AI treatment decision-making system for acute varicocele hemorrhage of liver cirrhosis

Abstract

The invention provides a liver cirrhosis acute varicose vein hemorrhage AI treatment decision making system, and relates to the technical field of treatment decision making, a transient characteristic indication factor of blood flow pressure is extracted from a pressure fluctuation signal, and a transient pressure peak value of portal vein blood flow during acute varicose vein hemorrhage is predicted through the transient characteristic indication factor and a hemodynamic model; predicting a quasi-steady-state pressure field of the portal vein blood flow during acute varicose vein bleeding according to the gradient distribution of the portal vein blood flow pressure and the initial treatment strategy of the acute varicose vein bleeding; and performing multi-scale coupling on the transient pressure peak value and the quasi-steady-state pressure field to obtain coupling characteristics of portal vein blood flow, and further performing graded coupling adjustment on a treatment strategy of acute varicocele hemorrhage of liver cirrhosis by using the coupling characteristics of blood flow pressure. Based on the scheme, hierarchical coupling of treatment strategies of acute varicose vein hemorrhage of liver cirrhosis can be realized, so that the portal vein blood flow pressure prediction precision during acute varicose vein hemorrhage can be improved.

Description

Technical Field

[0001] This application relates to the technical field of treatment decision-making, and more specifically, to an AI treatment decision-making system for acute variceal bleeding in liver cirrhosis. Background Art

[0002] Acute variceal bleeding in liver cirrhosis is a serious complication of portal hypertension in liver cirrhosis, often caused by rupture of esophageal and gastric fundal varices. Patients may present with symptoms such as hematemesis, melena, dizziness, shock, etc. Diagnosis mainly relies on medical history, physical signs, and gastroscopy. Treatment includes emergency hemostasis (drugs, endoscopic treatment, compression with a Sengstaken-Blakemore tube), maintaining blood volume, preventing infection, etc. Long-term management requires preventing rebleeding, and TIPS or surgical operation may be necessary when needed.

[0003] In the prior art, treatment strategies are usually formulated based on general clinical criteria, lacking fine adjustment to the individual pathological state of patients. In the treatment of acute variceal bleeding, traditional methods rely more on rough judgments based on medical history and symptoms, unable to fully consider the physiological differences of each patient, such as specific dynamic changes in portal vein blood flow, pressure fluctuations, and vascular wall stress. This may lead to overly single treatment plan formulation, failure to accurately model the blood flow pressure fluctuations and their impact on the vascular wall, and thus inability to effectively prevent or control the bleeding risk. Therefore, how to achieve hierarchical coupling of treatment strategies for acute variceal bleeding in liver cirrhosis, thereby improving the prediction accuracy of portal vein blood flow pressure during acute variceal bleeding, has become a difficult problem faced by the industry. Summary of the Invention

[0004] This application provides an AI treatment decision-making system for acute variceal bleeding in liver cirrhosis, which can achieve hierarchical coupling of treatment strategies for acute variceal bleeding in liver cirrhosis, thereby improving the prediction accuracy of portal vein blood flow pressure during acute variceal bleeding.

[0005] This application provides an AI treatment decision-making system for acute variceal bleeding in liver cirrhosis, and the decision-making system includes: A model construction module, configured to collect three-dimensional reconstruction data and phase-contrast magnetic resonance blood flow parameters in the liver cirrhosis vein, and then construct a blood flow dynamic model of the liver cirrhosis vein through the three-dimensional reconstruction data and the phase-contrast magnetic resonance blood flow parameters; A transient feature determination module, configured to obtain the pressure fluctuation signal of the portal vein during the stable period before bleeding, and then extract the transient feature indicator factor of the blood flow pressure from the pressure fluctuation signal, and predict the transient pressure peak value of the portal vein blood flow during acute variceal bleeding through the transient feature indicator factor and the three-dimensional reconstruction feature in the blood flow dynamic model; A steady-state feature determination module, configured to extract the gradient distribution of the portal vein blood flow pressure during the pre-hemorrhage stable period based on the hemodynamic features in the hemodynamic model, and then predict the quasi-steady pressure field of the portal vein blood flow during acute variceal hemorrhage according to the gradient distribution of the blood flow pressure and the initial treatment strategy for acute variceal hemorrhage; A coupling regulation module, configured to perform multi-scale coupling on the transient pressure peak and the quasi-steady pressure field to obtain the coupling features of the portal vein blood flow during acute variceal hemorrhage, and then use the coupling features of the blood flow pressure to perform hierarchical coupling regulation on the treatment strategy for cirrhotic acute variceal hemorrhage.

