CN118172348A - Method and device for predicting shearing stress of wall surface of blood vessel, electronic equipment and storage medium - Google Patents
Method and device for predicting shearing stress of wall surface of blood vessel, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN118172348A CN118172348A CN202410392897.0A CN202410392897A CN118172348A CN 118172348 A CN118172348 A CN 118172348A CN 202410392897 A CN202410392897 A CN 202410392897A CN 118172348 A CN118172348 A CN 118172348A
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- vessel
- contour
- shear stress
- type
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 210000004204 blood vessel Anatomy 0.000 title claims abstract description 402
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000010008 shearing Methods 0.000 title abstract description 9
- 230000011218 segmentation Effects 0.000 claims abstract description 66
- 238000012545 processing Methods 0.000 claims abstract description 42
- 238000002586 coronary angiography Methods 0.000 claims abstract description 37
- 238000012549 training Methods 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 16
- 238000004088 simulation Methods 0.000 claims description 13
- 239000012530 fluid Substances 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 10
- 238000010586 diagram Methods 0.000 description 12
- 238000004891 communication Methods 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 7
- 239000002699 waste material Substances 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000003709 image segmentation Methods 0.000 description 5
- 230000000877 morphologic effect Effects 0.000 description 3
- 230000002107 myocardial effect Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000002591 computed tomography Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000002526 effect on cardiovascular system Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000002792 vascular Effects 0.000 description 2
- 208000037273 Pathologic Processes Diseases 0.000 description 1
- 238000002583 angiography Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 230000017531 blood circulation Effects 0.000 description 1
- 210000000748 cardiovascular system Anatomy 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000002872 contrast media Substances 0.000 description 1
- 208000029078 coronary artery disease Diseases 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000013421 nuclear magnetic resonance imaging Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 230000009054 pathological process Effects 0.000 description 1
- 230000035790 physiological processes and functions Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Landscapes
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a method and a device for predicting shearing stress of a vessel wall surface, electronic equipment and a storage medium. Comprising the following steps: acquiring a coronary angiography image, and performing segmentation processing on the coronary angiography image to obtain blood vessel segmentation data; extracting a blood vessel center line of the blood vessel segmentation data, and constructing a blood vessel three-dimensional contour based on the blood vessel center line and the blood vessel segmentation data; intercepting a blood vessel contour to be predicted on a three-dimensional blood vessel contour, and selecting a plurality of contour points on the blood vessel contour; and matching a pre-trained vessel wall shear stress prediction model according to the vessel type of the vessel profile, and performing prediction processing on a plurality of profile points of the vessel profile based on the matched vessel wall shear stress prediction model to obtain vessel wall shear stress prediction results of the profile points, wherein the vessel type comprises a bifurcation type and a non-bifurcation type. According to the scheme, the shearing stress of the wall surface of the blood vessel is predicted through the model, so that the automatic prediction efficiency is improved, and the hardware requirements and the professional requirements of operators are reduced.
Description
Technical Field
The present invention relates to the field of cardiovascular prediction technologies, and in particular, to a method and apparatus for predicting a shear stress on a wall surface of a blood vessel, an electronic device, and a storage medium.
Background
The wall shear stress of the blood vessel has important application in the cardiovascular field, the cardiovascular system comprises heart and blood vessel, the wall shear stress is the shear stress acting on the surface of the blood when the blood flows through the inner wall of the heart and the blood vessel, and the research of the wall shear stress of the heart and the blood vessel has important significance for understanding the physiological and pathological processes of the heart.
And carrying out three-dimensional computational fluid dynamics simulation by computational fluid software of professional software, and obtaining a speed field by simulation of simulation software, and further obtaining wall shear stress by post-processing. The simulation setting of the simulation method is complex, the requirement on the professional level of operators is high, the three-dimensional simulation software is operated with huge calculation resource consumption, the configuration requirement on hardware equipment for executing the three-dimensional simulation software is quite high, and the problems of high resource waste and high cost are caused.
Disclosure of Invention
The invention provides a method, a device, electronic equipment and a storage medium for predicting shearing stress of a vessel wall surface, which are used for solving the problems of large resource waste and high cost in the prior art and the problem of high professional level requirement on operators.
According to an aspect of the present invention, there is provided a method for predicting shear stress of a wall surface of a blood vessel, comprising:
Acquiring a coronary angiography image, and performing segmentation processing on the coronary angiography image to obtain blood vessel segmentation data;
extracting a blood vessel center line of the blood vessel segmentation data, and constructing a blood vessel three-dimensional contour based on the blood vessel center line and the blood vessel segmentation data;
Intercepting a blood vessel contour to be predicted on a three-dimensional blood vessel contour, and selecting a plurality of contour points on the blood vessel contour;
And matching a pre-trained vessel wall shear stress prediction model according to the vessel type of the vessel profile, and performing prediction processing on a plurality of profile points of the vessel profile based on the matched vessel wall shear stress prediction model to obtain vessel wall shear stress prediction results of the profile points, wherein the vessel type comprises a bifurcation type and a non-bifurcation type.
Optionally, matching the pre-trained vessel wall shear stress prediction model according to the vessel type of the vessel profile includes:
determining the type of the region where the central point corresponding to the blood vessel contour is located;
Determining the blood vessel type of the blood vessel contour based on the region type, and if the blood vessel type is a bifurcation type, matching a pre-trained bifurcation blood vessel wall surface shear stress prediction model; if the vessel type is a non-bifurcation type, matching a pre-trained non-bifurcation vessel wall surface shear stress prediction model.
Optionally, predicting a plurality of contour points of the vessel contour based on the matched vessel wall shear stress prediction model to obtain vessel wall shear stress prediction results of the plurality of contour points, including:
Acquiring coordinate information of a plurality of contour points and boundary conditions of blood vessel contours, wherein the boundary conditions comprise pressure data, flow data and speed data;
and inputting the coordinate information of the contour points and the boundary conditions of the blood vessel contours into a matched blood vessel wall surface shear stress prediction model to obtain blood vessel wall surface shear stress prediction results of the contour points.
Optionally, acquiring boundary conditions of the vessel profile includes:
Taking pressure data, flow data and speed data of a blood vessel inlet as initial boundary conditions of a blood vessel contour;
If the vessel type of the vessel profile is a bifurcation type, determining the geometric parameters of each branch vessel corresponding to the vessel profile, and carrying out distribution processing on flow data and speed data of a primary main vessel of the branch vessel based on one or more of the geometric parameters through the Morey law to obtain the flow data and speed data of each branch vessel, thereby obtaining the boundary condition of the vessel profile, wherein the geometric parameters comprise vessel volume data, vessel length data and vessel outlet area data.
Optionally, the method further comprises:
If the blood vessel type corresponding to the blood vessel profile is a bifurcation type, carrying out average processing on the predicted result of the blood vessel profile, and taking the obtained average value as the predicted result of the blood vessel profile.
Optionally, the method further comprises:
And if the number of the plurality of contour points of the blood vessel contour is larger than a preset number threshold, encoding parameters of the plurality of contour points of the blood vessel contour by an encoder.
Optionally, the training process of the pre-trained vessel wall shear stress prediction model includes:
simulating a blood vessel model sample through three-dimensional computational fluid dynamics simulation based on preset boundary conditions, and determining a label value corresponding to the blood vessel model sample, wherein the preset boundary conditions comprise bifurcation type boundary conditions and non-bifurcation type boundary conditions;
Taking a label value corresponding to the blood vessel model sample as a label value of a pre-trained blood vessel wall shear stress prediction model;
training the prediction model based on the label value of the prediction model, a blood vessel model sample and boundary conditions of bifurcation types to obtain a blood vessel wall shear stress prediction model corresponding to bifurcation types; and, a step of, in the first embodiment,
Training the prediction model based on the label value of the prediction model, the blood vessel model sample and the boundary condition of the non-bifurcation type to obtain a blood vessel wall shear stress prediction model corresponding to the non-bifurcation type.
According to another aspect of the present invention, there is provided a vessel wall shear stress prediction apparatus comprising:
the blood vessel segmentation data determining module is used for acquiring a coronary angiography image, and carrying out segmentation processing on the coronary angiography image to obtain blood vessel segmentation data;
the three-dimensional contour determining module is used for extracting a blood vessel center line of the blood vessel segmentation data and constructing a three-dimensional contour of the blood vessel based on the blood vessel center line and the blood vessel segmentation data;
The contour point determining module is used for intercepting a to-be-predicted blood vessel contour on the three-dimensional blood vessel contour and selecting a plurality of contour points on the blood vessel contour;
the prediction result determining module is used for matching a pre-trained blood vessel wall shear stress prediction model according to the blood vessel type of the blood vessel profile, and predicting a plurality of profile points of the blood vessel profile based on the matched blood vessel wall shear stress prediction model to obtain blood vessel wall shear stress prediction results of the profile points, wherein the blood vessel type comprises a bifurcation type and a non-bifurcation type.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the vessel wall shear stress prediction method of any one of the embodiments of the present invention.
According to another aspect of the present invention, there is provided a computer readable storage medium storing computer instructions for causing a processor to execute a method for predicting a vessel wall shear stress according to any embodiment of the present invention.
According to the technical scheme, the coronary angiography image is acquired, and segmentation processing is carried out on the coronary angiography image to obtain blood vessel segmentation data; extracting a blood vessel center line of the blood vessel segmentation data, and constructing a blood vessel three-dimensional contour based on the blood vessel center line and the blood vessel segmentation data; intercepting a blood vessel contour to be predicted on a three-dimensional blood vessel contour, and selecting a plurality of contour points on the blood vessel contour; and matching a pre-trained vessel wall shear stress prediction model according to the vessel type of the vessel profile, and performing prediction processing on a plurality of profile points of the vessel profile based on the matched vessel wall shear stress prediction model to obtain vessel wall shear stress prediction results of the profile points, wherein the vessel type comprises a bifurcation type and a non-bifurcation type. According to the method, the device and the system, the blood vessel wall shear stress of different types of blood vessels is predicted through the prediction model, so that the blood vessel wall shear stress prediction result is obtained, the automatic prediction efficiency of the blood vessel wall shear stress is improved, the hardware requirements and the professional requirements of operators are reduced, and the resource waste and the prediction cost are reduced.
It should be understood that the description in this section is not intended to identify key or critical features of the embodiments of the invention or to delineate the scope of the invention. Other features of the present invention will become apparent from the description that follows.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for predicting shear stress of a vessel wall surface according to an embodiment of the present invention;
FIG. 2 is a schematic representation of a three-dimensional vascular model of bifurcation type and non-bifurcation type as applicable to embodiments of the present invention;
FIG. 3 is a schematic diagram of a non-bifurcation area vessel being converted into a two-dimensional mesh, as applicable to embodiments of the present invention;
FIG. 4 is a schematic diagram of a bifurcation area vessel conversion to a two-dimensional mesh, as applicable to embodiments of the present invention;
fig. 5 is a flowchart of a method for predicting shear stress of a wall surface of a blood vessel according to a second embodiment of the present invention;
FIG. 6 is a schematic diagram of a neural network to which embodiments of the present invention are applicable;
fig. 7 is a schematic structural diagram of a device for predicting shear stress on a wall surface of a blood vessel according to a third embodiment of the present invention;
fig. 8 is a schematic structural diagram of an electronic device for implementing a method for predicting a shear stress of a wall surface of a blood vessel according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and the claims of the present invention and the above figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments of the invention described herein may be implemented in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
Fig. 1 is a flowchart of a method for predicting a shear stress of a wall surface of a blood vessel according to an embodiment of the present invention, where the method may be performed by a device for predicting a shear stress of a wall surface of a blood vessel, the device for predicting a shear stress of a wall surface of a blood vessel may be implemented in hardware and/or software, and the device for predicting a shear stress of a wall surface of a blood vessel may be configured in a computer. As shown in fig. 1, the method includes:
s110, acquiring a coronary angiography image, and performing segmentation processing on the coronary angiography image to obtain blood vessel segmentation data.
The coronary angiography image is a gold standard for diagnosing coronary heart disease, and is characterized in that contrast agent is injected into blood vessels, so that the blood vessels are developed under the irradiation of X rays, the developed process is shot, the coronary angiography image can be acquired by using medical image acquisition equipment, and the coronary angiography image can be acquired by using computer tomography and nuclear magnetic resonance imaging equipment by way of example. The image segmentation of the coronary angiography image can be specifically understood as the process of segmenting the coronary angiography image by an image segmentation method, subdividing the image into different areas or objects and extracting blood vessel image information, wherein the image segmentation algorithm comprises but is not limited to a 3D-Unet segmentation network, a threshold segmentation algorithm, an edge segmentation algorithm, a preset image segmentation model and the like.
Specifically, a patient can be scanned in real time through a computed tomography device to obtain a coronary angiography image, or a matched coronary angiography image can be obtained from an image library according to patient information, and then image segmentation processing is carried out on the obtained coronary angiography image to obtain blood vessel segmentation data corresponding to the coronary angiography image, wherein the blood vessel segmentation data comprise blood vessel regions in a coronary angiography image.
S120, extracting a blood vessel center line of the blood vessel segmentation data, and constructing a blood vessel three-dimensional contour based on the blood vessel center line and the blood vessel segmentation data.
The central line of the blood vessel can be understood as the central line of the blood vessel, and the central line of the blood vessel is positioned by analyzing the intensity information and the morphological information in the medical image, wherein the intensity information can be represented by an image gray value, and the morphological information can be represented by a pixel position and a shape on the image. The blood vessel center line can be extracted from the image data containing the blood vessel through a blood vessel center line tracking algorithm, wherein the blood vessel center line tracking algorithm comprises blood vessel refinement, curve fitting, bifurcation node judgment and the like, and the blood vessel center line can be extracted through a pre-trained center line extraction neural network model.
Specifically, the vessel centerline extraction method is used for extracting the vessel centerline of the vessel segmentation data, the two-dimensional contour of the vessel can be obtained according to the vessel segmentation data, the vessel three-dimensional contour is constructed through the vessel centerline and the vessel segmentation data, and the three-dimensional contour of the vessel is obtained by projecting the contour corresponding to at least two vessel regions into the corresponding three-dimensional coordinate system based on at least two vessel regions corresponding to the same vessel, synthesizing the contour in each three-dimensional coordinate system, generating the three-dimensional vessel model corresponding to the vessel region, and exemplarily. The three-dimensional contour of the blood vessel corresponding to the blood vessel segmentation data is output by inputting the blood vessel segmentation data as input parameters into the trained neural network model for constructing the three-dimensional contour.
In this embodiment, the three-dimensional contour of the blood vessel is constructed based on the blood vessel center line and the blood vessel segmentation data, so that the interference of the coronary angiography image excluding the information outside the blood vessel region can be reduced, the three-dimensional contour of the blood vessel is constructed based on the blood vessel center line to better conform to the morphological information of the blood vessel in the angiography image, the accuracy of constructing the three-dimensional contour of the blood vessel is improved, and the accuracy of predicting the shear stress of the wall surface of the blood vessel in the follow-up process is further improved.
S130, intercepting a blood vessel contour to be predicted on the three-dimensional blood vessel contour, and selecting a plurality of contour points on the blood vessel contour.
Specifically, central points on the central line are cut along the central line corresponding to the three-dimensional contour of the blood vessel according to the preset interval, the cross section of the blood vessel is cut at each central point, the contour of the blood vessel to be predicted corresponding to each central point is obtained, the contour points with preset numbers are randomly selected from the contour points of the blood vessel to be predicted corresponding to each central point, and preferably, the preset number can be set to be 16 or more. It should be noted that, the interval between the center points corresponding to the two continuous blood vessel contours is not smaller than the preset interval distance, and preferably, the preset interval distance is set to be 0.5mm; the number of the blood vessel contours intercepted by each branch blood vessel is larger than a preset contour number threshold, and preferably, the preset contour number threshold is set to be 5, and it is noted that the number of contour points selected on each blood vessel contour is consistent.
In a specific embodiment, extracting the outer wall surface of the three-dimensional contour of the blood vessel, intercepting the contour of the blood vessel along the central line corresponding to the three-dimensional contour of the blood vessel according to a preset interval distance, wherein the distance between the central points corresponding to the two continuous contours is smaller than 0.5mm, the number of the intercepted contour of the blood vessel on each branch blood vessel is not less than 5, and selecting contour points of not less than 16 points on each contour of the blood vessel, so as to obtain the coordinate information corresponding to each contour point.
And S140, matching a pre-trained vessel wall shear stress prediction model according to the vessel type of the vessel profile, and performing prediction processing on a plurality of profile points of the vessel profile based on the matched vessel wall shear stress prediction model to obtain vessel wall shear stress prediction results of the profile points, wherein the vessel type comprises a bifurcation type and a non-bifurcation type.
Specifically, the blood vessel types include bifurcation type and non-bifurcation type, as shown in the three-dimensional blood vessel model schematic diagram of bifurcation type and non-bifurcation type in fig. 2, the number of center points in the neighborhood of each center point on the center line can be used for judging whether the current center point is in a bifurcation area or a non-bifurcation area, and then the blood vessel type of each blood vessel contour is determined according to the area type where the center point is located. For example, if the number of center points in the neighborhood of the current center point is less than or equal to 2, the current center point is indicated to be in a non-bifurcation area, if the number of center points in the neighborhood of the current center point is greater than 2, the current center point is indicated to be in a bifurcation area, in order to be able to more accurately predict the accuracy of the wall shear stress prediction result corresponding to a bifurcation type blood vessel, a preset number of center points are selected forward and backward along the center line with the bifurcation point as a starting point, and then a bifurcation area is formed together with the current bifurcation point, and the preset number may be set to 2, accordingly, the blood vessel type of the blood vessel profile corresponding to the center point in the bifurcation area is bifurcation type, and the blood vessel type of the blood vessel profile corresponding to the center point in the non-bifurcation area is non-bifurcation type. It should be noted that, the determination of the bifurcation area and the non-bifurcation area may be performed by marking a center point on the vessel centerline when extracting the vessel centerline, and marking the type of the area to which the corresponding center point belongs, or may be performed by marking in the process of cutting the vessel contour along the centerline, so as to determine the vessel type of each vessel contour. And (3) matching a pre-trained vessel wall shear stress prediction model according to the vessel type of the vessel profile, and performing prediction processing on a plurality of profile points of the vessel profile through the matched vessel wall shear stress prediction model to obtain vessel wall shear stress prediction results corresponding to the profile points.
Optionally, matching the pre-trained vessel wall shear stress prediction model according to the vessel type of the vessel profile includes: determining the type of the region where the central point corresponding to the blood vessel contour is located; determining the blood vessel type of the blood vessel contour based on the region type, and if the blood vessel type is a bifurcation type, matching a pre-trained bifurcation blood vessel wall surface shear stress prediction model; if the vessel type is a non-bifurcation type, matching a pre-trained non-bifurcation vessel wall surface shear stress prediction model.
Specifically, the type of the area where the center point is located may be determined based on the number of center points in the neighborhood of the center point, if the number of center points in the neighborhood of the center point is less than or equal to 2, the type of the area where the center point is located is a bifurcation area type, the current bifurcation point is taken as the center point, the type of the area where the center point in the preset neighborhood range is also set as a bifurcation area type, and preferably, the preset neighborhood range may be set according to any number ensuring that the number of center points adjacent to the current bifurcation node is between 2 and 5. Marking can be carried out after the region type of each center point is determined, the region type corresponding to each center point is marked, if the region type of the center point is a bifurcation region type, the blood vessel type corresponding to the corresponding blood vessel contour is a bifurcation type, and if the region type of the center point is a non-bifurcation region type, the blood vessel type corresponding to the corresponding blood vessel contour is a non-bifurcation type. Further, if the vessel type of the vessel profile is a bifurcation type, matching to a pre-trained bifurcation vessel wall surface shear stress prediction model; if the vessel type of the vessel profile is a non-bifurcation type, then a pre-trained non-bifurcation vessel wall shear stress prediction model should be matched.
On the basis of the above embodiment, the method further includes: if the blood vessel type corresponding to the blood vessel profile is a bifurcation type, carrying out average processing on the predicted result of the blood vessel profile, and taking the obtained average value as the predicted result of the blood vessel profile.
It should be noted that, for a blood vessel of a non-bifurcation type, as shown in fig. 3, a schematic diagram of converting a blood vessel of a non-bifurcation area into a two-dimensional grid may be obtained by converting a blood vessel of a non-bifurcation area into a two-dimensional grid, as shown in fig. 4, a schematic diagram of converting a blood vessel of a bifurcation area into a two-dimensional grid may be obtained by converting a blood vessel of a bifurcation area into a two-dimensional grid, and a plurality of 2D planes may be obtained by converting a blood vessel of a bifurcation area into a two-dimensional grid.
Specifically, the vessel type corresponding to the vessel profile is a bifurcation type, and after the vessel wall surface shear stress prediction processing is performed on a plurality of profile points of the vessel profile, the average value of the prediction results of each profile point is calculated, so as to obtain the prediction result of the current vessel profile.
On the basis of the above embodiment, the method further includes: and if the number of the plurality of contour points of the blood vessel contour is larger than a preset number threshold, encoding parameters of the plurality of contour points of the blood vessel contour by an encoder.
Specifically, if the contour points of the selected blood vessel contour are larger than the preset number threshold, encoding the parameters of a plurality of contour points of the blood vessel contour by an encoder before wall shear stress prediction is performed on each contour point, so that the parameters of the plurality of contour points are subjected to reduced order processing, and the number of data processed by a prediction model is reduced. The preset number threshold can be set according to actual requirements, so that the prediction model can finish the shearing stress of the vessel wall surface of a plurality of contour points of the vessel contour with the highest efficiency.
Optionally, the training process of the pre-trained vessel wall shear stress prediction model includes: simulating a blood vessel model sample through three-dimensional computational fluid dynamics simulation based on preset boundary conditions, and determining a label value corresponding to the blood vessel model sample, wherein the preset boundary conditions comprise bifurcation type boundary conditions and non-bifurcation type boundary conditions; taking a label value corresponding to the blood vessel model sample as a label value of a pre-trained blood vessel wall shear stress prediction model; training the prediction model based on the label value of the prediction model, a blood vessel model sample and boundary conditions of bifurcation types to obtain a blood vessel wall shear stress prediction model corresponding to bifurcation types; and training the prediction model based on the label value of the prediction model, the blood vessel model sample and the boundary condition of the non-bifurcation type to obtain a blood vessel wall shear stress prediction model corresponding to the non-bifurcation type.
The calculation of the shear stress on the wall surface of the blood vessel requires consideration of factors such as viscosity of the fluid, velocity gradient, friction between the fluid and the wall surface, and the like, and based on this, the preset boundary condition is a boundary condition between the fluid and the wall surface. According to the theory of flow mechanics, the shear stress of the wall surface of the blood vessel can be calculated by a shear stress formula, and the shear stress formula is an exemplary newton's law of viscosity, the formula describes the relationship between the shear stress of the wall surface and the velocity gradient, and the calculation formula of the shear stress tau of the wall surface is as follows: τ=μ× (du/dy), where μ denotes the dynamic coefficient of viscosity of the fluid and du/dy denotes the gradient of velocity in the direction perpendicular to the wall. Considering the boundary conditions, the velocity on the wall is usually assumed to be 0, i.e. the wall can be considered stationary, y=0 representing a position near the wall, in which case the wall shear stress can be reduced to: τ=μ (du/dy) |y=0.
Wherein, preset boundary conditions are set according to factors influencing wall shear stress, and exemplary preset boundary conditions include pressure, flow, speed field and the like. The parameter values corresponding to the preset boundary conditions can be obtained from clinical medical data or can be set according to prior experience. The blood vessel model sample can be specifically understood as a three-dimensional blood vessel model to be trained, a real three-dimensional blood vessel model can be obtained from a clinical medical image library, the blood vessel model can be adjusted according to requirements to obtain different types of three-dimensional blood vessel models, and the three-dimensional blood vessel model obtained after adjustment can be taken as blood vessel model samples by adjusting bifurcation points and angles of the three-dimensional blood vessel model to obtain a new three-dimensional blood vessel model, so that a plurality of types of three-dimensional blood vessel models can be obtained as samples to carry out model training, and the model obtained through training can meet prediction requirements more.
Specifically, a real three-dimensional blood vessel model can be obtained from a clinical medical image library and used as a blood vessel model sample, a new three-dimensional blood vessel model can be obtained by adjusting bifurcation points and angles of the three-dimensional blood vessel model according to requirements and used as a blood vessel model sample, further, preset boundary conditions are input into three-dimensional computational fluid mechanics simulation, the blood vessel model sample is simulated through the three-dimensional computational fluid mechanics simulation, a simulation result corresponding to the blood vessel model sample is obtained, and the simulation result is used as a label value of the corresponding blood vessel model sample. The preset boundary conditions of the wall surfaces of the blood vessels corresponding to different blood vessel types are different, the boundary conditions of the corresponding bifurcation type are set for the blood vessel of bifurcation type, and the boundary conditions of the corresponding non-bifurcation type are set for the blood vessel of non-bifurcation type.
The pre-trained blood vessel wall surface shear stress prediction model is a deep learning network model, a simulation result corresponding to the obtained blood vessel model sample is used as a label value of the pre-trained blood vessel wall surface shear stress prediction model, the blood vessel model sample is used as a parameter of an input layer of the blood vessel wall surface shear stress prediction model, a bifurcation type boundary condition and a non-bifurcation type boundary condition are used as parameters of a hidden layer of the blood vessel wall surface shear stress prediction model, the training of the blood vessel wall surface shear stress prediction model is started based on the parameters, and the training result meets a preset training ending condition until the training result meets a preset training ending condition, so that a blood vessel wall surface shear stress prediction model corresponding to a bifurcation type blood vessel model obtained by training the prediction model through the label value of the prediction model, the blood vessel model sample and the bifurcation type boundary condition, and a blood vessel wall surface shear stress prediction model corresponding to a non-bifurcation type blood vessel model obtained by training the prediction model through the label value of the prediction model, the blood vessel model sample and the non-bifurcation type boundary condition.
According to the technical scheme, the coronary angiography image is acquired, and segmentation processing is carried out on the coronary angiography image to obtain blood vessel segmentation data; extracting a blood vessel center line of the blood vessel segmentation data, and constructing a blood vessel three-dimensional contour based on the blood vessel center line and the blood vessel segmentation data; intercepting a blood vessel contour to be predicted on a three-dimensional blood vessel contour, and selecting a plurality of contour points on the blood vessel contour; and matching a pre-trained vessel wall shear stress prediction model according to the vessel type of the vessel profile, and performing prediction processing on a plurality of profile points of the vessel profile based on the matched vessel wall shear stress prediction model to obtain vessel wall shear stress prediction results of the profile points, wherein the vessel type comprises a bifurcation type and a non-bifurcation type. According to the method, the device and the system, the blood vessel wall shear stress prediction is carried out on different types of blood vessels through the prediction model, so that the blood vessel wall shear stress prediction result is obtained, the automatic prediction efficiency and accuracy of the blood vessel wall shear stress are improved, the hardware requirements and the professional requirements of operators are reduced, and the resource waste and the prediction cost are reduced.
Example two
Fig. 5 is a flowchart of a method for predicting shear stress on a wall surface of a blood vessel according to a second embodiment of the present invention, where the method according to the foregoing embodiment is further optimized, and optionally coordinate information of a plurality of contour points and boundary conditions of a contour of the blood vessel are obtained, where the boundary conditions include pressure data, flow data, and velocity data; and inputting the coordinate information of the contour points and the boundary conditions of the blood vessel contours into a matched blood vessel wall surface shear stress prediction model to obtain blood vessel wall surface shear stress prediction results of the contour points. As shown in fig. 5, the method includes:
S510, acquiring a coronary angiography image, and performing segmentation processing on the coronary angiography image to obtain blood vessel segmentation data.
S520, extracting a blood vessel center line of the blood vessel segmentation data, and constructing a blood vessel three-dimensional contour based on the blood vessel center line and the blood vessel segmentation data.
S530, cutting the to-be-predicted blood vessel contour on the three-dimensional blood vessel contour, and selecting a plurality of contour points on the blood vessel contour.
S540, matching a pre-trained blood vessel wall shear stress prediction model according to the blood vessel type of the blood vessel profile.
S550, acquiring coordinate information of a plurality of contour points and boundary conditions of the blood vessel contour, wherein the boundary conditions comprise pressure data, flow data and speed data.
Specifically, the coordinate information of the contour point on the three-dimensional contour of the blood vessel is the coordinate information of the corresponding contour point, and the coordinate information of the contour point on the three-dimensional contour of the blood vessel can be directly read on a display screen for displaying the three-dimensional contour of the blood vessel by way of example; the boundary condition of the blood vessel profile can be determined through a preset algorithm and/or detection tool, and the pressure data can be exemplified by average coronary pressure data clinically measured by a patient or coronary pressure data averaged by a crowd, the flow data can be obtained through calculation of myocardial volume in a CT image of the patient, and the speed data can be obtained according to the flow data and the area of the blood vessel.
S560, inputting coordinate information of the contour points and boundary conditions of the blood vessel contours into a matched blood vessel wall surface shear stress prediction model to obtain blood vessel wall surface shear stress prediction results of the contour points.
Specifically, coordinate information of a plurality of contour points on each contour is used as an input parameter of an input layer of a matched blood vessel wall surface shear stress prediction model, boundary conditions of the blood vessel contour are used as an input parameter of a hidden layer of the matched blood vessel wall surface shear stress prediction model, and after the matched blood vessel wall surface shear stress prediction model predicts, blood vessel wall surface shear stress prediction results corresponding to the plurality of contour points are obtained.
Optionally, acquiring boundary conditions of the vessel profile includes: taking pressure data, flow data and speed data of a blood vessel inlet as initial boundary conditions of a blood vessel contour; if the vessel type of the vessel profile is a bifurcation type, determining the geometric parameters of each branch vessel corresponding to the vessel profile, and carrying out distribution processing on flow data and speed data of a primary main vessel of the branch vessel based on one or more of the geometric parameters through the Morey law to obtain the flow data and speed data of each branch vessel, thereby obtaining the boundary condition of the vessel profile, wherein the geometric parameters comprise vessel volume data, vessel length data and vessel outlet area data.
The vessel inlet is understood to mean, in particular, the inlet of the vessel at the very beginning, i.e. the inlet of the main vessel. The geometric parameters of each branch blood vessel comprise blood vessel volume data, blood vessel length data and blood vessel outlet area data, the geometric parameters of each branch are the sum of the geometric parameters comprising the blood vessel section from the starting point of the branch to the blood vessel outlet, and the boundary condition of the current bifurcation point is determined according to the geometric parameters of the blood vessel section from the current bifurcation point to the blood vessel outlet for any bifurcation point.
Specifically, the average coronary pressure can be obtained by calling clinical measurement in a clinical medicine database to serve as pressure data of a blood vessel inlet, inlet flow data of the blood vessel can be obtained according to calculation of myocardial volume in a CT image of a patient, speed data of the blood vessel inlet can be calculated according to the flow data and the area of the blood vessel, the obtained pressure data, flow data and speed data of the blood vessel inlet are taken as initial boundary conditions of blood vessel outlines, and the initial boundary conditions are taken as first input parameters of a hidden layer of a blood vessel wall shear stress prediction model. For the blood vessel profile of which the blood vessel type is a bifurcation type, calculating geometrical parameters such as blood vessel volume data, blood vessel length data, blood vessel outlet area data and the like corresponding to a branch blood vessel formed by a blood vessel section between a current bifurcation node and a blood vessel outlet, and further, distributing and processing flow data and speed data of a primary main blood vessel of the branch blood vessel based on one or more of the geometrical parameters through the Morgan law to obtain the flow and speed of each branch blood vessel, and obtaining the boundary condition of the blood vessel profile of the bifurcation type.
In this embodiment, the obtaining of the boundary condition of the bifurcated vessel is related to the geometric parameter of the vessel corresponding to the current bifurcation node, but also related to the geometric parameter of the vessel segment between the current node and the vessel outlet, and the flow and the speed are distributed according to the merry law to obtain the flow and the speed of each branched vessel, so as to obtain the boundary condition of the vessel contour of the bifurcation type, obtain different boundary conditions for different vessel types, and perform prediction processing by using a wall shear stress prediction model, so that the obtained prediction result can be more fit with the wall shear stress of the corresponding vessel type, and the accuracy of the wall shear stress prediction model is improved.
