CN115661093A - Blood vessel data prediction method and device, electronic equipment and storage medium - Google Patents
Blood vessel data prediction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115661093A CN115661093A CN202211358379.4A CN202211358379A CN115661093A CN 115661093 A CN115661093 A CN 115661093A CN 202211358379 A CN202211358379 A CN 202211358379A CN 115661093 A CN115661093 A CN 115661093A
- Authority
- CN
- China
- Prior art keywords
- data
- branch
- predicted
- blood vessel
- prediction
- 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 122
- 238000000034 method Methods 0.000 title claims abstract description 54
- 230000017531 blood circulation Effects 0.000 claims abstract description 50
- 238000012545 processing Methods 0.000 claims abstract description 32
- 238000011144 upstream manufacturing Methods 0.000 claims description 30
- 230000010354 integration Effects 0.000 claims description 22
- 238000004590 computer program Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 abstract description 22
- 238000012795 verification Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 8
- 238000010801 machine learning Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- 238000012549 training Methods 0.000 description 7
- 239000000203 mixture Substances 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000014509 gene expression Effects 0.000 description 4
- 238000004088 simulation Methods 0.000 description 4
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000004913 activation Effects 0.000 description 2
- 230000000004 hemodynamic effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 230000003902 lesion Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 208000025494 Aortic disease Diseases 0.000 description 1
- 208000024172 Cardiovascular disease Diseases 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 238000004458 analytical method Methods 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
- 238000013528 artificial neural network 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
- 230000001413 cellular effect Effects 0.000 description 1
- 230000002490 cerebral effect Effects 0.000 description 1
- 208000026106 cerebrovascular disease Diseases 0.000 description 1
- 238000002591 computed tomography Methods 0.000 description 1
- 210000004351 coronary vessel Anatomy 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 239000013307 optical fiber Substances 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
- 208000019553 vascular disease Diseases 0.000 description 1
- 230000009278 visceral effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The invention discloses a blood vessel data prediction method, a blood vessel data prediction device, electronic equipment and a storage medium. The method determines a bifurcation area in a blood vessel to be analyzed; acquiring branch-in data and branch-out data of the bifurcation area; and for the predicted branch in each branch data, performing prediction processing on the branch entering data, the branch data of the predicted branch and other branch data except the predicted branch based on a preset blood vessel prediction model to obtain the mechanical energy loss prediction data of the predicted branch relative to the inlet of the bifurcation area. The calculation is carried out based on the geometric characteristics of the blood vessel bifurcation area, and the influence of factors such as the mutual influence among different branches, the blood flow form and the like is considered in the calculation, so that the accuracy of the blood vessel data calculation is improved.
Description
Technical Field
The embodiment of the invention relates to the field of hemodynamic simulation calculation, in particular to a method and a device for predicting blood vessel data, electronic equipment and a storage medium.
Background
With the improvement of living standard, vascular diseases such as coronary artery related disease (CAD), cerebrovascular disease, aortic disease, etc. become more and more threats to human health. For the assessment of blood flow disorders functional parameters such as FFR, blood flow velocity, blood flow pressure drop etc hemodynamic parameters become increasingly important in the diagnostic assessment of these disorders.
Bifurcation lesion is a common lesion in cardiovascular diseases, and the accuracy of calculation of its mechanical energy loss will greatly affect the final calculation result.
At present, the existing bifurcation resistance calculation model is mostly obtained by ideal lumen derivation, the flow of a branch is only related to the parameters of the branch and a parent branch, the influence of the branch and other branches is not considered, the considered bifurcation angle is the bifurcation angle on a plane, the flow state information of the inlet of a blood vessel is lost, the actual complex flow state of the real blood vessel cannot be described accurately, and the direct use of calculation leads to larger errors.
Disclosure of Invention
The invention provides a blood vessel data prediction method, a blood vessel data prediction device, electronic equipment and a storage medium, and aims to improve the accuracy of bifurcation calculation.
In a first aspect, an embodiment of the present invention provides a blood vessel data prediction method, including:
determining a bifurcation area in a blood vessel to be analyzed;
acquiring branch-in data and branch-out data of the bifurcation area;
and for the predicted branch in each branch-out data, performing prediction processing on the branch-in data, the branch-out data of the predicted branch and other branch-out data except the predicted branch based on a preset blood vessel prediction model to obtain mechanical energy loss prediction data of the predicted branch relative to the inlet of the bifurcation area.
Optionally, the incoming branch data and the outgoing branch data respectively include one or more of the following items: characteristic point coordinates, cross-sectional area, blood flow information, inlet flow rate distribution coefficient of bifurcation area.
Optionally, for a predicted branch in each of the branch data, performing prediction processing on the branch entry data, the branch exit data of the predicted branch, and other branch exit data except the predicted branch based on a preset blood vessel prediction model to obtain predicted data of mechanical energy loss of the predicted branch relative to the entrance of the bifurcation region, including:
and inputting branch entering data, branch exiting data of the predicted branch and other branch exiting data except the predicted branch into the preset blood vessel prediction model to obtain mechanical energy loss prediction data of the predicted branch relative to the entrance of the bifurcation area.
Optionally, for a predicted branch in each of the branch data, performing prediction processing on the branch entry data, the branch exit data of the predicted branch, and other branch exit data except the predicted branch based on a preset blood vessel prediction model to obtain predicted data of mechanical energy loss of the predicted branch relative to the entrance of the bifurcation region, including:
for a predicted branch in each branch data, determining the upstream branch data of the predicted branch in other branch data except the predicted branch;
and inputting the branch entering data, the branch exiting data of the predicted branch and the upstream branch exiting data into the preset blood vessel prediction model to obtain the mechanical energy loss prediction data of the predicted branch relative to the entrance of the bifurcation area.
Optionally, the determining, in the other outgoing branch data except the predicted branch, the outgoing branch data upstream of the predicted branch includes:
for the feature points in each of the other outgoing branches, feature point data located upstream of the predicted branch is determined as upstream outgoing branch data based on the position and blood flow direction of each feature point.
Optionally, the performing, based on a preset vessel prediction model, prediction processing on the branch entry data, the branch exit data of the predicted branch, and other branch exit data except the predicted branch includes:
respectively performing data integration on the incoming branch data or other outgoing branch data except the predicted branch to obtain first integrated data corresponding to the incoming branch data and second integrated data corresponding to the other outgoing branch data;
and performing prediction processing on the first integrated data, the second integrated data and the predicted branch data based on a preset blood vessel prediction model.
Optionally, performing data integration on the branch entry data or other branch exit data except the predicted branch to obtain first integration data corresponding to the branch entry data and second integration data corresponding to the other branch exit data, respectively, includes:
and for any data item in the branch-in data or the other branch-out data, weighting a plurality of data items corresponding to the data item to obtain integrated data corresponding to the data item.
In a second aspect, an embodiment of the present invention further provides a blood vessel data prediction apparatus, including:
a bifurcation area determining module, which is used for determining a bifurcation area in a blood vessel to be analyzed;
the data acquisition module is used for acquiring the branch-in data and the branch-out data of the bifurcation area;
and the prediction module is used for carrying out prediction processing on the branch entering data, the branch leaving data of the prediction branch and other branch leaving data except the prediction branch based on a preset blood vessel prediction model for the prediction branch in the branch leaving data so as to obtain the mechanical energy loss prediction data of the prediction branch relative to the inlet of the bifurcation area.
In a third aspect, an embodiment of the present invention further provides an electronic device, where the electronic device includes:
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 data prediction method of any one of the first aspect.
In a fourth aspect, the present invention further provides a computer-readable storage medium, which stores computer instructions for causing a processor to implement the blood vessel data prediction method according to any one of the first aspect when executed.
The method comprises the steps of obtaining image data of a blood vessel to be analyzed, determining a bifurcation area in the blood vessel to be analyzed based on the image data, obtaining branch entering data and branch exiting data of the bifurcation area, and carrying out prediction processing on the branch entering data and the branch exiting data based on a preset blood vessel prediction model to obtain mechanical energy loss prediction data of the bifurcation area. The calculation is carried out based on the geometric characteristics of the blood vessel bifurcation area, and the influence of factors such as the mutual influence among different branches, the blood flow form and the like is considered in the calculation, so that the accuracy of the blood vessel data calculation is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a blood vessel data prediction method according to a first embodiment of the present invention;
FIG. 2 is a schematic illustration of a vessel bifurcation area provided in accordance with a first embodiment of the present invention;
fig. 3 is a schematic structural diagram of a blood vessel data prediction apparatus according to a second embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device according to a third embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or 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 one
Fig. 1 is a flowchart of a blood vessel data prediction method according to an embodiment of the present invention, where the embodiment is applicable to a case of blood vessel bifurcation calculation, and the method may be executed by a blood vessel data prediction apparatus, which may be implemented in the form of hardware and/or software, and may be configured in an electronic device, such as a computer, a server, a mobile terminal, and the like. As shown in fig. 1, the method includes:
and S110, determining a bifurcation area in the blood vessel to be analyzed.
The blood vessel to be analyzed may include, but is not limited to, a cerebral blood vessel, a coronary blood vessel, an aortic blood vessel, a visceral blood vessel, etc. of a target object, wherein the target object may be a human body or an animal body, etc., without being limited thereto. The bifurcation area in the vessel to be analyzed may be determined based on the medical image of the vessel to be analyzed, or may be determined by using a three-dimensional geometric model of the vessel to be analyzed, wherein the three-dimensional geometric model may be externally introduced or reconstructed based on the medical image of the vessel to be analyzed.
Scanning a blood vessel to be analyzed to obtain image data of the blood vessel to be analyzed, wherein the scanning mode of the blood vessel to be analyzed includes but is not limited to angiography, CT scanning and the like. Based on the characteristics of different types of blood vessels, a bifurcation region may exist in the blood vessel to be analyzed, and the bifurcation region is analyzed independently in the embodiment because the bifurcation region has a complex structure relative to a non-bifurcation region. The identification of the bifurcation region from the image data of the blood vessel to be analyzed may be implemented by a preset machine learning model. Specifically, the machine learning model may be a neural network model or the like, and the structure and type of the machine learning model are not limited herein.
For example, referring to fig. 2 specifically, the region shown in fig. 2 is a bifurcation region, and correspondingly, the training method of the machine learning model may be to perform bifurcation region labeling on the acquired blood vessel image data, and perform iterative training on the machine learning model based on the original blood vessel image data and the blood vessel image data input model after the bifurcation region labeling, so that the effect of bifurcation region identification can be achieved, which is not limited specifically here. The recognition result of the output of the machine learning may be an image provided with a bifurcation area mark, wherein the bifurcation area mark may be realized by setting a distinguishing color to the bifurcation area or setting a distinguishing mark to the bifurcation area.
In this embodiment, the image data of the blood vessel to be analyzed may be three-dimensional image data.
And S120, acquiring the incoming branch data and the outgoing branch data of the bifurcation area.
The branch-in data may be feature point data of an inlet vessel section in the bifurcation region, and the branch-out data may be feature point data of an outlet vessel section in the bifurcation region.
Illustratively, referring specifically to fig. 2, IN is used as the identifier of the incoming branch feature point, OUT is used as the identifier of the outgoing branch feature point, the first digit represents the nth entry, the second digit represents the nth feature point, and correspondingly, IN11 represents the 1 st feature point of the 1 st incoming branch. Alternatively, for the incoming branch and the outgoing branch, a plurality of (at least two) feature points may be provided on each branch, and the feature points may be points located on the centerline of the blood vessel.
For the incoming branch feature point IN, the feature point with the second digit of 1 may be an intersection of the incoming branch blood vessel boundary and the blood vessel centerline, and the feature point with the second digit of 2 may be an intersection of the incoming branch blood vessel centerline and the common region boundary (trapezoidal region boundary IN fig. 2). For the feature point OUT with the branching feature point OUT, the feature point with the second digit of 1 may be represented as the intersection of the centerline of the branching blood vessel and the centerline of the common area, and the feature point with the second digit of 2 may be represented as the intersection of the centerline of the branching blood vessel and the boundary of the common area. Alternatively, if the feature points coincide or are too close, the second feature point may be taken a distance back along the centerline.
Optionally, the incoming branch data and the outgoing branch data respectively include one or more of the following items: characteristic point coordinates, cross-sectional area, blood flow information, inlet flow velocity distribution coefficient of bifurcation area.
The feature point coordinates may be spherical coordinate system coordinates, and an origin of the spherical coordinate system may be set according to requirements, for example, an entry point of an arbitrary entering branch blood vessel is used as the origin of the coordinate system, that is, the coordinates of the 1 st feature point of the entering branch blood vessel are (0,0,0). The cross-sectional area may be a cross-sectional area of the blood vessel at the feature point. The blood flow information may be a blood flow volume at each position in the blood vessel, that is, a volume velocity of the blood flow, and may be a blood volume flowing through a certain cross section of the blood vessel per unit time. The inlet flow velocity profile coefficient of the bifurcation region may be a parameter reflecting the blood flow conditions at various points on a section of the blood vessel.
It should be noted that the blood flow information may be a preset initial value, which may be set according to a boundary condition of the blood vessel, or may be a preset fixed value, a randomly generated random value, or may be obtained through iterative adjustment in an iterative analysis process of the blood vessel, which is not limited herein.
Optionally, the inlet flow velocity distribution coefficient of the bifurcation region may be obtained by a flow velocity distribution coefficient prediction model. The method for obtaining the flow velocity distribution coefficient prediction model may include obtaining sample blood vessels, performing three-dimensional blood flow simulation on the sample blood vessels, extracting blood flow velocity distribution, blood flow information, and blood vessel geometric parameters of the inlet section and the outlet section of each sample blood vessel in the bifurcation area, determining flow velocity distribution coefficients of the inlet section and the outlet section of each sample blood vessel in the bifurcation area based on the blood flow velocity distribution of the inlet section and the outlet section of each sample blood vessel in the bifurcation area, forming a plurality of sets of sample data based on the flow velocity distribution coefficients, the blood flow information, and the blood vessel geometric parameters of the inlet section and the outlet section of each sample blood vessel in the bifurcation area, and obtaining the flow velocity distribution coefficient prediction model based on sample data regression. Correspondingly, the blood flow information, the flow velocity distribution coefficient (the preset initial value) of the input end of the blood vessel to be analyzed and the geometric parameters of the blood vessel section before the bifurcation area in the blood vessel to be analyzed are input into the flow velocity distribution coefficient prediction model as input information, so that the inlet flow velocity distribution coefficient of the bifurcation area predicted by the flow velocity distribution coefficient prediction model is obtained.
By acquiring multiple groups of factor data as the branch-in data and the branch-out data of the bifurcation area, the high-precision calculation of the blood vessel data of the bifurcation area is facilitated.
And S130, for the predicted branch in the branch data, performing prediction processing on the branch entering data, the branch data of the predicted branch and other branch data except the predicted branch based on a preset blood vessel prediction model to obtain mechanical energy loss prediction data of the predicted branch relative to the entrance of the bifurcation area.
The vessel prediction model can be obtained by training, that is, by defining a required prediction model, setting an activation function to activate, obtaining a format adopted by the prediction model during working, and compiling and fitting the defined prediction model. And (3) training the prediction model, namely adjusting model parameters in the prediction model through a training data set, evaluating the prediction model according to the verification data, and finishing the training of the prediction model if the evaluation is satisfied. The activation function may be a regression function, a binary classification function, a multi-cumulative classification function, etc., and the present invention is not limited in particular.
Alternatively, the model types of the vessel prediction model may include, but are not limited to, a logistic regression model, an artificial neural network model, a decision tree model, and the like. The blood vessel prediction model has the function of performing prediction processing on the branch-in data and the branch-out data to obtain the mechanical energy loss prediction data of the bifurcation area through the training of sample data.
The branch-in data and the branch-out data can be extracted from the three-dimensional blood flow simulation result or calculated based on the extracted data, and the mechanical energy loss of the bifurcation area is fitted through model regression to obtain the blood vessel prediction model.
The method for obtaining the blood vessel prediction model may include obtaining sample blood vessels, performing three-dimensional blood flow simulation on the sample blood vessels, extracting blood flow velocity distribution, blood flow information, blood vessel geometric parameters, and blood flow pressure of each sample blood vessel at an inlet section and an outlet section of a bifurcation region, determining inlet mechanical energy data and outlet mechanical energy data of the bifurcation region based on the blood flow velocity distribution, the blood flow information, and the blood flow pressure of the inlet section and the outlet section of the bifurcation region, and obtaining mechanical energy loss data of each sample blood vessel based on a difference between the inlet mechanical energy data and the outlet mechanical energy data. Correspondingly, a plurality of groups of sample data are formed based on the flow velocity distribution coefficients, the blood flow volume information, the geometric parameters of the blood vessels and the corresponding mechanical energy loss data of the inlet section and the outlet section of each sample blood vessel in the bifurcation area, and the blood vessel prediction model is obtained based on sample data regression.
In some embodiments, for a predicted branch (any one of multiple branches) in each of the branch data, the branch data of the incoming branch, the branch data of the predicted branch, and other branch data except the predicted branch are input into a preset blood vessel prediction model, so as to obtain mechanical energy loss prediction data corresponding to the predicted branch.
Wherein the predicted branch may be an outgoing branch requiring calculation of mechanical energy loss prediction data. For example, the processing procedure of the predicted branch can be expressed by the following expression:
Δ E = f (IN information, OUT information other than j, j bifurcation information)
The IN information is the branch-entering data of the predicted branch, namely the branch-entering data of all branch-entering of the predicted branch, and comprises characteristic point coordinates, cross-sectional areas, blood flow volume information and inlet flow velocity distribution coefficients of branch-entering areas. The OUT information other than j is the data of the predicted branch other than the predicted branch, and the information composition of the OUT information is consistent with that of the IN information. The j-branch information is the branch-out data of the predicted branch, and the composition of the j-branch information is consistent with the information composition of the IN information. j may be the index of the outgoing branch, j is a positive number and is less than or equal to the total number of outgoing branches.
In some embodiments, the incoming branch data may be used as a data set, the predicted branch data may be used as a data set, and the outgoing branch data other than j may be used as a data set, which forms a data set as input information for the vessel prediction model. In the process of predicting mechanical energy loss prediction data of any prediction branch, not only the branch-in data and the predicted branch data are considered, but also other branch-out data are used as auxiliary data, so that the accuracy of a prediction structure is improved conveniently.
In some embodiments, for a predicted branch, in other branch data than the predicted branch, upstream branch data of the predicted branch is determined, and the incoming branch data, the branch data of the predicted branch, and the upstream branch data are input into a preset blood vessel prediction model to obtain mechanical energy loss prediction data corresponding to the predicted branch.
In the above method, feature point data located upstream of the predicted branch is determined as upstream branch data for each feature point in the other branches based on the position and blood flow direction of each feature point. For example, referring to fig. 2, regarding the blood flow direction at the first characteristic point OUT31 of the third outgoing branch, the blood flow direction flows from the first characteristic point OUT31 to the second characteristic point OUT32 and flows OUT through the third outgoing branch, and the position of the first characteristic point OUT31 of the third outgoing branch is in the lower direction of the incoming branch characteristic point relative to the first characteristic point OUT11 of the first outgoing branch and the first characteristic point OUT21 of the second outgoing branch, so the upstream outgoing branches of the third outgoing branch are the first outgoing branch and the second incoming branch. Accordingly, the upstream outgoing branch of the second outgoing branch is the first outgoing branch, and the first outgoing branch does not have an upstream outgoing branch.
For example, the processing procedure of the predicted branch can be expressed by the following expression:
Δ E = f (IN information, upstream OUT information other than j, j branch information)
The IN information is the branch-entering data of the predicted branch, namely the branch-entering data of all branch-entering of the predicted branch, and comprises characteristic point coordinates, cross-sectional areas, blood flow volume information and inlet flow velocity distribution coefficients of branch-entering areas. The branch information is the branch-out data of the predicted branch, and the composition thereof is consistent with the information composition of the IN information. The upstream OUT information is upstream OUT branch data of the predicted branch.
It should be noted that the upstream outgoing branch data is empty when there is no upstream outgoing branch in the predicted branch, for example, referring to fig. 2 specifically, if the first outgoing branch where the characteristic point OUT11 is located is taken as the predicted branch and there is no upstream outgoing branch in the first outgoing branch, the upstream OUT information input is empty.
In another optional embodiment, before performing prediction processing on incoming branch data and each outgoing branch data based on a preset vessel prediction model, data integration is performed on the incoming branch data or other outgoing branch data except the predicted branch, so as to obtain first integrated data corresponding to the incoming branch data and second integrated data corresponding to the other outgoing branch data, and accordingly, prediction processing is performed on the first integrated data, the second integrated data and the predicted branch data based on the preset vessel prediction model. Through the data integration process of other branch data and branch data, the data input into the blood vessel prediction model is simplified, and the data volume processed by the blood vessel prediction model is reduced.
The data integration may be to perform weighting processing on a plurality of data corresponding to the data item for any data item in other outgoing data or incoming data, so as to obtain integrated data corresponding to the data item. Alternatively, the data integration may be performed according to data values of the same data item of a plurality of feature points in the same branch. Optionally, the data integration may be data integration of data values of the same data item at each feature point in a plurality of other outgoing branch data, and data integration of data values of the same data item at each feature point in at least one incoming branch data.
The accuracy of the blood vessel data calculation is further improved by considering the influence of the branch data except the predicted branch in the calculation.
For example, the integration process of other out-branch data and in-branch data can be expressed by the following expressions:
integrate IN information = f (IN information 1, IN information 2.)
Integrate OUT information = f (OUT information 1, OUT information 2.)
The IN information is the integrated data of all the incoming branch data of the predicted branch, for example, referring to fig. 2 specifically, the IN information 1 is the incoming branch data of the first incoming branch where the characteristic point IN11 is located, and the IN information 2 is the incoming branch data of the second incoming branch where the characteristic point IN22 is located. The OUT information is the integrated data of the outgoing data of all other outgoing branches, and the information composition of the OUT information is consistent with that of the IN information. The processing procedure corresponding to "f" in the above expression may be a weighting processing procedure. The weight of the data of any data item can be preset, and can also be determined according to the data values of other data items. Alternatively, the cross-sectional area may be used as a weight of a data value corresponding to the data item of the feature point coordinates, and may be used as a weight of a data value corresponding to the data item of the blood flow information, and the like. The manner of determining the weight of each data item is not limited.
Taking a data item of spherical coordinates as an example, spherical coordinates of each feature point in the branch data are acquired, and data integration is performed on the spherical coordinates:
wherein, IN ij Feature points for data integration, r ij Is the cross-sectional radius at the location of the vessel where the feature point is located. And theta ij is the zenith angle of the position of the blood vessel where the characteristic point is located.
Is the azimuth angle at the vessel location where the feature point is located. Ak is the cross-sectional area at the location of the vessel where the feature point is located. Alternatively, the cross-sectional area, blood flow information, inlet flow velocity profile of the bifurcation area are treated in a similar manner.
According to the technical scheme, the image data of the blood vessel to be analyzed is obtained, the bifurcation area in the blood vessel to be analyzed is determined based on the image data, the branch-in data and the branch-out data of the bifurcation area are obtained, the branch-in data and the branch-out data are subjected to prediction processing based on a preset blood vessel prediction model, and the mechanical energy loss prediction data of the bifurcation area are obtained. The calculation is carried out based on the geometric characteristics of the blood vessel bifurcation area, and the influence of factors such as the mutual influence among different branches, the blood flow form and the like is considered in the calculation, so that the accuracy of the blood vessel data calculation is improved.
As an executable embodiment, the feature point coordinates, the cross-sectional area, and the blood flow information of each outgoing branch, and the feature point coordinates, the cross-sectional area, and the blood flow information of each incoming branch are obtained, wherein the feature point coordinates and the cross-sectional area may be extracted from the image data, and the blood flow information may be a preset initial value. And predicting the mechanical energy loss data of the branch data based on the branch-out data and the branch-in data. And performing conservation verification of mechanical energy data on the branch data, if the conservation verification is not satisfied, adjusting the blood flow information in each branch data, and predicting the mechanical energy loss data again based on the adjusted outgoing branch data and incoming branch data. And iteratively executing the regression operation until the conservation verification of the mechanical energy data is met, and determining the mechanical energy loss prediction data of the conservation verification of the mechanical energy data as the target mechanical energy loss prediction data.
As an executable embodiment, the coordinates of the characteristic point, the cross-sectional area, the blood flow volume information, the distribution coefficient of the inlet flow velocity of each outgoing branch, and the coordinates of the characteristic point, the cross-sectional area, the blood flow volume information, the distribution coefficient of the inlet flow velocity of each incoming branch are obtained. The feature point coordinates and the cross-sectional area may be extracted from the image data, the blood flow volume information may be a preset initial value, and the inlet flow velocity distribution coefficient may be predicted based on the blood flow volume information. And predicting the mechanical energy loss data of the branch data based on the branch-out data and the branch-in data. And performing conservation verification of mechanical energy data on the branch data, if the conservation verification is not satisfied, adjusting the blood flow information in each branch data, updating the inlet flow rate distribution coefficient based on the adjusted blood flow information, and predicting the mechanical energy loss data again based on the adjusted outlet branch data and inlet branch data. And iteratively executing the regression operation until the conservation verification of the mechanical energy data is met, and determining the mechanical energy loss prediction data of the conservation verification of the mechanical energy data as the target mechanical energy loss prediction data.
Example two
Fig. 3 is a schematic structural diagram of a blood vessel data prediction apparatus according to a second embodiment of the present invention. As shown in fig. 3, the apparatus includes:
a bifurcation region determining module 310 for determining a bifurcation region in a blood vessel to be analyzed;
a data obtaining module 320, configured to obtain incoming branch data and outgoing branch data of the bifurcation area;
the prediction module 330 is configured to, for a predicted branch in each of the branch data, perform prediction processing on the branch entry data, the branch exit data of the predicted branch, and other branch exit data except the predicted branch based on a preset blood vessel prediction model, so as to obtain mechanical energy loss prediction data of the predicted branch relative to the entrance of the bifurcation region.
Optionally, the incoming branch data and the outgoing branch data respectively include one or more of the following items: characteristic point coordinates, cross-sectional area, blood flow information, inlet flow rate distribution coefficient of bifurcation area.
Optionally, the prediction module 330 includes:
and a first calculation unit, configured to input, to the preset blood vessel prediction model, for a predicted branch in each of the branch exit data, branch entry data of the predicted branch, and branch exit data other than the predicted branch, to obtain mechanical energy loss prediction data of the predicted branch with respect to an entrance of the bifurcation region.
Optionally, the prediction module 330 includes:
an upstream branch-out prediction unit configured to determine, for a predicted branch in each of the branch-out data, an upstream branch-out data of the predicted branch from among other branch-out data other than the predicted branch;
and the second calculation unit is used for inputting the branch-in data, the branch-out data of the predicted branch and the upstream branch-out data into the preset blood vessel prediction model to obtain the mechanical energy loss prediction data of the predicted branch relative to the entrance of the bifurcation area.
Optionally, the upstream branch prediction unit is specifically configured to:
for the feature points in each of the other outgoing branches, feature point data located upstream of the predicted branch is determined as upstream outgoing branch data based on the position and blood flow direction of each feature point.
Optionally, the prediction module 330 further includes:
an integration unit, configured to perform data integration on the incoming branch data or other outgoing branch data except the predicted branch, respectively, to obtain first integration data corresponding to the incoming branch data and second integration data corresponding to the other outgoing branch data;
and the integrated data prediction unit is used for performing prediction processing on the first integrated data, the second integrated data and the predicted branch data based on a preset blood vessel prediction model.
Optionally, the integration unit is specifically configured to:
and for any data item in the branch-in data or the other branch-out data, weighting a plurality of data items corresponding to the data item to obtain integrated data corresponding to the data item.
The blood vessel data prediction device provided by the embodiment of the invention can execute the blood vessel data prediction method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
EXAMPLE III
Fig. 4 is a schematic structural diagram of an electronic device according to a third 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. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, 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. 4, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 can 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.
A number of 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, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, 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, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. The processor 11 performs the various methods and processes described above, such as a vessel data prediction method.
In some embodiments, the blood vessel data prediction method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as 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 the RAM 13 and executed by the processor 11, one or more steps of the blood vessel data prediction method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the vessel data prediction method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a 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 that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for implementing the vessel data prediction method 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 performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.
Example four
An embodiment of the present invention further provides a computer-readable storage medium, where computer instructions are stored, and the computer instructions are used to enable a processor to execute a blood vessel data prediction method, where the method includes:
determining a bifurcation area in a blood vessel to be analyzed; acquiring branch-in data and branch-out data of the bifurcation area; and for the predicted branch in each branch data, performing prediction processing on the branch entering data, the branch data of the predicted branch and other branch data except the predicted branch based on a preset blood vessel prediction model to obtain the mechanical energy loss prediction data of the predicted branch relative to the inlet of the bifurcation area.
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. A 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 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) by which a user may 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 can 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, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end 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 back-end, 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. A client and server are generally 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 host and VPS service are overcome.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A method of predicting blood vessel data, comprising:
determining a bifurcation area in a blood vessel to be analyzed;
acquiring branch-in data and branch-out data of the bifurcation area;
and for the predicted branch in each branch-out data, performing prediction processing on the branch-in data, the branch-out data of the predicted branch and other branch-out data except the predicted branch based on a preset blood vessel prediction model to obtain mechanical energy loss prediction data of the predicted branch relative to the inlet of the bifurcation area.
2. The method of claim 1, wherein the incoming branch data and the outgoing branch data each include one or more of: characteristic point coordinates, cross-sectional area, blood flow information, inlet flow velocity distribution coefficient of bifurcation area.
3. The method according to claim 1, wherein the performing prediction processing on the incoming branch data, outgoing branch data of the predicted branch, and outgoing branch data other than the predicted branch based on a preset vessel prediction model to obtain predicted mechanical energy loss data of the predicted branch relative to the entrance of the bifurcation region comprises:
inputting branch entering data, branch exiting data of the predicted branch and other branch exiting data except the predicted branch into the preset blood vessel prediction model to obtain mechanical energy loss prediction data of the predicted branch relative to the entrance of the bifurcation area.
4. The method according to claim 1, wherein the performing prediction processing on the incoming branch data, outgoing branch data of the predicted branch, and outgoing branch data other than the predicted branch based on a preset vessel prediction model to obtain predicted mechanical energy loss data of the predicted branch relative to the entrance of the bifurcation region comprises:
determining the upstream branch data of the predicted branch in other branch data except the predicted branch;
and inputting the branch entering data, the branch exiting data of the predicted branch and the upstream branch exiting data into the preset blood vessel prediction model to obtain the mechanical energy loss prediction data of the predicted branch relative to the entrance of the bifurcation area.
5. The method of claim 4, wherein determining the outgoing branch data upstream of the predicted branch from among the outgoing branch data other than the predicted branch comprises:
for the feature points in each of the other outgoing branches, feature point data located upstream of the predicted branch is determined as upstream outgoing branch data based on the position and blood flow direction of each feature point.
6. The method according to any one of claims 1 to 5, wherein the performing prediction processing on the incoming branch data, the outgoing branch data of the predicted branch, and the outgoing branch data other than the predicted branch based on a preset vessel prediction model comprises:
respectively integrating data of the incoming branch data or other outgoing branch data except the predicted branch to obtain first integrated data corresponding to the incoming branch data and second integrated data corresponding to the other outgoing branch data;
and performing prediction processing on the first integration data, the second integration data and the predicted branch data based on a preset blood vessel prediction model.
7. The method of claim 6, wherein performing data integration on the incoming branch data or the outgoing branch data other than the predicted branch comprises:
and for any data item in the branch-in data or the other branch-out data, weighting a plurality of data items corresponding to the data item to obtain integrated data corresponding to the data item.
8. A blood vessel data prediction apparatus, comprising:
a bifurcation area determining module, which is used for determining a bifurcation area in a blood vessel to be analyzed;
the data acquisition module is used for acquiring the incoming branch data and the outgoing branch data of the bifurcation area;
and the prediction module is used for carrying out prediction processing on the branch entering data, the branch exiting data of the predicted branch and other branch exiting data except the predicted branch based on a preset blood vessel prediction model for the predicted branch in the branch exiting data to obtain the mechanical energy loss prediction data of the predicted branch relative to the inlet of the bifurcation area.
9. An electronic device, characterized in that the electronic device comprises:
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 data 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 data prediction method of any one of claims 1-7 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211358379.4A CN115661093A (en) | 2022-11-01 | 2022-11-01 | Blood vessel data prediction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211358379.4A CN115661093A (en) | 2022-11-01 | 2022-11-01 | Blood vessel data prediction method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115661093A true CN115661093A (en) | 2023-01-31 |
Family
ID=84996063
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211358379.4A Pending CN115661093A (en) | 2022-11-01 | 2022-11-01 | Blood vessel data prediction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115661093A (en) |
-
2022
- 2022-11-01 CN CN202211358379.4A patent/CN115661093A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11487995B2 (en) | Method and apparatus for determining image quality | |
| CN112906502A (en) | Training method, device and equipment of target detection model and storage medium | |
| US20150278727A1 (en) | Systems and methods for using geometry sensitivity information for guiding workflow | |
| CN113313053B (en) | Image processing method, device, apparatus, medium, and program product | |
| CN112560874A (en) | Training method, device, equipment and medium for image recognition model | |
| CN112785582A (en) | Training method and device for thermodynamic diagram generation model, electronic equipment and storage medium | |
| CN115130894A (en) | Production planning method and device based on artificial intelligence, computer equipment and medium | |
| CN113961765A (en) | Searching method, device, equipment and medium based on neural network model | |
| CN113409898A (en) | Molecular structure acquisition method and device, electronic equipment and storage medium | |
| CN116128627A (en) | Risk prediction method, risk prediction device, electronic equipment and storage medium | |
| CN113642727B (en) | Training method of neural network model and processing method and device of multimedia information | |
| US20150278976A1 (en) | Systems and methods for using geometry sensitivity information for guiding workflow | |
| CN115661093A (en) | Blood vessel data prediction method and device, electronic equipment and storage medium | |
| CN116259078A (en) | Pesticide recommendation method, device, equipment and storage medium | |
| CN115439916A (en) | Face recognition method, apparatus, device and medium | |
| CN113989899A (en) | Method, device and storage medium for determining feature extraction layer in face recognition model | |
| CN113313049A (en) | Method, device, equipment, storage medium and computer program product for determining hyper-parameters | |
| CN114972220A (en) | Image processing method and device, electronic equipment and readable storage medium | |
| CN114429786A (en) | Omics data processing method and device, electronic device and storage medium | |
| CN113361575A (en) | Model training method and device and electronic equipment | |
| CN114581751B (en) | Training method of image recognition model, image recognition method and device | |
| CN115496007A (en) | Method and device for determining blood flow mechanical energy loss, electronic equipment and medium | |
| CN115497633B (en) | Data processing method, device, equipment and storage medium | |
| CN116245853A (en) | Fractional flow reserve determination method, fractional flow reserve determination device, electronic equipment and storage medium | |
| CN115965817B (en) | Training method and device for image classification model and electronic equipment |
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 |