A virtual patient physiological state real-time monitoring method and system based on digital twinning

Abstract

The application relates to the field of physiological state real-time monitoring, and provides a virtual patient physiological state real-time monitoring method and system based on digital twinning, which is used to solve the problems of nonlinear combination deviation of virtual patient physiological state monitoring and multi-source data synchronous lag caused by dependence on a static model and one-way feedback. The application comprises the following steps: constructing a valve three-dimensional model based on aortic CT data, combining a fluid mechanics equation to establish a simulation model containing a motion condition; real-time calculation of blood flow pressure difference and vortex parameters of valve opening and closing, embedding a fiber virtual sensor on a valve topology surface to simulate blood flow deformation, and output of valve state mechanical signals; input of parameters and signals into a digital twinning engine, adjustment of particle trajectories and refractive indexes to generate a visual interface, extraction of blood flow velocity-pressure gradient space-time data, and reverse correction of model boundary conditions to synchronize valve movement with patient physiological states. The technical scheme provided by the application can simulate heart valve movement in real time and automatically match the real heartbeat rhythm of a patient.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of physiological state real-time monitoring, and in particular to a virtual patient physiological state real-time monitoring method and system based on digital twinning. BACKGROUND

[0002] In the pre-operation of cardiovascular surgery, the individualized anatomic structure and real-time physiological parameters of the patient are needed to simulate the hemodynamic state of the heart in the virtual environment, so as to evaluate the influence of the operation scheme on the blood flow distribution, the blood vessel wall stress and the organ perfusion. Due to the combination of the physiological regulation and the operation instrument operation of the heart blood flow, a virtual patient system capable of fusing multi-modal image data, real-time physiological feedback and hemodynamic model is needed to be constructed to support the pre-judgment and scheme optimization of the complex scenarios such as blood flow mutation and thrombus risk that may occur in the operation.

[0003] At present, one technical scheme for this demand is a static hemodynamic simulation system based on three-dimensional reconstruction of medical images. The geometric model of the heart and blood vessels of the patient is generated through preoperative CT or MRI images, and the parameters such as blood flow velocity and pressure distribution are simulated by combining computational fluid dynamics. This scheme drives the simulation by presetting fixed boundary conditions, and solves the hemodynamic equation by using the finite element method to generate the static prediction result of the blood flow state in the operation.

[0004] However, relying on preoperative static image data and hypothetical boundary conditions, the influence of real-time physiological parameters on hemodynamics cannot be reflected, resulting in significant deviation between the simulation results and the actual blood flow parameters in the operation. In addition, the static simulation lacks the response ability to the individualized physiological feedback mechanism of the patient, and it is difficult to capture the instantaneous blood flow mutation or local turbulent flow phenomenon triggered by the operation, which limits its reliability in complex operation pre-operation. SUMMARY

[0005] The present application provides a virtual patient physiological state real-time monitoring method and system based on digital twinning, to solve the problems of nonlinear combination deviation and multi-source data synchronization lag caused by relying on static model and one-way feedback in the prior art.

[0006] In a first aspect, the present application provides a virtual patient physiological state real-time monitoring method based on digital twinning, comprising:

[0007] Obtaining CT image data of the aorta of the virtual patient, constructing a three-dimensional geometric model of the aortic valve based on the CT image data, combining the three-dimensional geometric model with the fluid mechanics control equation, and establishing a simulation model containing the valve motion condition;

[0008] Based on the simulation model, the pressure difference parameters and vortex parameters of the blood flow in the opening and closing process of the aortic valve are calculated in real time;

[0009] embedding a fiber virtual sensor in a valve surface topology of the three-dimensional geometric model to simulate deformation of a pressure sensing node under blood flow by the fiber virtual sensor, and generating a mechanical signal reflecting an opening and closing state of the valve;

[0010] inputting the pressure difference, the vortex parameter and the mechanical signal into a rendering engine in a digital twin environment, generating a visual interface by adjusting an optical refractive index distribution of a blood flow particle trajectory and a pressure gradient field;

[0011] acquiring spatiotemporal relationship data of blood flow velocity and pressure gradient in the visual interface to correct boundary conditions of the simulation model, so that valve movement of the three-dimensional geometric model is mapped synchronously with an actual physiological state of the patient.

[0012] Optionally, based on the simulation model, real-time calculation of pressure difference parameters and vortex parameters of blood flow in the aortic valve opening and closing process includes:

[0013] extracting geometric deformation data in the aortic valve opening and closing process from the simulation model, and dividing a dynamic region synchronous with the opening and closing state of the valve in the three-dimensional geometric model based on a moving trajectory of a valve vertex in the geometric deformation data;

[0014] in the dynamic region, calculating a pressure difference between adjacent valve vertices according to differences in the moving trajectory of the valve vertex, and constructing a valve surface pressure distribution path through the pressure difference;

[0015] based on a mutation position of the pressure difference in the valve surface pressure distribution path, marking an area where the blood flow direction mutates as a vortex initial area, and counting a geometric center of the vortex initial area;

[0016] matching the geometric center of the vortex initial area to a corresponding time point according to a time sequence of the opening and closing state of the valve, calculating a displacement difference value of the geometric center between adjacent time points to determine a moving distance corresponding to each time point, and calculating a diffusion intensity based on a coverage range change of the vortex initial area at different time points, to generate a vortex diffusion parameter including the moving distance and the diffusion intensity;

[0017] the weighted superposition result between the intensity change of the valve surface pressure distribution path and the moving distance and the diffusion intensity in the vortex diffusion parameter as the pressure difference parameter;

[0018] the ratio of the moving distance and the diffusion intensity as the vortex parameter.

[0019] Optionally, the geometric center of the vortex initial region is matched to the corresponding time point according to the time sequence of the valve opening and closing state, the displacement difference value of the geometric center between adjacent time points is calculated to determine the movement distance corresponding to each time point, and the diffusion intensity is calculated based on the coverage range change of the vortex initial region at different time points, to generate the vortex diffusion parameter containing the movement distance and the diffusion intensity, including:

[0020] The geometric center position of the vortex initial region at each time point is marked as the corresponding spatial coordinates from the time sequence of the valve opening and closing state;

[0021] The spatial coordinates of adjacent time points are arranged in time sequence, the straight line distance difference value of the spatial coordinates of the adjacent time points in three-dimensional space is calculated, and the displacement difference value of the geometric center between adjacent time points is generated;

[0022] The diffusion rate is calculated based on the number of coverage grids of the vortex initial region at different time points, and the number of coverage grids is obtained by counting the total number of boundary grid units of the vortex initial region;

[0023] The displacement difference value and the diffusion rate are superimposed in time sequence respectively, to generate the movement distance and the diffusion intensity corresponding to each time point;

[0024] The product of the movement distance and the diffusion intensity is taken as the vortex diffusion parameter containing the movement distance and the diffusion intensity.

[0025] Optionally, the spatiotemporal relationship data of blood flow velocity and pressure gradient in the visualization interface is obtained to correct the boundary condition of the simulation model, so that the valve movement of the three-dimensional geometric model is synchronized with the actual physiological state of the patient, including:

[0026] The spatiotemporal relationship data of blood flow velocity and pressure gradient is extracted from the visualization interface, the hemodynamic characteristics in the spatiotemporal relationship data are decomposed, and the blood flow characteristic parameters reflecting the actual physiological state of the patient are generated;

[0027] The blood flow characteristic parameters are compared with the boundary condition of the current valve movement in the simulation model, the matching deviation of the blood flow characteristic parameters and the boundary condition is identified, and the boundary condition correction requirement is generated;

[0028] Based on the boundary condition correction requirement, the correlation between the valve movement trajectory in the three-dimensional geometric model and the blood flow characteristic parameters is analyzed, and the influence weight of the valve movement on the blood flow characteristic parameters is determined;

[0029] The boundary condition of the simulation model is adjusted according to the influence weight, the coupling relationship between the amplitude of the valve opening and closing state and the blood flow velocity is constrained, and the boundary condition correction amount is generated.

[0030] injecting the boundary condition correction quantity into the simulation model to correct the simulation model, and verifying the spatiotemporal consistency of the valve movement and the blood flow characteristic parameter of the corrected simulation model, to generate a simulation model that is mapped synchronously with the physiological state of the patient.

[0031] Optionally, a fiber virtual sensor is embedded in the valve surface topology structure of the three-dimensional geometric model to simulate the deformation of the pressure sensing node under the action of the blood flow through the fiber virtual sensor, to generate a mechanical signal reflecting the opening and closing state of the valve, including:

[0032] Determining the node distribution position of the fiber virtual sensor in the curvature change region and the stress concentration region of the valve surface topology structure;

[0033] Setting a plurality of pressure sensing nodes in the node distribution position, and binding each pressure sensing node with the local geometric coordinates of the valve surface topology structure to establish the deformation constraint condition of each pressure sensing node under the action of the blood flow;

[0034] Calculating the displacement amount of each pressure sensing node through the deformation constraint condition, and converting the displacement amount into a three-dimensional space coordinate change sequence of the pressure sensing node;

[0035] Extracting the displacement change data of each pressure sensing node according to the three-dimensional space coordinate change sequence, and constructing a deformation characteristic curve of the node based on the displacement change data;

[0036] Converting the deformation characteristic curve into a mechanical signal waveform, and characterizing the mechanical signal waveform through the displacement amount amplitude, velocity change rate and acceleration change rate of the pressure sensing node, to generate a mechanical signal reflecting the opening and closing state of the valve.

[0037] Optionally, a three-dimensional geometric model of the aortic valve is constructed based on the CT image data, the three-dimensional geometric model is combined with the fluid mechanics control equation to establish a simulation model containing the valve movement condition, including:

[0038] Extracting the contour information of the aortic valve in the aortic CT image data, and constructing a preliminary three-dimensional geometric structure of the valve based on the contour information, the structure containing the morphological characteristics and spatial position of the valve;

[0039] Refining the preliminary three-dimensional geometric structure to supplement the detailed characteristics of the valve, to form a complete three-dimensional geometric model of the aortic valve;

[0040] Based on the three-dimensional geometric model, extracting the geometric characteristic parameters of the valve surface, and combining the physiological movement law of the valve in the three-dimensional geometric model to define the movement constraint condition in the opening and closing process of the valve;

[0041] combine the three-dimensional geometric model with the fluid mechanics control equation, construct a dynamic model of blood flow and valve interaction according to the valve motion constraint condition, wherein the dynamic model comprises pressure action of blood flow on the valve and response of the valve to the blood flow;

[0042] two-way coupling of the pressure action of blood flow on the valve and the response of the valve to the blood flow in the dynamic model, combination of the motion constraint condition and the morphological features of the three-dimensional geometric model, and construction of a simulation model comprising the valve motion condition.

[0043] Optionally, the three-dimensional geometric model is combined with the fluid mechanics control equation, and a dynamic model of blood flow and valve interaction is constructed according to the valve motion constraint condition, comprising:

[0044] extracting the valve surface topological structure of the three-dimensional geometric model, obtaining the curvature distribution features and node connection relationship in the valve surface topological structure, and generating a surface grid coupled with fluid and structure;

[0045] matching the surface grid with the boundary condition of the fluid mechanics control equation, analyzing the fluid pressure gradient pulsation features in the fluid mechanics control equation and the deformation response relationship of the valve surface topological structure, and generating a grid topology coupled with fluid and structure;

[0046] extracting the valve opening and closing phase and motion trajectory feature points in the valve motion constraint condition, matching the valve opening and closing phase and motion trajectory feature points with the grid topology coupled with fluid and structure, and generating fluid domain deformation parameters and valve motion boundary conditions;

[0047] inputting the fluid domain deformation parameters and the valve motion boundary conditions into the fluid mechanics control equation, synchronously solving the fluid mechanics control equation and the valve kinematics constraint, and generating pressure action of blood flow on the valve and response data of the valve to the blood flow;

[0048] mapping the response data to the valve surface topological structure of the three-dimensional geometric model, correcting the position offset of the valve surface topological structure according to the response data, and generating a dynamic model comprising blood flow and valve interaction through synchronous iterative updating of the position offset and pressure action.

[0049] In a second aspect, the present application provides a virtual patient physiological state real-time monitoring system based on digital twinning, comprising:

[0050] The construction module is used for acquiring CT image data of a virtual patient's aorta, constructing a three-dimensional geometric model of the aortic valve based on the CT image data, combining the three-dimensional geometric model with the fluid mechanics control equation, and establishing a simulation model comprising the valve motion condition.