In a specific embodiment, as shown in the neural network schematic diagram of fig. 6, coordinate points on each vessel contour form an input layer, where the input layer data includes X 1、X2, i.e., X, xn, for example, prediction is performed from a vessel inlet, the first vessel contour has 32 contour points, each contour point is a three-dimensional spatial point, i.e., each contour point has three values of X, y, z, so that the vessel contour has 32X 3 values corresponding to the input parameter, and it should be noted that if the number of points is too large, the 32X 3 values may be encoded by an encoder to complete the reduction of the values of the multiple parameters, illustratively, the order may be reduced to 16 values, reducing parameters of subsequent deep learning networks. For the hidden layer, the first parameter value S 0,S0 is set to include the inlet boundary conditions of the vessel, such as inlet pressure, flow, and velocity. For the initial vascular access, the pressure can be the average coronary pressure measured clinically by the patient or the average coronary pressure of the human population, the flow of the coronary can be calculated according to the myocardial volume in the CT image of the patient, the speed of the access can be assumed to be Poisson's flow, and the speed can be deduced according to the area of the blood vessel of the flow. S 0、X1 is used as input data of S 1, the output result is O 1,S1、X2, and is input to S 2, a corresponding output result O 2 is obtained, and the output layer outputs prediction results O 1、O2, i.e., on, of each contour point. The output layer outputs predicted values of wall shear stress corresponding to each contour point input in the input layer, wherein the predicted values of wall shear stress corresponding to each contour point may be wall shear stress vector values, for example, there are 32 points on the vessel contour, and the predicted values of wall shear stress corresponding to each contour point output should be values of 32×3 (wall shear stress is a vector, and there are three directions of x, y, and z). If the number of points input is too large, the output layer can output few values (such as 16 values) similar to the input layer, and the output layer decodes through a decoder network corresponding to an encoder when outputting the predicted value. For a bifurcated vessel, the volume, length or outlet area of the vessel segment 1 and the vessel segment 2 can be determined according to the vessel after the bifurcation point, such as the vessel segment 1 and the vessel segment 2 shown in fig. 4, so as to distribute the flow and the speed according to the merry law, and in a bifurcated network formed by the vessel segment 1 and the vessel segment 2, the flow and the speed of the hidden layer corresponding to the bifurcated vessel are calculated according to the merry law. Accordingly, in the bifurcated network formed by vessel segment 1 and vessel segment 3, the flow rate and speed of the hidden layer corresponding to the bifurcated vessel is used for the flow rate and speed of vessel segment 3. Further, for two bifurcated vessel segments, there are two output layers of the vessel segment 1, so that the vessel segment 1 has two sets of prediction results, at this time, the output layers of the vessel segment 1 are subjected to average processing, and the result after the average processing is the target prediction result corresponding to the current bifurcated vessel.
According to the technical scheme of the embodiment, the coronary angiography image is acquired, and segmentation processing is carried out on the coronary angiography image, so that blood vessel segmentation data are obtained. And extracting a blood vessel center line of the blood vessel segmentation data, and constructing a blood vessel three-dimensional contour based on the blood vessel center line and the blood vessel segmentation data. And intercepting the blood vessel contour to be predicted on the three-dimensional blood vessel contour, and selecting a plurality of contour points on the blood vessel contour. And matching a pre-trained vessel wall shear stress prediction model according to the vessel type of the vessel profile. Coordinate information of a plurality of contour points and boundary conditions of a blood vessel contour are acquired, wherein the boundary conditions comprise pressure data, flow data and speed data. And inputting the coordinate information of the contour points and the boundary conditions of the blood vessel contours into a matched blood vessel wall surface shear stress prediction model to obtain blood vessel wall surface shear stress prediction results of the contour points. According to the method and the device, the blood vessel wall shear stress prediction is carried out on different types of blood vessels through the prediction model, the blood vessel wall shear stress prediction result is obtained, and the prediction is carried out according to the boundary conditions of different blood vessel types, so that the obtained prediction result is more accurate, the automatic prediction efficiency of the blood vessel wall shear stress is improved, the running environment condition requirement of the blood vessel wall shear stress prediction model is low, the model is easy to operate, and therefore the hardware requirement and the professional technical requirement of operators are reduced, and the resource waste and the prediction cost are reduced.
Example III
Fig. 7 is a schematic structural diagram of a device for predicting shear stress on a wall surface of a blood vessel according to a third embodiment of the present invention. As shown in fig. 7, the apparatus includes:
The blood vessel segmentation data determining module 710 is configured to acquire a coronary angiography image, and segment the coronary angiography image to obtain blood vessel segmentation data;
The three-dimensional contour determination module 720 is configured to extract a vessel centerline of the vessel segmentation data, and construct a three-dimensional contour of the vessel based on the vessel centerline and the vessel segmentation data;
the contour point determining module 730 is configured to intercept a vessel contour to be predicted on a three-dimensional vessel contour, and select a plurality of contour points on the vessel contour;
the prediction result determining module 740 is configured to match a pre-trained vessel wall shear stress prediction model according to a vessel type of a vessel profile, and perform prediction processing on a plurality of profile points of the vessel profile based on the matched vessel wall shear stress prediction model to obtain vessel wall shear stress prediction results of the plurality of profile points, where the vessel type includes a bifurcation type and a non-bifurcation type.
According to the technical scheme, a coronary angiography image is acquired through a blood vessel segmentation data determining module, segmentation processing is carried out on the coronary angiography image, and blood vessel segmentation data are obtained; the three-dimensional blood vessel contour determining module extracts a blood vessel center line of the blood vessel segmentation data and constructs a three-dimensional blood vessel contour based on the blood vessel center line and the blood vessel segmentation data; the contour point determining module intercepts a to-be-predicted blood vessel contour on a three-dimensional blood vessel contour, and selects a plurality of contour points on the blood vessel contour; the prediction result determining module is used for matching a pre-trained blood vessel wall shear stress prediction model according to the blood vessel type of the blood vessel profile, and predicting a plurality of profile points of the blood vessel profile based on the matched blood vessel wall shear stress prediction model to obtain blood vessel wall shear stress prediction results of the profile points, wherein the blood vessel type comprises a bifurcation type and a non-bifurcation type. The device realizes the prediction of the shearing stress of the wall surface of the blood vessel to different types of blood vessels through the prediction model, obtains the prediction result of the shearing stress of the wall surface of the blood vessel, improves the automatic prediction efficiency of the shearing stress of the wall surface of the blood vessel, reduces the hardware requirements and the professional requirements of operators, and reduces the resource waste and the prediction cost.
Based on the above embodiment, the optional prediction result determining module 740 is specifically configured to:
determining the type of the region where the central point corresponding to the blood vessel contour is located;
Determining the blood vessel type of the blood vessel contour based on the region type, and if the blood vessel type is a bifurcation type, matching a pre-trained bifurcation blood vessel wall surface shear stress prediction model; if the vessel type is a non-bifurcation type, matching a pre-trained non-bifurcation vessel wall surface shear stress prediction model
Acquiring coordinate information of a plurality of contour points and boundary conditions of blood vessel contours, wherein the boundary conditions comprise pressure data, flow data and speed data;
and inputting the coordinate information of the contour points and the boundary conditions of the blood vessel contours into a matched blood vessel wall surface shear stress prediction model to obtain blood vessel wall surface shear stress prediction results of the contour points.
Taking pressure data, flow data and speed data of a blood vessel inlet as initial boundary conditions of a blood vessel contour;
If the vessel type of the vessel profile is a bifurcation type, determining the geometric parameters of each branch vessel corresponding to the vessel profile, and carrying out distribution processing on flow data and speed data of a primary main vessel of the branch vessel based on one or more of the geometric parameters through the Morey law to obtain the flow data and speed data of each branch vessel, thereby obtaining the boundary condition of the vessel profile, wherein the geometric parameters comprise vessel volume data, vessel length data and vessel outlet area data.
Simulating a blood vessel model sample through three-dimensional computational fluid dynamics simulation based on preset boundary conditions, and determining a label value corresponding to the blood vessel model sample, wherein the preset boundary conditions comprise bifurcation type boundary conditions and non-bifurcation type boundary conditions;
Taking a label value corresponding to the blood vessel model sample as a label value of a pre-trained blood vessel wall shear stress prediction model;
training the prediction model based on the label value of the prediction model, a blood vessel model sample and boundary conditions of bifurcation types to obtain a blood vessel wall shear stress prediction model corresponding to bifurcation types; and, a step of, in the first embodiment,
Training the prediction model based on the label value of the prediction model, the blood vessel model sample and the boundary condition of the non-bifurcation type to obtain a blood vessel wall shear stress prediction model corresponding to the non-bifurcation type.
Optionally, the device is further specifically configured to:
If the blood vessel type corresponding to the blood vessel profile is a bifurcation type, carrying out average processing on the predicted result of the blood vessel profile, and taking the obtained average value as the predicted result of the blood vessel profile.
And if the number of the plurality of contour points of the blood vessel contour is larger than a preset number threshold, encoding parameters of the plurality of contour points of the blood vessel contour by an encoder.
The blood vessel wall shear stress prediction device provided by the embodiment of the invention can execute the blood vessel wall shear stress prediction method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example IV
Fig. 8 is a schematic structural diagram of an electronic device according to a fourth embodiment of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. Electronic equipment may also represent various forms of mobile devices, such as personal digital processing, cellular telephones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 8, the electronic device 10 includes at least one processor 11, and a memory, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, etc., communicatively connected to the at least one processor 11, in which the memory stores a computer program executable by the at least one processor, and the processor 11 may perform various appropriate actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from the storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 may also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to bus 14.
Various components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, etc.; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network, such as the internet, and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, digital Signal Processors (DSPs), and any suitable processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as the vessel wall shear stress prediction method.
In some embodiments, the vessel wall shear stress prediction method may be implemented as a computer program tangibly embodied on a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the vessel wall shear stress prediction method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the vessel wall shear stress prediction method in any other suitable way (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuit systems, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), systems On Chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs, the one or more computer programs may be executed and/or interpreted on a programmable system including at least one programmable processor, which may be a special purpose or general-purpose programmable processor, that may receive data and instructions from, and transmit data and instructions to, a storage system, at least one input device, and at least one output device.
The computer program for practicing the vessel wall shear stress prediction methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be implemented. The computer program may execute entirely on the machine, partly on the machine, as a stand-alone software package, partly on the machine and partly on a remote machine or entirely on the remote machine or server.
Example five
The fifth embodiment of the present invention further provides a computer readable storage medium, where computer instructions are stored, where the computer instructions are configured to cause a processor to execute a method for predicting a shear stress of a wall surface of a blood vessel, the method including:
Acquiring a coronary angiography image, and performing segmentation processing on the coronary angiography image to obtain blood vessel segmentation data;
extracting a blood vessel center line of the blood vessel segmentation data, and constructing a blood vessel three-dimensional contour based on the blood vessel center line and the blood vessel segmentation data;
Intercepting a blood vessel contour to be predicted on a three-dimensional blood vessel contour, and selecting a plurality of contour points on the blood vessel contour;
And matching a pre-trained vessel wall shear stress prediction model according to the vessel type of the vessel profile, and performing prediction processing on a plurality of profile points of the vessel profile based on the matched vessel wall shear stress prediction model to obtain vessel wall shear stress prediction results of the profile points, wherein the vessel type comprises a bifurcation type and a non-bifurcation type.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) through which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic input, speech input, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a background component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such background, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the internet.
The computing system may include clients and servers. The client and server are typically remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical hosts and VPS service are overcome.
It should be appreciated that various forms of the flows shown above may be used to reorder, add, or delete steps. For example, the steps described in the present invention may be performed in parallel, sequentially, or in a different order, so long as the desired results of the technical solution of the present invention are achieved, and the present invention is not limited herein.
The above embodiments do not limit the scope of the present invention. It will be apparent to those skilled in the art that various modifications, combinations, sub-combinations and alternatives are possible, depending on design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method for predicting shear stress of a vessel wall surface, comprising:
Acquiring a coronary angiography image, and performing segmentation processing on the coronary angiography image to obtain blood vessel segmentation data;
extracting a blood vessel center line of the blood vessel segmentation data, and constructing a blood vessel three-dimensional contour based on the blood vessel center line and the blood vessel segmentation data;
Intercepting a blood vessel contour to be predicted on the three-dimensional blood vessel contour, and selecting a plurality of contour points on the blood vessel contour;
and according to the blood vessel type of the blood vessel contour, matching a pre-trained blood vessel wall shear stress prediction model, and carrying out prediction processing on a plurality of contour points of the blood vessel contour based on the matched blood vessel wall shear stress prediction model to obtain blood vessel wall shear stress prediction results of the contour points, wherein the blood vessel type comprises a bifurcation type and a non-bifurcation type.
2. The method of claim 1, wherein matching a pre-trained vessel wall shear stress prediction model according to a vessel type of the vessel profile comprises:
Determining the type of the region where the central point corresponding to the blood vessel contour is located;
determining the blood vessel type of the blood vessel profile based on the region type, and if the blood vessel type is a bifurcation type, matching a pre-trained bifurcation blood vessel wall surface shear stress prediction model; and if the blood vessel type is a non-bifurcation type, matching a pre-trained non-bifurcation blood vessel wall surface shear stress prediction model.