[0006] In this embodiment, three-dimensional reconstruction data and phase-contrast magnetic resonance blood flow parameters in the cirrhotic veins are collected using CT angiography combined with a 3.0T magnetic resonance scanner.

[0007] In this embodiment, the phase-contrast magnetic resonance blood flow parameters in the cirrhotic veins are collected using an electrocardiogram-gated phase-contrast magnetic resonance imaging sequence.

[0008] In this embodiment, extracting the transient feature indicator factor of the blood flow pressure from the pressure fluctuation signal specifically includes: Extracting the high-frequency component in the pressure fluctuation signal; Determining the transient feature indicator factor of the blood flow pressure through the high-frequency component.

[0009] In this embodiment, predicting the transient pressure peak of the portal vein blood flow during acute variceal hemorrhage through the transient feature indicator factor and the three-dimensional reconstruction feature in the hemodynamic model specifically includes: Initializing a vascular wall stress fatigue model based on a neural network; Taking the transient feature indicator factor as the dynamic input feature in the vascular wall stress fatigue model; Taking the three-dimensional reconstruction feature in the hemodynamic model as the structural parameter in the vascular wall stress fatigue model; Using this vascular wall stress fatigue model to predict the pressure peak of the portal vein blood flow during acute variceal hemorrhage, and obtaining the transient pressure peak of the portal vein blood flow during acute variceal hemorrhage.

[0010] In this embodiment, extracting the gradient distribution of the portal vein blood flow pressure during the pre-hemorrhage stable period based on the hemodynamic features in the hemodynamic model specifically includes: Obtaining the stable period of the portal vein blood flow pressure before hemorrhage; Obtaining the blood flow pressure at each monitoring point in the portal vein during the stable period from the hemodynamic features of the hemodynamic model; Determining the gradient distribution of the portal vein blood flow pressure during the pre-hemorrhage stable period according to all the blood flow pressures.

[0011] In this embodiment, predicting the quasi-steady state pressure field of the portal vein blood flow during acute variceal bleeding based on the gradient distribution of the blood flow pressure and the initial treatment strategy for acute variceal bleeding specifically includes: Determining the fluctuation characteristics of the blood flow pressure at each monitoring point in the portal vein during treatment according to the initial treatment strategy for acute variceal bleeding; Predicting the quasi-steady state pressure field of the portal vein blood flow during acute variceal bleeding through the fluctuation characteristics and the gradient distribution of the blood flow pressure.

[0012] In this embodiment, performing multi-scale coupling on the transient pressure peak value and the quasi-steady state pressure field to obtain the coupling characteristics of the portal vein blood flow during acute variceal bleeding specifically includes: Obtaining the characteristic contribution degrees of different scale characteristics to the blood flow pressure of the portal vein during portal variceal bleeding; Performing weighted fusion on the transient pressure peak value and the quasi-steady state pressure field through each characteristic contribution degree to obtain the coupling characteristics of the portal vein blood flow during acute variceal bleeding.

[0013] In this embodiment, using the coupling characteristics of the blood flow pressure to perform hierarchical coupling adjustment on the treatment strategy for cirrhotic acute variceal bleeding specifically includes: Obtaining the grade mapping table of the treatment strategy for cirrhotic acute variceal bleeding; Screening out the treatment grade for cirrhotic acute variceal bleeding from the grade mapping table through the coupling characteristics of the blood flow pressure; Obtaining the treatment strategy corresponding to the treatment grade as the treatment strategy for cirrhotic acute variceal bleeding.

[0014] In this embodiment, the blood flow dynamics model is a three-dimensional vascular geometry model based on hydrodynamics.

[0015] The technical solutions provided by the disclosed embodiments of the present application have the following beneficial effects: By collecting three-dimensional reconstruction data and phase-contrast magnetic resonance blood flow parameters in the cirrhotic veins, and then constructing a hemodynamic model of the cirrhotic veins through the three-dimensional reconstruction data and the phase-contrast magnetic resonance blood flow parameters; obtaining the pressure fluctuation signal of the portal vein in the pre-bleeding stable period, and then extracting the transient characteristic indicator factor of the blood flow pressure from the pressure fluctuation signal, and predicting the transient pressure peak value of the portal vein blood flow during acute variceal bleeding through the transient characteristic indicator factor and the three-dimensional reconstruction characteristics in the hemodynamic model; extracting the gradient distribution of the portal vein blood flow pressure in the pre-bleeding stable period based on the hemodynamic characteristics in the hemodynamic model, and then predicting the quasi-steady pressure field of the portal vein blood flow during acute variceal bleeding according to the gradient distribution of the blood flow pressure and the initial treatment strategy for acute variceal bleeding; performing multi-scale coupling on the transient pressure peak value and the quasi-steady pressure field to obtain the coupling characteristics of the portal vein blood flow during acute variceal bleeding, and then using the coupling characteristics of the blood flow pressure to perform hierarchical coupling adjustment on the treatment strategy for cirrhotic acute variceal bleeding.