[0051] a calculation module, configured to calculate, in real time, a pressure difference parameter and a vortex parameter of blood flow in aortic valve opening and closing process based on the simulation model;

[0052] a generation module, configured to embed an optical fiber virtual sensor in a valve surface topology of the three-dimensional geometric model, to simulate deformation of a pressure sensing node under the action of blood flow by the optical fiber virtual sensor, and to generate a mechanical signal reflecting a valve opening and closing state;

[0053] an input module, configured to input the pressure difference, the vortex parameter and the mechanical signal into a rendering engine in a digital twin environment, to generate a visual interface by adjusting an optical refractive index distribution of a blood flow particle trajectory and a pressure gradient field;

[0054] a correction module, configured to obtain spatiotemporal relationship data of blood flow velocity and pressure gradient in the visual interface, to correct a boundary condition of the simulation model, and to keep synchronization between valve movement of the three-dimensional geometric model and an actual physiological state of a patient.

[0055] In a third aspect, an embodiment of the present application provides a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component, to implement the virtual patient physiological state real-time monitoring method based on digital twin as described in the first aspect.

[0056] In a fourth aspect, an embodiment of the present application provides a computer storage medium, storing a computer program, when the computer program is executed by a computer, a virtual patient physiological state real-time monitoring method based on digital twin as described in the first aspect is implemented.

[0057] The beneficial effects of the present application are as follows:

[0058] The embodiment of the application obtains CT image data of a virtual patient, constructs a three-dimensional geometric model of an aortic valve based on the CT image data, combines the three-dimensional geometric model with a fluid mechanics control equation, and establishes a simulation model containing valve motion conditions; based on the simulation model, real-time calculation of pressure difference and vortex parameters of blood flow in the opening and closing process of the aortic valve is performed, and the vortex parameters are compared with a preset physiological threshold range; a fiber virtual sensor is embedded in the valve surface topology of the three-dimensional geometric model, the fiber virtual sensor generates a mechanical signal reflecting the opening and closing state of the valve by simulating the deformation of a pressure sensing node under the action of blood flow; the pressure difference, vortex parameters and mechanical signal are input into a rendering engine in a digital twin environment, the optical refractive index distribution of the blood flow particle trajectory and the pressure gradient field is adjusted to generate a visual interface; the spatiotemporal relationship data of blood flow velocity and pressure gradient in the visual interface is obtained, the boundary conditions of the simulation model are corrected, and the valve motion of the three-dimensional geometric model is kept synchronous mapping with the actual physiological state of the patient.

[0059] The application can realize high-precision blood flow dynamics model construction based on individualized anatomical structure, improve the physiological matching degree of valve motion simulation by obtaining CT image data of a virtual patient, constructing a three-dimensional geometric model of an aortic valve based on the CT image data, and combining the three-dimensional geometric model with a fluid mechanics control equation to establish a simulation model containing valve motion conditions; by real-time calculation of pressure difference parameters and vortex parameters of blood flow in the opening and closing process of the aortic valve based on the simulation model, the key indicators of blood flow energy loss and turbulent flow characteristics can be dynamically captured; by embedding a fiber virtual sensor in the valve surface topology of the three-dimensional geometric model, the fiber virtual sensor can simulate the deformation of a pressure sensing node under the action of blood flow to generate a mechanical signal reflecting the opening and closing state of the valve, and a multi-physical field coupled valve deformation feedback mechanism can be established; by inputting the pressure difference, vortex parameters and mechanical signal into a rendering engine in a digital twin environment, adjusting the optical refractive index distribution of the blood flow particle trajectory and the pressure gradient field to generate a visual interface, the holographic visual expression of the blood flow dynamic process and mechanical characteristics can be realized; by obtaining the spatiotemporal relationship data of blood flow velocity and pressure gradient in the visual interface to correct the boundary conditions of the simulation model, the valve motion of the three-dimensional geometric model is kept synchronous mapping with the actual physiological state of the patient, a closed-loop optimized digital twin system can be constructed to ensure the dynamic consistency of the model prediction results and the real physiological behavior.

[0060] Further, by extracting the geometric deformation data of the aortic valve opening and closing process and dividing the dynamic region based on the valve vertex moving track, the spatial synchronization mapping of the valve motion state and the dynamic characteristics of the three-dimensional model can be realized, and the spatio-temporal accuracy of local blood flow dynamic analysis is improved; by constructing a surface pressure distribution path driven by the pressure difference between adjacent valve vertices, the conduction law and energy distribution characteristics of the valve surface pressure gradient under the action of blood flow impact can be revealed; by identifying the pressure mutation region to mark the vortex initial position and counting the geometric center, the turbulent core area generated by the mutation of blood flow direction can be accurately positioned; by matching the displacement difference and coverage range change of the vortex center in time sequence, the coupling relationship between the energy transfer intensity and the spatial evolution track in the vortex diffusion process can be quantified; by superimposing the weighted results of pressure distribution intensity and vortex diffusion parameters to generate pressure difference parameters, the multidimensional mechanical characteristics of local pressure gradient and vortex dynamic propagation can be fused; by establishing the ratio of moving distance and diffusion intensity as the vortex parameter, the time dimension interference can be eliminated and a quantitative index representing the energy dissipation efficiency of vortex can be constructed, and finally a hemodynamic feature evaluation system considering spatial heterogeneity and time continuity is formed, which provides high-resolution dynamic quantitative basis for valve function abnormal diagnosis.

[0061] These and other aspects of the present application will become more fully understood from the following description of the embodiments. BRIEF DESCRIPTION OF DRAWINGS

[0062] 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 needed to be used in the embodiment or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0063] Figure 1 A flow chart of a virtual patient physiological state real-time monitoring method based on digital twinning provided by the present application is shown;

[0064] Figure 2 A structural schematic diagram of a virtual patient physiological state real-time monitoring system based on digital twinning provided by the present application is shown;

[0065] Figure 3 A structural schematic diagram of a computing device provided by the present application is shown. DETAILED DESCRIPTION

[0066] In order to enable personnel in the technical field to better understand the present application scheme, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application.

[0067] In some of the flowcharts described in the specification and claims of the present application and in the above description of the drawings, a plurality of operations are included in the order in which they occur, but it should be clearly understood that these operations can be executed or performed in an order different from that in which they occur or in parallel, and the serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these flowcharts can include more or fewer operations, and the operations can be executed or performed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this paper are used to distinguish different messages, devices, modules, etc., and do not represent the order of precedence, nor do "first" and "second" represent different types.

[0068] Researchers found that existing aortic valve blood flow simulation models are difficult to map real-time changes in patient physiological conditions, and lack dynamic perception of valve surface mechanical characteristics, resulting in large deviations between simulation results and real blood flow parameters. Based on this, a digital twin modeling method for aortic valve is provided, which can realize synchronous visual analysis of valve movement and blood flow parameters through dynamic coupling of optical fiber virtual sensing and fluid mechanics. The technical solution of the present application can be applied to preoperative planning and digital twin assisted diagnosis and treatment scenarios of cardiovascular diseases.

[0069] The entire research and development process embodies the technical path of multi-modal data fusion and dynamic boundary condition collaborative optimization, aiming to overcome the defects in existing schemes that static modeling cannot adapt to physiological state fluctuations and simulation parameters are disconnected from real mechanical feedback. This method significantly improves the clinical credibility of aortic valve blood flow simulation through a closed-loop feedback mechanism of mechanical signals and fluid parameters, providing a high-precision dynamic twin platform for personalized diagnosis and treatment.

[0070] The technical solutions in the embodiments of the present application will be described clearly and completely in the embodiments of the present application combined with the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0071] Figure 1 A flowchart of a virtual patient physiological state real-time monitoring method based on digital twinning is provided for the embodiments of the present application, as shown in Figure 1 The method comprises:

[0072] 101, acquiring aortic CT image data of a virtual patient, constructing a three-dimensional geometric model of the aortic valve based on the CT image data, combining the three-dimensional geometric model with fluid mechanics control equations to establish a simulation model containing valve movement conditions;

[0073] In this step, the virtual patient's aortic CT image data refers to the digital aortic structure dataset generated by medical image reconstruction technology. The three-dimensional geometric model refers to the three-dimensional structure model of the aortic valve established based on the CT data. The fluid mechanics control equation refers to the Navier-Stokes equation and continuity equation describing blood flow. The valve motion condition refers to the boundary motion constraint simulating the opening and closing of the valve leaflet.

[0074] In the embodiments of the present application, first, the medical image processing software (such as Mimics or 3D Slicer) is used to perform threshold segmentation and morphological optimization on the virtual patient's aortic CT image data, extract the contour information of the aortic valve, and generate two-dimensional slice layers. Second, the three-dimensional reconstruction algorithm (such as MarchingCubes) is used to stack the two-dimensional slice layers into a three-dimensional geometric model, and the surface is smoothed and the holes are repaired through the mesh optimization tool (such as MeshLab). Then, the surface mesh of the three-dimensional geometric model is imported into the fluid mechanics simulation software (such as ANSYS or OpenFOAM) to generate a body mesh (such as a dynamic layer mesh) containing the boundary conditions of the valve motion. Finally, the Navier-Stokes equation (fluid mechanics control equation) is combined with the periodic opening and closing conditions of the valve (such as the closing speed of the diastolic valve) to establish a simulation model that can simulate blood flow.

[0075] In the preoperative evaluation of a 58-year-old patient with aortic valve stenosis, the medical team obtained the aortic root image data of the patient through electrocardiogram-gated CT scanning (layer thickness 0.5mm, matrix 512x512), reconstructed a three-dimensional geometric model containing three valve leaflets using adaptive meshing technology, accurately presented the calcified area of the valve leaflet (thickness 2.1-3.5mm) and the irregular shape of the annulus. The model is imported into the blood flow-structure coupling simulation platform, sets the peak inlet flow velocity during left ventricular systole to 2.1m / s, and matches the patient's actual measured 135 / 85mmHg characteristic pressure waveform. By defining the valve leaflet material stiffness gradient (elastic modulus of calcified area 8MPa, normal tissue 2MPa) through the two-way fluid-structure coupling algorithm, a simulation environment that dynamically simulates the opening and closing of the valve (maximum opening angle 68°) is established, providing a basis for subsequent blood flow analysis.

[0076] 102、Based on the simulation model, real-time calculation of the pressure difference parameters and vortex parameters of the blood flow during the opening and closing of the aortic valve;

[0077] In this step, the pressure difference parameter refers to the transient pressure difference peak between the upstream and downstream of the valve. The vortex parameters include vortex intensity, vortex core position and other turbulent flow characteristic parameters.

[0078] In the embodiments of the present application, first, the fluid mechanics solver parameters (such as transient time step 0.001 seconds, Newtonian fluid assumption) are set in the simulation model, and the physical parameters of blood (such as density, viscosity) are loaded. Second, the control equation is solved by finite volume method to calculate the pressure difference parameters (such as pressure difference on both sides of the valve orifice) and vortex parameters (such as vortex intensity) at different positions in the process of valve opening and closing in real time. Then, the flow field data (such as peak pressure in systole) at key time points are extracted by post-processing tools (such as Paraview) to generate pressure-time curve and vortex distribution cloud chart. Finally, the calculation results are stored as space-time data set for sensor simulation and visualization calling.

[0079] When the simulation model runs to the middle of systole (the valve opens to the maximum angle), the fluid mechanics equation is solved in real time by the system, a peak pressure difference of 55 mmHg (corresponding to severe stenosis) is detected downstream of the valve, and a vortex core area with a diameter of 7 mm is formed on the back of the right coronary leaflet, with a rotation intensity parameter of 4.3 m² / s². Particle tracking shows that the vortex causes blood retention time to be prolonged to 0.28 seconds (which should be less than 0.15 seconds), indicating an increased risk of thrombosis. At the same time, in the regurgitation stage at the beginning of diastole, abnormal reverse flow velocity (0.6 m / s) caused by delayed valve closure is detected, and these parameters are updated at a rate of 150 frames per second to provide dynamic input for the virtual sensor network.

