CN112001893B - Calculation method, device and equipment of vascular parameters and storage medium - Google Patents
Calculation method, device and equipment of vascular parameters and storage medium Download PDFInfo
- Publication number
- CN112001893B CN112001893B CN202010761635.9A CN202010761635A CN112001893B CN 112001893 B CN112001893 B CN 112001893B CN 202010761635 A CN202010761635 A CN 202010761635A CN 112001893 B CN112001893 B CN 112001893B
- Authority
- CN
- China
- Prior art keywords
- vascular
- mesh
- grid
- blood vessel
- matrix
- 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.)
- Active
Links
- 230000002792 vascular Effects 0.000 title claims abstract description 191
- 238000004364 calculation method Methods 0.000 title abstract description 28
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 134
- 239000011159 matrix material Substances 0.000 claims abstract description 114
- 238000000034 method Methods 0.000 claims abstract description 56
- 238000012549 training Methods 0.000 claims abstract description 8
- 239000013598 vector Substances 0.000 claims description 44
- 239000012530 fluid Substances 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 5
- 238000003672 processing method Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 7
- 238000010586 diagram Methods 0.000 description 17
- 230000011218 segmentation Effects 0.000 description 10
- 238000012545 processing Methods 0.000 description 9
- 238000003062 neural network model Methods 0.000 description 7
- 230000003287 optical effect Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000000004 hemodynamic effect Effects 0.000 description 5
- 239000008280 blood Substances 0.000 description 4
- 210000004369 blood Anatomy 0.000 description 4
- 238000003384 imaging method Methods 0.000 description 4
- 230000017531 blood circulation Effects 0.000 description 3
- 238000002591 computed tomography Methods 0.000 description 3
- 238000003709 image segmentation Methods 0.000 description 3
- 208000031481 Pathologic Constriction Diseases 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000036772 blood pressure Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000002059 diagnostic imaging Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 230000036262 stenosis Effects 0.000 description 2
- 208000037804 stenosis Diseases 0.000 description 2
- 206010002329 Aneurysm Diseases 0.000 description 1
- CIWBSHSKHKDKBQ-JLAZNSOCSA-N Ascorbic acid Chemical compound OC[C@H](O)[C@H]1OC(=O)C(O)=C1O CIWBSHSKHKDKBQ-JLAZNSOCSA-N 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 210000000709 aorta Anatomy 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036770 blood supply Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 210000004351 coronary vessel Anatomy 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000002595 magnetic resonance imaging Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000002560 therapeutic procedure Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000011426 transformation method Methods 0.000 description 1
- 238000012285 ultrasound imaging Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30101—Blood vessel; Artery; Vein; Vascular
- G06T2207/30104—Vascular flow; Blood flow; Perfusion
Abstract
The embodiment of the invention discloses a calculation method, a device, equipment and a storage medium of vascular parameters. The method comprises the following steps: acquiring an original blood vessel image, and determining a blood vessel grid matrix based on the original blood vessel image; and determining the blood vessel parameters corresponding to the original blood vessel image according to the blood vessel grid matrix and the pre-trained blood vessel parameter network model. The embodiment of the invention determines a vascular grid matrix based on an original vascular image; according to the vascular grid matrix and the vascular parameter network model which is trained in advance, determining vascular parameters corresponding to the original vascular image, solving the problem of complex calculation process of the vascular parameters, and adopting the vascular grid matrix to represent the original vascular image can improve the training precision of the vascular parameter network model, thereby improving the calculation accuracy and precision of the vascular parameters.
Description
Technical Field
The embodiment of the invention relates to the technical field of blood vessel images, in particular to a calculation method, a device, equipment and a storage medium of blood vessel parameters.
Background
Medical imaging techniques such as computed tomography (Computed Tomography, CT) and magnetic resonance examination (Magnetic Resonance, MR) play an important role in medical diagnosis and therapy. Especially when the imaging analysis is carried out on the blood vessel by the medical imaging technology, the current prior art mainly divides the blood vessel image by an image dividing method, so that a doctor can clearly observe the morphological structure of the target blood vessel, and further judge whether the target blood vessel has the problems of stenosis, plaque, aneurysm and the like. Further, if the doctor wants to further understand the hemodynamic parameters corresponding to the blood vessel image, such as flow resistance, the doctor needs to acquire the physiological parameters of the measured part, such as blood pressure values, through other blood flow parameter detection devices, and calculate the hemodynamic parameters based on the physiological parameters.
Further, since the blood vessel has the most important function for life activities of the human body, only the morphology and the overall blood flow parameters of the blood vessel are observed, and it is not enough to judge whether or not the blood supply of a specific target blood vessel segment is sufficient, or whether or not the stenosis of the blood vessel at that location is the main cause of influencing the abnormality of the blood flow parameters. Thus, studies on vascular kinetic parameters at arbitrary vascular locations are becoming increasingly important.
The calculation process in the prior art is complex, the requirement on calculation performance is high, the calculation time is long, the operability is not strong, and the accuracy of the obtained hemodynamic parameters is not high.
Disclosure of Invention
The embodiment of the invention provides a calculation method, a calculation device, calculation equipment and a storage medium for vascular parameters, so as to improve the calculation accuracy and precision of the vascular parameters.
In a first aspect, an embodiment of the present invention provides a method for calculating a vascular parameter, including:
acquiring an original blood vessel image, and determining a blood vessel grid matrix based on the original blood vessel image;
and determining the blood vessel parameters corresponding to the original blood vessel image according to the blood vessel grid matrix and the pre-trained blood vessel parameter network model.