[0016] Thus, it can be seen that in this application, first, the transient pressure peak value and the quasi-steady pressure field are subjected to multi-scale coupling to obtain the coupling characteristics of the portal vein blood flow during acute variceal bleeding, and then the coupling characteristics of the blood flow pressure are used to perform hierarchical coupling adjustment on the treatment strategy for cirrhotic acute variceal bleeding; first, determining the transient pressure peak value helps to identify the critical moment of blood flow pressure mutation, reflects the stress state of the blood vessel during rapid pressure change, and the accurate prediction of the transient pressure peak value provides an accurate parameter basis for the hierarchical coupling of the treatment strategy, enabling the clinic to adjust the treatment intensity based on the change of blood flow pressure, avoid over-intervention or under-treatment, reduce the bleeding risk of patients, and improve the accuracy of the hierarchical adjustment of the treatment strategy by combining individualized transient pressure data, providing a more targeted treatment plan for patients, thereby effectively improving the accuracy of predicting the portal vein blood flow pressure during acute variceal bleeding; then, determining the quasi-steady pressure field helps to understand the long-term stability and change trend of the blood flow during acute variceal bleeding, provides a basis for treatment decision-making, can reveal the stability and potential risks of the blood flow through the analysis of the quasi-steady characteristics of the pressure field, provides guidance for further adjustment of the treatment strategy, and accurately predicting the quasi-steady pressure field enables the treatment to timely adjust the treatment intensity when the patient's blood flow pressure reaches a stable or quasi-stable state, avoid over-intervention or causing adverse reactions, so that it is convenient to combine the quasi-steady pressure field with the transient pressure peak value later. After multi-scale coupling, more accurate blood flow coupling characteristics can be obtained, providing an effective basis for the hierarchical adjustment of the treatment strategy for acute variceal bleeding, and then improving the accuracy of predicting the portal vein blood flow pressure during acute variceal bleeding, providing strong support for the individuation and optimization of the treatment plan.

[0017] In summary, based on the above solution, the hierarchical coupling of the treatment strategy for cirrhotic acute variceal bleeding can be achieved, thereby improving the prediction accuracy of portal venous blood flow pressure during acute variceal bleeding. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0019] Figure 1 is a module structure diagram of an AI treatment decision-making system for cirrhotic acute variceal bleeding provided by the present application; Figure 2 is an exemplary flowchart for determining the transient pressure peak; Figure 3 is an exemplary flowchart for determining the gradient distribution. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0021] The embodiments of the present application provide an AI treatment decision-making system for cirrhotic acute variceal bleeding. Its core is to extract the transient feature indicator factors of blood flow pressure from the pressure fluctuation signal, and predict the transient pressure peak of portal venous blood flow during acute variceal bleeding through the transient feature indicator factors and the hemodynamic model; predict the quasi-steady pressure field of portal venous blood flow during acute variceal bleeding according to the gradient distribution of portal venous blood flow pressure and the initial treatment strategy for acute variceal bleeding; perform multi-scale coupling on the transient pressure peak and the quasi-steady pressure field to obtain the coupling characteristics of portal venous blood flow, and then use the coupling characteristics of blood flow pressure to hierarchically couple and adjust the treatment strategy for cirrhotic acute variceal bleeding. Based on the above solution, the hierarchical coupling of the treatment strategy for cirrhotic acute variceal bleeding can be achieved, thereby improving the prediction accuracy of portal venous blood flow pressure during acute variceal bleeding.

[0022] To better understand the above technical solutions, the following will describe the above technical solutions in detail with reference to the accompanying drawings of the specification and specific embodiments. Refer to Figure 1As shown in the figure, it is a module structure diagram of an AI treatment decision-making system for acute variceal bleeding in liver cirrhosis according to this embodiment of the present application. The decision-making system includes: a model construction module 100, a transient feature determination module 200, a steady-state feature determination module 300, and a coupling adjustment module 400, which are described as follows: The model construction module 100 is used to collect three-dimensional reconstruction data and phase-contrast magnetic resonance blood flow parameters in the cirrhotic vein, and then construct a hemodynamic model of the cirrhotic vein through the three-dimensional reconstruction data and the phase-contrast magnetic resonance blood flow parameters.

[0023] It should be noted that in the present application, the three-dimensional reconstruction data represents the three-dimensional geometric information of the vascular structure in the cirrhotic vein; the phase-contrast magnetic resonance blood flow parameters represent hemodynamic parameters such as blood flow velocity, flow rate, and shear stress obtained through phase-contrast magnetic resonance imaging (PC-MRI); specifically, when implemented, CT angiography combined with a 3.0T magnetic resonance scanner is used to collect the three-dimensional reconstruction data in the cirrhotic vein, and an electrocardiogram-gated phase-contrast magnetic resonance imaging sequence is used to collect the phase-contrast magnetic resonance blood flow parameters in the cirrhotic vein.

[0024] Specifically, when implemented, the construction of the hemodynamic model of the cirrhotic vein through the three-dimensional reconstruction data and the phase-contrast magnetic resonance blood flow parameters can be achieved by the following method, that is: using the three-dimensional reconstruction data to reconstruct a high-precision three-dimensional vascular geometric model, and using the phase-contrast magnetic resonance blood flow parameters as the fluid boundary conditions of the model. During the model solution process, the Navier-Stokes equation is used to describe the blood flow characteristics, and a non-Newtonian fluid model (such as: Carreau-Yasuda model) is combined to more accurately simulate the hemodynamic characteristics of cirrhotic patients. Numerical calculations use the finite element or finite volume method, and key parameters such as blood flow velocity, shear stress, and pressure distribution are solved through CFD simulation software (such as: COMSOL Multiphysics). To improve the calculation accuracy, grid meshing optimization is required, and an adaptive grid refinement strategy is used to improve the calculation accuracy in areas of vascular stenosis or high shear stress. At the same time, experimental data (such as: intravascular pressure measurement data) is used to verify and correct the model, and hemodynamic parameters are adjusted to optimize the simulation accuracy to ensure that the model can accurately reflect the true hemodynamic characteristics of the cirrhotic vein.

[0025] The transient feature determination module 200 is used to obtain the pressure fluctuation signal of the portal vein during the pre-bleeding stable period, and then extract the transient feature indicator factor of the blood flow pressure from the pressure fluctuation signal, and predict the transient pressure peak of the portal vein blood flow during acute variceal bleeding through the transient feature indicator factor and the three-dimensional reconstruction feature in the hemodynamic model.

[0026] It should be noted that in this application, the pressure fluctuation signal reflects the pulsatile nature of blood flow in the vascular system; in specific implementation, the pressure fluctuation signal of the portal vein during the pre-bleeding stable period can be obtained in the following manner, that is: the Womersley equation can be used to convert the catheter pressure measurement data before transjugular intrahepatic portosystemic shunt (TIPS) into the pressure fluctuation signal of the portal vein during the pre-bleeding stable period. The Womersley equation is a mathematical model describing periodic fluid flow, especially suitable for the pulsatile flow of blood in blood vessels. This Womersley equation is based on the Navier-Stokes equation, taking into account the viscosity and pulsatile nature of blood, and can predict the velocity and pressure distribution of blood in blood vessels through given conditions such as flow frequency, vascular geometric parameters, and blood viscosity. The main role of the Womersley equation is to introduce frequency-domain analysis in fluid dynamics to solve the non-constancy problem in blood flow, especially suitable for dealing with the relationship between pressure and velocity in pulsatile flow and complex vascular systems. Before TIPS, by measuring catheter pressure data, the Womersley equation can be used to convert it into the pressure fluctuation signal of the portal vein during the pre-bleeding stable period. Through the Womersley equation, more accurate blood flow pressure prediction can be obtained, and then the pressure distribution and its fluctuation characteristics of the portal vein can be evaluated, providing key data support for subsequent treatment plans and risk prediction.

[0027] In this embodiment, extracting the transient characteristic indicator factor of blood flow pressure from the pressure fluctuation signal can be achieved by the following steps: Extract the high-frequency component in the pressure fluctuation signal; Determine the transient characteristic indicator factor of blood flow pressure through the high-frequency component.

[0028] It should be noted that in this application, the transient characteristic indicator factor is a key parameter reflecting the sudden change characteristics of blood flow pressure; in specific implementation, first, wavelet transform can be used to extract the high-frequency component in the pressure fluctuation signal, and this high-frequency component represents the high-frequency fluctuation component in the blood flow pressure signal; then, this high-frequency component is used as the transient characteristic indicator factor of blood flow pressure. By extracting the high-frequency component in the blood flow pressure signal as the transient characteristic indicator factor, the sudden change characteristics of blood flow pressure can be effectively reflected, providing key parameters for predicting the transient changes of blood flow and acute events.

[0029] Preferably, in this embodiment, referring to Figure 2 as shown, this figure is an exemplary flowchart for determining the transient pressure peak in the embodiment of this application. In this embodiment, predicting the transient pressure peak of portal vein blood flow during acute variceal bleeding through the transient characteristic indicator factor and the three-dimensional reconstruction characteristics in the hemodynamic model can be achieved by the following steps: In step S21, initialize a neural network-based vascular wall stress fatigue model; In step S22, the transient feature indicator is used as a dynamic input feature in the vascular wall stress fatigue model; In step S23, the three-dimensional reconstruction feature in the hemodynamic model is used as a structural parameter in the vascular wall stress fatigue model; In step S24, the vascular wall stress fatigue model is used to predict the peak pressure of the portal vein blood flow during acute variceal bleeding, and the transient peak pressure of the portal vein blood flow during acute variceal bleeding is obtained.

[0030] It should be noted that in this application, the transient peak pressure represents the maximum pressure value reached instantaneously during the blood flow pressure fluctuation process; the vascular wall stress fatigue model is a mathematical model based on physical mechanics principles, which is used to describe the long-term stress accumulation and fatigue damage process of the vascular wall under the action of blood flow pressure. This vascular wall stress fatigue model considers the force of blood pulsation on the vascular wall, combines the elasticity of the vascular wall and the stress-strain relationship, and simulates the fatigue evolution of the vascular wall under multiple pressure fluctuations. Specifically, the dynamic input feature in the vascular wall stress fatigue model, the transient feature indicator reflecting the blood flow pressure fluctuation and mutation characteristics, can affect the stress response of the vascular wall, and the three-dimensional reconstruction features (such as the shape and structure of blood vessels) in the hemodynamic model are used as structural parameters to provide the geometric information of the vascular wall. Through the neural network algorithm, this model can learn complex non-linear relationships and dynamically predict the stress state of the vascular wall under different pressure fluctuations. Especially during acute variceal bleeding, it can accurately predict the transient peak pressure of the portal vein blood flow.

[0031] The steady-state feature determination module 300 is configured to extract the gradient distribution of the portal vein blood flow pressure during the pre-bleeding stable period based on the hemodynamic features in the hemodynamic model, and then predict the quasi-steady-state pressure field of the portal vein blood flow during acute variceal bleeding according to the gradient distribution of the blood flow pressure and the initial treatment strategy for acute variceal bleeding.

[0032] Preferably, in this embodiment, refer to Figure 3 As shown, this figure is an exemplary flowchart for determining the transient peak pressure in the embodiment of this application. The extraction of the gradient distribution of the portal vein blood flow pressure during the pre-bleeding stable period based on the hemodynamic features in the hemodynamic model in this embodiment can be implemented by the following steps: In step S31, the stable period of the portal vein blood flow pressure before bleeding is obtained; In step S32, the blood flow pressures at each monitoring point in the portal vein during the stable period are obtained from the hemodynamic features of the hemodynamic model; In step S33, the gradient distribution of the portal vein blood flow pressure during the pre-bleeding stable period is determined according to all the blood flow pressures.

[0033] It should be noted that in this application, the gradient distribution represents the rate of change of the portal venous blood flow pressure in space; the stable period represents the time period during which the portal venous blood flow pressure fluctuates less and tends to be constant before bleeding; the blood flow pressure in the stable period represents the average pressure value of the portal venous blood flow during the stable period.

[0034] When specifically implemented, first, the time series analysis method (e.g., autoregressive moving average ARMA model) is used to perform stable screening on the monitored portal venous blood flow pressure data, so as to screen out the time periods with smaller pressure changes and the fluctuation amplitude within the stable range, which are defined as the stable period before bleeding; then, the set of all phase-contrast magnetic resonance blood flow parameters in the hemodynamic model is used as the hemodynamic characteristics in the hemodynamic model, so that the blood flow parameters of each monitoring point in the stable period in the hemodynamic characteristics of the hemodynamic model are used as the blood flow pressure of each monitoring point in the portal vein during the stable period; finally, the difference in blood flow pressure between adjacent monitoring points can be calculated as the blood flow pressure gradient value, and all the blood flow pressure gradient values are arranged according to the positions of the monitoring points as the gradient distribution of the portal venous blood flow pressure during the stable period before bleeding.

[0035] In this embodiment, predicting the quasi-steady state pressure field of the portal venous blood flow during acute variceal bleeding according to the gradient distribution of the blood flow pressure and the initial treatment strategy for acute variceal bleeding can be achieved by the following steps: Determine the fluctuation characteristics of the blood flow pressure of each monitoring point in the portal vein during treatment according to the initial treatment strategy for acute variceal bleeding; Predict the quasi-steady state pressure field of the portal venous blood flow during acute variceal bleeding through the fluctuation characteristics and the gradient distribution of the blood flow pressure.

[0036] It should be noted that in this application, the quasi-steady state pressure field represents the pressure distribution state in which the portal venous blood flow tends to be stable before bleeding but still has small fluctuations; the fluctuation characteristics represent the dynamic characteristics of the portal venous blood flow pressure changing with time.

[0037] When specifically implemented, first, before acute variceal bleeding, a hemodynamic simulation model can be used to perform a large number of simulations on the initial treatment strategy for acute variceal bleeding, so that the standard deviation of the corresponding pressure simulation results of each monitoring point in the portal vein is used as the fluctuation characteristics of the blood flow pressure of the corresponding monitoring point during treatment, and thus the fluctuation characteristics of the blood flow pressure of each monitoring point in the portal vein during treatment can be obtained; then, for each monitoring point in the portal vein, the product of the fluctuation characteristics of the monitoring point and the blood flow pressure gradient value between the monitoring point and the previous monitoring point in the gradient distribution of the blood flow pressure is used as the quasi-steady state pressure prediction value of the monitoring point. Through the above method, the quasi-steady state pressure prediction values of each monitoring point in the portal vein can be obtained, and all the quasi-steady state pressure prediction values are arranged in a field according to the positions of the monitoring points as the quasi-steady state pressure field of the portal venous blood flow during acute variceal bleeding.

[0038] A coupling adjustment module 400 is configured to perform multi-scale coupling on the transient pressure peak and the quasi-steady pressure field to obtain the coupling characteristics of the portal vein blood flow during acute variceal bleeding, and then use the coupling characteristics of the blood flow pressure to perform hierarchical coupling adjustment on the treatment strategy for cirrhotic acute variceal bleeding.

[0039] In this embodiment, performing multi-scale coupling on the transient pressure peak and the quasi-steady pressure field to obtain the coupling characteristics of the portal vein blood flow during acute variceal bleeding can be achieved by the following steps: Obtain the characteristic contribution degrees of different-scale characteristics to the blood flow pressure of the portal vein during portal variceal bleeding; Perform weighted fusion on the transient pressure peak and the quasi-steady pressure field through each characteristic contribution degree to obtain the coupling characteristics of the portal vein blood flow during acute variceal bleeding.

[0040] It should be noted that in this application, the coupling characteristics represent the comprehensive influence characteristics of the transient pressure peak and the quasi-steady pressure field at multiple scales; the characteristic contribution degree represents the relative influence weight of different-scale characteristics on the change of the portal vein blood flow pressure.

[0041] Specifically, when implementing, first, the characteristic contribution degrees of the transient characteristic scale and the steady-state characteristic scale to the blood flow pressure of the portal vein during portal variceal bleeding can be preset by combining historical experience and the physical characteristics of cirrhotic patients; then, the characteristic contribution degree of the transient characteristic scale to the blood flow pressure of the portal vein during portal variceal bleeding is used as the fusion weight of the transient pressure peak, and the characteristic contribution degree of the steady-state characteristic scale to the blood flow pressure of the portal vein during portal variceal bleeding is used as the fusion weight of the quasi-steady pressure field. Thus, the transient pressure peak and the quasi-steady pressure field are fused using the weight fusion method optimized by Bayesian, and the fusion characteristic value of the fused blood flow pressure can be used as the coupling characteristics of the portal vein blood flow during acute variceal bleeding.

[0042] In this embodiment, performing hierarchical coupling adjustment on the treatment strategy for cirrhotic acute variceal bleeding using the coupling characteristics of the blood flow pressure can be achieved by the following steps: Obtain the level mapping table of the treatment strategy for cirrhotic acute variceal bleeding; Screen out the treatment level for cirrhotic acute variceal bleeding from the level mapping table through the coupling characteristics of the blood flow pressure; Obtain the treatment strategy corresponding to the treatment level as the treatment strategy for cirrhotic acute variceal bleeding.