[0080] 103、In the valve surface topology of the three-dimensional geometric model, a fiber virtual sensor is embedded to simulate the deformation of a pressure sensing node under the action of blood flow, and generate a mechanical signal reflecting the opening and closing state of the valve;

[0081] In this step, the fiber virtual sensor refers to a mechanical signal acquisition logic unit embedded in the digital model. The mechanical signal includes the stress distribution and strain rate change of the leaflet surface.

[0082] In the embodiments of the present application, first, key topological nodes (such as leaflet edges and hinge points) are selected in the valve surface grid of the three-dimensional geometric model as the embedded positions of the fiber virtual sensor. Second, based on the pressure difference data calculated by fluid mechanics, the deformation amount (such as 0.1 mm of node displacement per 10 Pa of pressure increase) of the sensor node under the action of blood flow is simulated by finite element analysis (such as ABAQUS). Then, the deformation amount is converted into a virtual mechanical signal (such as voltage or light intensity change), and a time stamp is bound to reflect the opening and closing state of the valve (such as a sudden increase in signal amplitude when closed). Finally, the mechanical signal sequence with spatial position label is output for dynamic rendering in the digital twin environment.

[0083] 320 fiber optic virtual sensors were implanted on the surface of each leaflet in the 3D model to simulate the strain sensing capability of a real fiber optic grating. When the left coronary leaflet undergoes a 0.15mm bending deformation due to blood flow impact, the corresponding sensor node generates a mechanical signal with a frequency offset of 1.8 pm. After signal processing, the pressure distribution map of the leaflet surface (peak pressure 95 kPa) is reconstructed. At the instant of diastolic closure, two adjacent sensors at the edge of the non-coronary leaflet detect a frequency mutation (amplification of 2.4 pm) within 0.6 ms, triggering a valve insufficiency warning. These mechanical signals are strictly synchronized with the simulation clock and input into the visualization system with a sampling accuracy of 2500 times per second.

[0084] 104. Input the pressure difference, eddy current parameters and mechanical signals into the rendering engine in the digital twin environment, and generate a visualization interface by adjusting the optical refractive index distribution of the blood flow particle trajectory and the pressure gradient field.

[0085] In this step, the digital twin environment refers to a virtual simulation space that integrates a physical model with real-time data. Optical refractive index distribution refers to a visualized parameter that adjusts the light propagation path based on the pressure gradient.

[0086] In this embodiment, firstly, pressure difference parameters, eddy current parameters, and mechanical signals are imported into a digital twin rendering engine (such as Unity or Unreal Engine), and blood flow trajectories are simulated through a particle system (e.g., red particles represent high-speed flow, and blue particles represent eddies). Secondly, the optical refractive index distribution is adjusted according to the pressure gradient field data (e.g., increased refractive index in high-pressure areas enhances particle path deflection), generating dynamic color mapping (e.g., warm colors represent high pressure, and cool colors represent low pressure). Next, the mechanical signals are bound to the valve surface deformation, and the dynamic deformation of the 3D model is driven by a vertex shader (e.g., sensor node displacement triggers valve leaflet opening and closing animation). Finally, all elements are integrated to generate an interactive visualization interface that supports multi-view observation (e.g., a cross-sectional view displays the flow field, and a surface view displays the mechanical signal intensity).

[0087] Pressure differential parameters are mapped to color gradients of blood flow particles (red > 50 mmHg, yellow 30-50 mmHg), and eddy current parameters are converted into the helical density of particle trajectories (dense white eddy lines appear in high eddy current regions). The mechanical signal intensity (80-120 kPa) of the fiber optic virtual sensor is superimposed on the valve surface through a semi-transparent halo layer, with halo brightness proportional to local pressure. When regurgitation is detected, the interface automatically activates the profile cutting function, generating dynamic pressure isosurfaces (10 mmHg intervals) in the aortic sinus and highlighting orange warning boxes in areas of delayed closure. Physicians can use an interactive timeline to revisit key phases (such as the valve opening and closing inflection point) and analyze the correlation between abnormal blood flow and structural deformation.

[0088] 105. Obtain the spatiotemporal relationship data of blood flow velocity and pressure gradient in the visualization interface to correct the boundary conditions of the simulation model, so that the valve movement of the three-dimensional geometric model is mapped in synchronization with the actual physiological state of the patient.

[0089] In this step, the spatiotemporal relationship data refers to the time evolution trajectory of multi-dimensional parameters in three-dimensional space. Synchronization mapping refers to virtual-real dynamic calibration achieved through data assimilation.

[0090] In the embodiments of the present application, first, a timeline control is embedded in the visualization interface to allow the user to replay or pause the simulation process, and to synchronously display the pressure difference curve, vortex distribution and valve deformation. Second, the mechanical signal amplitude is mapped to the valve surface halo effect (e.g., the stronger the signal, the brighter the halo) through shader programming (such as GLSL) to enhance state awareness. Third, a data probe tool is added, and the user can click on any position to view real-time pressure, flow rate and deformation data. Finally, the visualization results are exported as dynamic video or interactive VR scenes for surgical planning or medical education demonstration.

[0091] Through the visualization interface, it is found that the systolic blood flow velocity reaches 5.2 m / s (15% higher than the initial simulation setting value) in the calcified area of the valve. The spatiotemporal relationship data (velocity gradient 14 m / s², pressure oscillation ±22 mmHg) of this area is extracted, and the simulation inlet boundary conditions are corrected in reverse: the left ventricular ejection waveform is adjusted from an ideal curve to a patient-specific double-peak shape (peak value 2.3 m / s @ 150 ms, 1.8 m / s @ 300 ms). At the same time, according to the spatial distribution characteristics of the regurgitant vortex, the material damping parameter of the valve leaflet in the closed phase is adjusted (from 0.18 N·s / m to 0.25 N·s / m), so that the simulated closing delay time is shortened from 40 ms to 28 ms (close to the ultrasonic measurement value). After three iterations, the deviation of the simulation results from the catheter measured pressure difference is reduced from the initial 18% to 3%, achieving precise synchronization of the digital twin with the patient's physiological state.

[0092] In summary, steps 101 to 105 realize a full-process closed-loop system for dynamically mapping a virtual aortic valve from medical images to a digital twin. By integrating CT image three-dimensional modeling, fluid mechanics simulation, virtual sensor embedding and visualization interface generation, a high-precision mapping relationship between valve movement and blood flow dynamics is established. In the digital twin environment, based on real-time interactive rendering of pressure difference, vortex parameters and mechanical signals, the dynamic process of the coupling between the valve and the blood flow is intuitively presented, and the boundary conditions of the simulation model are corrected in reverse through spatiotemporal data, establishing an adaptive regulation and control mechanism of "simulation-feedback-optimization". This method breaks through the limitations of traditional static models, ensuring dynamic synchronization of virtual valve movement with actual physiological state, and providing high-fidelity three-dimensional visualization and real-time mechanical monitoring capability for clinical decision-making and pathological analysis.

[0093] To establish the cross-scale correlation mechanism between aortic valve dynamic deformation and blood flow characteristics, by synchronously analyzing the dynamic evolution of the valve geometric deformation and the surface pressure distribution path, accurately positioning the initial area of vortex flow triggered by the pressure gradient mutation in the opening and closing process of the valve, quantifying the diffusion intensity and moving track parameters of the vortex flow in the time and space dimensions, revealing the disturbance law of valve motion abnormalities on the hemodynamic environment, and constructing a blood flow energy dissipation evaluation model based on the coupling of pressure difference-vortex double parameters, dynamic quantitative basis is provided for the blood flow reverse reconstruction simulation of heart valve diseases and the optimization of the fluid mechanics performance of valve interventional instruments.

[0094] In some embodiments, as described in step 102, based on the simulation model, the pressure difference parameters and vortex parameters of the blood flow in the opening and closing process of the aortic valve are calculated in real time, including:

[0095] 201. Extract the geometric deformation data in the opening and closing process of the aortic valve from the simulation model, and divide the dynamic area synchronous with the opening and closing state of the valve in the three-dimensional geometric model based on the moving track of the valve vertex in the geometric deformation data;

[0096] In step 201, the dynamic area refers to the local area where the vertex motion track is highly synchronized in the opening and closing process of the valve. The geometric deformation data is the coordinate information of the position of each point on the valve surface recorded in the simulation model.

[0097] In the embodiments of the present application, first, the geometric deformation data (such as the displacement of the vertex coordinates changing with time) in the opening and closing process of the aortic valve is derived from the simulation model, and the moving track (such as the displacement of vertex A by 5mm in the systolic period) of each valve vertex is extracted by grid processing software (such as Paraview). Secondly, based on the spatial similarity (such as the area with consistent displacement direction and amplitude) of the moving track, a clustering algorithm (such as K-means) is used to divide the valve surface into multiple dynamic areas (such as the center area of the valve leaflet, the edge area). Finally, according to the phase of the opening and closing state of the valve (such as the fully closed period, the half-open period), the dynamic area is bound with the time stamp to generate a time and space synchronous region division mapping table.

[0098] 202. In the dynamic area, according to the difference of the moving track of the valve vertex, the pressure difference between adjacent valve vertices is calculated, and the valve surface pressure distribution path is constructed by the pressure difference;

[0099] In step 202, the pressure distribution path is a spatial distribution characteristic line formed by the pressure difference of the valve surface. The pressure difference is the local pressure gradient caused by the different motion of adjacent vertices.

[0100] In this embodiment, firstly, adjacent valve vertex pairs (e.g., vertex A and B with a distance of 0.1 mm) are traversed within the dynamic region, and their corresponding pressure data (e.g., pressure at vertex A is 120 Pa, and pressure at vertex B is 100 Pa) are read. Secondly, the absolute value of the pressure difference between adjacent vertices (e.g., 20 Pa) is calculated, and a continuous pressure distribution path on the valve surface (e.g., a gradient line extending from the high-pressure area to the low-pressure area) is generated using an interpolation algorithm. Finally, extreme points of pressure difference on the path (e.g., differences exceeding 50 Pa) are marked as key nodes, and a network topology diagram of the valve surface pressure distribution path is constructed.

[0101] 203. Based on the abrupt change locations of pressure differences in the pressure distribution path on the valve surface, mark the regions where blood flow direction changes abruptly as the initial vortex region, and count the geometric center of the initial vortex region;

[0102] In step 203, the initial vortex region is the starting position where the rotation is triggered by the abrupt change in blood flow direction. The geometric center is the centroid coordinate of the vortex region.

[0103] In this embodiment, firstly, locations of abrupt pressure differences (e.g., a sudden increase of more than 50 Pa in pressure difference between adjacent nodes) are identified in the pressure distribution path. The boundaries of these abrupt regions are then expanded using a morphological dilation algorithm and marked as initial vortex regions (e.g., circular regions with a diameter of 2 mm). Secondly, the centroid of each vertex within each initial vortex region is calculated (e.g., by taking the average of all vertex coordinates within the region) to obtain the geometric center position (e.g., coordinates x=10mm, y=5mm). Finally, the geometric center is bound to a region number and a timestamp to generate a spatial distribution list of initial vortex regions.

[0104] 204. Match the geometric center of the initial vortex region to the corresponding time point according to the time sequence of the valve opening and closing state, calculate the displacement difference value of the geometric center between adjacent time points to determine the moving distance corresponding to each time point, and calculate the diffusion intensity based on the change of the coverage area of ​​the initial vortex region at different time points to generate vortex diffusion parameters including moving distance and diffusion intensity.

[0105] In step 204, the coordinates of the vortex center at each time point are arranged chronologically, and the Euclidean distance between adjacent frames is calculated. Simultaneously, the rate of change of the vortex region area is measured. Finally, a data table containing timestamps, travel distances, and diffusion intensity is generated.

[0106] In this embodiment, firstly, the geometric center of the initial vortex region is matched according to the time sequence of valve opening and closing states (e.g., one frame every 0.1 seconds), and the difference in center displacement between adjacent time points (e.g., t=0.1s and t=0.2s) is calculated (e.g., a movement from x=10mm to x=12mm, a displacement of 2mm). Secondly, the change in coverage area of ​​the same initial vortex region at different time points is statistically analyzed (e.g., an increase from 2mm² to 5mm²), and the diffusion intensity is calculated (e.g., an area change rate of 150%). Finally, the displacement difference value is bound to the diffusion intensity to generate a vortex diffusion parameter table containing the movement distance (2mm) and the diffusion intensity (150%).