In a second aspect, an embodiment of the present invention further provides a computing device for a vascular parameter, including:
the blood vessel grid matrix determining module is used for acquiring an original blood vessel image and determining a blood vessel grid matrix based on the original blood vessel image;
and the blood vessel parameter determining module is used for determining blood vessel parameters corresponding to the original blood vessel image according to the blood vessel grid matrix and the pre-trained blood vessel parameter network model.
In a third aspect, an embodiment of the present invention further provides an apparatus, including:
one or more processors;
a memory for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method of calculating vascular parameters of any of the above-described references.
In a fourth aspect, embodiments of the present invention also provide a storage medium containing computer-executable instructions which, when executed by a computer processor, are used to perform a method of calculating a vascular parameter as described in any of the above.
The embodiment of the invention determines a vascular grid matrix based on an original vascular image; according to the vascular grid matrix and the vascular parameter network model which is trained in advance, determining vascular parameters corresponding to the original vascular image, solving the problem of complex calculation process of the vascular parameters, and adopting the vascular grid matrix to represent the original vascular image can improve the training precision of the vascular parameter network model, thereby improving the calculation accuracy and precision of the vascular parameters.
Drawings
Fig. 1 is a flowchart of a method for calculating a blood vessel parameter according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a two-dimensional pixel image and a two-dimensional grid image according to a first embodiment of the present invention.
Fig. 3 is a flowchart of a calculation method of a blood vessel parameter according to a second embodiment of the present invention.
Fig. 4 is a schematic diagram of a structured grid model according to a second embodiment of the present invention.
Fig. 5 is a schematic diagram of generating a vascular mesh matrix according to a second embodiment of the present invention.
Fig. 6 is a schematic diagram of an unstructured grid model according to a second embodiment of the present invention.
Fig. 7 is a schematic diagram of a computing device for vascular parameters according to a third embodiment of the present invention.
Fig. 8 is a schematic structural diagram of an apparatus according to a fourth embodiment of the present invention.
Detailed Description
The invention is described in further detail below with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting thereof. It should be further noted that, for convenience of description, only some, but not all of the structures related to the present invention are shown in the drawings.
Example 1
Fig. 1 is a flowchart of a method for calculating a blood vessel parameter according to an embodiment of the present invention, where the method may be performed by a device for calculating a blood vessel parameter, the device may be implemented in software and/or hardware, and the device may be configured in a terminal device. The method specifically comprises the following steps:
s110, acquiring an original blood vessel image, and determining a blood vessel grid matrix based on the original blood vessel image.
In one embodiment, the raw blood vessel image comprises an image acquired by an imaging device, wherein the imaging device includes, by way of example and not limitation, at least one of a computed tomography device, a magnetic resonance imaging device, an ultrasound imaging device, and a digital imaging device.
In one embodiment, optionally, a vascular mesh model is determined according to the original vascular image, and the vascular mesh model is subjected to numerical processing to obtain a vascular mesh matrix.
In one embodiment, optionally, determining the vessel mesh model from the raw vessel image comprises: image segmentation is carried out on the original blood vessel image to obtain a blood vessel segmentation image, and three-dimensional reconstruction is carried out on the blood vessel segmentation image to obtain a blood vessel geometric model; and carrying out grid division on the vascular geometric model to obtain a vascular grid model.
The image segmentation method may be, for example, a threshold-based segmentation method, a region-based segmentation method, an edge-based segmentation method, a genetic algorithm-based segmentation method, or an active contour model-based segmentation method. The image segmentation method is not limited here. Wherein the blood vessel segmentation image refers to an image comprising only blood vessels in the original blood vessel image, and the type of blood vessels may be an aorta or a coronary artery, etc. by way of example. In one embodiment, optionally, performing three-dimensional reconstruction on the vessel segmentation image to obtain a vessel geometric model includes: extracting a central line of a target blood vessel in the blood vessel segmentation image, and determining a contour curve of the target blood vessel according to the central line; and constructing a vessel geometric model of the target vessel according to the central line and the contour curve of the target vessel. The method for extracting the central line of the target blood vessel can be based on a topology refinement method, a tracking method, a shortest path method, a distance transformation method and a similar region growing algorithm. Wherein, specifically, the meshing refers to dividing the interior and boundary of the continuous medium into discrete units of a limited size to output meshing information. The meshing method may be, for example, a transformation extension method, a Delaunay triangle method, an overlay method, and a leading edge method.
Fig. 2 is a schematic diagram of a two-dimensional pixel image and a two-dimensional grid image according to a first embodiment of the present invention. Circles in fig. 2, a, b, and c, respectively, represent images of a real object, a and b represent schematic views describing images of the real object using different pixel sizes, and c represents schematic views representing images of the real object using grids. As shown in fig. 2, the gridded representation describes the outline of a real object more accurately and with higher accuracy than the pixel representation.
In one embodiment, optionally, the meshing density is determined from a surface curvature of the vessel geometry model. The surface curvature refers to the angle between the tangential direction angle and the arc length of a certain point of the surface of the geometric model of the blood vessel, and can be used for describing the degree of deviation from a straight line. Where, illustratively, the meshing density is greater when the surface curvature is greater. When the surface curvature is smaller, the meshing density is smaller. Specifically, a mapping relationship between the surface region and the meshing density may be established, and the meshing density corresponding to the surface curvature may be determined according to the mapping relationship.
Wherein, illustratively, the digitizing process includes representing each grid in the vascular grid model in digitized form. In one embodiment, optionally, a one-dimensional vessel mesh matrix is constructed from the mesh point coordinates in the vessel mesh model. Wherein the vascular mesh matrix comprises a row vector or a column vector.
And S120, determining the blood vessel parameters corresponding to the original blood vessel image according to the blood vessel grid matrix and the pre-trained blood vessel parameter network model.
The type of the vascular parameter grid model can be a full-connection network model, a full-convolution network model or a cyclic neural network model, and can also be superposition of multiple types of network models. The type of vascular parametric network model is not limited here.
In one embodiment, optionally, the vascular parameter comprises a hemodynamic parameter at a preset position of the blood vessel. Illustratively, the preset location includes, but is not limited to, at least one of an inlet location of the blood vessel, an outlet location of the blood vessel, a center location of the blood vessel, and a location of greater surface curvature. In one embodiment, the hemodynamic parameters optionally include at least one of blood pressure, flow resistance, flow rate, flow velocity, shear force, and pressure drop between preset locations. In another embodiment, the vessel parameter optionally includes a centerline of the vessel.
In one embodiment, optionally, determining the vessel parameters corresponding to the original vessel image according to the vessel mesh matrix and the pre-trained vessel parameter network model includes: inputting the vascular grid matrix into a pre-trained vascular parameter network model to obtain output vascular parameters corresponding to the original vascular image; or inputting the vascular grid matrix and the fluid parameters into a pre-trained vascular parameter network model to obtain the output vascular parameters corresponding to the original vascular image. Exemplary fluid parameters include, but are not limited to, at least one of blood density, blood viscosity, blood average flow rate, and blood average flow rate, among others. Inputting the fluid parameters into the vascular parameter network model can further improve the accuracy of the output vascular parameters.
On the basis of the embodiment, optionally, according to the output result of the initial vascular parameter network model and the standard vascular parameter, adjusting the model parameters of the initial vascular parameter network model to obtain a trained vascular parameter network model; wherein the standard blood vessel parameters comprise blood vessel parameters calculated based on a computational fluid dynamics method. Specifically, the hydrodynamic equation used in the computational fluid dynamics method may be the Navier-Stokes equation (N-S equation).
The embodiment of the invention determines a vascular grid matrix based on an original vascular image; according to the vascular grid matrix and the vascular parameter network model which is trained in advance, determining vascular parameters corresponding to the original vascular image, solving the problem of complex calculation process of the vascular parameters, and adopting the vascular grid matrix to represent the original vascular image can improve the training precision of the vascular parameter network model, thereby improving the calculation accuracy and precision of the vascular parameters.
Example two
Fig. 3 is a flowchart of a calculation method of a blood vessel parameter according to a second embodiment of the present invention, and the technical solution of this embodiment is further refinement based on the foregoing embodiment. Optionally, the performing the digitizing processing on the vascular mesh model to obtain a vascular mesh matrix includes: dividing the vascular mesh model into at least one target mesh layer along the axis direction of the vascular mesh model, and determining a vascular mesh matrix according to mesh point coordinates of each target mesh layer; wherein the target mesh layer represents a vessel cross-section.
The specific implementation steps of the embodiment include:
s210, acquiring an original blood vessel image, and determining a blood vessel grid model according to the original blood vessel image.
In one embodiment, optionally, the vessel mesh model comprises a structured mesh model comprising a structured surface mesh and a structured volume mesh. The structured grid is characterized in that nodes in the grid system are orderly arranged, and the relation between adjacent points is clear. The surface mesh model refers to mesh cells that contain only the surface contours of the blood vessel, and the volume mesh model refers to mesh cells that include the interior regions of the blood vessel. Fig. 4 is a schematic diagram of a structured grid model according to a second embodiment of the present invention. Wherein panels a and b in fig. 4 represent a structured surface grid and a structured body grid, respectively.
S220, dividing the vascular mesh model into at least one target mesh layer along the axis direction of the vascular mesh model, and determining a vascular mesh matrix according to the mesh point coordinates of each target mesh layer.
Specifically, the axis direction of the vascular mesh model refers to the direction of the central axis of the vascular mesh model. In this embodiment, the target mesh layer represents a blood vessel cross section.
In one embodiment, optionally, when the vascular mesh model is a structured surface mesh, a first row vector is determined from the coordinates of the network points of the surface mesh cells of the first target mesh layer, a second row vector is determined from the coordinates of the network points of the surface mesh cells of the second target mesh layer adjacent to the first target mesh layer, and so on, resulting in a two-dimensional vascular mesh matrix. Wherein, illustratively, the target mesh layer of the structured surface mesh comprises mesh cells on the surface profile of the structured surface mesh. Specifically, the grid point coordinates may be used as column vectors of a two-dimensional vascular grid matrix.
In one embodiment, optionally, when the vessel mesh model is a structured body mesh, determining a first two-dimensional matrix according to grid point coordinates of the grid cells of the first target mesh layer from outside to inside, determining a second two-dimensional matrix according to grid point coordinates of the grid cells of the second target mesh layer adjacent to the first target mesh layer from outside to inside, and so on, obtaining a three-dimensional vessel mesh matrix; wherein the ith row vector of the two-dimensional matrix corresponds to the grid point coordinates of the grid cells of the ith layer of the target grid layer. Wherein, specifically, the target grid layer of the structured body grid comprises grid cells of the structured body grid from outside to inside, and exemplary, the target grid layer comprises grid cells of the 1 st layer to the n th layer of the structured body grid, wherein the grid cells of the first layer represent grid cells on the surface profile of the structured body grid, and the grid cells of the n th layer represent grid cells of the inner last layer of the structured body grid. Specifically, the grid point coordinates of the grid cells of the ith layer may be used as the ith column vector of the two-dimensional matrix.
Fig. 5 is a schematic diagram of generating a vascular mesh matrix according to a second embodiment of the present invention. Fig. 5 shows a schematic diagram of a structured surface mesh generation vessel mesh matrix, fig. 5 shows a schematic diagram of a structured volume mesh generation vessel mesh matrix. When the vascular mesh model is a structured surface mesh model, as shown in a diagram a, the vascular mesh model is divided into a plurality of target mesh layers, each target mesh layer includes a layer of mesh units on the surface contour, the mesh point coordinates of the mesh units of the layer correspond to one row vector or one column vector, each row vector or each column vector together form a two-dimensional vascular mesh matrix, and the diagram a is explained by taking the row vector corresponding to the mesh point coordinates as an example. As shown in the b-chart, when the structured mesh model is a structured volume mesh model, the vessel mesh model is divided into a plurality of target mesh layers. For each target grid layer, the target grid layer comprises grid cells of multiple layers from outside to inside, grid point coordinates of the grid cells of each layer in the target grid layer correspond to a row vector or a column vector, a plurality of row vectors or a plurality of column vectors of the multi-layer grid cell object jointly form a two-dimensional matrix, and a plurality of two-dimensional matrices of the corresponding multiple target grid layers form a three-dimensional vascular grid matrix.
The advantage of adopting the surface grid model is that fewer grid units can be used for describing the geometric structure of the blood vessel compared with a body network model, so that the number of parameters needing to be trained in the blood vessel parameter identification model is reduced, and the occupation of a memory is further reduced.
In one embodiment, optionally, when the number of row elements of the current row vector in the two-dimensional matrix is smaller than the number of row elements of the previous row vector, the number of row elements of the current row vector is complemented according to the adjacency relationship between the grid cell corresponding to the current row vector and the grid cell corresponding to the previous row vector, so that the number of row elements of each row vector in the two-dimensional matrix is the same.
Wherein, the position relation among each grid unit in the structured grid model is regularly distributed. Illustratively, taking a structured body grid as an example, one grid cell is fixed adjacent to four grid cells in four directions, and the adjacency relationship between grid cells can be automatically generated according to the grid numbers.
The present row vector is an ith row, the previous row vector is an ith-1 row, and the grid cell B and the grid cell C correspond to an ith-1 row, an nth column element and an ith-1 row, and an (n+1) th column element, respectively. The grid point coordinates corresponding to the grid cell a are respectively taken as the ith row nth column element and the ith row nth+1th column element.
On the basis of the above embodiment, optionally, the vascular mesh model includes an unstructured mesh model, and correspondingly, performing a numerical processing on the mesh model to obtain a vascular mesh matrix includes: mapping the unstructured grid model into a structured grid model, and determining a vascular grid matrix based on a numerical processing method corresponding to the structured grid model; alternatively, a one-dimensional vascular mesh matrix is determined from mesh point coordinates in the unstructured mesh model.
Wherein, in particular, the unstructured grid model comprises an unstructured surface grid model and an unstructured body grid model. Unlike structured grids, the locations of nodes in unstructured grids cannot be named sequentially with a fixed rule. Fig. 6 is a schematic diagram of an unstructured grid model according to a second embodiment of the present invention. Wherein panels a and b in fig. 6 represent unstructured surface grids and unstructured body grids, respectively. Wherein the one-dimensional vascular mesh matrix illustratively comprises one-dimensional row vectors or one-dimensional column vectors.
The grid point coordinates of the grid units in the vascular grid model are used as matrix elements of the vascular grid matrix, and the vascular grid model has the advantage that the grid point coordinates are three-dimensional floating point coordinates, and compared with the representation mode of the image pixel values, the vascular grid model has higher precision.
S230, determining the blood vessel parameters corresponding to the original blood vessel images according to the blood vessel grid matrix and the pre-trained blood vessel parameter network model.
Conventional neural network models are mostly based on matrix data for deep learning, and a dedicated neural network model is usually required to be adopted for the grid-type image, and may be, for example, a graph neural network model. That is, the number of neural network models suitable for meshing images is small. According to the technical scheme, different vascular grid matrixes are determined for different types of vascular grid models, so that the problem that grid images limit the selection of the neural network model is solved, the detection of vascular parameters can be realized by adopting a conventional neural network model, and the reusability of the vascular parameter network model is improved. Meanwhile, the original blood vessel image is represented by the blood vessel grid matrix, so that the training precision of the blood vessel parameter network model can be improved, and the calculation accuracy and precision of blood vessel parameters are further improved.
Example III
Fig. 7 is a schematic diagram of a computing device for vascular parameters according to a third embodiment of the present invention. The embodiment can be applied to the case of calculating the blood vessel parameters at the preset position of the blood vessel, the device can be realized in a software and/or hardware mode, and the device can be configured in the terminal equipment. The calculation device of the vascular parameter comprises: a vessel mesh matrix determination module 310 and a vessel parameter determination module 320.