3. The method according to claim 1, wherein the predicting a plurality of contour points of the vessel contour based on the matched vessel wall shear stress prediction model to obtain vessel wall shear stress prediction results of the plurality of contour points includes:
Acquiring coordinate information of the contour points and boundary conditions of the blood vessel contour, wherein the boundary conditions comprise pressure data, flow data and speed data;
and inputting the coordinate information of the contour points and the boundary conditions of the blood vessel contour into the matched blood vessel wall shear stress prediction model to obtain blood vessel wall shear stress prediction results of the contour points.
4. A method according to claim 3, wherein obtaining boundary conditions of the vessel profile comprises:
Taking pressure data, flow data and speed data of a blood vessel inlet as initial boundary conditions of the blood vessel outline;
If the vessel type of the vessel profile is a bifurcation type, determining the geometric parameters of each branch vessel corresponding to the vessel profile, and carrying out distribution processing on the flow data and the speed data of the primary main vessel of the branch vessel based on one or more of the geometric parameters through the merry law to obtain the flow data and the speed data of each branch vessel, thereby obtaining the boundary condition of the vessel profile, wherein the geometric parameters comprise vessel volume data, vessel length data and vessel outlet area data.
5. The method according to claim 1, wherein the method further comprises:
And if the blood vessel type corresponding to the blood vessel profile is the bifurcation type, carrying out average processing on the predicted result of the blood vessel profile, wherein the obtained average value is used as the predicted result of the blood vessel profile.
6. The method according to claim 1, wherein the method further comprises:
and if the number of the plurality of contour points of the blood vessel contour is larger than a preset number threshold, encoding parameters of the plurality of contour points of the blood vessel contour by an encoder.
7. The method of claim 1, wherein the training process of the pre-trained vessel wall shear stress prediction model comprises:
Simulating a blood vessel model sample through three-dimensional computational fluid dynamics simulation based on a preset boundary condition, and determining a label value corresponding to the blood vessel model sample, wherein the preset boundary condition comprises a boundary condition of the bifurcation type and a boundary condition of the non-bifurcation type;
taking a label value corresponding to the blood vessel model sample as a label value of the pre-trained blood vessel wall shear stress prediction model;
Training the prediction model based on the label value of the prediction model, the blood vessel model sample and the boundary condition of the bifurcation type to obtain the blood vessel wall shear stress prediction model corresponding to the bifurcation type; and, a step of, in the first embodiment,
Training the prediction model based on the label value of the prediction model, the blood vessel model sample and the boundary condition of the non-bifurcation type to obtain the blood vessel wall shear stress prediction model corresponding to the non-bifurcation type.
8. A vessel wall shear stress prediction device, comprising:
the blood vessel segmentation data determining module is used for acquiring a coronary angiography image, and carrying out segmentation processing on the coronary angiography image to obtain blood vessel segmentation data;
The blood vessel three-dimensional contour determining module is used for extracting a blood vessel center line of the blood vessel segmentation data and constructing a blood vessel three-dimensional contour based on the blood vessel center line and the blood vessel segmentation data;
the contour point determining module is used for intercepting a to-be-predicted blood vessel contour on the three-dimensional blood vessel contour and selecting a plurality of contour points on the blood vessel contour;
The prediction result determining module is used for matching a pre-trained blood vessel wall shear stress prediction model according to the blood vessel type of the blood vessel profile, and predicting a plurality of profile points of the blood vessel profile based on the matched blood vessel wall shear stress prediction model to obtain blood vessel wall shear stress prediction results of the profile points, wherein the blood vessel type comprises a bifurcation type and a non-bifurcation type.
9. An electronic device, the electronic device comprising:
at least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the vessel wall shear stress prediction method of any one of claims 1-7.
10. A computer readable storage medium storing computer instructions for causing a processor to perform the vessel wall shear stress prediction method of any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410392897.0A CN118172348A (en) | 2024-04-02 | 2024-04-02 | Method and device for predicting shearing stress of wall surface of blood vessel, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410392897.0A CN118172348A (en) | 2024-04-02 | 2024-04-02 | Method and device for predicting shearing stress of wall surface of blood vessel, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118172348A true CN118172348A (en) | 2024-06-11 |
Family
ID=91351084
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410392897.0A Pending CN118172348A (en) | 2024-04-02 | 2024-04-02 | Method and device for predicting shearing stress of wall surface of blood vessel, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118172348A (en) |
-
2024
- 2024-04-02 CN CN202410392897.0A patent/CN118172348A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20210272030A1 (en) | Systems and methods for using geometry sensitivity information for guiding workflow | |
| CN107977709B (en) | Deep learning model and system for predicting blood flow characteristics on blood vessel path of blood vessel tree | |
| CN109949300B (en) | Method, system and computer readable medium for anatomical tree structure analysis | |
| Gharleghi et al. | Deep learning for time averaged wall shear stress prediction in left main coronary bifurcations | |
| US10354349B2 (en) | Systems and methods for using geometry sensitivity information for guiding workflow | |
| CN111652876B (en) | Method for detecting three-dimensional basin bottom ultrasonic image | |
| CN117593083A (en) | Commodity image generation method, commodity image generation device, electronic equipment and storage medium | |
| CN118172348A (en) | Method and device for predicting shearing stress of wall surface of blood vessel, electronic equipment and storage medium | |
| CN116091702A (en) | Vascular structure reconstruction method, device, equipment and storage medium | |
| CN115762798A (en) | Method and device for determining hemodynamic parameters, storage medium and electronic equipment | |
| CN115861189A (en) | Image registration method and device, electronic equipment and storage medium | |
| CN115482261A (en) | Blood vessel registration method, device, electronic equipment and storage medium | |
| CN115409856A (en) | Lung medical image processing method, device, equipment and storage medium | |
| CN114880960A (en) | Method for evaluating radioactive embolism dose and injection position based on fluid dynamics | |
| CN117333487B (en) | Acne classification method, device, equipment and storage medium | |
| CN118172349A (en) | Vascular quantization parameter prediction method and device, electronic equipment and storage medium | |
| CN114972242B (en) | Training method and device for myocardial bridge detection model and electronic equipment | |
| CN115100222B (en) | Image processing method and device for separating artery and vein blood vessels, storage medium and terminal | |
| CN116245853A (en) | Fractional flow reserve determination method, fractional flow reserve determination device, electronic equipment and storage medium | |
| CN117688867A (en) | Method, device, equipment and medium for determining microcirculation resistance reserve fraction | |
| CN117688865A (en) | Microcirculation resistance index determination method, device, equipment and medium | |
| CN117689680A (en) | Pulmonary artery segmentation method and device, electronic equipment and storage medium | |
| CN116883358A (en) | Vascular image processing method and device, electronic equipment and storage medium | |
| CN117688866A (en) | Microcirculation resistance reserve fraction obtaining method, device, equipment and medium | |
| CN117476216A (en) | Model prediction method, device, equipment and storage medium based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |