Information processing system, method, apparatus, and medium for performing position prediction

Abstract

The application discloses an information processing system, method, device and medium for position prediction, relates to the technical field of information processing, and comprises the following steps: a data input interface is used to receive enhanced images of a pulmonary artery of a CTEPH object; a three-dimensional modeling module is used to create a target three-dimensional model of a blood vessel of the pulmonary artery based on the enhanced images; a parameter extraction tool is used to perform fluid dynamics operation on the target three-dimensional model based on preset blood flow boundary conditions, extract global blood flow parameters and local blood flow characteristic parameters of the pulmonary artery, and screen at least one candidate lesion area; a virtual balloon adjustment module is used to adjust the virtual balloon expansion shape of the candidate lesion area according to the lesion type of the candidate lesion area; and a position prediction module is used to perform fluid dynamics operation on a new target three-dimensional model obtained after adjustment based on the preset blood flow boundary conditions, and determine the final position of the balloon expansion operation from the candidate lesion area. Invalid candidate areas are pre-screened through a virtual verification link.

Description

Technical Field

[0001] This invention relates to the field of information processing technology, and in particular to information processing systems, methods, devices and media for location prediction. Background Technology

[0002] In the interventional treatment planning of chronic thromboembolic pulmonary hypertension (CTEPH), clinicians rely on medical imaging (such as Computed Tomographic Pulmonary Angiography, CT pulmonary angiography, and pulmonary artery angiography) for manual observation and analysis to identify abnormal vascular areas. However, traditional manual observation techniques have significant limitations. First, the selection of abnormal areas is highly dependent on physician experience and lacks quantitative assessment standards. Second, it cannot analyze the impact of local vascular abnormalities on overall pulmonary artery hemodynamics (such as eddy current distribution and wall shear stress). Finally, existing medical image processing systems lack virtual treatment simulation capabilities and cannot predict the blood flow improvement effect after interventional procedures. Summary of the Invention

[0003] In view of this, the object of the present invention is to provide an information processing system, method, apparatus, and medium for location prediction, capable of accurately estimating the optimal location. The specific solution is as follows:

[0004] In a first aspect, this application discloses an information processing system for location prediction, applied to a computer device, comprising:

[0005] The data input interface is used to receive enhanced images of the pulmonary arteries of CTEPH subjects;

[0006] A 3D modeling module is used to create a target 3D model of the pulmonary artery vessels based on the enhanced image;

[0007] A parameter extraction tool is used to perform fluid dynamics calculations on the target three-dimensional model based on preset blood flow boundary conditions, so as to extract the global blood flow parameters and local blood flow characteristic parameters of the pulmonary artery, and to screen at least one candidate lesion area based on the global blood flow parameters and the local blood flow characteristic parameters.

[0008] The virtual balloon adjustment module is used to adjust the virtual balloon expansion morphology of the candidate lesion areas according to the lesion type of each candidate lesion area.

[0009] The location prediction module is used to perform hydrodynamic calculations on the new target three-dimensional model obtained after the virtual balloon dilation morphology adjustment based on preset blood flow boundary conditions, so as to determine the final location of the balloon dilation surgery from the candidate lesion area.

[0010] Optionally, the information processing system for location prediction further includes:

[0011] The inlet boundary condition setting module is used to set the right heart output as the inlet flow boundary condition of the preset inlet boundary condition.

[0012] The recursive module is used to recursively generate sub-vessel branches from the cut-off exit point according to a preset bifurcation ratio factor.

[0013] The structure tree construction module is used to stop the branching when the radius of the sub-vessel branch is less than a preset termination threshold, so as to construct a recursive impedance structure tree model.

[0014] The frequency domain impedance acquisition module is used to control the pressure calculation value of the root node of the recursive impedance structure tree model where the cut-off outlet is located to converge to the pulmonary artery wedge pressure measurement value based on the pulmonary artery wedge pressure measurement value of the CTEPH object, so as to obtain the frequency domain impedance of the current root node of the structure tree.

[0015] The exit boundary condition setting module is used to convert the frequency domain impedance into a time domain convolution kernel function, and generate dynamic exit boundary conditions based on the time domain convolution kernel function and the cardiac cycle parameters of the CTEPH object.

[0016] The preset blood flow boundary condition construction module is used to construct the preset blood flow boundary conditions based on the preset inlet boundary conditions and the dynamic outlet boundary conditions.

[0017] Optionally, the parameter extraction tool includes:

[0018] The trimming module is used to perform geometric trimming on the target 3D model to obtain a computational domain that includes the entrance / exit boundaries;

[0019] The mesh generation module is used to perform unstructured mesh generation processing on the computational domain to generate a discrete mesh model;

[0020] The condition loading module is used to load the preset inlet boundary conditions and the dynamic outlet boundary conditions;

[0021] The solution module is used to perform transient hydrodynamic solution processing on the discrete grid model through the Navier-Stokes equations to obtain the spatiotemporal distribution results including the pulmonary artery velocity field;

[0022] The analysis area determination module is used to obtain the global average flow velocity based on the pulmonary artery velocity field, to filter local velocity point values ​​that meet the preset flow velocity ratio conditions based on the global average flow velocity, and to determine the corresponding blood vessel location as the analysis area based on the three-dimensional coordinates corresponding to the local velocity point values.

[0023] The curve generation module is used to extract the radial velocity distribution of the blood vessel cross sections of the region to be analyzed and the corresponding downstream region to obtain the corresponding velocity distribution curves.

[0024] The clustering module is used for clustering based on the flow velocity distribution curve to obtain the coordinates of the corresponding feature points in the central area of ​​the blood vessel as local blood flow feature parameters.

[0025] The eddy structure identification module is used to perform eddy structure identification processing on the pulmonary artery velocity field in the spatiotemporal distribution results to obtain the eddy volume distribution;

[0026] The blood flow parameter acquisition module is used to calculate the spatial wall shear stress distribution of the spatiotemporal distribution results in the whole domain, so as to obtain the eddy volume distribution and spatial wall shear stress as global blood flow parameters.

[0027] Optionally, the analysis area determination module includes:

[0028] The velocity point filtering unit is used to filter local velocity point values ​​that meet the preset velocity ratio condition based on the global average flow velocity and sort them in order of size, and to filter a preset number of target local velocity point values ​​from the local velocity point values ​​in order of size.

[0029] The analysis area determination unit is used to determine the corresponding blood vessel location as the analysis area based on the three-dimensional coordinates corresponding to the target local velocity point value.

[0030] Optionally, the parameter extraction tool includes:

[0031] The candidate region screening unit is used to screen at least one candidate lesion region from the region to be analyzed based on the eddy volume distribution and the spatial wall shear stress.

[0032] Optionally, the virtual balloon adjustment module includes:

[0033] The first adjustment unit is used to adjust the virtual balloon expansion morphology of the candidate lesion area by uniformly expanding the blood vessel midline if the lesion type of the candidate lesion area is a ring-shaped lesion.

[0034] The second adjustment unit is used to adjust the virtual balloon dilation morphology of the candidate lesion area based on the anatomical morphology restoration method of healthy blood vessel geometry if the lesion type of the candidate lesion area is a reticular lesion type.

[0035] Optionally, the location prediction module includes:

[0036] The distance calculation unit is used to calculate the Euclidean distance between the blood flow characteristic parameters of the current candidate lesion area obtained from the virtual postoperative operation and the standard blood flow characteristic parameters of the standard three-dimensional model of the standard pulmonary artery, so as to obtain the corresponding Euclidean distance; wherein, the standard three-dimensional model is a three-dimensional model of blood vessels constructed based on healthy anatomical features;

[0037] The location prediction unit is used to determine that the current candidate lesion is the final location of the balloon dilation surgery if the Euclidean distance is less than a preset distance threshold.

[0038] Secondly, this application discloses an information processing method for location prediction, including:

[0039] Receive enhanced images of the pulmonary arteries of CTEPH patients;

[0040] A target 3D model of the pulmonary artery vessels is created based on the enhanced image;

[0041] Based on preset blood flow boundary conditions, the target three-dimensional model is subjected to fluid dynamics calculations to extract global blood flow parameters and local blood flow characteristic parameters of the pulmonary artery, so as to screen at least one candidate lesion area according to the global blood flow parameters and the local blood flow characteristic parameters.

[0042] The virtual balloon dilation morphology of the candidate lesion areas is adjusted according to the lesion type of each candidate lesion area;

[0043] Based on preset blood flow boundary conditions, fluid dynamics calculations are performed on the new target 3D model obtained after the virtual balloon dilation morphology adjustment to determine the final location of the balloon dilation surgery from the candidate lesion area.

[0044] Thirdly, this application discloses an electronic device, including:

[0045] Memory, used to store computer programs;

[0046] A processor is configured to execute the computer program to implement the steps of the aforementioned disclosed information processing method for location prediction.

[0047] Fourthly, this application discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the steps of the aforementioned disclosed information processing method for location prediction.

[0048] As can be seen, this application discloses an information processing system for location prediction, applied to a computer device, comprising: a data input interface for receiving enhanced images of the pulmonary artery of a CTEPH object; a three-dimensional modeling module for creating a target three-dimensional model of the pulmonary artery based on the enhanced images; a parameter extraction tool for performing hydrodynamic calculations on the target three-dimensional model based on preset blood flow boundary conditions to extract global blood flow parameters and local blood flow characteristic parameters of the pulmonary artery, and to screen at least one candidate lesion area based on the global blood flow parameters and the local blood flow characteristic parameters; a virtual balloon adjustment module for adjusting the virtual balloon expansion morphology of the candidate lesion areas according to the lesion type of each candidate lesion area; and a location prediction module for performing hydrodynamic calculations on the new target three-dimensional model obtained after the virtual balloon expansion morphology adjustment based on preset blood flow boundary conditions, to determine the final location of the balloon dilation surgery from the candidate lesion areas. Therefore, by extracting global blood flow parameters and local blood flow characteristic parameters, at least one candidate lesion area can be screened based on the degree of parameter abnormality. Quantifying parameters replaces manual experience, and candidate areas are sorted and screened according to the degree of parameter abnormality, avoiding the intervention of physician experience. The virtual balloon dilation morphology is adjusted according to the lesion type to generate a virtual postoperative vascular model and recalculate the fluid dynamics. It can be seen that by adjusting the morphology to match the lesion type, the postoperative model is generated to ensure that the postoperative model conforms to the real physiological response. By comparing the degree of improvement of blood flow parameters before and after virtual surgery, coordinate data that can be directly used for surgical planning is generated, reducing manual analysis time. The virtual verification process pre-screens invalid candidate areas, avoiding the waste of clinical resources. Attached Figure Description

[0049] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0050] Figure 1 This is a schematic diagram of the structure of an information processing system for location prediction disclosed in this application;

[0051] Figure 2 This is a schematic diagram of the exit boundary conditions for a recursive impedance structure tree model disclosed in this application;

[0052] Figure 3 This is a flowchart of a method for screening candidate lesion areas using a parameter extraction tool disclosed in this application;

[0053] Figure 4This is a schematic diagram of an assessment of blood flow recovery based on the center deviation of four clusters disclosed in this application, wherein... Figure 4 (a) is the normalized velocity distribution curve of the vessel cross-section in the Pre state; Figure 4 (b) shows the clustering results of cross-sectional velocities; Figure 4 (c) is a normalized velocity distribution map of the vascular cross section at the lesion site after the first balloon pulmonary artery angioplasty; Figure 4 (d) is the normalized velocity distribution curve of the blood vessel cross section in the vPOST state; Figure 4 (e) is a map showing the location of specific vascular lesions and their associated locations, based on the location of each velocity distribution curve and cluster analysis. Figure 4 (f) is a normalized velocity distribution map of the vessel cross-section at the lesion site after the second balloon pulmonary artery angioplasty.

[0054] Figure 5 This is a schematic diagram of a global eddy current structure extraction method disclosed in this application;

[0055] Figure 6 This application discloses a flowchart for information processing and evaluation for location prediction.