[0107] 205. The weighted superposition result of the intensity change of the pressure distribution path on the valve surface and the moving distance and diffusion intensity in the eddy diffusion parameters is used as the pressure difference parameter;

[0108] In step 205, weighted superposition is a calculation method that proportionally integrates the pressure path intensity and eddy current diffusion parameters. The pressure difference parameter is a composite index that combines the effects of the pressure gradient and eddy currents.

[0109] In this embodiment, firstly, the intensity change value of the pressure distribution path on the valve surface is extracted (e.g., the pressure difference along the path increases from 50 Pa to 80 Pa, with an intensity change rate of 60%). Secondly, the movement distance (2 mm) and diffusion intensity (150%) in the eddy current diffusion parameters are weighted and superimposed according to preset weights (e.g., movement distance weight 0.6, diffusion intensity weight 0.4) (e.g., 2 × 0.6 + 150% × 0.4 = 1.2 + 0.6 = 1.8). Finally, the superimposed result is multiplied by the pressure path intensity change value (e.g., 1.8 × 60% = 1.08) to generate a comprehensive pressure difference parameter (1.08), which is used to quantify the impact effect of abnormal blood flow on the valve.

[0110] 206. The ratio of the moving distance to the diffusion intensity is used as the eddy current parameter.

[0111] In step 206, the eddy current parameters are comprehensive indicators that quantify the characteristics of eddy current motion. The ratio of the moving distance to the diffusion intensity reflects the balance between the eddy current's moving speed and its expansion speed.

[0112] In this embodiment, firstly, the moving distance (2 mm) and diffusion intensity (150%) are extracted from the eddy diffusion parameters. Secondly, the ratio of the two (2 mm / 150% ≈ 1.33 mm / %) is calculated as the eddy parameter. Finally, the eddy parameter and the pressure difference parameter (1.08) are input into the health assessment model to determine the risk level of valvular lesions (e.g., a higher ratio indicates a more unstable eddy current).

[0113] Here is a specific example:

[0114] In the scenario of computer-aided assessment of aortic valve in patients with cardiovascular disease, a hospital performed preoperative hemodynamic simulation on a patient with severe aortic valve stenosis. In the three-dimensional valve model constructed based on the patient's CT image, the system extracted the dynamic deformation data of the three cusp apices of the valve leaflets from the closed position (distance 2.8 mm) to 18.3 mm during the opening of the valve in systole, and divided the dynamic pressure response area centered on the annulus. Simulation shows that at the middle stage of valve opening (0.25 seconds), the pressure difference between the adjacent vertices at the junction of the right coronary cusp and the non-coronary cusp reaches 32 mmHg, forming a high-pressure gradient zone extending from the annulus to the aortic sinus, and the edge area is marked as the initial area of vortex flow with a geometric center located at the coordinates (X35, Y62, Z18) in the aortic sinus. As the valve enters the maximum opening state at 0.35 seconds, the vortex center moves 9.7 mm towards the ascending aorta, covering an area from the initial 15 mm² to 42 mm², and the calculated diffusion intensity coefficient is 0.83. The system superimposes the pressure gradient zone intensity change (32→18 mmHg) and the vortex displacement distance with a weight of 0.6:0.4 to generate a pressure difference parameter 68 (normal value <30) representing the abnormal function of the valve, and according to the ratio of 9.7 mm displacement to 42 mm² diffusion range 0.23 (threshold 0.15), it is determined that there is pathological vortex flow. This quantitative result is highly consistent with the abnormal blood flow acceleration zone caused by calcification of the valve leaflets found by transesophageal echocardiography during surgery, and ultimately guides the surgical team to use a 25 mm artificial mechanical valve for replacement. Postoperative simulation parameters show that the pressure difference parameter has decreased to 22, and the vortex ratio has returned to 0.09, effectively avoiding the risk of perivalvular complications that may be missed by traditional assessment methods.

[0115] In summary, steps 201 to 206 realize a precise quantification method of blood flow parameters based on dynamic tracking of valve geometric deformation. By extracting the difference in cusp movement trajectory to divide the dynamic area, and correlating the pressure distribution path with the geometric characteristics of the vortex initial area, a vortex diffusion parameter calculation model based on the number of coverage grids and spatial displacement is innovatively proposed. By weighted superposition of pressure difference parameters and vortex parameters, a composite index reflecting the spatiotemporal evolution of blood flow disturbance is constructed, solving the problem of insufficient dynamic capture of complex vortex flow by traditional single-parameter methods. This technology significantly improves the quantifiable characterization of blood flow disturbances during valve opening and closing, providing new dimensional data support for early identification and assessment of hemodynamic abnormalities.

[0116] In some embodiments, in step 204, the geometric center of the vortex initial region is matched to the corresponding time point according to the time sequence of the valve opening and closing state, the displacement difference value of the geometric center between adjacent time points is calculated to determine the movement distance corresponding to each time point, and the diffusion intensity is calculated based on the coverage range change of the vortex initial region at different time points, to generate the vortex diffusion parameters including the movement distance and the diffusion intensity, including:

[0117] 301. Extracting consecutive time points from the time sequence of the valve opening and closing state, and marking the geometric center position of the vortex initial region in each time point as the corresponding spatial coordinates;

[0118] In step 301, consecutive time points refer to equally spaced sampling time points taken from the valve motion cycle. The vortex initial region refers to the first rotating structure region formed when the fluid separates from the valve edge. The geometric center position refers to the spatial symmetry center point coordinates of the region calculated by mathematical methods.

[0119] In the embodiments of the present application, first, consecutive time points (for example, one time point per second) are extracted from the time sequence of the valve opening and closing state, and the geometric center position data of the vortex initial region in each time point is read. The three-dimensional coordinates (X, Y, Z) of the geometric center are extracted by data processing software (such as Paraview), and are marked as the spatial coordinates of the corresponding time point (for example, the time point t=1 second corresponds to the coordinates [10, 5, 2]). Then, the time points and the coordinates are stored in a time sequence database (such as the time sequence database InfluxDB) in time order, forming a “time-coordinate” mapping table, which provides input for subsequent displacement calculation.

[0120] 302. Arranging the spatial coordinates of adjacent time points in time order, calculating the straight line distance difference of the spatial coordinates of the adjacent time points in three-dimensional space, and generating the displacement difference value of the geometric center between adjacent time points;

[0121] In step 302, the displacement difference value refers to the straight line movement amount of the vortex center in three-dimensional space at adjacent time points. The spatial coordinate arrangement refers to organizing the time sequence data into an ordered coordinate set according to the collection order.

[0122] In the embodiments of the present application, firstly, the spatial coordinates of adjacent time points are taken out from the "time-coordinate" mapping table in chronological order (for example, the coordinates [10, 5, 2] of t=1 second and the coordinates [12, 6, 3] of t=2 second). Secondly, the linear distance difference between the two is calculated by a three-dimensional space distance formula (for example, √[(12-10)²+(6-5)²+(3-2)²]=√6≈2.45mm, √ represents square root). Then, the linear distance difference is stored in the displacement difference value list, and the corresponding adjacent time points are associated (for example, the displacement difference between t=1 and t=2 seconds is 2.45mm), to generate a displacement difference value sequence for quantifying the instantaneous speed of the vortex center movement.

[0123] 303. Calculate the ratio of the number of covered grids between adjacent time points as the diffusion rate based on the number of covered grids of the vortex initial region at different time points, wherein the number of covered grids is obtained by counting the total number of boundary grid units of the vortex initial region;

[0124] In step 303, the number of covered grids refers to the total number of grids occupied by the vortex region after dividing the three-dimensional space into unit cubic grid. The diffusion rate refers to the spatial expansion proportion of the vortex region per unit time.

[0125] In the embodiments of the present application, firstly, based on the grid division of the three-dimensional geometric model (for example, dividing the vortex initial region into cubic grid with 1mm side length), the total number of grid units covered by the vortex initial region at each time point is counted (for example, 50 grids are covered at t=1 second). Secondly, the ratio of the number of covered grids between adjacent time points is calculated (for example, 75 grids are covered at t=2 second, and the ratio is 75 / 50=1.5). Finally, the ratio is taken as the diffusion rate (for example, the diffusion rate 1.5 indicates that the coverage range is expanded by 50%), to generate a diffusion rate sequence reflecting the speed of the vortex region diffusion over time.

[0126] 304. Superimpose the displacement difference value and the diffusion rate respectively in chronological order to generate the moving distance and the diffusion intensity corresponding to each time point;

[0127] In step 304, the moving distance refers to the length of the spatial trajectory accumulated by the vortex center over time. The diffusion intensity refers to the cumulative amount of expansion kinetic energy of the vortex region.

[0128] In the embodiments of the present application, first, the displacement difference value sequence is subjected to accumulation operation (for example, t=1 to t=2 seconds displacement 2.45 mm, t=2 to t=3 seconds displacement 3 mm, then the moving distance of t=3 seconds is 2.45+3=5.45 mm), and the cumulative moving distance corresponding to each time point is generated. Secondly, the diffusion rate sequence is subjected to weighted average (for example, taking the average of the diffusion rates of the last three time points), and the diffusion intensity of each time point is generated (for example, the average of 1.5 corresponds to the diffusion intensity “medium”). Finally, the moving distance and the diffusion intensity are bound according to the time point to form a “time-moving distance-diffusion intensity” parameter table.

[0129] 305. The product relationship operation result between the moving distance and the diffusion intensity is taken as the eddy current diffusion parameter containing the moving distance and the diffusion intensity.

[0130] In step 305, the eddy current diffusion parameter refers to a composite kinetic index that comprehensively considers the motion trajectory and the expansion ability.

[0131] In the embodiments of the present application, first, the moving distance (such as 5.45 mm) and the diffusion intensity (such as 1.5) of each time point are extracted from the parameter table. Secondly, the two are subjected to product relationship operation (for example, 5.45×1.5≈8.175), and the eddy current diffusion parameter (such as parameter value 8.175) containing the moving distance and the diffusion intensity is generated. Finally, the parameter value is mapped to the eddy current diffusion level (for example, 0-5 is low risk, and 5-10 is medium risk), and the time sequence is associated, and the output is an eddy current diffusion risk assessment report for clinical or engineering analysis.

[0132] The following is a specific example:

[0133] In the postoperative evaluation scene of aortic valve replacement patients, a hospital conducted CT image hemodynamic simulation analysis on a patient implanted with a biological valve. Based on the dynamic valve opening and closing data at 1 year after surgery, the system captured the initial region of vortex flow formed at the junction of the left and right coronary valves when the valve leaflets closed at the diastolic period 0.12 seconds, with its geometric center located at the three-dimensional coordinates (X28, Y45, Z12). As the time sequence advances to 0.18 seconds, the vortex center moves along the ascending aortic wall to the distal end (X31, Y49, Z15), with a straight-line displacement of 4.3 mm between adjacent time points, while the coverage grid expands from 56 to 89, and the diffusion rate is calculated to be 1.59. By 0.24 seconds, the vortex center continues to displace 3.8 mm to (X34, Y52, Z17), and the coverage grid increases to 123, corresponding to a diffusion rate of 1.38. The system fuses the cumulative displacement of 8.1 mm during 0.12-0.24 seconds with the diffusion intensity coefficient (1.59x1.38=2.19) to generate a vortex diffusion parameter of 17.7 (8.1x2.19), which is significantly higher than the normal threshold of 5.0. This quantitative result is highly consistent with the paravalvular micro-regurgitation area detected by ultrasound Doppler, revealing the abnormal hemodynamic characteristics of the biological valve suture margin caused by local tissue hyperplasia. Based on this, the clinical team developed a targeted follow-up plan, and found that the parameter decreased to 6.3 at the 18-month review, verifying the treatment effect of adaptive remodeling of hyperplastic tissue and avoiding the risk of premature secondary surgical intervention.

[0134] In summary, steps 301 to 305 achieve the precise modeling capability of the spatiotemporal evolution of three-dimensional vortex diffusion characteristics. Through the multiplication operation of the displacement difference value of the geometric center coordinates at consecutive time points and the diffusion rate of the coverage grid, the vector coupling parameter of the vortex diffusion intensity and the moving distance is established. This method completely describes the position migration law and scale expansion trend of the vortex core area through dynamic tracking of the three-dimensional space coordinate sequence and statistical analysis of the grid coverage range, breaking through the limitations of traditional fixed observation points in describing the dynamic characteristics of vortex flow. This technology enhances the modeling accuracy of the vortex evolution process in complex blood flow scenarios, providing high spatiotemporal resolution quantitative basis for blood flow energy loss assessment caused by valve lesions.

[0135] In some embodiments, as described in step 105, the spatiotemporal relationship data of blood flow velocity and pressure gradient in the visualization interface is obtained to correct the boundary conditions of the simulation model, so that the valve motion of the three-dimensional geometric model is synchronized with the actual physiological state of the patient, including:

[0136] 401、extracting the spatiotemporal relationship data of blood flow velocity and pressure gradient from the visualization interface, decomposing the hemodynamic characteristics in the spatiotemporal relationship data to generate blood flow characteristic parameters reflecting the actual physiological state of the patient;

[0137] In step 401, the spatiotemporal relationship data refers to a three-dimensional dynamic data set containing blood flow velocity distribution and pressure gradient changes. The hemodynamic characteristics refer to key index parameters reflecting the heart pumping function extracted from the spatiotemporal data. In the embodiments of the present application, first, the spatiotemporal relationship data of blood flow velocity and pressure gradient (such as velocity vector diagram and pressure cloud diagram) is extracted from the data interface of the visualization interface, and the discrete data is converted into continuous time series through spatiotemporal interpolation algorithm. Secondly, the periodicity, pulsatility and other hemodynamic characteristics (such as systolic flow velocity peak, diastolic pressure valley) in the data are separated by using feature decomposition technology (such as principal component analysis or wavelet transform). Finally, the normalized processing of the decomposed features is combined with the clinical standard parameters (such as normal cardiac output range) to generate blood flow characteristic parameters (such as flow velocity abnormality index, pressure gradient fluctuation rate) reflecting the actual physiological state of the patient, and stored as a structured parameter table.

[0138] 402, compare the blood flow characteristic parameters with the boundary conditions of the current valve motion in the simulation model, identify the matching deviation of the blood flow characteristic parameters and the boundary conditions, and generate boundary condition correction requirements;

[0139] In step 402, the boundary condition correction requirement refers to the parameter adjustment direction indicated by the difference between the simulation model calculation result and the actual measurement data. The matching deviation refers to the model prediction error of the characteristic parameters in the spatial distribution and time evolution. In the embodiments of the present application, first, the boundary conditions (such as valve leaflet opening angle, closing speed) of the current valve motion are read from the simulation model, which are aligned with the blood flow characteristic parameters of step 401 according to the time window. Secondly, the differences (such as actual flow velocity peak is 15% lower than the simulation value) between the two are compared item by item through residual calculation or dynamic time warping algorithm (DTW), and the matching deviation (such as valve closure delay leading to insufficient flow velocity) is identified. Finally, the boundary condition correction requirements (such as “increase the valve leaflet opening angle by 10%” or “advance the closing phase by 0.1 seconds”) are generated according to the deviation type (amplitude deviation, time sequence deviation), and a correction requirement list is formed.

[0140] 403, based on the boundary condition correction requirement, analyze the correlation between the valve motion trajectory in the three-dimensional geometric model and the blood flow characteristic parameters, and determine the influence weight of the valve motion on the blood flow characteristic parameters;

[0141] In step 403, the influence weight refers to a quantitative indicator of the degree of sensitivity of the valve motion trajectory change to the blood flow parameter. The correlation refers to the nonlinear coupling mechanism between the valve leaflet displacement and the blood flow characteristic parameter. In the embodiments of the present application, first, the valve motion trajectory data (such as the hinge point displacement curve) is extracted in the three-dimensional geometric model, and is spatiotemporally aligned with the blood flow characteristic parameter (such as the pressure gradient). Second, the influence weight (such as the weight of the opening and closing speed on the pressure gradient is 0.6) of the valve motion parameter (such as the opening and closing speed) on the blood flow characteristic parameter (such as the pressure gradient) is calculated through gray correlation analysis or multivariate regression model. Finally, the key correction term (such as the opening and closing angle of the valve leaflet with high weight is adjusted first) is determined according to the weight order, an influence weight distribution table is generated, and the priority of subsequent boundary condition adjustment is guided.

[0142] 404. Adjust the boundary conditions of the simulation model according to the influence weight, generate a boundary condition correction amount by constraining the coupling relationship between the amplitude of the valve opening and closing state and the blood flow velocity;

[0143] In step 404, the boundary condition correction amount refers to the parameter value range that needs to be adjusted to realize model calibration. The coupling relationship constraint refers to limiting the parameter adjustment range by establishing a physical correlation equation between the valve motion amplitude and the blood flow velocity.

[0144] In the embodiments of the present application, first, according to the influence weight distribution table, the boundary condition parameters (such as the valve opening and closing amplitude and the closing time) of the simulation model are gradient adjusted (such as the parameter with a weight of 0.6 is increased by an adjustment amount). Second, the coupling relationship between the valve motion and the blood flow velocity is balanced (such as the opening and closing amplitude needs to be adjusted simultaneously after the upper limit of the flow velocity is increased) through a constraint optimization algorithm (such as a particle swarm optimization). Finally, the boundary condition correction amount (such as “opening and closing angle + 12%”) is generated and packaged as a configuration file recognizable by the simulation model, which is used for model parameter updating.

[0145] 405. Inject the boundary condition correction amount into the simulation model to modify the simulation model, and verify the spatiotemporal consistency of the valve motion and the blood flow characteristic parameter of the modified simulation model, and generate a simulation model that is synchronously mapped with the physiological state of the patient.

[0146] In step 405, the spatiotemporal consistency verification refers to the degree of agreement test of the spatial distribution and the time evolution of the modified simulation result with the actual data. The synchronous mapping refers to the dynamic matching of the simulation model with the real-time physiological state of the patient.

[0147] In the embodiments of the present application, first, the boundary condition correction amount is injected into the simulation model (such as replacing the original configuration file), and the fluid mechanics solver is re-run to calculate the corrected valve movement and blood flow parameters. Second, the matching degree of the correction result and the actual patient data is compared through the spatiotemporal consistency verification algorithm (such as dynamic time warping or root mean square error calculation) (such as the flow velocity peak error is reduced from 15% to 5%). Finally, the spatiotemporal consistency report of the corrected model is output, and if the verification is passed, the simulation model synchronized with the patient's physiological state is generated; if not, iterative correction is performed until the standard is met.

[0148] The following is a specific example:

[0149] In the preoperative planning scenario of a patient with complex bicuspid aortic valve malformation, a cardiovascular center uses a hemodynamic simulation system to optimize the surgical plan. Based on the three-dimensional model constructed from the patient's enhanced CT, it is shown that there is an abnormally high pressure area in the left coronary sinus area during systole. The visualization interface extracts the characteristic parameters of peak blood flow velocity 5.2 m / s and transvalvular pressure difference 68 mmHg, but the simulation model generates only 4.8 m / s flow velocity and 58 mmHg pressure difference under the default boundary conditions. The system identifies a 10 mmHg deviation between the actual blood flow characteristics and the model prediction, and traces it back to find that the valve leaflet opening amplitude 85% set in the model does not match the 72% opening and closing degree measured by the patient's CT. Through correlation analysis, it is determined that the influence weight of the valve movement amplitude on the transvalvular pressure difference is 0.78, and accordingly the simulation boundary condition of the valve leaflet opening and closing parameter is adjusted from the free movement mode to the restricted mode, the opening amplitude is constrained to 70%, and the annulus radial stiffness is enhanced. The corrected model generates a flow velocity of 5.1 m / s and a pressure difference of 65 mmHg at 0.25 seconds, with an error of 3% compared to the ultrasonic Doppler measured value, and successfully reproduces a 4 mm diameter turbulent core area behind the left coronary sinus. This accurate model successfully predicts the paravalvular flow abnormalities that may occur after the implantation of a biological valve, guiding the selection of a 27 mm valve and adjusting the suture angle during the operation. Postoperative review shows that the actual transvalvular pressure difference 42 mmHg is highly consistent with the simulation prediction 45 mmHg, verifying the effectiveness of the model correction strategy and providing quantitative decision support for personalized treatment of complex valve malformations.

[0150] In summary, steps 401 to 405 realize a digital twin data-driven simulation model dynamic optimization mechanism. The hemodynamic spatiotemporal features extracted through the visual interface reverse analyze the matching deviation between the simulation model boundary conditions and the real physiological state, and construct a boundary condition correction model based on the valve motion influence weight. The technology constrains the coupling relationship between the valve opening and closing amplitude and the blood flow velocity, so that the simulation model can adaptively adjust the fluid domain deformation parameters, and form a closed loop optimization through spatiotemporal consistency verification. This method fundamentally solves the model distortion problem caused by the lack of physiological data in traditional simulation, and significantly improves the biomechanical consistency between the virtual valve motion and the individualized blood flow characteristics of the patient.

[0151] In some embodiments, as described in step 103, the optical fiber virtual sensor is embedded in the valve surface topology of the three-dimensional geometric model to simulate the deformation of the pressure sensing node under the action of blood flow, generate mechanical signals reflecting the opening and closing state of the valve, including:

[0152] 501. Determine the node distribution position of the optical fiber virtual sensor in the curvature change area and the stress concentration area of the valve surface topology structure;

[0153] In step 501, the curvature change area refers to the area where the geometric shape of the valve surface changes suddenly, such as the leaflet junction or calcified protrusion site. The stress concentration area refers to the site where the valve bears the maximum mechanical stress under the impact of blood flow. The optical fiber virtual sensor refers to a bionic sensor network established through mathematical modeling, and the node distribution position refers to the deployment coordinates of the simulated sensor on the valve surface. In the embodiments of the present application, first, based on the finite element analysis results of the valve surface topology structure, the coordinate distribution of the curvature change area (such as the curved edge of the leaflet) and the stress concentration area (such as the vicinity of the valve hinge point) is extracted. The surface curvature mutation point is identified through a geometric curvature calculation algorithm (such as Gaussian curvature), and the grid nodes of the stress concentration area are selected in combination with the stress cloud map. Secondly, mark the candidate node position in the double-high area of curvature and stress (such as the junction between the center of the leaflet and the hinge point), and ensure that the optical fiber virtual sensor covers the mechanically sensitive area. Finally, generate a node distribution position list and associate the local geometric coordinates of the valve three-dimensional model to provide input for pressure sensor node deployment.

[0154] 502. Set a plurality of pressure sensing nodes in the node distribution position, and bind each pressure sensing node with the local geometric coordinates of the valve surface topology structure to establish the deformation constraint condition of each pressure sensing node under the action of blood flow;

[0155] In step 502, the pressure sensing node refers to the computing unit that undertakes the function of collecting mechanical signals in the virtual sensor network. The deformation constraint condition refers to the physical correlation equation between the node displacement and the elastic deformation of the valve surface material. In the embodiment of the present application, first, the specific coordinates of the pressure sensing node are selected in the node distribution position of step one, and each node is bound to the local geometric coordinates of the valve surface topology (such as node A is bound to coordinates [x1, y1, z1]) through a grid mapping algorithm. Secondly, according to the elastic modulus of the valve material and the blood flow pressure data, the deformation constraint condition of each node is set (such as the maximum displacement of the node under the blood flow pressure is not more than 2mm). Finally, the displacement boundary conditions (such as X / Y / Z direction deformation freedom degree limitation) of each node are defined by the finite element solver to generate the node constraint parameter table and provide rules for displacement calculation.

[0156] 503、calculate the displacement of each pressure sensing node through the deformation constraint condition, and convert the displacement into a three-dimensional space coordinate change sequence of the pressure sensing node;

[0157] In step 503, the displacement refers to the three-dimensional space position offset of the pressure sensing node under the impact of blood flow. The coordinate change sequence refers to the trajectory data set of the node position evolution over time. In the embodiment of the present application, first, the blood flow pressure data is loaded into the finite element simulation model, and the displacement of each pressure sensing node under the action of blood flow is calculated based on the deformation constraint condition (such as the displacement of node A in the systolic period is 1.5mm). Secondly, the displacement is converted into the three-dimensional space coordinate change sequence of the node through the coordinate transformation algorithm (such as rigid body transformation or affine transformation) (such as the coordinate [x1+0.3, y1+0.2, z1+0.1] at t=0.1 second). Finally, the coordinate change data of all nodes is stored in time sequence to form a "time-coordinate" mapping table for deformation feature extraction.

[0158] 504、extract the displacement change data of each pressure sensing node according to the three-dimensional space coordinate change sequence, and construct the deformation feature curve of the node based on the displacement change data;

[0159] In step 504, the deformation characteristic curve refers to a time-amplitude relationship map reflecting the displacement mode of the node. The displacement change data refers to a multi-element time series containing displacement, velocity, and acceleration. In the embodiments of the present application, first, the time series displacement change data of each pressure sensing node is extracted from the "time-coordinate" mapping table (for example, the displacement of node A increases from 0 to 1.5 mm within 0-0.5 seconds). Second, the deformation characteristic curve of the node is constructed by a cubic spline interpolation or polynomial fitting algorithm (for example, the displacement-time curve shows a trend of first acceleration and then deceleration). Finally, the curve parameters (such as peak displacement and slope change point) are associated with the valve opening and closing state (such as the displacement peak corresponding to the complete closing period), and a deformation characteristic curve library with time markers is generated.

[0160] 505, the deformation characteristic curve is converted into a mechanical signal waveform, and the mechanical signal waveform is characterized by the displacement amplitude, velocity change rate, and acceleration change rate of the pressure sensing node to generate a mechanical signal reflecting the opening and closing state of the valve.

[0161] In step 505, the mechanical signal waveform refers to the deformation characteristic converted into a quantifiable biomechanical index curve. Feature extraction refers to the process of identifying key parameters from the waveform. In the embodiments of the present application, first, the displacement amplitude (such as 1.5 mm), the velocity change rate (such as the displacement from 0 to 1.5 mm takes 0.3 seconds corresponding to a speed of 5 mm / s), and the acceleration change rate (such as the speed from 0 to 5 mm / s takes 0.1 seconds corresponding to an acceleration of 50 mm / s²) in the deformation characteristic curve are taken as input, and a mechanical signal waveform (such as the displacement amplitude is mapped to the voltage signal amplitude, and the acceleration is mapped to the frequency modulation) is generated through a signal conversion model (such as a mechanical transfer function). Second, the key features of the waveform (such as the high-frequency pulse signal corresponding to the closing period) are extracted using wavelet transform or Fourier analysis. Finally, the feature parameters are bound to the valve motion state, and the mechanical signal reflecting the opening and closing state (such as the signal amplitude suddenly rising when completely closed) is output for real-time mapping and visualization by the digital twin system.

[0162] In summary, steps 501 to 505 realize a distributed mechanical monitoring virtualization technology based on valve topology deformation. Through the node intelligent distribution strategy of curvature change and stress concentration area, combined with the local geometric coordinate binding algorithm, a spatial position optimization model of the optical fiber virtual sensor is constructed. The displacement conversion and dynamic mapping technology based on deformation constraint conditions convert the three-dimensional space coordinate sequence into a mechanical signal waveform containing amplitude, velocity, and acceleration change, which can accurately reflect the mechanical conduction path of the valve surface micro-deformation. This technology first realizes the equivalent distributed mechanical feedback of the virtual environment as the real sensor measurement, providing a high-precision virtual detection means for the mechanical tracing of valve opening and closing dysfunction.

[0163] The following is a specific example:

[0164] In the preoperative planning of mitral valve repair for rheumatic heart disease patients, a cardiovascular center constructed a dynamic valve model based on the MRI data of the patients. For the curvature mutation area (the curvature radius suddenly dropped from 8.2 mm to 3.5 mm) and the stress concentration area (the peak stress reached 0.85 MPa) found in the middle of the posterior leaflet, the system laid 12 groups of virtual sensing nodes on the surface of the three-dimensional model, among which the key node P07 was located at the junction of the posterior leaflet and the chordae (X45, Y28, Z15). By binding the geometric coordinates of this area, a deformation constraint was established: when the valve is closed, the Z-axis displacement is limited to not more than 2.3 mm. During the simulation of the systolic period of the heart, the P07 node detected a composite deformation of X-axis positive displacement 1.8 mm and Z-axis compression displacement 2.1 mm at 0.25 seconds, and its displacement velocity increased from 4 mm / s to 12 mm / s between 0.18-0.22 seconds, forming a characteristic double-peak waveform. After the system converted this deformation data into mechanical signals, it showed that an abnormal impact waveform with an amplitude of 5.6 N and an acceleration of 15 m / s² appeared at 0.28 seconds, which was highly consistent with the spatial position of the calcified point of the chordae (X44, Y27, Z16) found by ultrasound contrast. Based on this, the clinical team adjusted the surgical plan, added calcified lesion removal and artificial chordae implantation on the basis of preserving the native valve, and postoperative simulation showed that the amplitude of the impact waveform of the P07 node decreased to 2.1 N, verifying the optimization effect of the repair strategy on the stress distribution of the valve.

[0165] In some embodiments, as described in step 101, a three-dimensional geometric model of the aortic valve is constructed based on the CT image data, and the three-dimensional geometric model is combined with the fluid mechanics control equation to establish a simulation model containing the valve motion conditions, including:

[0166] 601、Extract the contour information of the aortic valve in the aortic CT image data, and construct a preliminary three-dimensional geometric structure of the valve based on the contour information, which contains the morphological features and spatial position of the valve;

[0167] In step 601, the contour information refers to the pixel set of the valve edge segmented from the CT image. The preliminary three-dimensional geometry refers to the triangular mesh model containing the basic shape of the valve. In the embodiment of the present application, first, the threshold segmentation is performed on the aortic CT image data by a medical image processing software (such as Mimics or 3D Slicer), the two-dimensional contour information of the aortic valve is extracted, and the morphological optimization (such as the erosion and expansion algorithm) is used to remove the noise interference. Secondly, the continuous two-dimensional contour layers are stacked, the Marching Cubes algorithm is used to generate the preliminary three-dimensional geometry, and the morphological characteristics (such as the leaflet thickness, curvature) and the spatial position (such as the connection relationship with the aortic root) of the leaflet are retained. Finally, the model is aligned with the original CT coordinate system through the spatial registration technology, and the anatomical position accuracy of the three-dimensional structure is ensured.

[0168] 602, refining the preliminary three-dimensional geometry, supplementing the detailed features of the valve, and forming a complete three-dimensional geometric model of the aortic valve;

[0169] In step 602, the detailed features refer to the small anatomical structures of the valve surface such as calcified nodules and fibrotic stripes. The complete three-dimensional geometric model refers to the refined digital model containing physiological surface features. In the embodiment of the present application, first, the mesh refinement (such as based on the Laplacian smoothing algorithm) is performed on the preliminary three-dimensional geometry, and the contour jump or hole defect (such as the jagged structure of the leaflet edge) is repaired. Secondly, the contact surface details (such as the microstructure of the leaflet joint area) when the valve is closed are supplemented by manual or semi-automatic tools (such as the “hole filling” function of MeshLab), and the hinge points, annulus and other key anatomical markers are added. Finally, the geometric rationality of the model is verified in combination with the clinical data (such as the normal valve opening and closing angle range), and the complete three-dimensional geometric model is output.

[0170] 603, based on the three-dimensional geometric model, extracting the geometric feature parameters of the valve surface, and combining the physiological motion law of the valve in the three-dimensional geometric model, defining the motion constraint condition in the opening and closing process of the valve;

[0171] In step 603, the geometric feature parameters include leaflet thickness, radius of curvature, surface area, and other morphological indicators. The motion constraint condition refers to the physical motion rules restricted by the anatomical structure during the opening and closing of the valve. In the embodiments of the present application, first, the curvature, thickness, area, and other geometric feature parameters of the valve surface (such as the radius of curvature of the leaflet center 2 mm) are extracted from the three-dimensional geometric model, and the physiological motion law of the valve (such as the closing speed of the leaflet in diastole) is simulated based on finite element analysis (such as ABAQUS). Secondly, the constraint conditions are defined according to the motion law: the opening and closing angle limit (such as the maximum opening angle 85°), the closing phase delay time (such as 0.1 seconds), and other parameters are set through motion capture data or clinical observation. Finally, a structured constraint parameter table containing geometric features and motion rules is generated.

[0172] 604, combine the three-dimensional geometric model with the fluid mechanics control equation, and construct a dynamic model of the interaction between blood flow and the valve according to the motion constraint condition of the valve, the dynamic model including the pressure effect of blood flow on the valve and the response of the valve to blood flow;

[0173] In step 604, the fluid mechanics control equation includes the Navier-Stokes equation and the continuity equation. The dynamic model refers to the mathematical expression system of fluid-structure interaction. In the embodiments of the present application, first, the three-dimensional geometric model is imported into the fluid mechanics simulation software (such as ANSYS or OpenFOAM), and the body grid is divided (such as the dynamic layer grid adapting to the motion of the valve). Secondly, the Navier-Stokes equation is combined with the motion constraint condition of the valve, and the blood flow boundary parameters (such as the inlet flow rate, the outlet pressure) and the dynamic response parameters of the valve (such as the elastic modulus, the damping coefficient) are set. Then, the fluid-structure interaction equation is solved by the finite volume method, and the pressure effect of blood flow on the valve (such as the leaflet surface pressure distribution) and the reaction of the valve deformation to blood flow (such as the flow field disturbance) are calculated. Finally, a dynamic model containing bidirectional action parameters is generated.

[0174] 605, bidirectionally couple the pressure effect parameters of blood flow on the valve and the response parameters of the valve to blood flow in the dynamic model, combine the motion constraint condition with the morphological features of the three-dimensional geometric model, and construct a simulation model containing the motion condition of the valve.

[0175] In step 605, the bidirectional coupling refers to the real-time interaction calculation of fluid pressure and structural deformation. The simulation model refers to a digital twin system that can reproduce the dynamic behavior of the valve under physiological conditions. In the embodiments of the present application, first, the blood flow pressure parameters (such as the peak systolic pressure 120 Pa) and the valve response parameters (such as the leaflet displacement 2 mm) are extracted from the dynamic model, and the real-time feedback relationship between the two is established through a bidirectional coupling iterative algorithm (such as strong coupling FSI). Second, according to the motion constraint condition (such as the opening angle limit 85°), the grid deformation parameters (such as the maximum displacement threshold) are adjusted to ensure that the valve movement conforms to the physiological law. Finally, the convergence of the model (such as the residual less than 1e-5) is verified through multi-physical field simulation, and the simulation model containing the dynamic opening and closing of the valve, the blood flow pressure fluctuation and the flow field vortex characteristics is output to support pathological analysis and surgical planning.

[0176] The following is a specific example:

[0177] In the preoperative planning of transcatheter aortic valve replacement (TAVR) for a patient with severe aortic valve stenosis, a certain heart center carried out hemodynamic simulation based on the patient's enhanced CT image data. First, the system extracted the contour information of the valve calcification area from the CT sequence, reconstructed the initial three-dimensional structure, and showed that the valve leaflet thickened and fused, with an opening area of only 0.8 cm². Through detailed processing, the spatial distribution details of the calcification were supplemented, and in the complete model, a calcified nodule with a diameter of 6.3 mm was found at the root of the right coronary valve leaflet, causing the maximum opening angle of the valve leaflet to be limited to 32° (normal > 60°). Combined with the regularity of cardiac cycle motion, the constraint condition that the Z-axis displacement of the calcified nodule area should not exceed 1.2 mm when the valve leaflet is closed during diastole was set. After coupling the model with computational fluid dynamics, the simulation showed that the blood flow formed a jet of 8.5 m / s at the calcified nodule, and the local pressure gradient reached 78 mmHg. When the bidirectional coupling parameter was iterated to the 5th time, the model successfully reproduced the abnormal vibration mode of the valve leaflet under the constraint of calcification: the right coronary valve leaflet appeared a 3.7 mm lag displacement at the 0.22 second time point, which was consistent with the 93% agreement degree of the out-of-sync feature of the valve leaflet motion measured by echocardiography. Based on the model, the surgical team chose a 26 mm balloon-expanded valve, and the simulation predicted that after implantation, the valve orifice flow velocity decreased to 2.3 m / s, with an error of only 0.2 m / s from the actual postoperative review data, accurately avoiding the risk of paravalvular leakage and verifying the clinical value of the whole process from imaging to simulation. In summary, steps 601 to 605 realize the aortic valve dynamics coupling modeling method based on CT images. Through contour information extraction and geometric refinement, a three-dimensional valve model with anatomical details and kinematic characteristics is established. Combined with the fluid mechanics control equation and the physiological motion constraint condition of the valve, a bidirectional coupling model of blood flow pressure action and valve mechanical response is constructed, and the dynamic solution of valve deformation and blood flow dynamics is realized. This method solves the precision loss problem of boundary condition simplification in traditional one-way fluid-solid coupling simulation, forms a high-fidelity simulation framework from static structure to dynamic blood flow interaction, and lays a precise numerical experimental foundation for the hemodynamic study of valve pathological mechanisms.

[0178] In some embodiments, in step 604, the three-dimensional geometric model is combined with the fluid mechanics control equation to construct a dynamic model of the interaction between blood flow and the valve according to the valve motion constraint condition, including:

[0179] 701. Extract the valve surface topology of the three-dimensional geometric model, obtain the curvature distribution characteristics and node connection relationship in the valve surface topology, and generate a surface grid for fluid-structure coupling;

[0180] In step 701, the surface topology refers to the meshed mathematical expression of the valve surface geometry. The curvature distribution characteristics refer to the quantitative indicators of the bending degree of each region of the surface. The surface grid refers to the hybrid element grid used for fluid-structure coupling analysis.

[0181] In this embodiment, firstly, mesh data (such as vertex coordinates and facet connectivity) of the valve surface topology is extracted from the three-dimensional geometric model. Surface curvature distribution characteristics (such as Gaussian curvature and mean curvature) are obtained using curvature calculation tools (such as the curvature analysis module of MeshLab). Secondly, a fluid-structure coupled surface mesh is constructed based on node connectivity (such as vertex sharing rules for triangular facets), ensuring that mesh nodes are aligned with the valve deformation region. Next, jagged edges are eliminated using mesh optimization algorithms (such as Laplacian smoothing), generating a surface mesh suitable for fluid dynamics calculations. This mesh is then exported in a format recognizable by finite element analysis software (such as ANSYS) to provide input for boundary condition matching.

[0182] 702. Match the surface mesh with the fluid dynamics control equations by boundary conditions, analyze the relationship between the fluid pressure gradient pulsation characteristics in the fluid dynamics control equations and the deformation response of the valve surface topology, and generate a mesh topology that couples fluid and structure.

[0183] In step 702, boundary condition matching refers to mathematically associating fluid pressure fluctuations with structural deformation. Mesh topology refers to the data transfer network at the fluid-structure interface. In this embodiment, firstly, the surface mesh is imported into a fluid dynamics simulation environment (such as OpenFOAM), and the inlet, outlet, and wall boundary conditions of the fluid domain are set (e.g., the valve surface is set as a fluid-structure coupling boundary). Secondly, the pressure gradient fluctuation characteristics in the Navier-Stokes equations (e.g., the high-pressure region during systole and the low-pressure region during diastole) are analyzed, and the deformation response of the valve surface mesh under fluid pressure is calculated through finite element analysis (e.g., deformation of 0.1 mm for every 10 Pa increase in pressure). Next, the fluid pressure gradient and structural deformation data are correlated to generate a dynamic fluid-structure coupling mesh topology (e.g., the deformation mesh is updated in real time with pressure), ensuring bidirectional synchronization of data between the fluid and structural domains.

[0184] 703. Extract the valve opening and closing phase and motion trajectory feature points from the valve motion constraint conditions, match the valve opening and closing phase and motion trajectory feature points with the mesh topology of the fluid-structure coupling, and generate fluid domain deformation parameters and valve motion boundary conditions.

[0185] In step 703, the motion trajectory feature point refers to the key coordinate point of the landmark position in the opening and closing process of the valve. The fluid domain deformation parameter refers to the deformation quantitative index of the blood flow area with the valve movement. In the embodiment of the present application, first, the opening and closing phase (such as the systolic period 0-0.3 seconds, the diastolic period 0.3-0.6 seconds) and the motion trajectory feature point (such as the displacement path of the valve leaflet hinge point) are extracted from the valve motion constraint condition. Second, the phase and the trajectory point are mapped to the grid topology of fluid and structure coupling: through time series alignment (such as the high-pressure fluid boundary corresponding to the systolic period), the displacement constraint (such as the X direction displacement not more than 2mm) of the trajectory feature point is marked at the key node (such as the valve leaflet edge) of the grid. Then, the fluid domain deformation parameter (such as the grid stretching ratio) and the valve motion boundary condition (such as the valve leaflet opening and closing speed limit) are generated according to the displacement constraint, forming a dynamically updated grid deformation rule table.

[0186] 704, input the fluid domain deformation parameter and the valve motion boundary condition into the fluid mechanics control equation, and synchronously solve the fluid mechanics control equation and the valve kinematics constraint to generate the pressure action of blood flow on the valve and the response data of the valve to the blood flow;

[0187] In step 704, synchronous solving refers to the real-time joint calculation of the fluid equation and the structure equation. The response data refers to the bidirectional mechanical parameters of fluid-structure interaction. In the embodiment of the present application, first, the fluid domain deformation parameter (such as the grid stretching ratio 0.1) and the valve motion boundary condition (such as the maximum opening angle of the valve leaflet 85°) are input into the fluid mechanics control equation (such as the transient Navier-Stokes equation), and the fluid pressure and the structure deformation are synchronously solved by the strong coupling solver (such as the FSI module). Second, the pressure action of blood flow on the valve (such as the valve surface pressure distribution) and the reaction of valve deformation to the flow field (such as the flow velocity fluctuation caused by the change of flow passage cross-sectional area) are iteratively calculated in each time step. Finally, the bidirectional response data set containing the pressure action peak value, the valve displacement amount and the vortex characteristics of the flow field is output for model correction.

[0188] 705, map the response data to the valve surface topology structure of the three-dimensional geometric model, correct the position offset amount of the valve surface topology structure according to the response data, and generate a dynamic model containing the interaction of blood flow and valve through the synchronous iterative update of the position offset amount and the pressure action.

[0189] In step 705, the position offset refers to the displacement of the structural mesh nodes relative to the initial position. The synchronous iterative update refers to the real-time feedback correction of the fluid pressure and structural deformation. In the embodiments of the present application, first, the pressure action and valve displacement in the response data are mapped to the surface topology nodes of the three-dimensional geometric model (for example, node A pressure 120 Pa corresponds to displacement 1.2 mm), and the node position offset is corrected through coordinate transformation algorithm (such as affine transformation). Second, the fluid domain mesh deformation is recalculated according to the corrected position (such as the flow passage width increases by 0.5 mm), and the model convergence is verified through iterative update (such as synchronization once every 0.01 seconds) (such as residual error less than 1e-5). Finally, the dynamic model containing dynamic blood flow pressure, valve deformation and grid topology real-time update is output, which supports pathological simulation and surgical plan evaluation.

[0190] The following is a specific example:

[0191] In the interventional treatment planning of a patient with congenital bicuspid aortic valve malformation, the medical team constructed a three-dimensional model of the abnormal valve based on high-resolution CT data. For the dumbbell-shaped opening formed by the fusion of the left and right coronary valves, the system found that the curvature radius of the anterior commissure area decreased from 5.2 mm of the normal valve leaflet to 1.8 mm, and a high-density coupled mesh was laid out in this area. When the surface mesh is matched with the fluid mechanics equation, the model captures that when the valve leaflet opens to the maximum angle of 32° (normal tricuspid valve about 60°) in systole, the mesh nodes in the anterior commissure area generate a local pressure gradient of 14 kPa due to the sudden change of curvature, causing an abnormal backward displacement of 3.2 mm in this area at the 0.22 second time point. By matching the valve opening and closing phase data obtained from echocardiogram, the model links the valve closure trajectory feature points in early diastole (0.15 seconds) with the fluid domain deformation parameters, and reproduces the eccentric regurgitant jet caused by poor coaptation of the valve leaflets, with a peak flow velocity of 4.8 m / s. After three iterations of bidirectional coupling, the model shows that the abnormal displacement causes a persistent vortex with a diameter of 6 mm in the left coronary sinus, which matches the actual regurgitant area detected by cardiac MRI four-dimensional blood flow imaging with a matching degree of 91%. Based on this, the surgical team adjusts the original interventional plan and selects a 26 mm artificial valve with an external skirt. Postoperative simulation shows that the regurgitant velocity decreases to 1.2 m / s, with an error of 1.3 m / s measured by the actual catheter, which is within the clinical allowable range, successfully avoiding the risk of paravalvular leakage that may be missed by traditional image evaluation.

[0192] In summary, steps 701 to 705 realize the efficient dynamic simulation algorithm of fluid-structure coupling field. Through the curvature feature driven fluid-structure grid topology matching technology, the valve opening and closing phase and the motion trajectory feature point are embedded into the solving process of the fluid domain deformation parameter. The kinematic constraints of the valve are integrated in the fluid mechanics equation, and through the iteration correction mechanism of pressure action and displacement response, the real-time synchronous solution of bidirectional fluid-structure coupling is realized. This technology significantly improves the dynamic response modeling accuracy of valve deformation to blood flow pressure gradient, solves the energy transfer error problem caused by time sequence mismatch in the traditional step-by-step solving method, and provides a high-reliability simulation platform for the prediction of hemodynamic effects of complex valvular lesions.

[0193] Figure 2 A structure diagram of a virtual patient physiological state real-time monitoring system based on digital twinning is provided for the embodiments of the present application, as shown in Figure 2 The system comprises:

[0194] The construction module 21 is configured to acquire CT image data of the virtual patient's aorta, construct a three-dimensional geometric model of the aortic valve based on the CT image data, combine the three-dimensional geometric model with a fluid mechanics control equation, and establish a simulation model containing valve motion conditions.

[0195] The calculation module 22 is configured to calculate the pressure difference parameters and vortex parameters of blood flow in the opening and closing process of the aortic valve in real time based on the simulation model.

[0196] The generation module 23 is configured to embed an optical fiber virtual sensor in the valve surface topology structure of the three-dimensional geometric model, simulate the deformation of the pressure sensing node under the action of blood flow through the optical fiber virtual sensor, and generate a mechanical signal reflecting the opening and closing state of the valve.

[0197] The input module 24 is configured to input the pressure difference, vortex parameters and mechanical signal into a rendering engine in a digital twinning environment, adjust the optical refractive index distribution of the blood flow particle trajectory and pressure gradient field, and generate a visual interface.

[0198] The correction module 25 is configured to acquire the space-time relationship data of blood flow velocity and pressure gradient in the visual interface, correct the boundary conditions of the simulation model, and make the valve motion of the three-dimensional geometric model keep synchronous mapping with the actual physiological state of the patient.

[0199] Figure 2 The virtual patient physiological state real-time monitoring system based on digital twinning can execute Figure 1The implementation principle and technical effects of the virtual patient physiological state real-time monitoring method based on digital twinning according to the embodiment are not repeated. The specific operation modes of each module and unit in the virtual patient physiological state real-time monitoring system based on digital twinning according to the embodiment are described in detail in the embodiment of the method, and will not be described in detail here.

[0200] In one possible design, Figure 2 The virtual patient physiological state real-time monitoring system based on digital twinning according to the embodiment can be implemented as a computing device, such as Figure 3 According to the embodiment, the computing device can include a storage component 31 and a processing component 32.

[0201] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32.

[0202] The processing component 32 is configured to perform the above Figure 1 The embodiment provides a virtual patient physiological state real-time monitoring method based on digital twinning.

[0203] The processing component 32 can include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component can also be one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components, for executing the above method.

[0204] The storage component 31 is configured to store various types of data to support the operation of the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0205] Of course, the computing device can also include other components, such as an input / output interface, a display component, a communication component, etc.

[0206] The input / output interface provides an interface between the processing component and the peripheral interface module, which can be an output device, an input device, etc.

[0207] The communication component is configured to facilitate wired or wireless communication between the computing device and other devices, etc.

[0208] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform, and the computing device can be a cloud server, and the processing component and the storage component can be a basic server resource rented or purchased from the cloud computing platform.

[0209] The embodiment of the application further provides a computer storage medium storing a computer program, and the computer program can implement the above-mentioned method when executed by a computer. Figure 1 The embodiment shown in the figure is a virtual patient physiological state real-time monitoring method based on digital twinning.

[0210] Those skilled in the art can clearly understand the specific working process of the system, device and unit described above for the convenience and brevity of description, and the corresponding process in the foregoing method embodiments can be referred to, which will not be repeated here.

[0211] The device embodiments described above are only schematic, and the units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place or distributed on multiple network units. Part or all of the modules can be selected to achieve the purpose of the embodiment scheme according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0212] Through the description of the foregoing embodiments, those skilled in the art can clearly understand that each embodiment can be realized by means of software and a necessary general hardware platform, and of course, it can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the method described in each embodiment or some part of the embodiment.

[0213] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the application, and not to limit them; although the application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the application.

Claims

1. A method for real-time monitoring of the physiological state of a virtual patient based on digital twins, characterized in that, The method comprises the following steps: acquiring CT image data of a virtual patient's aorta, constructing a three-dimensional geometric model of the aortic valve based on the CT image data, combining the three-dimensional geometric model with fluid mechanics control equations to establish a simulation model containing valve motion conditions; based on the simulation model, real-time calculation of the pressure difference parameters and vortex parameters of blood flow in the opening and closing process of the aortic valve; embedding optical fiber virtual sensors in the valve surface topology of the three-dimensional geometric model to simulate the deformation of pressure sensing nodes under the action of blood flow through the optical fiber virtual sensors, and generating mechanical signals reflecting the opening and closing state of the valve; inputting the pressure difference, vortex parameters and mechanical signals into the rendering engine in the digital twin environment, generating a visual interface by adjusting the optical refractive index distribution of the blood flow particle trajectory and the pressure gradient field; acquiring the spatiotemporal relationship data of blood flow velocity and pressure gradient in the visual interface to correct the boundary conditions of the simulation model, so that the valve motion of the three-dimensional geometric model is synchronized with the actual physiological state of the patient; based on the simulation model, real-time calculation of the pressure difference parameters and vortex parameters of blood flow in the opening and closing process of the aortic valve, comprising: extracting geometric deformation data in the opening and closing process of the aortic valve from the simulation model, dividing dynamic regions synchronized with the opening and closing state of the three-dimensional geometric model based on the moving trajectory of the valve vertex in the geometric deformation data; in the dynamic region, according to the difference of the moving trajectory of the valve vertex, the pressure difference between adjacent valve vertices is calculated, and the valve surface pressure distribution path is constructed through the pressure difference; based on the mutation position of the pressure difference in the valve surface pressure distribution path, the region where the blood flow direction changes is marked as the vortex initial region, and the geometric center of the vortex initial region is counted; matching the geometric center of the vortex initial region to the corresponding time point according to the time sequence of the opening and closing state of the valve, calculating the displacement difference value of the geometric center between adjacent time points to determine the moving distance corresponding to each time point, and calculating the diffusion intensity based on the coverage range change of the vortex initial region at different time points to generate vortex diffusion parameters containing moving distance and diffusion intensity; the weighted superposition result between the intensity change of the valve surface pressure distribution path and the moving distance and diffusion intensity in the vortex diffusion parameters is taken as the pressure difference parameter; the ratio of the moving distance and diffusion intensity is taken as the vortex parameter.

2. The method of claim 1, wherein, matching the geometric center of the vortex initial region to the corresponding time point according to the time sequence of the opening and closing state of the valve, calculating the displacement difference value of the geometric center between adjacent time points to determine the moving distance corresponding to each time point, and calculating the diffusion intensity based on the coverage range change of the vortex initial region at different time points to generate vortex diffusion parameters containing moving distance and diffusion intensity, comprising: extracting consecutive time points from the time sequence of the opening and closing state of the valve, and marking the position of the geometric center of the vortex initial region in each time point as the corresponding spatial coordinates; Arranging the spatial coordinates of adjacent time points in time sequence, calculating the linear distance difference of the spatial coordinates of the adjacent time points in three-dimensional space, and generating the displacement difference value of the geometric center between the adjacent time points; Based on the number of coverage grids of the vortex initial region at different time points, the ratio of the number of coverage grids between adjacent time points is calculated as the diffusion rate, and the number of coverage grids is obtained by counting the total number of boundary grid units of the vortex initial region; Superimpose the displacement difference value and the diffusion rate in time sequence respectively to generate the movement distance and diffusion intensity corresponding to each time point; The product of the movement distance and the diffusion intensity is taken as the vortex diffusion parameter containing the movement distance and the diffusion intensity.

3. The method of claim 1, wherein, Obtain the space-time relationship data of blood flow velocity and pressure gradient in the visualization interface to correct the boundary conditions of the simulation model, so that the valve movement of the three-dimensional geometric model is synchronized with the actual physiological state of the patient, including: Extract the space-time relationship data of blood flow velocity and pressure gradient from the visualization interface, decompose the hemodynamic characteristics in the space-time relationship data, and generate blood flow characteristic parameters reflecting the actual physiological state of the patient; Compare the blood flow characteristic parameters with the boundary conditions of the current valve movement in the simulation model, identify the matching deviation of the blood flow characteristic parameters and the boundary conditions, and generate boundary condition correction requirements; Based on the boundary condition correction requirements, analyze the correlation between the valve movement trajectory in the three-dimensional geometric model and the blood flow characteristic parameters, and determine the influence weight of the valve movement on the blood flow characteristic parameters; Adjust the boundary conditions of the simulation model according to the influence weight, generate the boundary condition correction amount by constraining the coupling relationship between the amplitude of the valve opening and closing state and the blood flow velocity; and Inject the boundary condition correction amount into the simulation model to correct the simulation model, and verify the space-time consistency of the valve movement and the blood flow characteristic parameters of the corrected simulation model, and generate a simulation model synchronized with the physiological state of the patient.

4. The method of claim 1, wherein, Embed the optical fiber virtual sensor in the valve surface topology structure of the three-dimensional geometric model to simulate the deformation of the pressure sensing node under the action of blood flow, generate mechanical signals reflecting the opening and closing state of the valve, including: Determine the node distribution position of the optical fiber virtual sensor in the curvature change area and stress concentration area of the valve surface topology structure; Set multiple pressure sensing nodes in the node distribution position, bind each pressure sensing node with the local geometric coordinates of the valve surface topology structure to establish the deformation constraint condition of each pressure sensing node under the action of blood flow; Calculate the displacement of each pressure sensing node through the deformation constraint condition, and convert the displacement into a three-dimensional space coordinate change sequence of the pressure sensing node; Extract the displacement change data of each pressure sensing node according to the three-dimensional space coordinate change sequence, and construct the deformation feature curve of the node based on the displacement change data; The deformation characteristic curve is converted into a mechanical signal waveform, the mechanical signal waveform is characterized by a displacement amount amplitude, a velocity change rate and an acceleration change rate of the pressure sensing node, and a mechanical signal reflecting an opening and closing state of the valve is generated.

5. The method of claim 1, wherein, A three-dimensional geometric model of the aortic valve is constructed based on the CT image data, the three-dimensional geometric model is combined with a fluid mechanics control equation to establish a simulation model containing valve motion conditions, including: Contour information of the aortic valve in the aortic CT image data is extracted, and a preliminary three-dimensional geometric structure of the valve is constructed based on the contour information, the structure containing morphological characteristics and spatial positions of the valve; The preliminary three-dimensional geometric structure is refined to supplement detailed characteristics of the valve, and a complete three-dimensional geometric model of the aortic valve is formed; Based on the three-dimensional geometric model, geometric characteristic parameters of the valve surface are extracted, and in combination with physiological motion laws of the valve in the three-dimensional geometric model, motion constraint conditions in the opening and closing process of the valve are defined; The three-dimensional geometric model is combined with the fluid mechanics control equation to construct a dynamic model of the interaction between blood flow and the valve according to the valve motion constraint conditions, the dynamic model containing pressure action of the blood flow on the valve and response of the valve to the blood flow; The pressure action parameters of the blood flow on the valve and the response parameters of the valve to the blood flow in the dynamic model are bidirectionally coupled, the simulation model containing the valve motion conditions is constructed in combination with the motion constraint conditions and the morphological characteristics of the three-dimensional geometric model.

6. The method of claim 5, wherein, The three-dimensional geometric model is combined with the fluid mechanics control equation to construct a dynamic model of the interaction between blood flow and the valve according to the valve motion constraint conditions, including: The topological structure of the valve surface of the three-dimensional geometric model is extracted, the curvature distribution characteristics and node connection relationships in the topological structure of the valve surface are obtained, and a surface grid coupled with fluid and structure is generated; The surface grid is matched with the boundary conditions of the fluid mechanics control equation, the fluid pressure gradient pulsation characteristics in the fluid mechanics control equation and the deformation response relationship of the topological structure of the valve surface are analyzed, and a grid topology coupled with fluid and structure is generated; The opening and closing phase and the motion trajectory feature points of the valve in the valve motion constraint conditions are extracted, the opening and closing phase and the motion trajectory feature points are matched with the grid topology coupled with fluid and structure, and fluid domain deformation parameters and valve motion boundary conditions are generated; The fluid domain deformation parameters and the valve motion boundary conditions are input into the fluid mechanics control equation, the fluid mechanics control equation and the kinematic constraint of the valve are solved synchronously, and pressure action of the blood flow on the valve and response data of the valve to the blood flow are generated; The response data are mapped to the topological structure of the valve surface of the three-dimensional geometric model, the position offset of the topological structure of the valve surface is corrected according to the response data, and a dynamic model containing the interaction between blood flow and the valve is generated through synchronous iterative updating of the position offset and the pressure action.

7. A real-time monitoring system of physiological state of virtual patient based on digital twinning, characterized in that, including: The construction module is configured to acquire CT image data of a virtual patient's aorta, construct a three-dimensional geometric model of an aortic valve based on the CT image data, and combine the three-dimensional geometric model with a fluid mechanics control equation to establish a simulation model containing a valve motion condition; The calculation module is configured to calculate, based on the simulation model, a pressure difference parameter and a vortex parameter of blood flow in the opening and closing process of the aortic valve in real time; The generation module is configured to embed a fiber virtual sensor in a valve surface topology of the three-dimensional geometric model to simulate deformation of a pressure sensing node under the action of blood flow by the fiber virtual sensor and generate a mechanical signal reflecting the opening and closing state of the valve; The input module is configured to input the pressure difference, vortex parameter, and mechanical signal into a rendering engine in a digital twin environment to generate a visual interface by adjusting a blood flow particle trajectory and an optical refractive index distribution of a pressure gradient field; The correction module is configured to acquire spatiotemporal relationship data of blood flow velocity and pressure gradient in the visual interface to correct boundary conditions of the simulation model, so that the valve motion of the three-dimensional geometric model is mapped synchronously with the actual physiological state of the patient. The calculation module is configured to calculate, based on the simulation model, a pressure difference parameter and a vortex parameter of blood flow in the opening and closing process of the aortic valve in real time, including: extracting geometric deformation data in the opening and closing process of the aortic valve from the simulation model, dividing a dynamic region synchronous with the opening and closing state of the valve in the three-dimensional geometric model based on a moving trajectory of a valve vertex in the geometric deformation data; in the dynamic region, calculating a pressure difference between adjacent valve vertices according to the difference in the moving trajectory of the valve vertex, and constructing a valve surface pressure distribution path based on the pressure difference; based on a mutation position of the pressure difference in the valve surface pressure distribution path, marking a region where the blood flow direction is mutated as a vortex initial region, and counting a geometric center of the vortex initial region; matching the geometric center of the vortex initial region to a corresponding time point according to a time sequence of the opening and closing state of the valve, calculating a displacement difference value of the geometric center between adjacent time points to determine a moving distance corresponding to each time point, and calculating a diffusion intensity based on the coverage range change of the vortex initial region at different time points to generate a vortex diffusion parameter containing the moving distance and the diffusion intensity; using a weighted superposition result between the intensity change of the valve surface pressure distribution path and the moving distance and the diffusion intensity in the vortex diffusion parameter as the pressure difference parameter; using a ratio of the moving distance and the diffusion intensity as the vortex parameter.

8. A computing device, comprising: The storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement the virtual patient physiological state real-time monitoring method based on digital twinning according to any one of claims 1-6.

9. A computer storage medium, characterized in that The computer program is stored in the computer and is executed by the computer to implement the virtual patient physiological state real-time monitoring method based on digital twinning according to any one of claims 1-6.

Images