The blood vessel grid matrix determining module 310 is configured to acquire an original blood vessel image, and determine a blood vessel grid matrix based on the original blood vessel image;
the blood vessel parameter determining module 320 is configured to determine a blood vessel parameter corresponding to the original blood vessel image according to the blood vessel mesh matrix and the pre-trained blood vessel parameter network model.
According to the technical scheme, a vascular grid matrix is determined based on an original vascular image; according to the vascular grid matrix and the vascular parameter network model which is trained in advance, determining vascular parameters corresponding to the original vascular image, solving the problem of complex calculation process of the vascular parameters, and adopting the vascular grid matrix to represent the original vascular image can improve the training precision of the vascular parameter network model, thereby improving the calculation accuracy and precision of the vascular parameters.
Based on the above technical solution, optionally, the vascular mesh matrix determining module 310 includes:
the vascular grid matrix determining unit is used for determining a vascular grid model according to the original vascular image and carrying out numerical processing on the vascular grid model to obtain a vascular grid matrix.
On the basis of the above technical solution, optionally, the vascular mesh matrix determining unit includes:
the vessel grid matrix determining subunit is used for dividing the vessel grid model into at least one target grid layer along the axis direction of the vessel grid model and determining a vessel grid matrix according to grid point coordinates of each target grid layer; wherein the target mesh layer represents a vessel cross-section.
On the basis of the above technical solution, the optional vascular grid matrix sub-determining unit is specifically configured to:
when the vascular mesh model is a structured surface mesh, determining a first row vector according to the network point coordinates of the surface mesh units of the first target mesh layer, determining a second row vector according to the mesh point coordinates of the surface mesh units of the second target mesh layer adjacent to the first target mesh layer, and the like, so as to obtain a two-dimensional vascular mesh matrix.
On the basis of the above technical solution, the optional vascular grid matrix sub-determining unit is specifically configured to:
when the vascular mesh model is a structured body mesh, determining a first two-dimensional matrix according to the mesh point coordinates of the mesh units from outside to inside of the first target mesh layer, determining a second two-dimensional matrix according to the mesh point coordinates of the mesh units from outside to inside of a second target mesh layer adjacent to the first target mesh layer, and so on to obtain a three-dimensional vascular mesh matrix; wherein the ith row vector of the two-dimensional matrix corresponds to the grid point coordinates of the grid cells of the ith layer of the target grid layer.
On the basis of the above technical solution, the optional vascular grid matrix sub-determining unit is specifically configured to:
when the number of the row elements of the current row vector in the two-dimensional matrix is smaller than that of the row elements of the previous row vector, the number of the row elements of the current row vector is complemented according to the adjacent relation between the grid cells corresponding to the current row vector and the grid cells corresponding to the previous row vector, so that the number of the row elements of each row vector in the two-dimensional matrix is the same.
On the basis of the above technical solution, optionally, the vascular mesh model includes an unstructured mesh model, and the corresponding vascular mesh matrix determining unit is specifically configured to: mapping the unstructured grid model into a structured grid model, and determining a vascular grid matrix based on a numerical processing method corresponding to the structured grid model; alternatively, a one-dimensional vascular mesh matrix is determined from mesh point coordinates in the unstructured mesh model.
Based on the above technical solution, optionally, the blood vessel parameter determining module 320 is specifically configured to:
inputting the vascular grid matrix into a pre-trained vascular parameter network model to obtain output vascular parameters corresponding to the original vascular image; or,
and inputting the vascular grid matrix and the fluid parameters into a pre-trained vascular parameter network model to obtain the output vascular parameters corresponding to the original vascular images.
On the basis of the technical scheme, the training method of the vascular parameter network model comprises the following optional steps:
according to the output result of the initial vascular parameter network model and the standard vascular parameter, the model parameters of the initial vascular parameter network model are adjusted to obtain a trained vascular parameter network model; wherein the standard blood vessel parameters comprise blood vessel parameters calculated based on a computational fluid dynamics method.
The calculation device of the vascular parameter provided by the embodiment of the invention can be used for executing the calculation method of the vascular parameter provided by the embodiment of the invention, and has the corresponding functions and beneficial effects of the execution method.
It should be noted that, in the embodiment of the computing device for vascular parameters, each unit and module included are only divided according to the functional logic, but not limited to the above-mentioned division, so long as the corresponding functions can be implemented; in addition, the specific names of the functional units are also only for distinguishing from each other, and are not used to limit the protection scope of the present invention.
Example IV
Fig. 8 is a schematic structural diagram of an apparatus according to a fourth embodiment of the present invention, where the embodiment of the present invention provides services for implementing the method for calculating a blood vessel parameter according to the foregoing embodiment of the present invention, and the computing device for a blood vessel parameter according to the foregoing embodiment of the present invention may be configured. Fig. 8 illustrates a block diagram of an exemplary device 12 suitable for use in implementing embodiments of the present invention. The device 12 shown in fig. 8 is merely an example and should not be construed as limiting the functionality and scope of use of embodiments of the present invention.
As shown in fig. 8, device 12 is in the form of a general purpose computing device. Components of device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, a bus 18 that connects the various system components, including the system memory 28 and the processing units 16.
Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor, and a local bus using any of a variety of bus architectures. By way of example, and not limitation, such architectures include Industry Standard Architecture (ISA) bus, micro channel architecture (MAC) bus, enhanced ISA bus, video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Device 12 typically includes a variety of computer system readable media. Such media can be any available media that is accessible by device 12 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM) 30 and/or cache memory 32. Device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from or write to non-removable, nonvolatile magnetic media (not shown in FIG. 8, commonly referred to as a "hard disk drive"). Although not shown in fig. 8, a magnetic disk drive for reading from and writing to a removable non-volatile magnetic disk (e.g., a "floppy disk"), and an optical disk drive for reading from or writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In such cases, each drive may be coupled to bus 18 through one or more data medium interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored in, for example, memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each or some combination of which may include an implementation of a network environment. Program modules 42 generally perform the functions and/or methods of the embodiments described herein.
Device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), one or more devices that enable a user to interact with device 12, and/or any devices (e.g., network card, modem, etc.) that enable device 12 to communicate with one or more other computing devices. Such communication may occur through an input/output (I/O) interface 22. Also, device 12 may communicate with one or more networks such as a Local Area Network (LAN), a Wide Area Network (WAN) and/or a public network, such as the Internet, via network adapter 20. As shown in fig. 8, network adapter 20 communicates with other modules of device 12 over bus 18. It should be appreciated that although not shown, other hardware and/or software modules may be used in connection with device 12, including, but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, data backup storage systems, and the like.
The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, for example, implementing the calculation method of blood vessel parameters provided by the embodiment of the present invention.
By the device, the problem of complex calculation process of the blood vessel parameters is solved, and the training precision of the blood vessel parameter network model can be improved by adopting the blood vessel grid matrix to express the original blood vessel image, so that the calculation accuracy and precision of the blood vessel parameters are improved.
Example five
A fifth embodiment of the present invention also provides a storage medium containing computer-executable instructions, which when executed by a computer processor, are configured to perform a method of calculating a vascular parameter, the method comprising:
acquiring an original blood vessel image, and determining a blood vessel grid matrix based on the original blood vessel image;
and determining the blood vessel parameters corresponding to the original blood vessel image according to the blood vessel grid matrix and the pre-trained blood vessel parameter network model.
The computer storage media of embodiments of the invention may take the form of any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium would include the following: an electrical connection having 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. In this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
The computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, either in baseband or as part of a carrier wave. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations of the present invention may be written in one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).
Of course, the storage medium containing the computer executable instructions provided in the embodiments of the present invention is not limited to the above method operations, and may also perform the related operations in the method for calculating the vascular parameter provided in any embodiment of the present invention.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (11)
1. A method of calculating a vascular parameter, comprising:
acquiring an original blood vessel image, and determining a blood vessel grid matrix based on the original blood vessel image;
determining a blood vessel parameter corresponding to the original blood vessel image according to the blood vessel grid matrix and a pre-trained blood vessel parameter network model;
the determining a vessel mesh matrix based on the original vessel image comprises:
determining a vascular grid model according to the original vascular image, and carrying out numerical treatment on the vascular grid model to obtain a vascular grid matrix;
the step of carrying out numerical treatment on the vascular mesh model to obtain a vascular mesh matrix comprises the following steps:
dividing the vascular mesh model into at least one target mesh layer along the axis direction of the vascular mesh model, and determining a vascular mesh matrix according to mesh point coordinates of each target mesh layer; wherein the target mesh layer represents a vessel cross-section.
2. The method of claim 1, wherein the vessel mesh model comprises a structured mesh model comprising a structured surface mesh and a structured volume mesh.
3. The method of claim 1, wherein said determining a vascular mesh matrix from mesh point coordinates of each of said target mesh layers comprises:
when the vascular mesh model is a structured surface mesh, determining a first row vector according to the network point coordinates of the surface mesh units of the first target mesh layer, determining a second row vector according to the mesh point coordinates of the surface mesh units of the second target mesh layer adjacent to the first target mesh layer, and the like, so as to obtain a two-dimensional vascular mesh matrix.
4. The method of claim 1, wherein said determining a vascular mesh matrix from mesh point coordinates of each of said target mesh layers comprises:
when the vascular mesh model is a structured body mesh, determining a first two-dimensional matrix according to the mesh point coordinates of the mesh units from outside to inside of a first target mesh layer, determining a second two-dimensional matrix according to the mesh point coordinates of the mesh units from outside to inside of a second target mesh layer adjacent to the first target mesh layer, and so on to obtain a three-dimensional vascular mesh matrix; wherein the ith row vector of the two-dimensional matrix corresponds to the grid point coordinates of the grid cells of the ith layer of the target grid layer.
5. The method of claim 4, wherein said determining a vascular mesh matrix from mesh point coordinates of each of said target mesh layers comprises:
when the number of the row elements of the current row vector in the two-dimensional matrix is smaller than that of the row elements of the previous row vector, the number of the row elements of the current row vector is complemented according to the adjacent relation between the grid cells corresponding to the current row vector and the grid cells corresponding to the previous row vector, so that the number of the row elements of each row vector in the two-dimensional matrix is the same.
6. The method of claim 1, wherein the vascular mesh model comprises an unstructured mesh model, and wherein the digitizing the vascular mesh model, accordingly, results in a vascular mesh matrix, comprising:
mapping the unstructured grid model into a structured grid model, and determining a vascular grid matrix based on a numerical processing method corresponding to the structured grid model; or,
and determining a one-dimensional vascular mesh matrix according to the mesh point coordinates in the unstructured mesh model.
7. The method of claim 1, wherein said determining a vessel parameter corresponding to the original vessel image from the vessel mesh matrix and a pre-trained vessel parameter network model comprises:
inputting the vascular grid matrix into a pre-trained vascular parameter network model to obtain output vascular parameters corresponding to the original vascular image; or,
and inputting the vascular grid matrix and the fluid parameters into a pre-trained vascular parameter network model to obtain the output vascular parameters corresponding to the original vascular image.
8. The method of claim 1, wherein the training method of the vascular parameter network model comprises:
adjusting model parameters of the initial vascular parameter network model according to an output result of the initial vascular parameter network model and standard vascular parameters to obtain a trained vascular parameter network model; wherein the standard blood vessel parameters comprise blood vessel parameters calculated based on a computational fluid dynamics method.
9. A computing device for vascular parameters, comprising:
the blood vessel grid matrix determining module is used for acquiring an original blood vessel image and determining a blood vessel grid matrix based on the original blood vessel image;
the blood vessel parameter determining module is used for determining blood vessel parameters corresponding to the original blood vessel image according to the blood vessel grid matrix and a pre-trained blood vessel parameter network model;
the vascular mesh matrix determination module further includes:
the blood vessel grid matrix determining unit is used for determining a blood vessel grid model according to the original blood vessel image and carrying out numerical treatment on the blood vessel grid model to obtain a blood vessel grid matrix;
the vascular mesh matrix determination unit further includes:
the vessel grid matrix determining subunit is used for dividing the vessel grid model into at least one target grid layer along the axis direction of the vessel grid model and determining a vessel grid matrix according to grid point coordinates of each target grid layer; wherein the target mesh layer represents a vessel cross-section.
10. An apparatus, comprising:
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, causes the one or more processors to implement the method of calculating a vascular parameter as claimed in any one of claims 1 to 8.
11. A storage medium containing computer executable instructions which, when executed by a computer processor, are for performing the method of calculating a vascular parameter as claimed in any one of claims 1 to 8.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010761635.9A CN112001893B (en) | 2020-07-31 | 2020-07-31 | Calculation method, device and equipment of vascular parameters and storage medium |
| PCT/CN2020/138408 WO2022001026A1 (en) | 2020-06-30 | 2020-12-22 | Systems and methods for determining blood vessel parameters |
| US18/149,040 US20230134402A1 (en) | 2020-06-30 | 2022-12-30 | Systems and methods for determining blood vessel parameters |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010761635.9A CN112001893B (en) | 2020-07-31 | 2020-07-31 | Calculation method, device and equipment of vascular parameters and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112001893A CN112001893A (en) | 2020-11-27 |
| CN112001893B true CN112001893B (en) | 2024-02-20 |
Family
ID=73464182
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010761635.9A Active CN112001893B (en) | 2020-06-30 | 2020-07-31 | Calculation method, device and equipment of vascular parameters and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112001893B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022001026A1 (en) * | 2020-06-30 | 2022-01-06 | Shanghai United Imaging Healthcare Co., Ltd. | Systems and methods for determining blood vessel parameters |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015059706A2 (en) * | 2013-10-24 | 2015-04-30 | Cathworks Ltd. | Vascular characteristic determination with correspondence modeling of a vascular tree |
| CN106887000A (en) * | 2017-01-23 | 2017-06-23 | 上海联影医疗科技有限公司 | The gridding processing method and its system of medical image |
| WO2018133118A1 (en) * | 2017-01-23 | 2018-07-26 | 上海联影医疗科技有限公司 | System and method for analyzing blood flow state |
| CN108564574A (en) * | 2018-04-11 | 2018-09-21 | 上海联影医疗科技有限公司 | Determine method, computer equipment and the computer readable storage medium of blood flow reserve score |
| CN109064559A (en) * | 2018-05-28 | 2018-12-21 | 杭州阿特瑞科技有限公司 | Vascular flow analogy method and relevant apparatus based on mechanical equation |
| CN109461138A (en) * | 2018-09-29 | 2019-03-12 | 深圳睿心智能医疗科技有限公司 | Calculation method of parameters, system, readable storage medium storing program for executing and computer equipment |
| CN109524119A (en) * | 2018-11-09 | 2019-03-26 | 深圳市孙逸仙心血管医院（深圳市心血管病研究所） | Based on GAN blood flow reserve Score on Prediction method, apparatus, equipment and medium |
| US10249048B1 (en) * | 2017-11-15 | 2019-04-02 | Beijing Curacloud Technology Co., Ltd. | Method and system for predicting blood flow features based on medical images |
| CN109559326A (en) * | 2018-11-05 | 2019-04-02 | 深圳睿心智能医疗科技有限公司 | A kind of hemodynamic parameter calculation method, system and electronic equipment |
| CN110070534A (en) * | 2018-05-22 | 2019-07-30 | 深圳科亚医疗科技有限公司 | For obtaining the method for characteristic sequence and the device of prediction blood flow reserve score automatically based on blood-vessel image |
| CN110634572A (en) * | 2019-09-24 | 2019-12-31 | 杭州阿特瑞科技有限公司 | Blood vessel blood flow simulation method based on mechanical equation and related device |
| EP3654281A1 (en) * | 2018-11-15 | 2020-05-20 | General Electric Company | Deep learning for arterial analysis and assessment |
| CN111317455A (en) * | 2020-03-03 | 2020-06-23 | 上海联影医疗科技有限公司 | Method, device and equipment for determining hemodynamic parameters and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6380949B2 (en) * | 2014-07-17 | 2018-08-29 | 富士通株式会社 | Visualization device, visualization method, and visualization program |
-
2020
- 2020-07-31 CN CN202010761635.9A patent/CN112001893B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015059706A2 (en) * | 2013-10-24 | 2015-04-30 | Cathworks Ltd. | Vascular characteristic determination with correspondence modeling of a vascular tree |
| CN106887000A (en) * | 2017-01-23 | 2017-06-23 | 上海联影医疗科技有限公司 | The gridding processing method and its system of medical image |
| WO2018133118A1 (en) * | 2017-01-23 | 2018-07-26 | 上海联影医疗科技有限公司 | System and method for analyzing blood flow state |
| US10249048B1 (en) * | 2017-11-15 | 2019-04-02 | Beijing Curacloud Technology Co., Ltd. | Method and system for predicting blood flow features based on medical images |
| CN108564574A (en) * | 2018-04-11 | 2018-09-21 | 上海联影医疗科技有限公司 | Determine method, computer equipment and the computer readable storage medium of blood flow reserve score |
| CN110070534A (en) * | 2018-05-22 | 2019-07-30 | 深圳科亚医疗科技有限公司 | For obtaining the method for characteristic sequence and the device of prediction blood flow reserve score automatically based on blood-vessel image |
| CN109064559A (en) * | 2018-05-28 | 2018-12-21 | 杭州阿特瑞科技有限公司 | Vascular flow analogy method and relevant apparatus based on mechanical equation |
| CN109461138A (en) * | 2018-09-29 | 2019-03-12 | 深圳睿心智能医疗科技有限公司 | Calculation method of parameters, system, readable storage medium storing program for executing and computer equipment |
| CN109559326A (en) * | 2018-11-05 | 2019-04-02 | 深圳睿心智能医疗科技有限公司 | A kind of hemodynamic parameter calculation method, system and electronic equipment |
| CN109524119A (en) * | 2018-11-09 | 2019-03-26 | 深圳市孙逸仙心血管医院（深圳市心血管病研究所） | Based on GAN blood flow reserve Score on Prediction method, apparatus, equipment and medium |
| EP3654281A1 (en) * | 2018-11-15 | 2020-05-20 | General Electric Company | Deep learning for arterial analysis and assessment |
| CN111192316A (en) * | 2018-11-15 | 2020-05-22 | 通用电气公司 | Deep learning for artery analysis and assessment |
| CN110634572A (en) * | 2019-09-24 | 2019-12-31 | 杭州阿特瑞科技有限公司 | Blood vessel blood flow simulation method based on mechanical equation and related device |
| CN111317455A (en) * | 2020-03-03 | 2020-06-23 | 上海联影医疗科技有限公司 | Method, device and equipment for determining hemodynamic parameters and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 面向血管疾病诊断及预测分析的血流动力学模拟综述;徐梦佳等;《中国图象图形学报》;第20卷(第3期);第297-320页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112001893A (en) | 2020-11-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112446866B (en) | Blood flow parameter calculation method, device, equipment and storage medium | |
| US20210272030A1 (en) | Systems and methods for using geometry sensitivity information for guiding workflow | |
| CN112446867B (en) | Method, device, equipment and storage medium for determining blood flow parameters | |
| US20230104173A1 (en) | Method and system for determining blood vessel information in an image | |
| US10874461B2 (en) | Systems and methods for determining and visualizing a functional relationship between a vascular network and perfused tissue | |
| CN111815598B (en) | Calculation method, device and equipment of vascular parameters and storage medium | |
| Morales Ferez et al. | Deep learning framework for real-time estimation of in-silico thrombotic risk indices in the left atrial appendage | |
| US11861851B2 (en) | Anatomical and functional assessment of CAD using machine learning | |
| CN112419484B (en) | Three-dimensional vascular synthesis method, system, coronary artery analysis system and storage medium | |
| CN111640124B (en) | Blood vessel extraction method, device, equipment and storage medium | |
| KR20220032067A (en) | Data processing methods, devices, devices and storage media | |
| Meuschke et al. | Classification of blood flow patterns in cerebral aneurysms | |
| CN112150454A (en) | Aortic dissection assessment method, device, equipment and storage medium | |
| CN114004793A (en) | Blood flow characteristic acquisition method and device, electronic equipment and storage medium | |
| CN112001893B (en) | Calculation method, device and equipment of vascular parameters and storage medium | |
| CN115731232A (en) | Blood vessel image processing method and device, readable storage medium and electronic equipment | |
| CN113205488B (en) | Blood flow characteristic prediction method, device, electronic equipment and storage medium | |
| US20150278976A1 (en) | Systems and methods for using geometry sensitivity information for guiding workflow | |
| Pajaziti et al. | Shape-driven deep neural networks for fast acquisition of aortic 3D pressure and velocity flow fields | |
| CN115049582A (en) | Multi-task learning framework for fully automated assessment of coronary artery disease | |
| JP6748370B2 (en) | Biological model generation device, biological model generation method, and biological model generation program | |
| CN112419308B (en) | Plaque evaluation method, plaque evaluation device, electronic equipment and storage medium | |
| US20240135550A1 (en) | Anatomical and functional assessment of cad using machine learning | |
| CN116363243A (en) | Method, device and storage medium for determining cylindrical projection image of blood vessel | |
| Kostiris | From pixels to clinical insight: Computer vision and deep learning for automated left ventricular segmentation and ejection fraction prediction in pediatric echocardiography videos |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |