic diagram of the implementation process of the infusion pressure monitoring method provided in Embodiment 1 of this application;

[0018] Figure 2 This is a schematic diagram of the implementation process of the infusion pressure monitoring method provided in Embodiment 2 of this application;

[0019] Figure 3 This is a schematic diagram of the implementation process of the infusion pressure monitoring method provided in Embodiment 3 of this application;

[0020] Figure 4 This is a schematic diagram of the implementation process of the infusion pressure monitoring method provided in Embodiment 4 of this application;

[0021] Figure 5 This is a schematic diagram of the implementation process of the infusion pressure monitoring method provided in Embodiment 5 of this application;

[0022] Figure 6 This is a schematic diagram of the implementation process of the infusion pressure monitoring method provided in Embodiment Six of this application;

[0023] Figure 7 This is a schematic diagram of the infusion pressure monitoring device provided in the embodiments of this application;

[0024] Figure 8 This is a schematic diagram of the terminal device provided in the embodiments of this application. Detailed Implementation

[0025] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0026] To illustrate the technical solution described in this application, specific embodiments are provided below.

[0027] Figure 1 A flowchart illustrating the implementation of the infusion pressure monitoring method provided in Embodiment 1 of this application is shown, and is described in detail below:

[0028] Step S101: Obtain bile duct pressure monitoring information, bile duct ambient temperature monitoring information, infusion tubing fluid fluctuation monitoring information, suction tubing ambient temperature monitoring information, and multiple bile duct infusion images.

[0029] In this embodiment, multi-dimensional monitoring data of the entire intraoperative bile duct perfusion process can be simultaneously collected through the integrated sensing and acquisition components, tubing clamp-type sensing devices, and intraoperative high-definition image acquisition devices that are equipped with rigid choledochoscopes. This enables real-time and synchronous acquisition of bile duct pressure monitoring information, bile duct ambient temperature monitoring information, perfusion tubing fluid fluctuation monitoring information, suction tubing ambient temperature monitoring information, and multiple bile duct perfusion images. All collected raw monitoring data are transmitted to the intelligent control host to complete the reception and preliminary buffering of raw signals.

[0030] In this embodiment, the biliary tract pressure monitoring information may include cholangioscopy end-point pressure monitoring information, biliary tract proximal pressure monitoring information, and biliary tract pressure gradient change monitoring information. The cholangioscopy end-point pressure monitoring information is real-time intraluminal pressure data near the water outlet of the rigid cholangioscopy, with a monitoring range of -50 to 200 cmH2O and a monitoring accuracy of ±1 cmH2O. It directly reflects the true perfusion pressure state inside the human biliary cavity. The biliary tract proximal pressure monitoring information is the pressure data at the connection point between the cholangioscopy interface and the perfusion tubing, which can help verify the accuracy of the intraluminal pressure value. The biliary tract pressure gradient change monitoring information is the dynamic difference data between the end-point and proximal pressures, which can identify abnormal pressure changes caused by tubing blockage or fluid stagnation. All three types of pressure data are collected using medical piezoresistive pressure sensors, and the sensor signals are transmitted to the intelligent control host via shielded cables.

[0031] In this embodiment, the environmental temperature monitoring information of the bile duct tubing may include real-time temperature monitoring information of the bile duct irrigation fluid, environmental temperature monitoring information of the outer wall of the bile duct tubing, and environmental temperature fluctuation difference monitoring information of the bile duct tubing. Among them, the real-time temperature monitoring information of the bile duct irrigation fluid is the real-time temperature value of the physiological saline irrigation fluid flowing inside the tubing; the environmental temperature monitoring information of the outer wall of the bile duct tubing is the real-time temperature value of the intraoperative environment outside the irrigation tubing; and the environmental temperature fluctuation difference monitoring information of the bile duct tubing is the real-time difference between the temperature of the irrigation fluid and the temperature of the outer wall of the tubing. The temperature monitoring range is 0 to 50°C, the temperature resolution is 0.01°C, and the temperature accuracy is ±0.5°C. Temperature fluctuations will indirectly affect the fluid flow stability and pressure monitoring accuracy. The three types of temperature data are synchronously collected and transmitted to the intelligent control host through the integrated temperature sensor probe of the tubing.

[0032] In this embodiment, the fluid fluctuation monitoring information in the injection pipeline can include instantaneous flow rate fluctuation monitoring information of the injection fluid, fluid pulsation frequency monitoring information of the injection pipeline, and steady-state flow monitoring information of the injection pipeline. Among them, the instantaneous flow rate fluctuation monitoring information of the injection fluid is the dynamic offset data of the real-time flow rate of the fluid inside the injection pipeline, with a flow rate monitoring range of 0 to 1000 ml / min; the fluid pulsation frequency monitoring information of the injection pipeline is the number of periodic fluctuations during the fluid flow process, which can reflect the operational stability of the injection pump; and the steady-state flow monitoring information of the injection pipeline is the state data of the fluid's continuous and constant flow. The three types of fluid fluctuation data are collected non-contactly through a clamp-type ultrasonic flow sensor, thereby providing fluid-dimensional data support for pressure deviation tracing.

[0033] In this embodiment, the ambient temperature monitoring information of the suction pipeline can include the temperature monitoring information of the suction waste liquid and the ambient temperature difference monitoring information of the suction pipeline. The temperature monitoring information of the suction waste liquid is the real-time temperature data of the bile and waste liquid mixture extracted by the suction pipeline, and the ambient temperature difference monitoring information of the suction pipeline is the temperature difference data of the environment inside and outside the suction pipeline. The temperature data can help determine whether there are problems such as condensation and scaling or changes in fluid viscosity in the suction pipeline, and then help to investigate the hidden danger of abnormal pressure rise caused by pipeline blockage. The data is synchronously transmitted to the intelligent control host for unified summary.

[0034] In this embodiment, the bile duct perfusion imaging information may include intraoperative bile duct cavity imaging information, tubing fluid flow imaging information, and bile duct stone and blood clot blockage location imaging information. Among them, the intraoperative bile duct cavity imaging information is a real-time visual image of the human bile duct cavity acquired by a rigid choledochoscope, which can intuitively show the bile duct dilation, stenosis, and congestion. The tubing fluid flow imaging information is an image of the fluid flow state inside the perfusion and suction tubing acquired by an external high-definition camera. The bile duct stone and blood clot blockage location imaging information is a captured image of the tubing and bile duct cavity where stone fragments and blood clots accumulate and block the bile duct. The image acquisition frame rate can be 30 frames / second, and then it is transmitted to the host image processing module to complete frame storage and preprocessing.

[0035] Step S102: Based on the preset biliary perfusion status feature extraction model, feature extraction processing is performed on the multiple biliary perfusion image information to generate multiple biliary perfusion status feature information.

[0036] In this embodiment, the preset biliary perfusion state feature extraction model can be manually preset and can employ a deep learning model fused with YOLOv7 and CBAM attention mechanisms. The preset biliary perfusion state feature extraction model includes a manually preset temporal feature extraction sub-model, a manually preset spatial feature extraction sub-model, and a manually preset spatiotemporal feature fusion sub-model. The temporal feature extraction sub-model uses a temporal convolutional network model, the spatial feature extraction sub-model uses a lightweight convolutional neural network model, and the spatiotemporal feature fusion sub-model uses... A multi-head feature fusion network model was used. First, the acquired biliary perfusion images were preprocessed by frame filtering and illumination equalization, with a filtering interval of 5 frames per frame. Then, the temporal feature extraction sub-model was used to extract the temporal variation features of fluid flow and the dynamic variation features of cavity status in the continuous frames of the images. Next, the spatial feature extraction sub-model was used to extract the spatial location features of duct blockage and the morphological features of biliary cavity in a single frame of the image. Finally, the temporal and spatial features were weighted and fused by the spatiotemporal feature fusion sub-model to generate multiple biliary perfusion status feature information with unified dimensions and accurate features.

[0037] Step S103: Based on the bile duct pressure monitoring information, bile duct ambient temperature monitoring information, infusion pipeline fluid fluctuation monitoring information, suction pipeline ambient temperature monitoring information, multiple bile duct infusion state characteristic information, and a preset bile duct infusion pressure prediction model, generate multiple bile duct infusion pressure prediction information.

[0038] In this embodiment, the preset biliary perfusion pressure prediction model can be manually preset and can employ a deep learning model fused with 1D-CNN and BiLSTM. The preset biliary perfusion pressure prediction model includes a manually preset biliary perfusion pressure fitting sub-model, a manually preset sub-model for calculating the correlation between tubing fluid fluctuations and temperature, and a manually preset sub-model for identifying biliary perfusion status. The biliary perfusion pressure fitting sub-model uses a multiple linear regression fitting algorithm, the tubing fluid fluctuation and temperature correlation calculation sub-model uses an adaptive correlation degree calculation algorithm, and the biliary perfusion status identification sub-model uses a lightweight gradient boosting tree algorithm model. Firstly, through the tubing fluid fluctuation and temperature correlation calculation sub-model, combined with fluid... The temperature-related threshold parameter is calculated, and the fluid temperature-related threshold parameter can be set to 0.92 to obtain the characteristic information of pipeline fluid fluctuation and temperature correlation. Then, through the biliary perfusion state identification sub-model, the biliary cavity state judgment parameter is matched, and the biliary cavity state judgment parameter can be set to 0.85. Combined with pressure monitoring data and image feature information, biliary perfusion state identification information is generated. Then, through the biliary perfusion pressure fitting sub-model, with a preset pressure fitting correction coefficient, the pressure fitting correction coefficient is set to 1.03, multi-dimensional data is integrated and fitted to generate multiple biliary perfusion pressure prediction information including instantaneous predicted pressure, time-series predicted pressure, and pressure extreme value prediction.

[0039] The perfusion pressure monitoring method provided in this application effectively solves the technical defects of existing biliary perfusion pressure monitoring that rely solely on a single sensor for data collection, such as low monitoring accuracy, pressure drift lag, and abnormality identification lag. It achieves millisecond-level dynamic monitoring and accurate prediction of intraoperative biliary perfusion pressure, effectively avoiding intraoperative complications caused by biliary hypertension and tubing blockage, and significantly improving the safety and intelligence level of perfusion control in rigid cholangioscopy surgery. It provides accurate data support for intraoperative intelligent pressure regulation, automatic backflushing, and risk warning.

[0040] Figure 2 The flowchart illustrating the implementation of the infusion pressure monitoring method provided in Embodiment 2 of this application is shown. The difference between this method and Embodiment 1 described above is that:

[0041] The preset biliary perfusion state feature extraction model includes a preset biliary perfusion state temporal feature extraction sub-model, a preset biliary perfusion state spatial feature extraction sub-model, and a preset biliary perfusion state spatiotemporal feature fusion sub-model.

[0042] Step S102 specifically includes:

[0043] Step S201: Based on the preset bile duct perfusion state temporal feature extraction sub-model, the temporal feature extraction processing is performed on the multiple bile duct perfusion image information to obtain multiple bile duct perfusion state temporal feature information.

[0044] In this embodiment, the preset sub-model for extracting the temporal features of biliary perfusion status can be pre-defined and can be a temporal convolutional network deep learning model. The temporal feature sampling interval parameter can be set to 5 frames, and the temporal feature weight ratio parameter can be set to 0.88. First, the preprocessed multiple biliary perfusion image information is reconstructed into a continuous frame temporal sequence. Then, the temporal sequence of the image is convolved layer by layer through the temporal convolutional network model to extract the temporal features of dynamic changes in perfusion fluid, temporal features of biliary cavity morphological fluctuations, and temporal features of the development and evolution of duct obstruction. Then, the extracted multidimensional temporal features are filtered and denoised to generate stable and accurate temporal feature information of multiple biliary perfusion statuses.

[0045] Step S202: Based on the preset biliary perfusion state spatial feature extraction sub-model, spatial feature extraction processing is performed on the multiple biliary perfusion image information to obtain multiple biliary perfusion state spatial feature information.

[0046] In this embodiment, the preset spatial feature extraction sub-model for biliary perfusion status can be pre-defined and can be a lightweight convolutional neural network deep learning model. The receptive field parameter of spatial features can be set to 3, and the confidence threshold of spatial features can be set to 0.90. First, the region of interest of a single frame of biliary perfusion image information is cropped and the pixels are normalized. Then, the feature convolution of the image spatial pixel matrix is ​​extracted by the lightweight convolutional neural network model, thereby capturing the spatial features of biliary cavity stenosis, the spatial features of the location of the obstruction in the pipeline, and the spatial features of fluid velocity distribution. Then, invalid background features are filtered out, thereby generating multiple highly recognizable spatial feature information of biliary perfusion status.

[0047] Step S203: Based on the preset spatiotemporal feature fusion sub-model of biliary perfusion state, feature fusion processing is performed on the multiple temporal feature information and multiple spatial feature information of biliary perfusion state to generate multiple biliary perfusion state feature information.

[0048] In this embodiment, the preset spatiotemporal feature fusion sub-model of biliary perfusion status can be pre-defined and can adopt a multi-head feature fusion network deep learning model. The spatiotemporal fusion weight balance parameter can be set to 0.95, and the feature fusion dimension unification parameter can be set to 128 dimensions. First, the extracted multiple temporal feature information of biliary perfusion status and multiple spatial feature information of biliary perfusion status are concatenated. Then, the concatenated features are subjected to multi-dimensional weight allocation operation through the multi-head feature fusion network, thereby completing the deep coupling and fusion of temporal dynamic features and spatial structural features. Then, the fused features are subjected to global pooling and feature purification processing to generate multiple biliary perfusion status feature information with both spatiotemporal dimension information and stronger representation ability.

[0049] The perfusion pressure monitoring method provided in this application embodiment can capture the dynamic changes in perfusion status and spatial structural anomalies in an all-round way, effectively avoiding the problems of feature omission and one-sided representation that exist in single feature extraction methods. This provides high-quality, high-dimensional image feature data support for subsequent intelligent prediction of perfusion pressure, and greatly improves the precision of perfusion pressure monitoring and prediction.

[0050] Figure 3 The flowchart illustrating the implementation of the infusion pressure monitoring method provided in Embodiment 3 of this application is shown. Its difference from Embodiment 1 described above lies in:

[0051] The preset biliary perfusion pressure prediction model includes a preset biliary perfusion pressure fitting sub-model, a preset pipeline fluid fluctuation and temperature correlation calculation sub-model, and a preset biliary perfusion state identification sub-model.

[0052] Step S103 specifically includes:

[0053] Step S301: Based on the fluid fluctuation monitoring information of the injection pipeline, the ambient temperature monitoring information of the suction pipeline, and the preset pipeline fluid fluctuation and temperature correlation calculation sub-model, the pipeline fluid fluctuation and temperature correlation characteristic information is calculated.

[0054] In this embodiment, the preset pipeline fluid fluctuation and temperature correlation calculation sub-model can be preset manually and can adopt an adaptive correlation degree calculation algorithm model. The fluid temperature correlation threshold parameter can be set to 0.92, and the fluid fluctuation correction coefficient can be set to 1.02. First, real-time monitoring information of fluid fluctuation in the injection pipeline and ambient temperature monitoring information of the suction pipeline are collected. Then, the adaptive correlation degree calculation algorithm model is used to perform correlation coupling calculation on multiple types of data such as fluid fluctuation amplitude, fluctuation frequency, and ambient temperature difference. Then, the influence law of temperature change on fluid viscosity and flow stability is analyzed. Finally, the quantitative calculation of multi-parameter correlation features is completed, thereby generating quantitatively accurate pipeline fluid fluctuation and temperature correlation feature information.

[0055] Step S302: Generate bile duct perfusion status identification information based on the bile duct pressure monitoring information, multiple bile duct perfusion status feature information and the preset bile duct perfusion status identification sub-model.

[0056] In this embodiment, the preset biliary perfusion status identification sub-model can be pre-defined and can adopt a lightweight gradient boosting tree algorithm model. The biliary cavity status judgment parameter can be set to 0.85, and the perfusion status grading threshold can be set to 0.78. First, the real-time pressure data and pressure gradient data contained in the biliary pipeline pressure monitoring information are aligned and integrated with multiple biliary perfusion status feature information. Then, the lightweight gradient boosting tree algorithm model is used to perform multi-feature joint judgment operation on the integrated data to distinguish between normal biliary perfusion status, slight pipeline blockage status, abnormal biliary high pressure status, and fluid instability fluctuation status. Finally, the accurate classification and judgment of the perfusion operation status is completed, thereby generating biliary perfusion status identification information containing status type, status level, and degree of abnormality.

[0057] Step S303: Based on the biliary tract pressure monitoring information, biliary tract perfusion status identification information, biliary fluid fluctuation and temperature correlation characteristic information, and the preset biliary tract perfusion pressure fitting sub-model, generate multiple biliary tract perfusion pressure prediction information.

[0058] In this embodiment, the preset biliary perfusion pressure fitting sub-model can be pre-set manually and can adopt a multiple linear regression fitting algorithm model. The pressure fitting correction coefficient can be set to 1.03, and the pressure time series fitting step size parameter can be set to 10 milliseconds. First, the three types of heterogeneous data, namely biliary pipeline pressure monitoring information, biliary perfusion status identification information, and pipeline fluid fluctuation and temperature correlation feature information, are subjected to dimensional normalization processing. Then, the multi-parameter coupled fitting operation is completed by the multiple linear regression fitting algorithm model. Subsequently, the real-time pressure is deviated and the trend is predicted by combining multi-dimensional parameters of temperature, fluid, and cavity status. Then, the pressure values ​​and extreme value prediction results at different time series nodes are output, thereby generating multiple biliary perfusion pressure prediction information including instantaneous predicted pressure, time series predicted pressure, and pressure extreme value prediction.

[0059] The perfusion pressure monitoring method provided in this application embodiment enables comprehensive quantitative analysis of fluid temperature correlation characteristics, bile duct perfusion operation status, and dynamic pressure changes. Through multi-parameter coupling fitting, it effectively compensates for drift deviation and hysteresis errors existing in single pressure sensor monitoring, thereby achieving real-time accurate monitoring and advanced prediction of bile duct perfusion pressure. This effectively improves the stability, accuracy, and timeliness of intraoperative perfusion pressure monitoring, and thoroughly improves the shortcomings of traditional monitoring methods such as insufficient accuracy and delayed abnormality identification. It provides reliable data algorithm support for intelligent perfusion pressure regulation, obstruction backflow, and high-pressure early warning in rigid cholangioscopy surgery.

[0060] Figure 4 The flowchart illustrating the implementation of the perfusion pressure monitoring method provided in Embodiment 4 of this application is shown. The difference between this method and Embodiment 1 is that, after step S103, the method further includes:

[0061] Step S401: Based on the preset standard curve library of bile duct perfusion pressure changes, the multiple bile duct perfusion pressure prediction information are compared and verified to obtain the bile duct perfusion pressure change standard curve information, bile duct perfusion instantaneous pressure deviation information, bile duct perfusion pressure time series drift information, and bile duct perfusion pressure extreme value mutation information.

[0062] In this embodiment, the preset standard curve library for biliary perfusion pressure changes can be manually preset. The library contains multiple sets of standard pressure time-series curve data corresponding to normal clinical perfusion conditions, slightly abnormal conditions, and high-pressure dangerous conditions. The curve comparison and matching threshold can be set to 0.91, and the pressure deviation identification accuracy can be set to ±1 cmH2O. First, standard pressure time-series curve samples adapted for rigid cholangioscopy surgery are retrieved from the preset standard curve library for biliary perfusion pressure changes. Then, the time-series pressure data corresponding to multiple biliary perfusion pressure prediction information are... The instantaneous pressure data, extreme pressure data, and standard curve data are compared and verified frame by frame and time by time. Then, the overlapping and offset regions of the real-time predicted pressure and the standard pressure curve are distinguished. Then, four types of data information are accurately extracted and divided: standard curve matching results, instantaneous pressure numerical deviation, long-term time series drift error, and instantaneous pressure extreme value jump change. Thus, the standard curve information of bile duct perfusion pressure change after comparison, bile duct perfusion instantaneous pressure deviation information, bile duct perfusion pressure time series drift information, and bile duct perfusion pressure extreme value jump change information are generated.

[0063] Step S402: Based on the standard curve information of the bile duct perfusion pressure change after comparison, and according to the bile duct perfusion instantaneous pressure deviation information, bile duct perfusion pressure time-series drift information, and bile duct perfusion pressure extreme value mutation information, calculate the bile duct perfusion instantaneous pressure deviation compensation information, bile duct perfusion pressure time-series drift compensation information, and bile duct perfusion pressure extreme value mutation compensation information.

[0064] In this embodiment, the preset pressure deviation compensation calculation model can be manually preset and can adopt an adaptive deviation correction algorithm model. The instantaneous deviation compensation coefficient can be set to 1.02, the time-series drift correction coefficient can be set to 0.98, and the extreme value mutation smoothing coefficient can be set to 0.95. First, the normal pressure fluctuation benchmark range is established by comparing the information of the standard curve of bile duct perfusion pressure change. Then, the instantaneous numerical offset is quantified by combining the instantaneous pressure deviation information of bile duct perfusion. The instantaneous deviation compensation amount is calculated by matching the instantaneous deviation compensation coefficient. Then, the long-term cumulative drift law is statistically analyzed based on the time-series drift information of bile duct perfusion pressure. The time-series drift correction amount is generated by combining the time-series drift correction coefficient. Then, abnormal jump amplitude is identified based on the extreme value mutation information of bile duct perfusion pressure. The extreme value mutation error correction calculation is completed by using the extreme value mutation smoothing coefficient. Thus, the instantaneous pressure deviation compensation information, the time-series drift compensation information, and the extreme value mutation compensation information of bile duct perfusion pressure are generated.

[0065] Step S403: Based on the instantaneous pressure deviation compensation information, the temporal drift compensation information, and the extreme value mutation compensation information of the bile duct perfusion pressure, the multiple bile duct perfusion pressure prediction information are compensated to generate multiple compensated bile duct perfusion pressure prediction information.

[0066] In this embodiment, the preset pressure data fusion compensation strategy can be manually preset, and a multi-dimensional error superposition correction strategy is adopted. The pressure accuracy threshold after compensation can be ±0.8cmH2O. First, the three types of compensation data, namely, the instantaneous pressure deviation compensation information of bile duct perfusion, the time-series drift compensation information of bile duct perfusion pressure, and the extreme value mutation compensation information of bile duct perfusion pressure, are integrated and summarized. Then, the instantaneous error, time-series drift error, and extreme value mutation error existing in the multiple bile duct perfusion pressure prediction information are corrected and offset one by one. Then, the corrected pressure data is uniformly calibrated and smoothed to remove invalid error data caused by sensor temperature drift, fluid fluctuation, and image noise during the monitoring process. Finally, the full-dimensional pressure data optimization and correction are completed, thereby generating multiple compensated bile duct perfusion pressure prediction information with higher accuracy, stronger stability, and closer fit to the actual bile duct pressure state during surgery.

[0067] The perfusion pressure monitoring method provided in this application achieves high-precision optimization and calibration of biliary perfusion pressure monitoring data, thereby effectively solving the problems of instantaneous deviation, time series drift, and extreme value mutation distortion existing in the existing pressure monitoring. It significantly improves the accuracy, stability, and authenticity of intraoperative biliary perfusion pressure monitoring, and provides more accurate and reliable core data support for intraoperative biliary high pressure early warning, pipeline blockage identification, and intelligent perfusion control, thereby improving the intelligence and safety management level of the rigid choledochoscopy perfusion system.

[0068] Figure 5The flowchart illustrating the implementation of the infusion pressure monitoring method provided in Embodiment 5 of this application is shown. The difference between this method and Embodiment 1 is that, after step S103, the method further includes:

[0069] Step S501: Based on the preset biliary perfusion pressure feature extraction model, feature extraction processing is performed on the multiple biliary perfusion pressure prediction information to generate multiple biliary perfusion pressure feature information.

[0070] In this embodiment, the preset biliary perfusion pressure feature extraction model can be pre-defined manually. It can be a lightweight one-dimensional convolutional neural network deep learning model, with the pressure feature extraction dimension parameter set to 64 dimensions and the pressure feature screening threshold set to 0.82. First, data normalization and time-series alignment preprocessing are performed on multiple biliary perfusion pressure prediction information. Then, the lightweight one-dimensional convolutional neural network deep learning model is used to extract multi-dimensional features from instantaneous pressure data, time-series pressure data, and pressure extreme value data. Subsequently, pressure steady-state features, pressure abrupt change features, pressure time-series fluctuation features, and pressure gradient change features are mined. Finally, the preset pressure feature screening threshold is used to remove invalid stray features and purify effective features, thereby generating multiple biliary perfusion pressure feature information with uniform dimensions and high feature recognition.

[0071] Step S502: Based on the preset mapping relationship between biliary infusion pressure characteristics and pump control parameters, multiple infusion pump parameter adjustment information is generated according to the multiple biliary infusion pressure characteristic information.

[0072] In this embodiment, the preset mapping relationship between biliary infusion pressure characteristics and pump control parameters can be preset manually. A multi-dimensional adaptive mapping rule model can be invoked. The pump speed adjustment gradient parameter can be set to 5 levels, and the pump flow rate adjustment accuracy parameter can be set to 5 ml / min. The preset mapping relationship between biliary infusion pressure characteristics and pump control parameters covers the adjustment standards of infusion pump speed, output flow rate, and operating frequency corresponding to the pressure steady-state range, the pressure slight fluctuation range, and the pressure over-limit abnormal range, respectively. First, the preset mapping relationship between biliary infusion pressure characteristics and pump control parameters is retrieved. Then, multiple biliary infusion pressure characteristic information is matched with the mapping rule one by one. Then, the current infusion working condition is determined according to the pressure fluctuation degree, the pressure extreme value, and the pressure time sequence change trend. Then, the corresponding pump speed adjustment value, pump output flow rate value, and pump start-stop control command are matched to generate multiple infusion pump parameter adjustment information adapted to the current biliary infusion working condition.

[0073] Step S503: Based on the preset mapping relationship between biliary infusion pressure characteristics and suction valve on / off control parameters, generate multiple suction valve on / off control parameter information according to the multiple biliary infusion pressure characteristic information.

[0074] In this embodiment, the preset mapping relationship between the bile duct infusion pressure characteristics and the suction valve on / off control parameters can be preset manually. A threshold linkage control rule model can be invoked. The suction valve opening pressure threshold can be set to 120 cmH2O, the suction valve closing pressure threshold can be set to 80 cmH2O, and the suction valve delay on / off parameter can be set to 200 milliseconds. The preset mapping relationship includes suction valve on / off, opening and closing duration, and intermittent start / stop control rules corresponding to high pressure abnormal conditions, normal infusion conditions, and low pressure stagnation conditions. First, the real-time intraluminal pressure condition of the bile duct is determined by multiple bile duct infusion pressure characteristic information. Then, the preset mapping relationship between the bile duct infusion pressure characteristics and the suction valve on / off control parameters is invoked to complete the condition matching. Then, the single opening duration, closing interval duration, and intermittent working frequency of the suction valve are determined according to the abnormal level of the pressure characteristics. Then, standardized valve control adjustment commands are generated in a quantified manner, thereby generating multiple suction valve on / off control parameter information adapted to the intraoperative pressure state.

[0075] The perfusion pressure monitoring method provided in this application dynamically matches the optimal perfusion and negative pressure suction parameters based on the real-time pressure status during surgery, thereby achieving closed-loop autonomous control of biliary perfusion pressure. This effectively avoids problems such as unstable biliary pressure, tubing blockage, and high-pressure biliary injury caused by lag in manual adjustment and unreasonable parameter matching. It significantly improves the stability and adaptability of the intraoperative biliary perfusion system, thereby enhancing the intelligence level and surgical safety of perfusion control in rigid choledochoscopy.

[0076] Figure 6 The flowchart illustrating the implementation of the infusion pressure monitoring method provided in Embodiment Six of this application is shown. The difference between this method and Embodiment Five is that, after step S503, the method further includes:

[0077] Step S601: Obtain the pressure monitoring information of the biliary tubing after regulation, the fluid fluctuation monitoring information of the perfusion tubing after regulation, and multiple biliary perfusion images after regulation.

[0078] In this embodiment, the postoperative control data acquisition frequency parameter can be preset by the user. The acquisition frequency can be set to 20 frames / second, and the control data acquisition duration parameter can be set to 5 seconds. The pressure monitoring information of the bile duct after control can be collected in real time through the integrated sensing acquisition component of the rigid cholangioscope. The fluid fluctuation monitoring information of the perfusion tubing after control can be collected synchronously through the tubing clamp-on sensing device. Multiple post-control bile duct perfusion images are continuously captured by the intraoperative high-definition imaging acquisition device. This completes the comprehensive synchronous acquisition of multi-dimensional working condition data after control, thereby ensuring that the acquired data can fully reflect the real perfusion working condition after the pump parameter adjustment and suction valve on / off adjustment. Then, all the original monitoring data after control are uniformly transmitted to the intelligent control host for caching and preprocessing, thereby obtaining complete post-control bile duct pressure monitoring information, post-control perfusion tubing fluid fluctuation monitoring information, and multiple post-control bile duct perfusion images.

[0079] Step S602: The pressure monitoring information of the regulated bile duct tubing, the fluid fluctuation monitoring information of the regulated perfusion tubing, and multiple regulated bile duct perfusion images are sent to the terminal device for display.

[0080] In this embodiment, a real-time dynamic visualization rendering algorithm model can be adopted, and the data refresh interval parameter can be set to 50 milliseconds. First, the intelligent control host performs data formatting, image frame optimization, and abnormal data annotation processing on the post-regulation biliary tubing pressure monitoring information, post-regulation perfusion tubing fluid fluctuation monitoring information, and multiple post-regulation biliary perfusion image information. Then, the structured data is transformed into a visual display form of dynamic curves, working condition annotations, and real-time image images. Subsequently, the processed multi-dimensional regulation data is synchronously pushed to the intraoperative operation terminal and medical monitoring terminal equipment through the wireless transmission module and wired data transmission interface. Then, the real-time data and images are dynamically refreshed and displayed, thereby enabling medical staff to observe the effect of biliary perfusion regulation in real time.

[0081] The perfusion pressure monitoring method provided in this application embodiment enables full-process visual monitoring of biliary perfusion conditions, thereby effectively solving the problems of existing perfusion control lacking real-time feedback and the inability to intuitively verify the control effect. It significantly improves the controllability and monitorability of intraoperative biliary perfusion control, providing intuitive and real-time data and image support for medical staff to perform precise intraoperative operations, dynamic interventions, and risk reviews, and comprehensively enhancing the intelligent operation and maintenance capabilities and surgical safety assurance capabilities of the rigid choledochoscopy perfusion system.

[0082] Corresponding to the method in the above embodiments, Figure 7 A structural block diagram of the infusion pressure monitoring device provided in the embodiments of this application is shown. For ease of explanation, only the parts related to the embodiments of this application are shown. Figure 7The example infusion pressure monitoring device can be the execution subject of the infusion pressure monitoring method provided in the aforementioned embodiment 1.

[0083] Reference Figure 7 The injection pressure monitoring device includes:

[0084] The information acquisition module 710 is used to acquire biliary tubing pressure monitoring information, biliary tubing ambient temperature monitoring information, perfusion tubing fluid fluctuation monitoring information, suction tubing ambient temperature monitoring information, and multiple biliary perfusion image information.

[0085] The biliary perfusion status feature information generation module 720 is used to perform feature extraction processing on the multiple biliary perfusion image information based on a preset biliary perfusion status feature extraction model, and generate multiple biliary perfusion status feature information.

[0086] The biliary perfusion pressure prediction information generation module 730 is used to generate multiple biliary perfusion pressure prediction information based on the biliary tubing pressure monitoring information, biliary tubing ambient temperature monitoring information, perfusion tubing fluid fluctuation monitoring information, suction tubing ambient temperature monitoring information, multiple biliary perfusion state characteristic information, and a preset biliary perfusion pressure prediction model.

[0087] The process by which each module in the infusion pressure monitoring device provided in this application implements its respective function can be specifically referred to the foregoing. Figure 1 The description of Embodiment 1 shown will not be repeated here.

[0088] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0089] It should be understood that, when used in this application specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or a collection thereof.

[0090] It should also be understood that the term “and / or” as used in this application specification and the appended claims means any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0091] As used in this application specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if detected [the described condition or event]" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once detected [the described condition or event]," or "in response to detection [the described condition or event]."

[0092] Furthermore, in the description of this application and the appended claims, the terms "first," "second," "third," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance. It should also be understood that although the terms "first," "second," etc., are used in the text to describe various elements in some embodiments of this application, these elements should not be limited by these terms. These terms are merely used to distinguish one element from another. For example, a first table may be named a second table, and similarly, a second table may be named a first table, without departing from the scope of the various described embodiments. Both the first table and the second table are tables, but they are not the same table.

[0093] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of this application include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0094] The perfusion pressure monitoring method provided in this application can be applied to terminal devices such as mobile phones, tablets, wearable devices, in-vehicle devices, augmented reality / virtual reality devices, laptops, super mobile personal computers, netbooks, and personal digital assistants. This application does not impose any restrictions on the specific type of terminal device.

[0095] For example, the terminal device may be a station in a WLAN, a cellular phone, a cordless phone, a session initiation protocol phone, a wireless local loop station, a personal digital processing device, a handheld device with wireless communication capabilities, a computing device or other processing device connected to a wireless modem, an in-vehicle device, a vehicle networking terminal, a computer, a laptop computer, a handheld communication device, a handheld computing device, a satellite wireless device, a wireless modem card, a set-top box, a user premises equipment, and / or other devices for communication over a wireless system, as well as next-generation communication systems, such as mobile terminals in 5G networks or mobile terminals in future evolved public terrestrial mobile networks, etc.

[0096] Figure 8 This is a schematic diagram of the structure of a terminal device provided in an embodiment of this application. For example... Figure 8 As shown, the terminal device 8 in this embodiment includes: at least one processor 80 ( Figure 8 Only one is shown in the diagram), and a memory 81 is stored in which a computer program 82 that can run on the processor 80 is stored. When the processor 80 executes the computer program 82, it implements the steps in the various perfusion pressure monitoring method embodiments described above, for example... Figure 1 Steps S101 to S103 are shown. Alternatively, when the processor 80 executes the computer program 82, it implements the functions of each module / unit in the above-described device embodiments, for example... Figure 7 The functions of modules 710 to 730 are shown.

[0097] The terminal device 8 can be a desktop computer, laptop, handheld computer, or cloud server, etc. The terminal device may include, but is not limited to, a processor 80 and a memory 81. Those skilled in the art will understand that... Figure 8 This is merely an example of terminal device 8 and does not constitute a limitation on terminal device 8. It may include more or fewer components than shown, or combine certain components, or different components. For example, the terminal device may also include input transmission devices, network access devices, buses, etc.

[0098] The processor 80 may be a central processing unit, or it may be other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0099] In some embodiments, the memory 81 may be an internal storage unit of the terminal device 8, such as a hard disk or memory of the terminal device 8. The memory 81 may also be an external storage device of the terminal device 8, such as a plug-in hard disk, smart memory card, secure digital card, flash memory card, etc., equipped on the terminal device 8. Furthermore, the memory 81 may include both internal and external storage units of the terminal device 8. The memory 81 is used to store operating systems, applications, bootloaders, data, and other programs, such as the program code of computer programs. The memory 81 can also be used to temporarily store data that has been sent or will be sent.

[0100] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0101] This application also provides a terminal device, which includes at least one memory, at least one processor, and a computer program stored in the at least one memory and executable on the at least one processor. When the processor executes the computer program, it causes the terminal device to implement the steps in any of the above method embodiments.

[0102] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps described in the various method embodiments above.

[0103] This application provides a computer program product that, when run on a terminal device, enables the terminal device to implement the steps described in the various method embodiments above.

[0104] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, a recording medium, a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, a computer memory, a read-only memory, a random access memory, an electrical carrier signal, a telecommunication signal, and a software distribution medium, etc.

[0105] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0106] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0107] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0108] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for monitoring injection pressure, characterized in that, include: Acquire information on biliary tubing pressure monitoring, biliary tubing ambient temperature monitoring, infusion tubing fluid fluctuation monitoring, suction tubing ambient temperature monitoring, and multiple biliary perfusion images. Based on a preset biliary perfusion status feature extraction model, feature extraction processing is performed on the multiple biliary perfusion image information to generate multiple biliary perfusion status feature information. Based on the biliary tract pressure monitoring information, biliary tract ambient temperature monitoring information, infusion pipeline fluid fluctuation monitoring information, suction pipeline ambient temperature monitoring information, multiple biliary tract infusion status characteristic information, and a preset biliary tract infusion pressure prediction model, multiple biliary tract infusion pressure prediction information are generated.

2. The infusion pressure monitoring method as described in claim 1, characterized in that, The preset biliary perfusion state feature extraction model includes a preset biliary perfusion state temporal feature extraction sub-model, a preset biliary perfusion state spatial feature extraction sub-model, and a preset biliary perfusion state spatiotemporal feature fusion sub-model. The step of extracting features from the multiple biliary perfusion images based on a preset biliary perfusion status feature extraction model to generate multiple biliary perfusion status feature information specifically includes: Based on a preset sub-model for extracting temporal features of biliary perfusion status, temporal feature extraction processing is performed on the multiple biliary perfusion image information to obtain multiple temporal feature information of biliary perfusion status. Based on a preset sub-model for extracting spatial features of biliary perfusion status, spatial feature extraction processing is performed on the multiple biliary perfusion image information to obtain multiple spatial feature information of biliary perfusion status. Based on a preset spatiotemporal feature fusion sub-model for biliary perfusion status, feature fusion processing is performed on the multiple temporal feature information and multiple spatial feature information of biliary perfusion status to generate multiple biliary perfusion status feature information.

3. The infusion pressure monitoring method as described in claim 1, characterized in that, The preset biliary perfusion pressure prediction model includes a preset biliary perfusion pressure fitting sub-model, a preset pipeline fluid fluctuation and temperature correlation calculation sub-model, and a preset biliary perfusion state identification sub-model. The step of generating multiple biliary perfusion pressure prediction information based on the biliary tubing pressure monitoring information, biliary tubing ambient temperature monitoring information, perfusion tubing fluid fluctuation monitoring information, suction tubing ambient temperature monitoring information, multiple biliary perfusion state characteristic information, and a preset biliary perfusion pressure prediction model specifically includes: Based on the fluid fluctuation monitoring information of the injection pipeline, the ambient temperature monitoring information of the suction pipeline, and the preset pipeline fluid fluctuation and temperature correlation calculation sub-model, the pipeline fluid fluctuation and temperature correlation characteristic information is calculated. Based on the biliary tract pressure monitoring information, multiple biliary perfusion status feature information and the preset biliary perfusion status identification sub-model, biliary perfusion status identification information is generated. Based on the biliary tract pressure monitoring information, biliary perfusion status identification information, duct fluid fluctuation and temperature correlation characteristics, and the preset biliary perfusion pressure fitting sub-model, multiple biliary perfusion pressure prediction information are generated.

4. The infusion pressure monitoring method as described in claim 1, characterized in that, After the step of generating multiple biliary perfusion pressure prediction information based on the biliary tubing pressure monitoring information, biliary tubing ambient temperature monitoring information, infusion tubing fluid fluctuation monitoring information, suction tubing ambient temperature monitoring information, multiple biliary perfusion state characteristic information, and a preset biliary perfusion pressure prediction model, the method further includes: Based on a pre-defined library of standard curves for changes in bile duct perfusion pressure, the multiple predicted information on bile duct perfusion pressure are compared and verified to obtain the standard curve information for changes in bile duct perfusion pressure, the instantaneous deviation information of bile duct perfusion pressure, the temporal drift information of bile duct perfusion pressure, and the information on extreme changes in bile duct perfusion pressure. Based on the standard curve information of the bile duct perfusion pressure change after comparison, and according to the bile duct perfusion instantaneous pressure deviation information, bile duct perfusion pressure time-series drift information, and bile duct perfusion pressure extreme value mutation information, the bile duct perfusion instantaneous pressure deviation compensation information, bile duct perfusion pressure time-series drift compensation information, and bile duct perfusion pressure extreme value mutation compensation information are calculated. Based on the instantaneous pressure deviation compensation information, the temporal drift compensation information, and the extreme value mutation compensation information of the bile duct perfusion pressure, the multiple bile duct perfusion pressure prediction information are compensated to generate multiple compensated bile duct perfusion pressure prediction information.

5. The method for monitoring injection pressure as described in claim 1, characterized in that, After the step of generating multiple biliary perfusion pressure prediction information based on the biliary tubing pressure monitoring information, biliary tubing ambient temperature monitoring information, infusion tubing fluid fluctuation monitoring information, suction tubing ambient temperature monitoring information, multiple biliary perfusion state characteristic information, and a preset biliary perfusion pressure prediction model, the method further includes: Based on a preset biliary perfusion pressure feature extraction model, feature extraction processing is performed on the multiple biliary perfusion pressure prediction information to generate multiple biliary perfusion pressure feature information. Based on the preset mapping relationship between biliary infusion pressure characteristics and pump control parameters, multiple infusion pump parameter adjustment information is generated according to the multiple biliary infusion pressure characteristic information. Based on the preset mapping relationship between biliary infusion pressure characteristics and suction valve on / off control parameters, multiple suction valve on / off control parameter information is generated according to the multiple biliary infusion pressure characteristic information.

6. The infusion pressure monitoring method as described in claim 5, characterized in that, After the step of generating multiple suction valve on / off control parameter information based on the preset mapping relationship between biliary perfusion pressure characteristics and suction valve on / off control parameters, the method further includes: Acquire post-regulation biliary tubing pressure monitoring information, post-regulation perfusion tubing fluid fluctuation monitoring information, and multiple post-regulation biliary perfusion imaging information; The pressure monitoring information of the regulated bile duct tubing, the fluid fluctuation monitoring information of the regulated perfusion tubing, and multiple regulated bile duct perfusion images are sent to the terminal device for display.

7. The method for monitoring injection pressure as described in claim 1, characterized in that, The biliary tract pressure monitoring information includes pressure monitoring information at the tip of the cholangioscope, pressure monitoring information at the proximal end of the biliary tract, and pressure gradient change monitoring information of the biliary tract. The environmental temperature monitoring information of the bile duct tubing includes real-time temperature monitoring information of the bile duct tubing infusion fluid, environmental temperature monitoring information of the outer wall of the bile duct tubing, and environmental temperature fluctuation difference monitoring information of the bile duct tubing. The fluid fluctuation monitoring information in the injection pipeline includes instantaneous flow velocity fluctuation monitoring information of the injection fluid, fluid pulsation frequency monitoring information of the injection pipeline, and fluid steady-state flow monitoring information of the injection pipeline. The ambient temperature monitoring information of the suction pipeline includes the temperature monitoring information of the suction waste liquid and the ambient temperature difference monitoring information of the suction pipeline. The biliary perfusion imaging information includes intraoperative biliary cavity imaging information, tubing fluid flow imaging information, and imaging information of the location of biliary stones and blood clots blocking the biliary tract.

8. A device for monitoring injection pressure, characterized in that, include: The information acquisition module is used to acquire biliary tubing pressure monitoring information, biliary tubing ambient temperature monitoring information, perfusion tubing fluid fluctuation monitoring information, suction tubing ambient temperature monitoring information, and multiple biliary perfusion images. The biliary perfusion status feature information generation module is used to perform feature extraction processing on the multiple biliary perfusion image information based on a preset biliary perfusion status feature extraction model, and generate multiple biliary perfusion status feature information. The biliary perfusion pressure prediction information generation module is used to generate multiple biliary perfusion pressure prediction information based on the biliary tubing pressure monitoring information, biliary tubing ambient temperature monitoring information, perfusion tubing fluid fluctuation monitoring information, suction tubing ambient temperature monitoring information, multiple biliary perfusion state characteristic information, and a preset biliary perfusion pressure prediction model.

9. A terminal device, characterized in that, The terminal device includes a memory and a processor. The memory stores a computer program that can run on the processor. When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 7.

Images