[0043] In specific implementation, first, a hierarchical mapping table of the treatment strategy for acute variceal bleeding in liver cirrhosis can be obtained from the console of the treatment decision system; then, the pressure range interval of the coupling characteristics of the blood flow pressure in the hierarchical mapping table is obtained, so that the treatment level corresponding to this pressure range interval is used as the treatment level for acute variceal bleeding in liver cirrhosis; finally, the treatment strategy corresponding to the treatment level can be obtained from the console of the treatment decision system as the treatment strategy for acute variceal bleeding in liver cirrhosis. Through the above scheme, when the predicted pressure value is greater than the preset treatment strategy threshold, treatment escalation can be automatically triggered.

[0044] It can be seen that in this application, first, the transient pressure peak and the quasi-steady pressure field are multi-scale coupled to obtain the coupling characteristics of the portal vein blood flow during acute variceal bleeding. Furthermore, the coupling characteristics of the blood flow pressure are used to perform hierarchical coupling adjustment on the treatment strategy for acute variceal bleeding in liver cirrhosis. First, determining the transient pressure peak helps to identify the critical moment of blood flow pressure mutation, reflects the stress state of blood vessels during rapid pressure changes, and accurate prediction of the transient pressure peak provides an accurate parameter basis for the hierarchical coupling of treatment strategies, enabling clinical adjustment of treatment intensity based on the changes in blood flow pressure, avoiding over-intervention or under-treatment, reducing the bleeding risk of patients. By combining individualized transient pressure data, the accuracy of hierarchical adjustment of treatment strategies is improved, providing a more targeted treatment plan for patients, thereby effectively improving the accuracy of predicting the portal vein blood flow pressure during acute variceal bleeding. Then, determining the quasi-steady pressure field helps to understand the long-term stability and change trend of blood flow during acute variceal bleeding, providing a basis for treatment decision-making. Through the analysis of the quasi-steady characteristics of the pressure field, the stability and potential risks of blood flow can be revealed, providing guidance for further adjustment of treatment strategies. Accurately predicting the quasi-steady pressure field enables treatment to timely adjust the treatment intensity when the patient's blood flow pressure reaches a stable or quasi-stable state, avoiding over-intervention or causing adverse reactions. Thus, it is convenient to combine the quasi-steady pressure field with the transient pressure peak for multi-scale coupling later, and more accurate blood flow coupling characteristics can be obtained, providing an effective basis for the hierarchical adjustment of the treatment strategy for acute variceal bleeding, and further improving the accuracy of predicting the portal vein blood flow pressure during acute variceal bleeding, providing strong support for the personalization and optimization of treatment plans.

[0045] In summary, based on the above scheme, the hierarchical coupling of the treatment strategy for acute variceal bleeding in liver cirrhosis can be realized, thereby improving the accuracy of predicting the portal vein blood flow pressure during acute variceal bleeding.

[0046] This application is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems) and computer program products according to embodiments of the present application. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate a means for implementing the functions specified in one process Figure 1 or more processes and / or blocks Figure 1 or a means for implementing the functions specified in one block or more blocks.

[0047] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program, and this program can be stored in a computer-readable storage medium. The storage medium includes read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc memories, magnetic disk memories, tape memories, or any other medium that can be used to carry or store data and is computer-readable.

[0048] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the statement "including one..." does not exclude the existence of another identical element in the process, method, commodity or device including the element.

Claims

1. An AI treatment decision-making system for acute variceal bleeding in liver cirrhosis, characterized in that, The decision-making system includes: A model construction module, which is used to collect three-dimensional reconstruction data and phase-contrast magnetic resonance blood flow parameters in the cirrhotic vein, and then construct a blood flow dynamic model of the cirrhotic vein through the three-dimensional reconstruction data and the phase-contrast magnetic resonance blood flow parameters; A transient feature determination module, which is used to obtain the pressure fluctuation signal of the portal vein during the pre-bleeding stable period, and then extract the transient feature indicator factor of the blood flow pressure from the pressure fluctuation signal, and predict the transient pressure peak of the portal vein blood flow during acute variceal bleeding through the transient feature indicator factor and the three-dimensional reconstruction features in the blood flow dynamic model; A steady-state feature determination module, which is used to extract the gradient distribution of the portal vein blood flow pressure during the pre-bleeding stable period based on the blood flow dynamic features in the blood flow dynamic model, and then predict the quasi-steady-state pressure field of the portal vein blood flow during acute variceal bleeding according to the gradient distribution of the blood flow pressure and the initial treatment strategy for acute variceal bleeding; A coupling regulation module, which is used to perform multi-scale coupling on the transient pressure peak and the quasi-steady-state pressure field to obtain the coupling features of the portal vein blood flow during acute variceal bleeding, and then use the coupling features of the blood flow pressure to perform hierarchical coupling regulation on the treatment strategy for cirrhotic acute variceal bleeding.

2. The AI treatment decision-making system for acute variceal bleeding in liver cirrhosis according to claim 1, wherein Use CT angiography combined with a 3.0T magnetic resonance scanner to collect three-dimensional reconstruction data and phase-contrast magnetic resonance blood flow parameters in the cirrhotic vein.

3. The AI treatment decision-making system for acute variceal bleeding in liver cirrhosis according to claim 1, wherein Use an electrocardiogram-gated phase-contrast magnetic resonance imaging sequence to collect phase-contrast magnetic resonance blood flow parameters in the cirrhotic vein.

4. The AI treatment decision-making system for acute variceal bleeding in liver cirrhosis according to claim 1, wherein Extracting the transient feature indicator factor of the blood flow pressure from the pressure fluctuation signal specifically includes: Extracting the high-frequency component in the pressure fluctuation signal; Determining the transient feature indicator factor of the blood flow pressure through the high-frequency component.

5. The AI treatment decision-making system for acute variceal bleeding in liver cirrhosis according to claim 1, wherein, Predicting the transient pressure peak of the portal vein blood flow during acute variceal bleeding through the transient feature indicator factor and the three-dimensional reconstruction features in the blood flow dynamic model specifically includes: Initializing a neural network-based vascular wall stress fatigue model; Taking the transient feature indicator factor as the dynamic input feature in the vascular wall stress fatigue model; Taking the three-dimensional reconstruction features in the blood flow dynamic model as the structural parameters in the vascular wall stress fatigue model; Using the vascular wall stress fatigue model to predict the pressure peak of the portal vein blood flow during acute variceal bleeding to obtain the transient pressure peak of the portal vein blood flow during acute variceal bleeding.

6. The AI treatment decision-making system for acute variceal bleeding in liver cirrhosis according to claim 1, wherein Extracting the gradient distribution of the portal vein blood flow pressure during the pre-bleeding stable period based on the blood flow dynamic features in the blood flow dynamic model specifically includes: Obtaining the stable period of the portal vein blood flow pressure before bleeding; Obtaining the blood flow pressure at each monitoring point in the portal vein during the stable period from the blood flow dynamic features of the blood flow dynamic model; Determining the gradient distribution of the portal vein blood flow pressure during the pre-bleeding stable period according to all the blood flow pressures.

7. The AI treatment decision-making system for acute variceal bleeding in liver cirrhosis according to claim 1, wherein Predicting the quasi-steady-state pressure field of the portal vein blood flow during acute variceal bleeding according to the gradient distribution of the blood flow pressure and the initial treatment strategy for acute variceal bleeding specifically includes: Determining the fluctuation characteristics of the blood flow pressure at each monitoring point in the portal vein during treatment according to the initial treatment strategy for acute variceal bleeding; Predict the quasi-steady pressure field of portal vein blood flow during acute variceal bleeding through the gradient distribution of the fluctuation characteristics and the blood flow pressure.

8. The AI treatment decision-making system for acute variceal bleeding in liver cirrhosis according to claim 1, wherein, Perform multi-scale coupling of the transient pressure peak and the quasi-steady pressure field to obtain the coupling characteristics of portal vein blood flow during acute variceal bleeding, specifically including: Obtain the characteristic contribution degrees of different scale characteristics to the blood flow pressure of portal vein during variceal bleeding. Perform weighted fusion of the transient pressure peak and the quasi-steady pressure field through each characteristic contribution degree to obtain the coupling characteristics of portal vein blood flow during acute variceal bleeding.

9. The AI treatment decision-making system for acute variceal bleeding in liver cirrhosis according to claim 1, wherein, Use the coupling characteristics of the blood flow pressure to perform hierarchical coupling regulation on the treatment strategy for cirrhotic acute variceal bleeding, specifically including: Obtain the grade mapping table of the treatment strategy for cirrhotic acute variceal bleeding. Screen out the treatment grade for cirrhotic acute variceal bleeding from the grade mapping table through the coupling characteristics of the blood flow pressure. Obtain the treatment strategy corresponding to the treatment grade as the treatment strategy for cirrhotic acute variceal bleeding.

10. The AI treatment decision-making system for acute variceal bleeding in liver cirrhosis according to claim 1, characterized in that, The blood flow dynamics model is a three-dimensional vascular geometry model based on hydrodynamics.

Images