[0056] Figure 7 This is a flowchart of an information processing method for location prediction disclosed in this application;

[0057] Figure 8 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation

[0058] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0059] In the interventional treatment planning of chronic thromboembolic pulmonary hypertension (CTEPH), clinicians rely on medical imaging (such as CTPA and pulmonary angiography) for manual observation and analysis to identify abnormal vascular areas. However, traditional manual observation techniques have significant shortcomings. First, the selection of abnormal areas is highly dependent on physician experience and lacks quantitative assessment standards. Second, it is impossible to analyze the impact of local vascular abnormalities on overall pulmonary artery hemodynamics (such as eddy current distribution and wall shear stress). Finally, existing medical image processing systems do not have virtual treatment simulation capabilities and cannot predict the blood flow improvement effect after interventional procedures.

[0060] Therefore, the present invention provides an information processing scheme for location prediction, which can accurately estimate the optimal location.

[0061] Reference Figure 1 As shown, this embodiment of the invention discloses an information processing system for location prediction, applied to a computer device, comprising:

[0062] Data input interface 11 is used to receive enhanced images of the pulmonary arteries of CTEPH subjects.

[0063] In this embodiment, the data input interface 11 first receives enhanced images of the pulmonary artery of the CTEPH patient. The acquisition process of these enhanced images is as follows: using a clinical standard multi-slice spiral CT or MRI (Magnetic Resonance Imaging) device, raw DICOM (Digital Imaging and Communications in Medicine) images are acquired while the CTEPH patient is holding their breath, and then transmitted to a medical image archiving system. The images are then enhanced using the following data enhancement techniques:

[0064] Histogram equalization or window width / window level adjustment can be used to optimize the distinction between the vessel lumen and the thrombus to obtain enhanced images; alternatively, anisotropic diffusion filtering can be used to preserve the vessel edge while suppressing noise to obtain enhanced images; or, end-to-end reconstruction based on deep learning can be used to improve the spatial resolution of small vessels (<2mm) to obtain enhanced images.

[0065] In this way, since the pulmonary artery and surrounding tissues have similar gray levels in the original CT / MRI images, enhancement processing can strengthen the vascular boundary, avoid missegmentation during 3D reconstruction, and eliminate image distortion caused by respiratory motion artifacts and ray hardening effects, ensuring the geometric accuracy of the fluid computation domain.

[0066] The 3D modeling module 12 is used to create a target 3D model of the pulmonary artery vessels based on the enhanced image.

[0067] In this embodiment, the 3D modeling module 12 is used to manually / automatically segment the enhanced images of the pulmonary arteries of the CTEPH object to generate a target 3D model of the pulmonary artery vessels. Specifically, it inputs an enhanced CT / MRI sequence in DICOM format and performs isotropic resampling; it uses a vessel lumen and thrombus segmentation algorithm and employs threshold segmentation to initially select vessel regions; it distinguishes between navigable vessel lumens and organized thrombi based on a U-Net deep learning model. It performs 3D connected component analysis on the segmentation results, retaining the largest connected component (main pulmonary artery tree), then performs morphological closure operations on lumens with a diameter <2mm, and removes terminal branches with a length <5mm and a sudden 50% reduction in diameter; it generates a topological skeleton from the root of the main pulmonary artery to the terminal branches; it calculates the maximum inscribed sphere radius of each branch point as the local vessel radius; it arranges control points along the centerline, for example, the spacing between control points = 0.5 times the radius; it fits a smooth B-spline surface to generate a watertight triangular mesh model with a patch size of 0.1-0.3mm. Then, the model was optimized and verified. Specifically, a hemispherical cap-shaped structure was added at the cut-off outlet; the inlet plane was extended by 5 times the pipe diameter to stabilize the flow field; the Dice coefficient of the model and the source image was measured to see if it was greater than the preset coefficient threshold, and the curvature continuity was checked. The watertight triangular mesh model that passed the verification was used as the target three-dimensional model of the pulmonary artery.

[0068] Information processing systems also include:

[0069] The inlet boundary condition setting module is used to set the right heart output as the inlet flow boundary condition of the preset inlet boundary condition.

[0070] The recursive module is used to recursively generate sub-vessel branches from the cut-off exit point according to a preset bifurcation ratio factor.

[0071] The structure tree construction module is used to stop the branching when the radius of the sub-vessel branch is less than a preset termination threshold, so as to construct a recursive impedance structure tree model.

[0072] The frequency domain impedance acquisition module is used to control the pressure calculation value of the root node of the recursive impedance structure tree model where the cut-off outlet is located to converge to the pulmonary artery wedge pressure measurement value based on the pulmonary artery wedge pressure measurement value of the CTEPH object, so as to obtain the frequency domain impedance of the current root node of the structure tree.

[0073] The exit boundary condition setting module is used to convert the frequency domain impedance into a time domain convolution kernel function, and generate dynamic exit boundary conditions based on the time domain convolution kernel function and the cardiac cycle parameters of the CTEPH object.

[0074] The preset blood flow boundary condition construction module is used to construct the preset blood flow boundary conditions based on the preset inlet boundary conditions and the dynamic outlet boundary conditions.

[0075] Understandably, constructing the initial pulmonary artery outlet structure tree, such as... Figure 2 As shown: Input parameters (boundary conditions): Extract the radius r0 of the branch (exit) vessel at the specific pulmonary artery truncation point; let A(x,t) represent the vessel area at the selected location at time t; define the bifurcation scaling factors α and β; define the minimum termination radius r. min The segment length to radius ratio l / r is defined as 50, and bifurcation parameters η = 1.16 and γ = 0.41 are defined to control bifurcation asymmetry. Blood physical parameters (density ρ, dynamic viscosity, kinematic viscosity), heart rate T obtained from clinical examination methods, and frequency range are also considered. , Let represent the angular frequency of the k-th discrete frequency component, k represent the index of the frequency point, and T represent the sampling period of the signal (in seconds). The formula relating the elastic modulus of the pulmonary artery wall to its radius is:

[0076] ;

[0077] Where E represents the elastic modulus of the pulmonary artery wall, also known as Young's modulus, and the unit is 1. h represents the thickness of the blood vessel wall, in cm. Indicates the initial radius of the pulmonary artery. All of these are fitting constants.

[0078] set up ;

[0079] ;

[0080] in, Indicates vascular segment Cross-sectional area at the location, Indicates vascular segment The radius of the blood vessel at that location. An index describing the dilatability of blood vessels in response to pressure changes, reflecting the ability of blood vessels to change volume with pressure. The higher the value, the more significant the vascular elasticity and other properties that cause changes in vascular volume.

[0081] Construct a tree structure where each parent vessel branches into two child vessels with radii αr and αr respectively. pa and βr pa When any sub-vessel radius r <r min Then the forking will stop.

[0082] Calculate the input impedance of a single blood vessel:

[0083] Impedance formula:

[0084] ;

[0085] in, This represents the input impedance at the blood vessel inlet (position 0) at angular frequency ω. The terminal impedance at the blood vessel outlet (location L) at angular frequency ω is represented, and c represents the wave velocity of blood flow in the blood vessel. The downstream impedance is given by C, where C represents vascular compliance. This represents the initial cross-sectional area of ​​the blood vessel. The density of blood, K is a term related to the Womersley parameter, and wave velocity. .

[0086] Recursively calculate the root impedance of the entire tree structure (i.e., the impedance at the vessel outlet), with the following conditions at the bifurcation:

[0087] Continuous pressure: ;

[0088] in, This indicates the blood pressure within the main blood vessel upstream of the bifurcation point. and These represent the two downstream branch vessels at the bifurcation point. Blood pressure within the body.

[0089] Flow conservation: ;

[0090] in, This indicates that the main blood vessel flowing into the bifurcation point is upstream of the main blood vessel (and...). Blood volume flow rate (corresponding to the same main blood vessel), and These represent the two downstream branch vessels that flow out respectively. ( ) blood volume flow rate.

[0091] Parallel impedance formula: ;

[0092] in, This represents the total input impedance of the upstream main blood vessel at the bifurcation point. and These represent the two downstream branch vessels ( The input impedance of ).

[0093] Time-domain boundary condition transformation:

[0094] Frequency domain impedance is obtained through inverse Fourier transform. Convert to a temporal convolution kernel z(t): ;

[0095] in, This represents the intravascular pressure at spatial location x and time t. This represents the blood flow at spatial location x and time τ. It is the temporal convolution kernel, t represents the current time, τ represents the integration variable, represents a past time point, and T represents the duration of the integration time window.

[0096] After iterative solution, an initial blood flow field is obtained. The initial pressure at the pulmonary artery inlet is checked (based on the mean pressure from clinical results or a self-defined baseline pressure). If the initial pressure is too high or too low, the input of C (vascular compliance) needs to be adjusted by decreasing or increasing the parameters. This is achieved by repeatedly iterating the calculation process until the pulmonary artery inlet pressure is close to the reference pressure.

[0097] The parameter extraction tool 13 is used to perform fluid dynamics calculations on the target three-dimensional model based on preset blood flow boundary conditions, so as to extract the global blood flow parameters and local blood flow characteristic parameters of the pulmonary artery, and to screen at least one candidate lesion area based on the global blood flow parameters and the local blood flow characteristic parameters.

[0098] The parameter extraction tool 13 includes:

[0099] The trimming module is used to perform geometric trimming on the target 3D model to obtain a computational domain that includes the entrance / exit boundaries;

[0100] The mesh generation module is used to perform unstructured mesh generation processing on the computational domain to generate a discrete mesh model;

[0101] The condition loading module is used to load the preset inlet boundary conditions and the dynamic outlet boundary conditions;

[0102] The solution module is used to perform transient hydrodynamic solution processing on the discrete grid model through the Navier-Stokes equations to obtain the spatiotemporal distribution results including the pulmonary artery velocity field;

[0103] The analysis area determination module is used to obtain the global average flow velocity based on the pulmonary artery velocity field, to filter local velocity point values ​​that meet the preset flow velocity ratio conditions based on the global average flow velocity, and to determine the corresponding blood vessel location as the analysis area based on the three-dimensional coordinates corresponding to the local velocity point values.

[0104] The curve generation module is used to extract the radial velocity distribution of the blood vessel cross sections of the region to be analyzed and the corresponding downstream region to obtain the corresponding velocity distribution curves.

[0105] The clustering module is used for clustering based on the flow velocity distribution curve to obtain the coordinates of the corresponding feature points in the central area of ​​the blood vessel as local blood flow feature parameters.

[0106] The eddy structure identification module is used to perform eddy structure identification processing on the pulmonary artery velocity field in the spatiotemporal distribution results to obtain the eddy volume distribution;

[0107] The blood flow parameter acquisition module is used to calculate the spatial wall shear stress distribution of the spatiotemporal distribution results in the whole domain, so as to obtain the eddy volume distribution and spatial wall shear stress as global blood flow parameters.

[0108] The analysis region determination module includes:

[0109] The velocity point filtering unit is used to filter local velocity point values ​​that meet the preset velocity ratio condition based on the global average flow velocity and sort them in order of size, and to filter a preset number of target local velocity point values ​​from the local velocity point values ​​in order of size.

[0110] The analysis area determination unit is used to determine the corresponding blood vessel location as the analysis area based on the three-dimensional coordinates corresponding to the target local velocity point value.

[0111] The parameter extraction tool 13 includes:

[0112] The candidate region screening unit is used to screen at least one candidate lesion region from the region to be analyzed based on the eddy volume distribution and the spatial wall shear stress.

[0113] Understandably, to meet the geometric processing requirements of the 3D pulmonary artery model for fluid dynamics calculations, inlet and outlet are trimmed, boundaries are named, and meshing is performed to satisfy the requirements of fluid dynamics calculations. Preset specific boundary conditions for the CTEPH object (preset inlet and dynamic outlet boundary conditions) are implemented. These specific boundary conditions specifically include parameters such as cardiac output, pulmonary artery pressure, pulmonary artery wedge pressure, and pulmonary vascular resistance obtained from right heart catheterization. Specifically, the patient's specific right heart output or pulmonary artery pressure obtained through clinical examination (right heart catheterization or ultrasound) is used as the inlet boundary condition. The outlet boundary condition can use the pulmonary artery wedge pressure value obtained from right heart catheterization, or it can be obtained by repeatedly performing rapid CFD (Computational Fluid Dynamics) calculations and parameter adjustments using a pulmonary artery structure tree algorithm combined with clinically obtained pulmonary artery pressure as a calibration index to obtain a physiologically realistic structure tree impedance-type outlet condition. This achieves the setting of patient-specific outlet boundary conditions, enabling fluid dynamics calculations for the pulmonary artery. Based on the fluid dynamics calculations, the overall pulmonary artery blood flow was observed. By evaluating overall pulmonary artery blood flow parameters (global eddy flow rate, spatial wall shear stress distribution, etc.) and local lesion blood flow characteristics, at least one significantly abnormal region was selected as a candidate lesion area (as a recommended surgical area). Specifically, the process of selecting candidate lesion areas is as follows: Figure 3 As shown:

[0114] The global average flow velocity Vmean is obtained based on the pulmonary artery velocity field.

[0115] Exclude the velocity values ​​at the outlet of each branch, filter the global velocity point values, select the local velocity point values ​​whose relative velocity ratio (local velocity Vi / Vmean) exceeds 1, and combine the three-dimensional coordinates corresponding to the above local velocity points to determine the blood vessel locations corresponding to the three-dimensional level as candidate regions, and sort them from high to low according to the ratio value (i=1,2,3...).

[0116] The first 10 regions (I=1,2,3,...,10) are selected as the regions to be analyzed, and velocity curves are observed on the above regions and downstream regions. In the current example, the selected vascular segment is the basal segment of the lower lobe of the right lung.

[0117] Generate velocity distribution curves (flow velocity distribution curves) along the corresponding cross-section, and perform standardization for cluster analysis to obtain four or more cluster centers. The specific number of clusters depends on the complexity of the velocity curves. The focus is on evaluating the nonlinear region of the curves (corresponding to blood flow characteristics near the vessel center, rather than near the wall). Figure 4 As shown, Figure 4 This diagram illustrates a method for assessing blood flow recovery based on the center deviation of four clusters. Specifically, it involves extracting cross-sectional velocity curves from initially selected lesion locations (four cluster centers: cluster 1, cluster 2, cluster 3, and cluster 4), performing cluster analysis, and assessing the degree of blood flow recovery based on Euclidean distance-based cluster center deviation. Figure 4 (a) is the normalized velocity distribution curve of the blood vessel cross section at the initially selected lesion site in the pre-procedure state. The horizontal axis (normalized X-axis) and the vertical axis (normalized velocity) show the blood flow velocity distribution at different X positions in this cross section before surgery, presenting the original state of blood flow before surgery and serving as the baseline data for subsequent comparison of postoperative changes. Figure 4 (d) Refers to the normalized velocity distribution of the vessel cross section in the vPOST state. Corresponding to the Pre plot, it is used to show the velocity distribution of the same or corresponding cross section. By comparing with the Pre plot, the change in the overall blood flow velocity distribution in the vPOST state compared with the preoperative state can be seen intuitively, and the impact of virtual surgery and other treatments on blood flow can be preliminarily judged. Figure 4 (c) shows the normalized velocity distribution of the vessel cross-section at the lesion site after the first balloon pulmonary angioplasty. This is used to separately present the changes in blood flow velocity distribution within the cross-section after the first BPA (Balloon Pulmonary Angioplasty) procedure. By comparing it with the Pre map, vPOST map, etc., it can be clearly identified the specific effect of the first BPA (vBPA1) on improving blood flow, such as which locations have increased flow velocity and how the distribution is adjusted. Figure 4 (f) shows the normalized velocity distribution of the vessel cross-section at the lesion site after the second balloon pulmonary artery angioplasty. Combined with vBPA1, this allows for observation of further changes in blood flow velocity distribution resulting from the second BPA procedure, analysis of the additional impact of the second surgery on blood flow, and assessment of the differences and cumulative effects of multiple BPA procedures. Figure 4 (b) Based on the cluster analysis results, the distribution of different cluster centers is displayed with the normalized X-axis as the horizontal axis and the normalized velocity as the vertical axis. Through clustering, the cross-sectional velocity data is classified. The location (coordinates and velocity) of the cluster centers and the degree of deviation between them (based on Euclidean distance) are used to quantitatively assess the degree of blood flow recovery. The smaller the deviation of the cluster centers, the closer the blood flow distribution is to the ideal state, reflecting that the blood flow recovery is closer to the expectation after surgery or other treatments. This is a quantitative and visual presentation of the blood flow recovery effect from the perspective of cluster analysis. Figure 4 (e) Used to locate the specific vascular lesions and associated locations corresponding to the above velocity distribution curves and cluster analysis, clarifying which branches and segments of the vascular tree the cross-sectional analysis was performed on, establishing the correspondence between spatial location and blood flow data, and assisting in understanding the significance of blood flow changes at different locations in the overall vascular structure. The colors represent the division of the velocity curves into four segments based on curve characteristics through cluster analysis (n=4). Blue and green can be defined as velocity development near the vessel wall in vascular flow, and are the results of cluster 1 and cluster 4 in cluster analysis; orange and green (non-linear curves) can be defined as velocity development near the vessel center in vascular flow (which is also a key flow characteristic; under stable flow, it is generally top-hat shaped, while the flow characteristic curve shape in the lesion area deviates from the top-hat shape to form an irregular curve), and are the results of cluster 2 and cluster 3 in cluster analysis. The square dots represent the center of each cluster.

[0118] Calculate the global vortex volume V of the pulmonary artery based on the pulmonary artery velocity field. Vortex1 The eddy structure extraction criterion is based on the Q-criterion. The selected eddy level is determined according to the normalized helicity H=(u·ω) / (|u|·|ω|), and the extraction threshold is defined (e.g., iso-surfaces=0.8), where u represents the blood flow velocity vector and ω represents the blood flow eddy volume vector. The eddy volume distribution of the pulmonary artery is shown in the figure. Figure 5 As shown. Combining the above-mentioned eddy volume distribution, spatial wall shear stress, and local blood flow characteristic parameters, at least one abnormally obvious region is selected as a candidate lesion area.

[0119] The virtual balloon adjustment module 14 is used to adjust the virtual balloon expansion morphology of the candidate lesion areas according to the lesion type of each candidate lesion area.

[0120] The virtual balloon adjustment module 14 includes:

[0121] The first adjustment unit is used to adjust the virtual balloon expansion morphology of the candidate lesion area by uniformly expanding the blood vessel midline if the lesion type of the candidate lesion area is a ring-shaped lesion.

[0122] The second adjustment unit is used to adjust the virtual balloon dilation morphology of the candidate lesion area based on the anatomical morphology restoration method of healthy blood vessel geometry if the lesion type of the candidate lesion area is a reticular lesion type.

[0123] Understandably, based on the original image data and the reconstructed 3D model of the pulmonary artery, and based on the lesion type of the obtained candidate lesion area, the selected area undergoes vascular morphology adjustment analogous to the effect of actual balloon dilation surgery. In this invention, two virtual dilation techniques are employed to address the vascular morphology changes caused by mimicking the effects of actual balloon dilation on different lesion types (such as reticular lesions, stenotic lesions, and other relatively common thrombus organization morphologies), generating a virtual balloon dilation post-operative pulmonary artery vascular model. Specifically, the virtual dilation processing methods are as follows: Virtual dilation method 1 (vBPA1) uses the original healthy vessel geometry as a baseline reference, extracts the NURBS (Non-Uniform Rational B-Splines) spline curve features from the healthy vessel wall, and adjusts the curve by combining the upstream and downstream vessel wall shapes of the lesion segment and controlling the basis functions and weighted summation of curve points in the NURBS, restoring the lesion segment to its anatomical baseline shape. Virtual dilation method 2 (vBPA2) is based on the vessel midline of the lesion segment, dilating along the vessel midline while maintaining geometric center alignment. This method assumes that the blood vessel diameter is uniformly dilated, without taking into account the specific morphology of the lesion.

[0124] The location prediction module 15 is used to perform hydrodynamic calculations on the new target three-dimensional model obtained after the virtual balloon expansion morphology adjustment based on preset blood flow boundary conditions, so as to determine the final location of the balloon expansion surgery from the candidate lesion area.

[0125] The location prediction module 15 includes:

[0126] The distance calculation unit is used to calculate the Euclidean distance between the blood flow characteristic parameters of the current candidate lesion area obtained from the virtual postoperative operation and the standard blood flow characteristic parameters of the standard three-dimensional model of the standard pulmonary artery, so as to obtain the corresponding Euclidean distance; wherein, the standard three-dimensional model is a three-dimensional model of blood vessels constructed based on healthy anatomical features;

[0127] The location prediction unit is used to determine that the current candidate lesion is the final location of the balloon dilation surgery if the Euclidean distance is less than a preset distance threshold.

[0128] Understandably, fluid dynamics calculations are performed on the target 3D model generated after the two virtual balloon dilation procedures.

[0129] like Figure 6 As shown, to meet the geometric processing requirements of the 3D model of the pulmonary artery for fluid dynamics calculations, the inlet and outlet are trimmed, the boundaries are named, and a mesh is generated for fluid dynamics calculations. The same patient-specific boundary conditions as in the previous steps (such as parameters obtained from right heart catheterization measurements of cardiac output, pulmonary artery pressure, pulmonary artery wedge pressure, and pulmonary vascular resistance) are preset, and fluid dynamics calculations are performed on the pulmonary artery. A cross-section at the same location as in the previous steps is generated, and the flow field processing process is repeated to obtain the relevant velocity curve clustering results. The steps for obtaining the eddy volume are repeated to obtain the global eddy volume V of vBPA1. Vortex2 Obtain the global eddy volume V of vBPA2. Vortex3 Then, a standard three-dimensional model of the pulmonary artery is established. Specifically, the standard three-dimensional model uses the baseline pulmonary artery model as the benchmark for the ideal pulmonary artery blood flow pattern, that is, its internal flow pattern is a stable flow pattern under lesion-free conditions, including the flow characteristic curves at different segmental vessel cross-sections exhibiting a top-hat morphology. A three-dimensional pulmonary artery model of a healthy individual can be used directly as the benchmark, or a standard three-dimensional model of the digital pulmonary artery can be constructed based on the anatomical features of a healthy pulmonary artery (ideal vessel midline network). Then, CFD calculations are performed on the target three-dimensional model (vPOST) using the same boundary conditions to obtain the corresponding blood flow pattern. The aforementioned dynamic processing method for the three-dimensional model is repeated to obtain the flow characteristic results (standard blood flow characteristic parameters) under the vPOST state. Further, a virtual postoperative hemodynamic recovery evaluation is performed. Specifically, using the cluster center point of the vPOST velocity curve as the benchmark, the Euclidean distance D from the cluster center points of Pre, vBPA1, and vBPA1 of the initially defined 10 planes to vPOST is calculated. pre D vBPA1 D vBPA2 The final lesion location is then screened, and the screening logic is: D vBPA1 and D vBPA2 All are less than D pre Given the above conditions, choose D. vBPA1 D vBPA2 The minimum 4 cross sections (4 being the common number of lesions treated in a single BPA surgery), D pre D vBPA1 D vBPA2 This represents the magnitude of the difference between the current state and the ideal / target blood flow characteristics; a smaller value indicates a smaller difference. Based on the selected candidate lesion location, two virtual dilation processes are performed to generate a 3D vascular model. CFD calculations are then performed to obtain the overall VBPA1 and VBPA2 values.Vortex2 V Vortex3 If the vortex volume is reduced relative to the preoperative volume, the current lesion location and number of lesions will be used as the recommended surgical plan. If the above conditions are not met, 1-2 additional candidate lesion locations will be selected after the candidate lesion locations have been determined.

[0130] As can be seen, this application discloses an information processing system for location prediction, applied to a computer device, comprising: a data input interface for receiving enhanced images of the pulmonary artery of a CTEPH object; a three-dimensional modeling module for creating a target three-dimensional model of the pulmonary artery based on the enhanced images; a parameter extraction tool for performing hydrodynamic calculations on the target three-dimensional model based on preset blood flow boundary conditions to extract global blood flow parameters and local blood flow characteristic parameters of the pulmonary artery, and to screen at least one candidate lesion area based on the global blood flow parameters and the local blood flow characteristic parameters; a virtual balloon adjustment module for adjusting the virtual balloon expansion morphology of the candidate lesion areas according to the lesion type of each candidate lesion area; and a location prediction module for performing hydrodynamic calculations on the new target three-dimensional model obtained after the virtual balloon expansion morphology adjustment based on preset blood flow boundary conditions, to determine the final location of the balloon dilation surgery from the candidate lesion areas. Therefore, by extracting global blood flow parameters and local blood flow characteristic parameters, at least one candidate lesion area can be screened based on the degree of parameter abnormality. Quantifying parameters replaces manual experience, and candidate areas are sorted and screened according to the degree of parameter abnormality, avoiding the intervention of physician experience. The virtual balloon dilation morphology is adjusted according to the lesion type to generate a virtual postoperative vascular model and recalculate the fluid dynamics. It can be seen that by adjusting the morphology to match the lesion type, the postoperative model is generated to ensure that the postoperative model conforms to the real physiological response. By comparing the degree of improvement of blood flow parameters before and after virtual surgery, coordinate data that can be directly used for surgical planning is generated, reducing manual analysis time. The virtual verification process pre-screens invalid candidate areas, avoiding the waste of clinical resources.

[0131] Reference Figure 7 As shown, the present invention also discloses an information processing method for location prediction, comprising:

[0132] Step S11: Receive enhanced images of the pulmonary arteries of the CTEPH patient;

[0133] Step S12: Create a target three-dimensional model of the pulmonary artery vessels based on the enhanced image;

[0134] Step S13: Perform fluid dynamics calculations on the target three-dimensional model based on preset blood flow boundary conditions to extract global blood flow parameters and local blood flow characteristic parameters of the pulmonary artery, and screen at least one candidate lesion area based on the global blood flow parameters and the local blood flow characteristic parameters;

[0135] Step S14: Adjust the virtual balloon dilation morphology of the candidate lesion areas according to the lesion type of each candidate lesion area;

[0136] Step S15: Perform fluid dynamics calculations on the new target three-dimensional model obtained after the virtual balloon dilation morphology adjustment based on preset blood flow boundary conditions, so as to determine the final location of the balloon dilation surgery from the candidate lesion area.

[0137] For more detailed processing procedures in steps S11, S12, S13, S14, and S15, please refer to the aforementioned disclosed embodiments; they will not be repeated here.

[0138] Therefore, extracting and quantifying blood flow parameters (global eddies / local velocity distribution) through fluid dynamics calculations eliminates reliance on human experience, leading to a more objective screening of candidate lesions. Virtual morphological adjustments and secondary fluid verification based on lesion type adaptation enable digital prediction of interventional outcomes, avoiding ineffective surgical locations.

[0139] Furthermore, embodiments of this application also disclose an electronic device, Figure 8 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application.

[0140] Figure 8 This is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of this application. Specifically, the electronic device 20 may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the information processing method for location prediction disclosed in any of the foregoing embodiments. Alternatively, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0141] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0142] The processor 21 may include one or more processing cores, such as a quad-core processor or an octa-core processor. The processor 21 may be implemented using at least one hardware form selected from DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), and PLA (Programmable Logic Array). The processor 21 may also include a main processor and a coprocessor. The main processor, also known as a CPU (Central Processing Unit), is used to process data in the wake-up state; the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 21 may integrate a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the screen. In some embodiments, the processor 21 may also include an AI (Artificial Intelligence) processor, which is used to handle computational operations related to machine learning.

[0143] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored thereon can include operating system 221, computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0144] The operating system 221 manages and controls the various hardware devices and computer programs 222 on the electronic device 20 to enable the processor 21 to perform calculations and processing on the massive amounts of data 223 in the memory 22. The operating system 221 can be Windows Server, Netware, Unix, Linux, etc. The computer program 222, in addition to including a computer program capable of performing the information processing method for location prediction executed by the electronic device 20 as disclosed in any of the foregoing embodiments, may further include computer programs capable of performing other specific tasks. The data 223 may include data received by the electronic device from external devices, as well as data collected by its own input / output interface 25.

[0145] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned information processing method for location prediction. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0146] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0147] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application. The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly in hardware, software modules executed by a processor, or a combination of both. The software module may be located in random access memory (RAM), memory, read-only memory (ROM), electrically programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), registers, hard disks, removable disks, CD-ROMs (Compact Disc-Read Only Memory), or any other form of storage medium known in the art.

[0148] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0149] The solution provided by the present invention has been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only for helping to understand the method and core ideas of the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. An information processing system for location prediction, characterized in that, Applied to computer devices, including: The data input interface is used to receive enhanced images of the pulmonary arteries of CTEPH subjects; A 3D modeling module is used to create a target 3D model of the pulmonary artery vessels based on the enhanced image; A parameter extraction tool is used to perform fluid dynamics calculations on the target three-dimensional model based on preset blood flow boundary conditions, so as to extract the global blood flow parameters and local blood flow characteristic parameters of the pulmonary artery, and to screen at least one candidate lesion area based on the global blood flow parameters and the local blood flow characteristic parameters. The virtual balloon adjustment module is used to adjust the virtual balloon expansion morphology of the candidate lesion areas according to the lesion type of each candidate lesion area. The location prediction module is used to perform hydrodynamic calculations on the new target three-dimensional model obtained after the virtual balloon dilation morphology adjustment based on preset blood flow boundary conditions, so as to determine the final location of the balloon dilation surgery from the candidate lesion area. The location prediction module includes: The distance calculation unit is used to calculate the Euclidean distance between the blood flow characteristic parameters of the current candidate lesion area obtained from the virtual postoperative operation and the standard blood flow characteristic parameters of the standard three-dimensional model of the standard pulmonary artery, so as to obtain the corresponding Euclidean distance; wherein, the standard three-dimensional model is a three-dimensional model of blood vessels constructed based on healthy anatomical features; The location prediction unit is used to determine that the current candidate lesion is the final location of the balloon dilation surgery if the Euclidean distance is less than a preset distance threshold.

2. The information processing system for location prediction according to claim 1, characterized in that, Also includes: The inlet boundary condition setting module is used to set the right heart output as the inlet flow boundary condition of the preset inlet boundary condition. The recursive module is used to recursively generate sub-vessel branches from the cut-off exit point according to a preset bifurcation ratio factor. The structure tree construction module is used to stop the branching when the radius of the sub-vessel branch is less than a preset termination threshold, so as to construct a recursive impedance structure tree model. The frequency domain impedance acquisition module is used to control the pressure calculation value of the root node of the recursive impedance structure tree model where the cut-off outlet is located to converge to the pulmonary artery wedge pressure measurement value based on the pulmonary artery wedge pressure measurement value of the CTEPH object, so as to obtain the frequency domain impedance of the current root node of the structure tree. The exit boundary condition setting module is used to convert the frequency domain impedance into a time domain convolution kernel function, and generate dynamic exit boundary conditions based on the time domain convolution kernel function and the cardiac cycle parameters of the CTEPH object. The preset blood flow boundary condition construction module is used to construct the preset blood flow boundary conditions based on the preset inlet boundary conditions and the dynamic outlet boundary conditions.

3. The information processing system for location prediction according to claim 2, characterized in that, The parameter extraction tool includes: The trimming module is used to perform geometric trimming on the target 3D model to obtain a computational domain that includes the entrance / exit boundaries; The mesh generation module is used to perform unstructured mesh generation processing on the computational domain to generate a discrete mesh model; The condition loading module is used to load the preset inlet boundary conditions and the dynamic outlet boundary conditions; The solution module is used to perform transient hydrodynamic solution processing on the discrete grid model through the Navier-Stokes equations to obtain the spatiotemporal distribution results including the pulmonary artery velocity field; The analysis area determination module is used to obtain the global average flow velocity based on the pulmonary artery velocity field, to filter local velocity point values ​​that meet the preset flow velocity ratio conditions based on the global average flow velocity, and to determine the corresponding blood vessel location as the analysis area based on the three-dimensional coordinates corresponding to the local velocity point values. The curve generation module is used to extract the radial velocity distribution of the blood vessel cross sections of the region to be analyzed and the corresponding downstream region to obtain the corresponding velocity distribution curves. The clustering module is used for clustering based on the flow velocity distribution curve to obtain the coordinates of the corresponding feature points in the central area of ​​the blood vessel as local blood flow feature parameters. The eddy structure identification module is used to perform eddy structure identification processing on the pulmonary artery velocity field in the spatiotemporal distribution results to obtain the eddy volume distribution; The blood flow parameter acquisition module is used to calculate the spatial wall shear stress distribution of the spatiotemporal distribution results in the whole domain, so as to obtain the eddy volume distribution and spatial wall shear stress as global blood flow parameters.

4. The information processing system for location prediction according to claim 3, characterized in that, The analysis region determination module includes: The velocity point filtering unit is used to filter local velocity point values ​​that meet the preset velocity ratio condition based on the global average flow velocity and sort them in order of size, and to filter a preset number of target local velocity point values ​​from the local velocity point values ​​in order of size. The analysis area determination unit is used to determine the corresponding blood vessel location as the analysis area based on the three-dimensional coordinates corresponding to the target local velocity point value.

5. The information processing system for location prediction according to claim 3, characterized in that, The parameter extraction tool includes: The candidate region screening unit is used to screen at least one candidate lesion region from the region to be analyzed based on the eddy volume distribution and the spatial wall shear stress.

6. The information processing system for location prediction according to claim 1, characterized in that, The virtual balloon adjustment module includes: The first adjustment unit is used to adjust the virtual balloon expansion morphology of the candidate lesion area by uniformly expanding the blood vessel midline if the lesion type of the candidate lesion area is a ring-shaped lesion. The second adjustment unit is used to adjust the virtual balloon dilation morphology of the candidate lesion area based on the anatomical morphology restoration method of healthy blood vessel geometry if the lesion type of the candidate lesion area is a reticular lesion type.

7. An information processing method for location prediction, characterized in that, include: Receive enhanced images of the pulmonary arteries of CTEPH patients; A target 3D model of the pulmonary artery vessels is created based on the enhanced image; Based on preset blood flow boundary conditions, the target three-dimensional model is subjected to fluid dynamics calculations to extract global blood flow parameters and local blood flow characteristic parameters of the pulmonary artery, so as to screen at least one candidate lesion area according to the global blood flow parameters and the local blood flow characteristic parameters. The virtual balloon dilation morphology of the candidate lesion areas is adjusted according to the lesion type of each candidate lesion area; Based on preset blood flow boundary conditions, a fluid dynamics calculation is performed on the new target three-dimensional model obtained after the virtual balloon dilation morphology adjustment to determine the final location of the balloon dilation surgery from the candidate lesion area. The step of performing fluid dynamics calculations on the new target 3D model obtained after adjusting the virtual balloon dilation morphology based on preset blood flow boundary conditions to determine the final location of the balloon dilation surgery from the candidate lesion area includes: The blood flow characteristic parameters of the current candidate lesion area obtained from the virtual postoperative operation are compared with the standard blood flow characteristic parameters of the standard three-dimensional model of the standard pulmonary artery to calculate the corresponding Euclidean distance; wherein, the standard three-dimensional model is a three-dimensional model of blood vessels constructed based on healthy anatomical features; If the Euclidean distance is less than a preset distance threshold, then the current candidate lesion is determined to be the final location for balloon dilation surgery.

8. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the information processing method for location prediction as described in claim 7.

9. A computer-readable storage medium, characterized in that, Used to store a computer program; wherein, when the computer program is executed by a processor, it implements the steps of the information processing method for location prediction as described in claim 7.

Images