Intracranial Aneurysm Rupture Risk Assessment Method, Device, Equipment and Storage Medium

Abstract

The present invention discloses a method, device, equipment and storage medium for intracranial aneurysm rupture risk assessment. First, based on the maximum intensity projection and centerline extraction processing of a two-dimensional angiographic image sequence, and combined with the analysis of the contrast agent concentration change curve, a time series image containing flow field information is generated; then, three-dimensional reconstruction, region of interest extraction and opening extension processing are performed on the three-dimensional image sequence to obtain detailed morphological parameters and a region of interest model after extension processing; then, the time series image with flow field information is overlapped and displayed with the region of interest model without extended opening, and by calculating the flow field vector sum in the observation sphere to determine the actual blood flow direction, the setting of boundary conditions is further optimized and fluid dynamics simulation is carried out to calculate the key hemodynamic parameters; finally, combining the morphological parameters, hemodynamic parameters and the patient's clinical information, the assessment result of the aneurysm rupture risk is obtained.

Description

Technical Field

[0001] The present invention relates to the technical field of medical image processing, and particularly to a method, device, equipment and storage medium for evaluating the rupture risk of intracranial aneurysms. Background Art

[0002] An intracranial aneurysm refers to an abnormal bulge in the wall of an intracranial artery. The overall prevalence of this disease in the general population is approximately 3% to 5%. Although most intracranial aneurysms do not rupture during their lifetime, once they rupture and cause subarachnoid hemorrhage, the consequences are extremely serious, and the fatality rate can be as high as about 40%. Therefore, it is particularly important to screen and evaluate the rupture risk of aneurysms in a timely and accurate manner, which not only helps to early detect potential risk factors, but also guides clinical to take effective preventive measures or treatment plans.

[0003] The risk of aneurysm rupture is not determined by a single factor, but is closely related to the patient's clinical characteristics, the specific morphological characteristics of the aneurysm, and the hemodynamic characteristics. In recent years, with the progress of medical imaging technology and the development of computational fluid dynamics (CFD), hemodynamic analysis has been widely used in the evaluation of aneurysm rupture risk. Specifically, researchers usually first reconstruct the vascular tree model based on intracranial medical images; next, select the region of interest (such as the aneurysm and its surrounding environment) from the reconstructed vascular tree model, and on this basis, determine the inlet and outlet positions of the blood flow, and apply the corresponding flow or velocity boundary conditions; subsequently, use the computational fluid dynamics method to simulate the selected region to obtain various physical parameters including the velocity field and pressure field. Based on these results, important hemodynamic indices such as wall shear stress (WSS) and oscillatory shear index (OSI) can be further calculated. By combining these hemodynamic parameters with morphological characteristics and the patient's clinical data, and using a machine learning model for comprehensive analysis, the rupture risk level of the aneurysm can be finally obtained.

[0004] However, although this method is highly scientific and practical in theory, there is still a significant problem in its actual application: it assumes the flow pattern of blood in the intracranial blood vessels. In fact, due to the natural complexity of the intracranial vascular system, it contains rich collateral blood supply mechanisms, such as the existence of the anterior communicating artery and the posterior communicating artery. This means that when performing hemodynamic simulations, simply treating certain arteries as fixed inlets or outlets may lead to incorrect judgments of the flow direction. For example, if the anterior communicating artery or the posterior communicating artery is inappropriately set as an outlet during the simulation, the simulated blood flow path may not match the actual situation, thus seriously affecting the accuracy of the aneurysm rupture risk assessment. Therefore, how to more accurately reflect the true blood flow pattern of the intracranial blood vessels has become one of the key challenges in improving the accuracy of aneurysm rupture risk assessment. Summary of the Invention

[0005] Based on this, the present invention provides a method, device, equipment, and storage medium for assessing the rupture risk of intracranial aneurysms in view of the above technical problems.

[0006] On the one hand, the present invention provides a method for assessing the rupture risk of intracranial aneurysms, the method comprising:

[0007] Obtain a two-dimensional angiographic image sequence and a three-dimensional image sequence of the blood vessels related to the intracranial aneurysm;

[0008] Based on the two-dimensional angiographic image sequence, perform maximum intensity projection and centerline extraction processing on it, and analyze in combination with the contrast agent concentration change curve to generate a time series image containing flow field information;

[0009] Based on the three-dimensional image sequence, perform three-dimensional reconstruction, region of interest extraction, and opening extension processing on it to obtain the morphological parameters of the blood vessels in the region of interest and the region of interest model after opening extension processing;

[0010] Overlay and display the time series image with flow field information and the region of interest model without extended opening, make the viewing angles consistent, and automatically generate observation spheres at all opening positions of the region of interest model without extended opening. By calculating the sum of the flow field vectors in each observation sphere, determine the actual blood flow direction at the opening positions of the region of interest model with extended opening, and finally complete the determination of boundary conditions and the construction of the flow field;

[0011] Based on the boundary conditions and the flow field, automatically mesh the region of interest model with extended opening, and perform fluid mechanics simulation and calculate hemodynamic parameters;

[0012] According to the morphological parameters and hemodynamic parameters, and in combination with the clinical information of the patient, obtain an assessment of the aneurysm rupture risk.

[0013] In one embodiment, the method for generating a time-series image containing flow field information based on a two-dimensional contrast image sequence, which involves performing maximum intensity projection and centerline extraction on the sequence and analyzing the contrast agent concentration change curve, includes the following steps:

[0014] Perform maximum intensity projection on all time frames of the two-dimensional contrast image sequence to obtain a projection image, and extract the two-dimensional vascular tree contour on the projection image;

[0015] Extract the centerline based on the two-dimensional vascular tree contour, and superimpose these centerlines on the original two-dimensional contrast image sequence to form a new image sequence with highlighted contours and centerlines;

[0016] In the newly generated image sequence, evenly set sampling points along the centerline, record the change curve of the contrast agent concentration over time at each sampling point, calculate the time to peak through fitting analysis of these curves, and determine the blood flow direction at each sampling point according to the trend of the contrast agent concentration change, construct the flow field along the centerline, and finally generate a time-series image containing flow field information.

[0017] In one embodiment, the method for performing three-dimensional reconstruction, region of interest extraction, and opening extension on a three-dimensional image sequence to obtain morphological parameters of the blood vessels in the region of interest and a region of interest model after opening extension includes the following steps:

[0018] Construct a first vascular tree model based on the three-dimensional image sequence, and extract the region of interest in the first vascular tree model to obtain a second vascular tree model;

[0019] Perform calculations on the second vascular tree model to obtain morphological parameters of the blood vessels in the region of interest;

[0020] Extend all openings on the second vascular tree model to obtain a region of interest model after opening extension.

[0021] In one embodiment, the step of performing calculations on the second vascular tree model to obtain morphological parameters of the blood vessels in the region of interest includes:

[0022] Select a point at an arbitrary position on the surface of the aneurysm cavity of the second vascular tree model, automatically separate the aneurysm cavity from the blood vessel, and automatically calculate the morphological parameters.

[0023] In one embodiment, the step of determining the actual blood flow direction at the opening position and finally completing the determination of boundary conditions and the construction of the flow field includes:

[0024] Calculate the vector sum of the flow fields in each observation sphere. The direction of the vector sum is the blood flow direction at the opening position. After obtaining the blood flow direction, set the flow rate at each inlet position;

[0025] Among them, the inlet flow rate is obtained by transcranial Doppler measurement. The inlet is defined as the opening where the blood flow direction is from the outside of the model to the inside of the model, and vice versa for the outlet. The outlet flow rate is jointly determined by the law of conservation of flow and Murray's law.

[0026] In one embodiment, the center of the observation sphere is the geometric center of the opening, and the radius is 2 - 5 times the equivalent radius of the opening area.

[0027] In one embodiment, automatic meshing is performed on the region - of - interest model of the extended opening, and fluid dynamics simulation is carried out to calculate hemodynamic parameters, including:

[0028] Perform automatic meshing on the region - of - interest model of the extended opening, carry out fluid dynamics simulation calculations, extract the calculation results of the last cardiac cycle as the final simulation results. The calculation results are the velocity distribution and pressure distribution at different times within the last cardiac cycle;

[0029] Using the velocity distribution and pressure distribution at different times, calculate the distribution of hemodynamic parameters and animations on the surface of the vascular tree model;

[0030] Combined with the aneurysm cavity of the blood vessels in the region of interest, automatically calculate the hemodynamic parameters of the aneurysm cavity.

[0031] On the other hand, the present invention provides an intracranial aneurysm rupture risk assessment device, which comprises:

[0032] An image sequence acquisition module, used to acquire two - dimensional angiographic image sequences and three - dimensional image sequences of blood vessels related to intracranial aneurysms;

[0033] A first image sequence processing module, used to perform maximum intensity projection and centerline extraction processing on the two - dimensional angiographic image sequence, and generate a time - series image containing flow field information by combining the analysis of the contrast agent concentration change curve;

[0034] A second image sequence processing module, used to perform three - dimensional reconstruction, region - of - interest extraction, and opening extension processing on the three - dimensional image sequence to obtain the morphological parameters of the blood vessels in the region of interest and the region - of - interest model after opening extension processing;

[0035] A boundary condition determination module, used to overlap and display the time - series image with flow field information and the region - of - interest model with unextended openings to make the viewing angles consistent, and automatically generate observation spheres at all opening positions of the region - of - interest model with unextended openings. By calculating the vector sum of the flow fields within each observation sphere, determine the actual blood flow direction at the opening positions of the region - of - interest model with extended openings, and finally complete the boundary condition determination and flow field construction;

[0036] A hemodynamic parameter calculation module, which is used to automatically mesh the region of interest model with an extended opening based on boundary conditions and the flow field, and perform hydrodynamic simulation and calculate hemodynamic parameters;

[0037] An evaluation module, which is used to obtain an evaluation of the aneurysm rupture risk according to the morphological parameters and hemodynamic parameters, combined with the clinical information of the patient.

[0038] On the other hand, the present invention provides a computer device, including a memory and a processor. When the processor executes the computer program, the following steps are implemented:

[0039] Obtain a two-dimensional angiography image sequence and a three-dimensional image sequence of the blood vessels related to the intracranial aneurysm;

[0040] Based on the two-dimensional angiography image sequence, perform maximum intensity projection and centerline extraction processing on it, and generate a time series image containing flow field information by combining the analysis of the contrast agent concentration change curve;

[0041] Based on the three-dimensional image sequence, perform three-dimensional reconstruction, region of interest extraction, and opening extension processing on it, and obtain the morphological parameters of the blood vessels in the region of interest and the region of interest model after the opening extension processing;

[0042] Overlay and display the time series image with flow field information and the region of interest model without an extended opening to make the viewing angles consistent, and automatically generate viewing spheres at all opening positions of the region of interest model without an extended opening. By calculating the sum of the flow field vectors in each viewing sphere, determine the actual blood flow direction at the opening position of the region of interest model with an extended opening, and finally complete the determination of boundary conditions and the construction of the flow field;

[0043] Based on the boundary conditions and the flow field, automatically mesh the region of interest model with an extended opening, and perform hydrodynamic simulation and calculate hemodynamic parameters;

[0044] Obtain an evaluation of the aneurysm rupture risk according to the morphological parameters and hemodynamic parameters, combined with the clinical information of the patient.

[0045] On yet another hand, the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0046] Obtain a two-dimensional angiography image sequence and a three-dimensional image sequence of the blood vessels related to the intracranial aneurysm;

[0047] Based on the two-dimensional angiography image sequence, perform maximum intensity projection and centerline extraction processing on it, and generate a time series image containing flow field information by combining the analysis of the contrast agent concentration change curve;

[0048] Based on a three-dimensional image sequence, perform three-dimensional reconstruction, region of interest extraction, and opening extension processing on it to obtain morphological parameters of the blood vessels in the region of interest and a region of interest model after opening extension processing;

[0049] Overlay and display the time series image with flow field information and the region of interest model without extended opening, make the viewing angles consistent, and automatically generate viewing spheres at all opening positions of the region of interest model without extended opening. By calculating the sum of flow field vectors within each viewing sphere, determine the actual blood flow direction at the opening position of the region of interest model with extended opening, and finally complete the determination of boundary conditions and the construction of the flow field;

[0050] Based on the boundary conditions and the flow field, perform automatic mesh generation on the region of interest model with extended opening, and perform fluid mechanics simulation and calculate hemodynamic parameters;

[0051] According to the morphological parameters and hemodynamic parameters, combined with the clinical information of the patient, obtain an assessment of the aneurysm rupture risk.

[0052] Compared with the prior art, the present invention performs maximum intensity projection and centerline extraction based on a two-dimensional angiographic image sequence, and combines the analysis of the contrast agent concentration change curve to generate a time series image containing flow field information, thereby accurately capturing the actual blood flow direction. Using a three-dimensional image sequence for three-dimensional reconstruction, region of interest extraction, and opening extension processing to ensure that the model can more realistically reflect the vascular structure. By overlaying and displaying the flow field information with the three-dimensional model and applying the viewing sphere technique to determine the actual blood flow direction, the boundary conditions are set. This method automatically determines the flow pattern of intracranial blood vessels, effectively overcomes the limitation of the traditional method that ignores the complex collateral blood supply mechanism, makes the results of hemodynamic simulation more reliable, and significantly improves the accuracy of aneurysm rupture risk assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a schematic flowchart of a method for assessing the risk of intracranial aneurysm rupture in an embodiment.

[0054] Figure 2 It is a schematic diagram of a two-dimensional vascular tree contour with sampling points in an embodiment.

[0055] Figure 3 It is a schematic diagram of a contrast agent concentration change curve in an embodiment.

[0056] Figure 4 It is a schematic diagram of a flow field and viewing spheres in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0057] To make the objectives, technical solutions and advantages of the present invention more clear and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0058] As Figure 1 shown, a method for assessing the rupture risk of intracranial aneurysms according to the present invention includes the following steps:

[0059] Step S100: Obtain a two-dimensional angiography image sequence and a three-dimensional image sequence of the blood vessels related to the intracranial aneurysm.

[0060] In step S100, the blood vessel images are read, including the two-dimensional angiography image sequence (time series) and the three-dimensional image sequence, which are respectively denoted as the first time series and the first spatial sequence.

[0061] Step S200: Based on the two-dimensional angiography image sequence, perform maximum intensity projection and centerline extraction processing on it, and combine the analysis of the contrast agent concentration change curve to generate a time series image containing flow field information.

[0062] This step S200 specifically includes the following sub-steps:

[0063] S210: Perform maximum intensity projection on all time frames of the two-dimensional angiography image sequence to obtain a projection image, and extract the two-dimensional blood vessel tree contour on the projection image. Specifically, perform maximum intensity projection on all time frames of the two-dimensional angiography image sequence, that is, the first time series, to obtain a projection image, and then extract the 2D blood vessel tree contour on the projection image.

[0064] S220: Extract the centerline based on the two-dimensional blood vessel tree contour, and superimpose these centerlines on the original two-dimensional angiography image sequence to form a new image sequence with highlighted contours and centerlines. Specifically, use the maximum inscribed circle algorithm to obtain the centerline of the blood vessel tree contour, and superimpose the contour and the centerline on the first time series to obtain a new image sequence with highlighted contours and highlighted centerlines, that is, the second time series.

[0065] S230: In the newly generated image sequence, uniformly set sampling points along the centerline, record the change curve of the contrast agent concentration over time at each sampling point, perform fitting analysis on these curves, calculate the time to peak, and judge the blood flow direction at each sampling point according to the trend of the contrast agent concentration change, construct the flow field along the centerline, and finally generate a time series image containing flow field information.

[0066] Specifically, in the new image sequence, that is, the second time series, uniformly set sampling points along the centerline, and the spacing between the sampling points is 1 mm, as Figure 2As shown. At the same time, record the change curve of the contrast agent concentration at each sampling point over time. Assuming there are n sampling points, there will be n curves. Usually, due to the continuous injection of the contrast agent, each curve will show an ascending segment, a plateau segment, and a descending segment, as Figure 3 shown. Fit the curve. The fitting function can be a simple piecewise linear function or other complex functions. Calculate the time corresponding to the intersection point of the ascending segment and the plateau segment on the fitted curve, that is, the time to peak (TTP).

[0067] Calculate the blood flow direction of each sampling point in turn , and the calculation method is as follows: If , then the blood flow direction is ; otherwise, . After traversing and calculating all sampling points, a flow field along the center line is obtained. The flow field is represented by assigning a unit vector to each sampling point. Display the flow field in the second time series to obtain a time series image with the flow field, that is, the third time series.

[0068] Step S300: Based on the three-dimensional image sequence, perform three-dimensional reconstruction, region of interest extraction, and opening extension processing to obtain the morphological parameters of the blood vessels in the region of interest and the region of interest model after opening extension processing.

[0069] This step S300 specifically includes the following sub-steps:

[0070] Step S310: Construct a first blood vessel tree model based on the three-dimensional image sequence, and extract the region of interest in the first blood vessel tree model to obtain a second blood vessel tree model. Specifically, based on the three-dimensional image sequence, that is, the first spatial sequence, perform three-dimensional reconstruction to obtain the first blood vessel tree model. The reconstruction algorithm can be a traditional threshold method, an active contour-based display algorithm, a level set-based implicit algorithm, or an algorithm based on an artificial intelligence model. Extract the region of interest in the first blood vessel tree model, denoted as the second blood vessel tree model, and the way to extract the region of interest can be a cropping sphere, a cropping cuboid, or a point selection-based cropping method.

[0071] Step S320: Calculate on the second vascular tree model to obtain the morphological parameters of the blood vessels in the region of interest. Specifically, select a point at any position on the surface of the aneurysm cavity of the second vascular tree model, automatically separate the aneurysm cavity from the blood vessels, and automatically calculate the morphological parameters. The morphological parameters include: aneurysm inflow angle, aneurysm inclination angle, vessel angle, maximum height of the aneurysm, middle diameter of the aneurysm, aneurysm neck diameter, parent artery diameter, vertical height of the aneurysm, aneurysm surface area, aneurysm volume, size ratio, aspect ratio, bottle-neck ratio, ellipticity index, non-sphericity index, aneurysm morphological irregularity index, etc.

[0072] Step S330: Extend all the openings on the second vascular tree model to obtain the model of the region of interest after the opening extension process. In this step, after extracting the region of interest in step S320, all the openings on the second vascular tree model are automatically extended. The extension length of the opening is 3 times the diameter of the blood vessel at the opening position, and the model of the region of interest with the extended openings is obtained, denoted as the third vascular tree model.

[0073] Step S400: Overlay and display the time-series image with flow field information on the model of the region of interest without extended openings, making the viewing angles consistent, and automatically generate observation spheres at all the opening positions of the model of the region of interest without extended openings. By calculating the vector sum of the flow fields within each observation sphere, determine the actual blood flow direction at the opening positions of the model of the region of interest with extended openings, and finally complete the determination of the boundary conditions and the construction of the flow field.

[0074] In step S400, rotate the camera of the model of the region of interest with extended openings, i.e., the third vascular tree model, so that the viewing angle is consistent with the angiography angle of the third time series, and then overlay and display the third vascular tree model with the third time series. Automatically generate observation spheres at all the opening positions of the third vascular tree model. The center of the observation sphere is the geometric center of the opening, and the radius is 2 - 5 times the equivalent radius of the opening area, as Figure 4 shown. Calculate the vector sum of the flow fields within each observation sphere. The direction of the vector sum is the blood flow direction at the opening position. After obtaining the blood flow direction, set the flow rate at each inlet position. The inlet flow rate can be obtained by transcranial Doppler measurement. The inlet is defined as the opening where the blood flow direction is from the outside of the model to the inside of the model, and vice versa for the outlet. The outlet flow rate is determined jointly by the law of conservation of flow rate and Murray's law.

[0075] Step S500: Based on the boundary conditions and the flow field, perform automatic mesh generation on the model of the region of interest with extended openings, and conduct fluid mechanics simulation and calculate the hemodynamic parameters.

[0076] This step S500 specifically includes the following sub-steps:

[0077] In step S510, automatic mesh generation is performed on the region of interest model with the extended opening, and computational fluid dynamics simulation is carried out. The calculation results of the last cardiac cycle are extracted as the final simulation results, and the calculation results are the velocity distribution and pressure distribution at different times within the last cardiac cycle. Specifically, automatic mesh generation is performed on the third vascular tree model, and then computational fluid dynamics simulation is carried out using the finite volume method or the finite element method. After calculations over multiple cardiac cycles, the simulation results tend to be stable. The calculation results of the last cardiac cycle are extracted as the final simulation results, and the calculation results are the velocity distribution and pressure distribution at different times within the last cardiac cycle.

[0078] In step S520, using the velocity distribution and pressure distribution at different times, the hemodynamic parameter distribution and animations on the surface of the vascular tree model are calculated, including: pressure distribution animation, WSS distribution animation, and OSI distribution animation. In addition, the streamline distribution, pathline animation, particle animation, and velocity isosurface animation within the lumen are calculated. The animation refers to the change effect of the parameter distribution over time within one cardiac cycle. For the particle animation, the density of the particles can be adjusted. For the pathline animation, the density and length of the pathlines can be adjusted. For the velocity isosurface animation, the display range of the velocity isosurface can be adjusted.

[0079] In step S530, in combination with the aneurysm cavity of the blood vessel in the region of interest, the hemodynamic parameters of the aneurysm cavity are automatically calculated. Using the aneurysm cavity obtained in step S320, the hemodynamic parameters of the aneurysm cavity are automatically calculated, including: mean aneurysm WSS, normalized mean aneurysm WSS, mean WSS of the parent artery, maximum aneurysm WSS, proportion of the area of the high WSS region, aneurysm OSI, maximum aneurysm OSI, relative aneurysm retention time, aneurysm WSSG, aneurysm gradient oscillation factor, proportion of the area of the low WSS region, and minimum aneurysm WSS.

[0080] In step S600, based on the morphological parameters and hemodynamic parameters, combined with the patient's clinical information, an assessment of the aneurysm rupture risk is obtained. In this step, the aneurysm morphological parameters and aneurysm hemodynamic parameters calculated in the previous steps are combined with the patient's clinical information, and a machine learning model is used to predict the aneurysm rupture risk. In particular, a machine learning model can be used to predict the rupture resemblance score (RRS) of the aneurysm as a quantitative representation form of the aneurysm rupture risk. Further, calculate the prediction using only morphological parameters to obtain the morphological RRS; calculate the prediction using only hemodynamic parameters to obtain the hemodynamic RRS; calculate the prediction by combining morphological parameters and hemodynamic parameters to obtain the composite RRS.

[0081] It should be understood that although Figure 1 the steps in the flowchart in Figure 1 are shown in sequence according to the indication of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, there is no strict order limit for the execution of these steps, and these steps can be executed in other orders. Moreover,

[0082] In one embodiment, the present invention provides an intracranial aneurysm rupture risk assessment device, including: an image sequence acquisition module, a first image sequence processing module, a second image sequence processing module, a boundary condition determination module, a hemodynamic parameter calculation module, and an evaluation module, where:

[0083] The image sequence acquisition module is used to acquire a two-dimensional angiographic image sequence and a three-dimensional image sequence of blood vessels related to the intracranial aneurysm.

[0084] The first image sequence processing module is used to perform maximum intensity projection and centerline extraction processing on the two-dimensional angiographic image sequence, and generate a time series image containing flow field information by combining the analysis of the contrast agent concentration change curve.

[0085] The second image sequence processing module is used to perform three-dimensional reconstruction, region of interest extraction, and opening extension processing on the three-dimensional image sequence to obtain morphological parameters of the blood vessels in the region of interest and a region of interest model after opening extension processing.

[0086] The boundary condition determination module is used to overlap and display the time series image with flow field information and the region of interest model without extended opening to make the viewing angles consistent, automatically generate observation spheres at all opening positions of the region of interest model without extended opening, determine the actual blood flow direction at the opening position of the region of interest model with extended opening by calculating the flow field vector sum in each observation sphere, and finally complete the boundary condition determination and flow field construction.

[0087] The hemodynamic parameter calculation module is used to automatically mesh the region of interest model with extended opening based on the boundary conditions and flow field, perform fluid mechanics simulation, and calculate hemodynamic parameters.

[0088] An evaluation module, configured to obtain an evaluation of the aneurysm rupture risk according to morphological parameters, hemodynamic parameters, and in combination with the clinical information of the patient.

[0089] For the specific limitations of the intracranial aneurysm rupture risk assessment device, reference can be made to the limitations of the intracranial aneurysm rupture risk assessment method in the above text, which will not be elaborated here. Each module in the above intracranial aneurysm rupture risk assessment device can be implemented in whole or in part by software, hardware, and their combinations. Each of the above modules can be embedded in or independent of the processor in the computer device in the form of hardware, or stored in the memory of the computer device in the form of software, so as to facilitate the processor to call and execute the operations corresponding to each of the above modules.

[0090] In one embodiment, a computer device is provided. The computer device can be a terminal, which includes a processor, a memory, a network interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements an intracranial aneurysm rupture risk assessment method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the shell of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0091] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0092] Step S100, obtaining a two-dimensional angiographic image sequence and a three-dimensional image sequence of the blood vessels related to the intracranial aneurysm.

[0093] Step S200, based on the two-dimensional angiographic image sequence, performing maximum intensity projection and centerline extraction processing on it, and analyzing in combination with the contrast agent concentration change curve to generate a time series image containing flow field information.

[0094] Step S300, based on the three-dimensional image sequence, performing three-dimensional reconstruction, region of interest extraction, and opening extension processing on it to obtain morphological parameters of the blood vessels in the region of interest and a region of interest model after opening extension processing.

[0095] Step S400: Overlay and display the time-series image with flow field information and the region-of-interest model without extended openings, making the viewing angles consistent, and automatically generate viewing spheres at all the opening positions of the region-of-interest model without extended openings. By calculating the sum of flow field vectors within each viewing sphere, determine the actual blood flow direction at the opening positions of the region-of-interest model with extended openings, and finally complete the determination of boundary conditions and the construction of the flow field.

[0096] Step S500: Based on the boundary conditions and the flow field, automatically mesh the region-of-interest model with extended openings, and perform fluid mechanics simulation and calculate hemodynamic parameters.

[0097] Step S600: According to the morphological parameters and hemodynamic parameters, combined with the patient's clinical information, obtain an assessment of the aneurysm rupture risk.

[0098] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0099] Step S100: Obtain the two-dimensional angiographic image sequence and three-dimensional image sequence of the blood vessels related to the intracranial aneurysm.

[0100] Step S200: Based on the two-dimensional angiographic image sequence, perform maximum intensity projection and centerline extraction processing on it, and combined with the analysis of the contrast agent concentration change curve, generate a time-series image containing flow field information.

[0101] Step S300: Based on the three-dimensional image sequence, perform three-dimensional reconstruction, region-of-interest extraction, and opening extension processing on it, to obtain the morphological parameters of the blood vessels in the region of interest and the region-of-interest model after opening extension processing.

[0102] Step S400: Overlay and display the time-series image with flow field information and the region-of-interest model without extended openings, making the viewing angles consistent, and automatically generate viewing spheres at all the opening positions of the region-of-interest model without extended openings. By calculating the sum of flow field vectors within each viewing sphere, determine the actual blood flow direction at the opening positions of the region-of-interest model with extended openings, and finally complete the determination of boundary conditions and the construction of the flow field.

[0103] Step S500: Based on the boundary conditions and the flow field, automatically mesh the region-of-interest model with extended openings, and perform fluid mechanics simulation and calculate hemodynamic parameters.

[0104] Step S600: According to the morphological parameters and hemodynamic parameters, combined with the patient's clinical information, obtain an assessment of the aneurysm rupture risk.

[0105] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided by the present invention can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0106] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0107] The above-described embodiments merely represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the invention patent should be subject to the appended claims.

Claims

1. A method for assessing the rupture risk of intracranial aneurysms, characterized in that, The method includes: Obtaining a two-dimensional angiographic image sequence and a three-dimensional image sequence of the blood vessels related to the intracranial aneurysm; Based on the two-dimensional angiographic image sequence, performing maximum intensity projection and centerline extraction processing on it, and combining the analysis of the contrast agent concentration change curve to generate a time-series image containing flow field information; Based on the three-dimensional image sequence, performing three-dimensional reconstruction, region of interest extraction, and opening extension processing on it to obtain the morphological parameters of the blood vessels in the region of interest and the region of interest model after opening extension processing; Overlapping and displaying the time-series image with flow field information and the region of interest model without opening extension, making the viewing angles consistent, automatically generating viewing spheres at all opening positions of the region of interest model without opening extension, and determining the actual blood flow direction at the opening position of the region of interest model with opening extension by calculating the sum of the flow field vectors in each viewing sphere, and finally completing the determination of boundary conditions and the construction of the flow field; Based on the boundary conditions and the flow field, automatically meshing the region of interest model with opening extension, and performing fluid mechanics simulation and calculating hemodynamic parameters; According to the morphological parameters and hemodynamic parameters, and combining the clinical information of the patient, obtaining an assessment of the aneurysm rupture risk.

2. The intracranial aneurysm rupture risk assessment method according to claim 1, wherein The step of based on the two-dimensional angiographic image sequence, performing maximum intensity projection and centerline extraction processing on it, and combining the analysis of the contrast agent concentration change curve to generate a time-series image containing flow field information includes: Performing maximum intensity projection on all time frames of the two-dimensional angiographic image sequence to obtain a projection image, and extracting the two-dimensional vascular tree contour on the projection image; Extracting the centerline based on the two-dimensional vascular tree contour and superimposing these centerlines on the original two-dimensional angiographic image sequence to form a new image sequence with highlighted contours and centerlines; In the newly generated image sequence, uniformly setting sampling points along the centerline, recording the change curve of the contrast agent concentration over time at each sampling point, calculating the time to peak by fitting analysis of these curves, and judging the blood flow direction at each sampling point according to the trend of the contrast agent concentration change, constructing the flow field along the centerline, and finally generating a time-series image containing flow field information.

3. The intracranial aneurysm rupture risk assessment method according to claim 1, wherein The step of based on the three-dimensional image sequence, performing three-dimensional reconstruction, region of interest extraction, and opening extension processing on it to obtain the morphological parameters of the blood vessels in the region of interest and the region of interest model after opening extension processing includes: Constructing a first vascular tree model based on the three-dimensional image sequence, and extracting the region of interest in the first vascular tree model to obtain a second vascular tree model; Performing calculations on the second vascular tree model to obtain the morphological parameters of the blood vessels in the region of interest; Extending all the openings on the second vascular tree model to obtain the region of interest model after opening extension processing.

4. The intracranial aneurysm rupture risk assessment method according to claim 3, wherein The step of performing calculations on the second vascular tree model to obtain the morphological parameters of the blood vessels in the region of interest includes: Selecting a point at an arbitrary position on the surface of the aneurysm cavity of the second vascular tree model, automatically separating the aneurysm cavity from the blood vessel, and automatically calculating the morphological parameters.

5. The intracranial aneurysm rupture risk assessment method according to claim 1, wherein Determining the actual blood flow direction at the opening position of the region of interest model of the extended opening, and finally completing the determination of boundary conditions and the construction of the flow field includes: Calculating the vector sum of the flow fields in each observation sphere. The direction of the vector sum is the blood flow direction at the opening position. After obtaining the blood flow direction, set the flow rate at each inlet position; Among them, the inlet flow rate is obtained by transcranial Doppler measurement. The inlet is defined as the opening where the blood flow direction is from outside the model to inside the model, and vice versa is the outlet. The outlet flow rate is jointly determined by the law of conservation of flow rate and Murray's law.

6. The intracranial aneurysm rupture risk assessment method according to claim 1, wherein, The center of the observation sphere is the geometric center of the opening, and the radius is 2 - 5 times the equivalent radius of the opening area.

7. The intracranial aneurysm rupture risk assessment method according to claim 1, wherein, Automatically meshing the region of interest model of the extended opening, performing fluid mechanics simulation, and calculating hemodynamic parameters includes: Automatically meshing the region of interest model of the extended opening, performing fluid mechanics simulation calculations, and extracting the calculation results of the last cardiac cycle as the final simulation results. The calculation results are the velocity distribution and pressure distribution at different times within the last cardiac cycle; Using the velocity distribution and pressure distribution at different times, calculating the hemodynamic parameter distribution and animation on the surface of the vascular tree model; Combining the aneurysm cavity of the blood vessel in the region of interest, automatically calculating the hemodynamic parameters of the aneurysm cavity.

8. An intracranial aneurysm rupture risk assessment device, characterized in that, The device includes: An image sequence acquisition module for acquiring two-dimensional angiographic image sequences and three-dimensional image sequences of blood vessels related to intracranial aneurysms; A first image sequence processing module for performing maximum intensity projection and centerline extraction processing on the two-dimensional angiographic image sequence, and generating a time series image containing flow field information by combining the analysis of the contrast agent concentration change curve; A second image sequence processing module for performing three-dimensional reconstruction, region of interest extraction, and opening extension processing on the three-dimensional image sequence to obtain the morphological parameters of the blood vessels in the region of interest and the region of interest model after opening extension processing; A boundary condition determination module for overlapping and displaying the time series image with flow field information and the region of interest model with the opening not extended to make the viewing angles consistent, and automatically generating observation spheres at all opening positions of the region of interest model with the opening not extended. By calculating the vector sum of the flow fields in each observation sphere, determining the actual blood flow direction at the opening position of the region of interest model of the extended opening, and finally completing the determination of boundary conditions and the construction of the flow field; A hemodynamic parameter calculation module for automatically meshing the region of interest model of the extended opening based on the boundary conditions and the flow field, performing fluid mechanics simulation, and calculating hemodynamic parameters; An evaluation module for obtaining an assessment of the aneurysm rupture risk based on the morphological parameters and hemodynamic parameters, in combination with the patient's clinical information.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method described in any one of claims 1 to 7.

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

Images