CN117495668B - Method, device and medium for determining a main vessel path and a branch vessel path - Google Patents
Method, device and medium for determining a main vessel path and a branch vessel path Download PDFInfo
- Publication number
- CN117495668B CN117495668B CN202311854766.1A CN202311854766A CN117495668B CN 117495668 B CN117495668 B CN 117495668B CN 202311854766 A CN202311854766 A CN 202311854766A CN 117495668 B CN117495668 B CN 117495668B
- Authority
- CN
- China
- Prior art keywords
- point
- path
- points
- determining
- branch vessel
- 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
- 238000000034 method Methods 0.000 title claims abstract description 62
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 43
- 238000004422 calculation algorithm Methods 0.000 claims description 55
- 230000004044 response Effects 0.000 claims description 14
- 238000010845 search algorithm Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 4
- 230000002792 vascular Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 238000002591 computed tomography Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 238000000605 extraction Methods 0.000 description 6
- 238000009499 grossing Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000002595 magnetic resonance imaging Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 230000005855 radiation Effects 0.000 description 3
- FESBVLZDDCQLFY-UHFFFAOYSA-N sete Chemical compound [Te]=[Se] FESBVLZDDCQLFY-UHFFFAOYSA-N 0.000 description 3
- 238000010968 computed tomography angiography Methods 0.000 description 2
- 238000003066 decision tree Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003628 erosive effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000002829 reductive effect Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 206010002329 Aneurysm Diseases 0.000 description 1
- 206010060965 Arterial stenosis Diseases 0.000 description 1
- 208000002251 Dissecting Aneurysm Diseases 0.000 description 1
- 206010028980 Neoplasm Diseases 0.000 description 1
- 208000002223 abdominal aortic aneurysm Diseases 0.000 description 1
- 210000000709 aorta Anatomy 0.000 description 1
- 208000007474 aortic aneurysm Diseases 0.000 description 1
- 206010002895 aortic dissection Diseases 0.000 description 1
- 210000001765 aortic valve Anatomy 0.000 description 1
- 210000001367 artery Anatomy 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000001727 in vivo Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013421 nuclear magnetic resonance imaging Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 210000000115 thoracic cavity Anatomy 0.000 description 1
- 238000012285 ultrasound imaging Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/20—Drawing from basic elements, e.g. lines or circles
- G06T11/203—Drawing of straight lines or curves
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2210/00—Indexing scheme for image generation or computer graphics
- G06T2210/41—Medical
Abstract
The present disclosure provides a method, apparatus and medium for determining a main vessel path and a branch vessel path, comprising: receiving three-dimensional model data of a blood vessel and converting the received three-dimensional model data into a point cloud set; determining invalid points and valid points comprising end points, connecting points and bifurcation points in the point cloud set; a main vessel path and a branch vessel path relative to the main vessel path are determined based on the end point, the junction point, and the bifurcation point.
Description
Technical Field
The present invention relates generally to the field of medical image processing, and more particularly, to a method, computing device, and computer readable storage medium for determining a main vessel path and a branch vessel path.
Background
Aneurysms, arterial thrombi, aortic dissection, arterial stenosis, etc. the doctor needs to perform operations such as EVER (Abdominal aortic aneurysm transluminal repair), TEVER (thoracic aortic transluminal repair), TAVR (transcatheter aortic valve replacement), etc. With the application of dynamic medical imaging technology, such as multidimensional dynamic CT (computed tomography (Computed Tomography), 4D nuclear magnetic imaging and the like, the method provides possibility for carrying out in-vivo stress or strain analysis on blood vessels.
At present, data of aortic artery CTA (CT angiography) is input for reconstruction, central lines of an aorta and a branch vessel of a model area are manually generated, and then blood vessel related parameters are measured. Currently, three-dimensional skeleton extraction algorithms are relatively common ways to extract centerlines. The result of the three-dimensional skeleton extraction algorithm is a point cloud image, only a rough center line point cloud image can be obtained, only the point cloud can be displayed, the center line of each trunk and each branch cannot be distinguished, and the point cloud image cannot be used for calculation. Subsequent calculations and processing are required. The algorithm cannot identify the main and branch vessel paths in the vessel. Even by manually selecting the main vessel path, it is difficult to find a branch vessel path connected to the main vessel and a lower branch vessel path connected to the branch vessel path, even a branch vessel path of a lower level. Aiming at point cloud data with numerous branches, the user operation is complicated and repeated.
Therefore, a technology for determining a main blood vessel path and a branch blood vessel path based on three-dimensional point cloud data is needed to automatically and accurately determine the main blood vessel path and the branch blood vessel path, and cumbersome selection of a user is reduced.
Disclosure of Invention
In view of at least one of the above problems, the present invention provides a solution for determining a main vessel path and a branch vessel path based on automatically extracting model features. By using computer vision and machine learning techniques, the trunk centerline is automatically calculated based on the input of the start and end points of the trunk centerline, and the lower level of the branch centerline, without additional input, is automatically located and judged. The calculation result distinguishes each complete trunk and branch central line data, and can be used for subsequent calculation or analysis.
According to one aspect of the present invention, there is provided a method for determining a main vessel path and a branch vessel path, comprising: receiving three-dimensional model data of a blood vessel and converting the received three-dimensional model data into a point cloud set; determining invalid points and valid points comprising end points, connecting points and bifurcation points in the point cloud set; determining a main vessel path and a branch vessel path relative to the main vessel path based on the end point, the junction point and the bifurcation point, wherein the end point or bifurcation point is started with the bifurcation point and the relative neighborhood N 3 -end point, connection point and bifurcation point connection in 1 pixel point, said connection being repeated until connected to end point or bifurcation point as end point, thereby obtaining adjacent edges of point-to-point connection based on selected start position and endAnd determining a starting point and an ending point on the adjacent sides, and determining a shortest path from the starting point to the ending point through the adjacent sides based on a shortest path planning algorithm, so that the shortest path is determined as a main blood vessel path, and a main blood vessel path and a branch blood vessel path are determined.
In one embodiment, determining a main vessel path and a branch vessel path relative to the main vessel path further comprises: determining all bifurcation points on the main vessel path, thereby taking the all bifurcation points as candidate starting points of branch vessel paths; executing a branch vessel path retrieval algorithm based on the candidate starting point to determine a branch vessel path connected to the main vessel path; and determining whether all bifurcation points exist on the branch vessel path.
In one embodiment, determining whether all bifurcation points exist on the branch vessel path includes: determining the branch vessel path as a final branch vessel path in response to the branch vessel path not having all bifurcation points present thereon; in response to the existence of all bifurcation points on the branch vessel path, again determining all bifurcation points on the branch vessel path as candidate starting points, repeatedly executing the branch vessel path retrieval algorithm to determine a subordinate branch vessel path connected to the determined branch vessel path.
In one embodiment, the branch vessel path retrieval algorithm includes: determining a plurality of shortest paths taking the candidate starting point as a starting point and the ending point as an ending point as candidate branch vessel paths based on a shortest path planning algorithm; screening candidate branch vessel paths meeting a threshold condition based on a minimum length threshold value of the branch vessel path, a maximum perimeter threshold value of the branch vessel and a minimum angle threshold value of the branch vessel path; and determining the candidate branch vessel path with the largest minimum angle value in the candidate branch vessel paths meeting the threshold condition as the branch vessel path.
In one embodiment, determining invalid points and valid points including end points, connection points, and bifurcation points in the set of point clouds comprises: determining non-0 images in the three-dimensional model dataPixel points of the pixel values are calculated, and therefore the relative neighborhood N of the pixel points is calculated 3 -the number of pixels of non-0 pixel value of 1 pixel, wherein N is a natural number equal to or greater than 2; responsive to pixel relative neighborhood N 3 -determining a pixel point as an invalid point when the number of pixels of non-0 pixel values of 1 pixel point is 0; responsive to pixel relative neighborhood N 3 -determining a pixel point as an end point in the valid points when the number of pixels of the non-0 pixel value of the 1 pixel points is 1; responsive to pixel relative neighborhood N 3 -determining a pixel point as a connection point in an active point when the number of pixels of non-0 pixel values of 1 pixel point is 2; and responsive to the pixel relative neighborhood N 3 -determining a pixel point as a bifurcation point in the effective points when the number of pixels of non-0 pixel values of 1 pixel point is greater than 2.
In one embodiment, the shortest path planning algorithm is a shortest path planning algorithm that searches for a vascular shortest path based on improvements of the dijkstra algorithm and the depth first search algorithm.
In one embodiment, the shortest path planning algorithm comprises: determining the starting point and the ending point of a blood vessel, and randomly determining a path; traversing each effective point on the determined path from the end point upwards in turn, and searching the path distance reversely to determine a potential path; and determining the shortest path among the potential paths as the optimal path based on the shortest distance condition, thereby determining the shortest path of the blood vessel.
According to another aspect of the present invention, a computing device is provided. The computing device includes: at least one processor; and at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions when executed by the at least one processor, cause the computing device to perform steps according to the method described above.
According to yet another aspect of the present invention, there is provided a computer readable storage medium having stored thereon computer program code which, when executed, performs a method as described above.
Drawings
The invention will be better understood and other objects, details, features and advantages of the invention will become more apparent by reference to the following description of specific embodiments thereof, which is given in the accompanying drawings.
Fig. 1 shows a schematic diagram of a system 1 for implementing a method for determining a main vessel path and a branch vessel path according to an embodiment of the invention.
Fig. 2 illustrates a flow chart of a method 200 for determining a main vessel path and a branch vessel path according to some embodiments of the invention.
Fig. 3 illustrates a flow chart of a method 300 for determining a main vessel path according to some embodiments of the invention.
Fig. 4 shows a schematic diagram of a shortest path planning algorithm according to an embodiment of the present disclosure.
Fig. 5 illustrates a flow chart of a method 500 for determining a branch vessel path according to some embodiments of the invention.
Fig. 6 illustrates a flow chart of a method 600 for determining a center point of a main vessel path and a branch vessel path according to some embodiments of the invention.
Fig. 7 shows a schematic diagram of determining a center point of the main and branch vessel paths according to an embodiment of the present disclosure.
Fig. 8 illustrates a block diagram of a computing device 800 suitable for implementing embodiments of the invention.
Detailed Description
Preferred embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. While the preferred embodiments of the present invention are shown in the drawings, it should be understood that the present invention may be embodied in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art.
In the following description, for the purposes of explanation of various inventive embodiments, certain specific details are set forth in order to provide a thorough understanding of the various inventive embodiments. One skilled in the relevant art will recognize, however, that an embodiment may be practiced without one or more of the specific details. In other instances, well-known devices, structures, and techniques associated with this application may not be shown or described in detail to avoid unnecessarily obscuring the description of the embodiments.
Throughout the specification and claims, unless the context requires otherwise, the word "comprise" and variations such as "comprises" and "comprising" will be understood to be open-ended, meaning of inclusion, i.e. to be interpreted to mean "including, but not limited to.
Reference throughout this specification to "one embodiment" or "some embodiments" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, appearances of the phrases "in one embodiment" or "in some embodiments" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Furthermore, the terms first, second, third, fourth and the like in the description and in the claims, are used for descriptive purposes only and not for limiting the size or other order of the objects described.
Fig. 1 shows a schematic diagram of a system 1 for implementing a method for determining a main vessel path and a branch vessel path according to an embodiment of the invention. As shown in fig. 1, the system 1 may comprise a console 10, a scanning bed 20 and a radiation generator 30, which may be, for example, a CT system. In operation of the system 1, a patient may lie on the scanning bed 20 and a doctor or operator may control the movement of the scanning bed 20 via the console 10 such that radiation from the radiation generator 30 scans a specific portion of the patient and three-dimensional model data (e.g., a three-dimensional point cloud) generated by the scan is returned to the console 10. Herein, the three-dimensional model data (e.g., three-dimensional point cloud set) is not limited to CT images, but may include MRI (magnetic resonance imaging, nuclear Magnetic Resonance Imaging) images, vascular ultrasound imaging images, etc., and the system 1 may have different structures and forms depending on the type of the three-dimensional model data (e.g., three-dimensional point cloud set), not limited to the specific structure and form shown in fig. 1.
At the console 10, or at another computing device (e.g., a physician's computing device, not shown) separate from the console 10, the three-dimensional model data (e.g., a three-dimensional point cloud set) generated as described above may be processed and analyzed to obtain the desired results. In this case, the console 10 or another computing device (also referred to herein collectively as a computing device) may include at least one processor and at least one memory coupled with the at least one processor, the memory having stored therein instructions executable by the at least one processor, which when executed by the at least one processor, perform at least a portion of the methods as described below. The specific structure of the computing device may be described, for example, in connection with fig. 8 as follows.
The Dijkstra algorithm is an algorithm proposed in 1959 by the netherlands computer science diecktra, and is a shortest path algorithm from one vertex to the rest of the vertices, and solves the problem of the shortest path in the weighted graph. The main principle of the Di Jie Style algorithm is that starting from a starting point, a greedy algorithm strategy is adopted, and each time the algorithm traverses to the adjacent nodes of the vertex which is nearest to the starting point and is not visited until the algorithm extends to the end point.
The depth-FIRST-SEARCH algorithm is a SEARCH algorithm for traversing, searching trees or graphs. The sense of search is as the name implies: recursion is performed first, and then backtracking is performed. That is, when one needs to search for an object in a graph, a search tree, or a traversal, the DFS will first go all the way to the bottom until it can no longer go down, return if an object is found, go back to the place of the last step if no one is found, and then repeat the above process with another way until an object is found or all objects are found.
The bezier curve is a mathematical curve applied to a graphics application program, and is determined by a set of vectors called control points, the given control points are sequentially connected to form a control polygon, the bezier curve approximates the polygon, and the shape of the curve is changed by adjusting the coordinates of the control points. By means of the Bezier curve, a smooth curve can be obtained under the condition that the original trend form of the input center point set is not changed.
Fig. 2 illustrates a flow chart of a method 200 for determining a main vessel path and a branch vessel path according to some embodiments of the invention. The method 200 may be performed, for example, by the console 10 or another computing device in the system 1 shown in fig. 1. The method 200 is described below in connection with fig. 1-8, taking as an example execution in the console 10.
In step 202, three-dimensional model data of a blood vessel may be received and the received image data converted into a point cloud set.
In one embodiment, three-dimensional medical image data, such as three-dimensional model data of CT (computed tomography) or MRI (magnetic resonance imaging), may be used and converted into a point cloud form for subsequent processing. This can be achieved by image processing and computational geometry methods. Specifically, a three-dimensional skeleton extraction algorithm may be used to extract a skeleton point set of a three-dimensional stereoscopic image, which is equivalent to a point cloud set. The core principle of the three-dimensional skeleton extraction algorithm is that image erosion operation (based on a decision tree method) is iterated, and the image is reduced to a central axis position of the image until only the skeleton of the image remains. To ensure that the correct center point data is obtained, the image erosion operation must be performed symmetrically. The decision tree method is an iterative process (N 3 -1) all possible binary combinations of object and background voxels in the neighborhood of the pixel point, and finding all deletable surface points at each iteration, where N is a natural number equal to or higher than 2, e.g. when N is equal to 3, the algorithm calculates 26 neighborhood pixels around the pixel point. The input to this algorithm is a binarized image, and for a voxel with a voxel value of 1 as the target region, a voxel with a voxel value of 0 as the background region. And outputting the point cloud images of 1 voxel grid through iterative computation for a plurality of times.
Through the technical means, the point cloud image which is not marked can be output by utilizing the three-dimensional skeleton extraction algorithm, and the point cloud image is subjected to pixel point extraction, classification and processing to obtain a set of nodes and adjacent edges. For example, based on the three-dimensional model data M1 of the blood vessel, a point cloud set M2 that can exhibit a rough centerline trajectory of the blood vessel is obtained by a mature skeletonizing algorithm.
In step 204, invalid points and valid points including end points, connection points, and bifurcation points may be determined in the point cloud collection.
In one embodiment, invalid points, such as noise or outliers, may be identified and excluded by geometric features in the point cloud set. The effective point is determined, which may include an end point (end of a blood vessel), a junction point (junction of the blood vessel), and a bifurcation point (bifurcation of the blood vessel). Determining invalid points and valid points including end points, connection points, and bifurcation points in the point cloud collection includes:
specifically, a pixel point of the three-dimensional model data that is not a 0 pixel value may be determined, thereby calculating the relative neighborhood (N 3 -1) the number of pixels of non-0 pixel value of the pixels, wherein N is a natural number of 2 or more; in response to the relative neighborhood of pixels (N 3 -1) when the number of pixel points of non-0 pixel value is 0, determining the pixel points as invalid points; in response to the relative neighborhood of pixels (N 3 -1) determining the pixel point as an end point in the valid points when the number of the pixel points with non-0 pixel value of the pixel points is 1; in response to the relative neighborhood of pixels (N 3 -1) determining the pixel points as connection points in the effective points when the number of the pixel points with non-0 pixel value of the pixel points is 2; and responsive to the pixel relative neighborhood (N 3 -1) determining the pixel points as bifurcation points in the effective points when the number of the pixel points with non-0 pixel value of the pixel points is more than 2. For example, when N is equal to 3, in response to the number of pixels of the pixel relative to the neighborhood 26 non-0 pixels, the pixels of the pixel of the neighborhood 26 pixels of the pixel can be classified by using the above technical means, and the number of pixels of the non-0 pixels in the neighborhood 26 pixels of the pixel can be calculated.
Discarding the pixel point in response to the number being 0; when the number is 1, the pixel point is marked as an end point P3; in response to the number being 2, the pixel point is marked as a connection point P1; in response to the number being greater than 2, the pixel point is noted as a bifurcation point P2.
In step 206, a main vessel path and a branch vessel path relative to the main vessel path may be determined based on the end point, the junction point, and the bifurcation point, wherein the end point or bifurcation point is started with a relative neighborhood N 3 -end points, connection points and bifurcation point connections in 1 pixel points, said connections being repeated until connected to an end point or bifurcation point as an end point, thereby obtaining adjacent edges where points are connected to points, determining starting and ending points on said adjacent edges based on selected starting and ending positions, determining shortest paths from starting point to ending point through said adjacent edges based on a shortest path planning algorithm, thereby determining said shortest paths as main vessel paths, thereby determining main vessel paths and branch vessel paths.
In one embodiment, the topology of the vessel is established by analyzing the spatial positional relationship of the active points. In combination with the information of the end point, the junction point and the bifurcation point, a main vessel path and a branch vessel path with respect to the main vessel path are determined. This can be achieved by graph theory and topology methods. The shortest path planning algorithm based on the Di Jie St algorithm and the depth-first search algorithm can obtain the optimal path of the target central line from the set of nodes and adjacent edges through the self-defined starting point and end point. Meanwhile, a new lower branch vessel central line starting point is automatically extracted from the target central line path, and a branch vessel central line path meeting a certain condition is obtained from the set of nodes and adjacent sides based on the shortest path planning algorithm.
A method of determining a main vessel path and a method of branching vessel paths with respect to the main vessel path will be described in detail below.
Optionally, the method 200 may further include step 208. In step 208, the center points of the main and branch vessel paths may be determined, and fitting smoothing may be performed on the center points to determine the centerlines of the main and branch vessel paths.
In one embodiment, a fitting smoothing operation is performed on the center points of the main and branch vessel paths to obtain vessel centerlines. This may be achieved by using a curve fitting algorithm, such as a Bezier curve fitting or spline curve fitting. Based on the central line path, extracting the characteristic points meeting certain conditions, re-calculating the circumference point of the blood vessel perpendicular to the characteristic points, and calculating the central point of the circumference point as a new characteristic point position. And finally, smoothing the fold lines formed by the characteristic points by using a Bezier curve to obtain smooth curve data, thereby determining the central lines of the main blood vessel path and the branch blood vessel path.
A method of determining the center points of the main and branch vessel paths will be described in detail below.
Fig. 3 illustrates a flow chart of a method 300 for determining a main vessel path according to some embodiments of the invention. Method 300 may be performed, for example, by console 10 or another computing device in system 1 shown in fig. 1.
In step 302, the end point or bifurcation point may be started with the relative neighborhood (N 3 -1) end point, connection point and bifurcation point connection among the pixel points.
In one embodiment, the pixels of the end point P3 and the bifurcation point P2 obtained in the method 200 can be marked as node N, resulting in a node dataset setN.
The connection point P1, the bifurcation point P2, and the end point P3 among 26 pixel points around the connection area are repeated with the end point P3 or the bifurcation point P2 as a start point until the connection to the end point P3 or the bifurcation point P2 is an end point.
In step 304, the connection may be repeated until it is connected to an ending point or bifurcation point as an ending point, thereby obtaining the point-to-point connected adjacent edges.
In one embodiment, the point-to-point adjacent edge E may be acquired based on a connection. By connecting all the connection points P1, the bifurcation point P2, and the end point P3 as non-repeated, non-direction-distinguishing adjacent edge data, an adjacent edge data set setE can be obtained. The point cloud data M2 is converted into data having a computational value through the above steps.
In step 306, a starting point and an ending point on the adjacent side may be determined based on the selected starting and ending positions.
In one embodiment, the start and end points of the main vessel path may be selected by the user. And searching nodes NStart and Nend closest to the pixel point set setN from the pixel point set setN by using the starting position Pstart and the ending position Pend of the main blood vessel path input by a user as a starting point and an ending point on the adjacent side.
In step 308, a shortest path through the adjacent edge from a start point to an end point may be determined based on a shortest path planning algorithm, thereby determining the shortest path as a main vessel path.
In one embodiment, a shortest path Cmain from the start point Nstart to the end point nen may be calculated in the range of the point set setN and the critical edge set setE based on a shortest path planning algorithm such as a dijkstra algorithm and a depth-first search algorithm, thereby determining the shortest path as a main vessel path.
Fig. 4 shows a schematic diagram of a shortest path planning algorithm according to an embodiment of the present disclosure. As shown in fig. 4, the present disclosure employs a shortest path planning algorithm for searching for a vascular shortest path that is improved based on the dijkstra algorithm and the depth first search algorithm. The adjacent sides including the node A, B, C, D, F, E and the node connected in fig. 4 are taken as a vessel topology model. Assuming that the distance between adjacent edges between each adjacent node is 1, a shortest path plan starting from B currently needs to be found. First, the start and end points of a blood vessel are determined, and a path is randomly determined. For example, a path B-C-D-F is obtained and stored at random by a depth-limited search algorithm, and the distance between each node and the starting point B is recorded. And then traversing each effective point upwards in turn from the end point on the determined path, searching the path distance reversely to determine a potential path, for example, returning to the last bifurcation node D on a random path, excluding the accessed node F, judging that neither B-C-D-C nor B-C-D-B meets the shortest distance condition and cannot be the potential path through the recorded distance, and meanwhile, the method avoids the node from being accessed repeatedly.
And finally, determining the path with the shortest distance in the potential paths as the optimal path based on the shortest distance condition, thereby determining the path as the shortest path of the blood vessel. For example, returning to the last forking node C, excluding the accessed node D, B-C-B not meeting the shortest distance condition, excluding the above nodes, and obtaining a B-C-E path meeting the condition. Returning to the starting point B, excluding the accessed node C, storing ase:Sub>A B-A path meeting the condition, judging the B-D path by the recorded shortest distance of the D, searching whether the path with the node D exists in the stored paths, and judging whether the path is ase:Sub>A more optimal shortest path or not according to the recorded shortest distance of the D: if so, updating the B-D portion of the stored path to B-D while updating the shortest distance recorded by the subsequent path node, and no longer recording a lower layer access search, in this example, the stored path B-C-D-F is updated to a B-D-F path; if not, continuing to access the search to the lower layer, thereby determining the shortest path of the blood vessel.
Fig. 5 illustrates a flow chart of a method 500 for determining a branch vessel path according to some embodiments of the invention. Method 500 may be performed, for example, by console 10 or another computing device in system 1 shown in fig. 1.
In step 502, all bifurcation points on the main vessel path may be determined such that they are candidate starting points for branch vessel paths.
In one embodiment, all nodes in the central vessel path acquired in method 300 that are determined to be bifurcation point P2 may be extracted, thereby yielding a set of nodes SetNbranchstart, all nodes in the set of nodes SetNbranchstart being candidate starting points for the branch vessel centerline path.
In step 504, a branch vessel path retrieval algorithm may be performed to determine a branch vessel path connected to the main vessel path based on the candidate starting point.
In one embodiment, the candidate set setcblanch for the shortest path of all possible branch vessels, each starting at all nodes in the set of branch vessel nodes and ending at point P3, may be calculated separately within the set of points setN and the set of critical edges setE based on a shortest path planning algorithm such as the dijkstra algorithm and the depth-first search algorithm. A candidate branch vessel path retrieval algorithm is then performed on each candidate branch vessel path setcblanch (i) in the candidate set.
The candidate branch vessel path retrieval algorithm comprises: and determining a plurality of shortest paths taking the candidate starting point as a starting point and the ending point as an ending point as candidate branch vessel paths based on a shortest path planning algorithm.
And screening candidate branch vessel paths meeting the threshold condition based on the minimum length threshold value of the branch vessel paths, the maximum perimeter threshold value of the branch vessels and the minimum angle threshold value of the branch vessel paths. Specifically, the minimum length threshold, the maximum circumference threshold, and the minimum angle threshold can be set by the medical characteristics of the branch blood vessel, and the above thresholds are used as screening conditions. And comparing the minimum angle of the length of each shortest path in the candidate branch vessel paths SetCbranch (i), the perimeter of the middle partial end point area of the shortest paths and all the angles of all adjacent three points in the shortest paths with a set condition, and eliminating the shortest paths which do not meet the condition.
Further, the candidate branch vessel path with the largest minimum angle value in the candidate branch vessel paths meeting the threshold condition is determined as the branch vessel path. Specifically, among the candidate branch vessel paths setcblanch (i) satisfying the condition, the shortest path having the largest minimum angle value among all the adjacent three point angles among the shortest paths is selected as the shortest branch vessel path cblanch (i) of the branch vessel. The branched blood vessel path cblanch (i) thus screened is the most gentle path among the shortest paths.
With the above technical means, the minimum length threshold may exclude centerline data calculated for some interfering bump locations on the three-dimensional model of the vessel, and the maximum perimeter threshold may exclude centerlines calculated for tumor locations. These constraints rule out inaccuracy in the results of the point cloud set M2 caused by the vessel three-dimensional model and the skeletonizing algorithm.
In step 506, after determining a branch vessel path connected to the main vessel path, it may be determined whether all bifurcation points exist on the branch vessel path.
In one embodiment, the calculations of steps 502 and 504 are repeated until all of the start nodes in the set of branch vessel start points SetNbranchstart are calculated. Further, it is also necessary to determine whether or not there is a subordinate vessel downstream of the branch vessel path cblanch (i) determined in step 504, that is, a branch vessel path connected to the branch vessel path.
In step 508, the branch vessel path retrieval algorithm may be repeatedly executed to determine a branch vessel path connected to the determined branch vessel path, in response to the presence of all bifurcation points on the branch vessel path, with all bifurcation points on the branch vessel path being determined as candidate starting points.
In one embodiment, the determination is performed by determining whether there is a node classified as a bifurcation point type in the branch vessel path cblanch (i). If there is a node classified as a bifurcation type, the branch vessel path search algorithm is repeatedly executed with the branch vessel path cblanch (i) as a center line until all the subordinate branch vessel paths have been generated, thereby determining a branch vessel path connected to the determined branch vessel path.
Fig. 6 illustrates a flow chart of a method 600 for determining a center point of a main vessel path and a branch vessel path according to some embodiments of the invention. Method 600 may be performed, for example, by console 10 or another computing device in system 1 shown in fig. 1.
In step 602, a minimum curvature threshold between two points and a minimum spacing threshold may be determined.
In one embodiment, the main vessel path Cmain and each main vessel path cblanch acquired in the methods 200, 400, 500 may be further calculated to determine the center points of the main and branch vessel paths.
In step 604, feature points that meet the determined minimum curvature threshold and minimum spacing threshold may be extracted from the connection points on the main and branch vessel paths.
In one embodiment, the curvature (K) of each point on the main vessel path Cmean and each main vessel path Cbranch is calculated from the three-dimensional coordinate point set information of the paths acquired in the methods 200, 400, 500. Based on the minimum curvature threshold value and the minimum distance threshold value between two adjacent characteristic points, points meeting one of two conditions in the three-dimensional coordinate point set on the main blood vessel path Cmean and each main blood vessel path Cbranch are marked as characteristic points, so that three-dimensional coordinate point set information SetPoint of a group of characteristic points is obtained.
In step 606, a plurality of vessel perimeter points perpendicular to the feature points and located on the vessel in a tangential plane may be determined using the feature points as base points.
In one embodiment, the exact center point positions corresponding to setpoints (i) other than the two end points on the blood vessel section may be calculated based on the acquired three-dimensional coordinate point set information feature point set setpoints, which requires determining a plurality of blood vessel perimeter points perpendicular to the feature points on the section and located on the blood vessel.
In particular, the tangential direction of the feature points on the main and branch vessel paths may be determined. And expanding the feature points outwards along a plurality of directions parallel to the tangential direction by taking the feature points as base points so as to perform voxel retrieval on the three-dimensional model data of the blood vessel. Based on voxel retrieval and a predefined threshold, a boundary position of the vessel in the tangential direction in the three-dimensional model data is determined. Based on the determined plurality of boundary positions, a plurality of vessel perimeter points perpendicular to the feature points on a tangent plane and located on the vessel are determined. For example, in order to determine a plurality of vessel circumference points perpendicular to the feature points on a tangential plane and located on the vessel, a tangential plane direction of SetPoint (i) in the vessel may be calculated; from SetPoint (i), the three-dimensional model data M1 is expanded outwardly in X (where X is a natural number) directions parallel to the tangential direction to perform voxel retrieval on the three-dimensional model data of the blood vessel. And determining the boundary position of the blood vessel in the tangential direction in the three-dimensional model data through voxel retrieval, namely finding the boundary position of the three-dimensional model data M1.
In step 608, a center point of the plurality of vessel perimeter points relative to each other may be determined, such that the center point is determined as the center point of the main vessel path and the branch vessel path.
Fig. 7 shows a schematic diagram of determining a center point of the main and branch vessel paths according to an embodiment of the present disclosure. In one embodiment, taking X as 8 as an example, X represents 8 search directions, the larger the value of X, the more accurate the computed Center (i) position. The feature point SetPoint (i) may be a dot, the triangle point may be a Center point Center (i) determined by Center point calculation, and the solid irregular circular polygon may be an actual blood vessel tangent plane. The dotted circle is a perfect circle with SetPoint (i) as the center point, and the radius of the dotted circle is the maximum value of the search range, so that the center line is prevented from influencing the position of the center point due to the position of the opening of the lower blood vessel. The dashed arrow aims at the vessel boundary in the direction of this search. The Center point Center (i) is obtained by calculating an average value from the boundary coordinate positions of the 8 search directions. The center point may be an average of coordinates of the plurality of blood vessel circumference points, thereby determining center points opposite to the plurality of blood vessel circumference points. An average point of a plurality of peripheral points may also be determined by a method such as a polygon determination method, a least square method, or the like, so that the average point is taken as a center point.
Finally, corresponding to step 208 in method 200, a bezier curve may be applied, coordinate information of each Center point Center (i) in the branch vessel polyline set Smain and each branch vessel path set sblanch is reserved, and smoothing processing is performed on the branch vessel polyline set Smain and the branch vessel path set sblanch, so as to obtain a smooth and accurate centerline data centerline set Lmain and a path set lblanch of each branch vessel. Fitting smoothing may be performed for the main vessel path by a similar method, which is not described here in detail, to determine the centerlines of the main vessel path and the branch vessel path.
By using the technical means, the trunk center line and the lower branch center line can be automatically calculated based on the input of the starting point and the ending point of the trunk center line, and the trunk center line and the lower branch center line are automatically positioned and judged without additional input. And the center line data is subjected to recalibration and smoothing treatment, so that the position is accurate and the display effect is good. The calculation result distinguishes each complete trunk and branch central line data, and can be used for subsequent calculation or analysis.
Fig. 8 illustrates a block diagram of a computing device 800 suitable for implementing embodiments of the invention. The computing device 800 may be, for example, the console 10 or another computing device for performing the methods 200, 400, 500, 600 as described above.
As shown in fig. 8, computing device 800 may include one or more Central Processing Units (CPUs) 810 (only one schematically shown) that may perform various suitable actions and processes in accordance with computer program instructions stored in a Read Only Memory (ROM) 820 or loaded from storage unit 850 into Random Access Memory (RAM) 830. In RAM 830, various programs and data required for the operation of computing device 800 may also be stored. The CPU810, ROM 820, and RAM 830 are connected to each other by a bus 840. An input/output (I/O) interface 880 is also connected to bus 840.
Various components in computing device 800 are connected to I/O interfaces 880, including: an input unit 860 such as a keyboard, a mouse, etc.; an output unit 870, such as various types of displays, speakers, and the like; a storage unit 850 such as a magnetic disk, an optical disk, or the like; and communication unit 890 such as a network card, modem, wireless communication transceiver, etc. Communication unit 890 allows computing device 800 to exchange information/data with other devices over a computer network, such as the internet, and/or various telecommunications networks.
The methods 200, 400, 500, 600 described above may be performed, for example, by a CPU810 of a computing device 800 (e.g., the console 10 or another computing device). For example, in some embodiments, the methods 200, 400, 500, 600 may be implemented as a computer software program tangibly embodied on a machine-readable medium, such as the storage unit 850. In some embodiments, some or all of the computer program may be loaded and/or installed onto computing device 800 via ROM 820 and/or communication unit 890. When the computer program is loaded into RAM 830 and executed by CPU810, one or more of the operations of methods 200, 400, 500, 600 described above may be performed. In addition, the communication unit 890 may support a wired or wireless communication function.
Those skilled in the art will appreciate that the computing device 800 shown in fig. 8 is merely illustrative. In some embodiments, computing device 800 may contain more or fewer components.
The methods 200, 400, 500, 600 for determining a main vessel path and a branch vessel path according to the present invention and a computing device 800 that may be used as a console 10 or another computing device are described above in connection with the accompanying drawings. It will be appreciated by those skilled in the art, however, that the steps of the methods 200, 400, 500, 600 and their sub-steps are not limited to the order shown in the figures and described above, but may be performed in any other reasonable order. Furthermore, computing device 800 need not include all of the components shown in FIG. 8, but may include only some of the components necessary to perform the functions described herein, and the manner in which these components are connected is not limited to the form shown in the figures.
The present invention may be a method, apparatus, system, and/or computer program product. The computer program product may include a computer readable storage medium having computer readable program instructions embodied thereon for performing various aspects of the present invention.
In one or more exemplary designs, the functions described herein may be implemented in hardware, software, firmware, or any combination thereof. For example, if implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium.
The various units of the apparatus disclosed herein may be implemented using discrete hardware components or may be integrally implemented on one hardware component, such as a processor. For example, the various illustrative logical blocks, modules, and circuits described in connection with the invention may be implemented or performed with a general purpose processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein.
Those of ordinary skill would further appreciate that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the embodiments of the invention may be implemented as electronic hardware, computer software, or combinations of both.
The previous description of the invention is provided to enable any person skilled in the art to make or use the present invention. Various modifications to the disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other variations without departing from the spirit or scope of the disclosure. Thus, the present invention is not intended to be limited to the examples and designs described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A method for determining a main vessel path and a branch vessel path, comprising:
receiving three-dimensional model data of a blood vessel and converting the received three-dimensional model data into a point cloud set;
determining invalid points and valid points comprising end points, connecting points and bifurcation points in the point cloud set, wherein the method comprises determining pixel points of non-0 pixel values in the three-dimensional model data, thereby calculating the relative neighborhood N of the pixel points 3 -1 number of pixels of non-0 pixel value, where N is a natural number equal to or greater than 2, in response to a pixel relative neighborhood N 3 -determining a pixel point as an invalid point when the number of pixels of the non-0 pixel value of 1 pixel point is 0, responsive to the relative neighborhood N of pixels 3 -determining a pixel point as an end point in the valid point when the number of pixels of the non-0 pixel value of the 1 pixel points is 1, in response to the pixel point being relatively adjacent to the neighborhood N 3 Non-0 image of 1 pixel pointWhen the number of pixel points with pixel values is 2, determining the pixel points as connection points in the effective points, and responding to the relative neighborhood N of the pixel points 3 -determining a pixel point as a bifurcation point in the effective points when the number of pixels of non-0 pixel values of 1 pixel point is greater than 2; and
determining a main vessel path and a branch vessel path relative to the main vessel path based on the end point, the junction point and the bifurcation point, wherein the end point or bifurcation point is started with the opposite neighborhood N by taking the bifurcation point or end point as a starting point 3 -end points, connection points and bifurcation point connections in 1 pixel points, said connections being repeated until connected to an end point or bifurcation point as an end point, thereby obtaining adjacent edges where points are connected to points, determining starting and ending points on said adjacent edges based on selected starting and ending positions, determining shortest paths from starting point to ending point through said adjacent edges based on a shortest path planning algorithm, thereby determining said shortest paths as main vessel paths, thereby determining main vessel paths and branch vessel paths.
2. The method of claim 1, wherein determining a main vessel path and a branch vessel path relative to the main vessel path further comprises:
determining all bifurcation points on the main vessel path, thereby taking the all bifurcation points as candidate starting points of branch vessel paths;
executing a branch vessel path retrieval algorithm based on the candidate starting point to determine a branch vessel path connected to the main vessel path; and
determining whether all bifurcation points exist on the branch vessel path.
3. The method of claim 2, wherein determining whether all bifurcation points exist on the branch vessel path comprises:
determining the branch vessel path as a final branch vessel path in response to the branch vessel path not having all bifurcation points present thereon;
in response to the existence of all bifurcation points on the branch vessel path, again determining all bifurcation points on the branch vessel path as candidate starting points, repeatedly executing the branch vessel path retrieval algorithm to determine a subordinate branch vessel path connected to the determined branch vessel path.
4. A method according to claim 3, wherein the branch vessel path retrieval algorithm comprises:
determining a plurality of shortest paths taking the candidate starting point as a starting point and the ending point as an ending point as candidate branch vessel paths based on a shortest path planning algorithm;
screening candidate branch vessel paths meeting a threshold condition based on a minimum length threshold value of the branch vessel path, a maximum perimeter threshold value of the branch vessel and a minimum angle threshold value of the branch vessel path; and
and determining the candidate branch vessel path with the largest minimum angle value in the candidate branch vessel paths meeting the threshold condition as a branch vessel path.
5. The method of any of claims 1-4, wherein the shortest path planning algorithm is a shortest path planning algorithm that searches for a vascular shortest path based on improvements of the dijkstra algorithm and depth first search algorithm.
6. The method of claim 5, wherein the shortest path planning algorithm comprises:
determining the starting point and the ending point of a blood vessel, and randomly determining a path;
traversing each effective point on the determined path from the end point upwards in turn, and searching the path distance reversely to determine a potential path; and
and determining the shortest path among the potential paths as the optimal path based on the shortest distance condition, thereby determining the shortest path of the blood vessel.
7. A computing device, comprising:
at least one processor; and
at least one memory coupled to the at least one processor and storing instructions for execution by the at least one processor, the instructions when executed by the at least one processor cause the computing device to perform the steps of the method according to any one of claims 1 to 6.
8. A computer readable storage medium having stored thereon computer program code which, when executed, performs the method of any of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311854766.1A CN117495668B (en) | 2023-12-29 | 2023-12-29 | Method, device and medium for determining a main vessel path and a branch vessel path |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311854766.1A CN117495668B (en) | 2023-12-29 | 2023-12-29 | Method, device and medium for determining a main vessel path and a branch vessel path |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117495668A CN117495668A (en) | 2024-02-02 |
| CN117495668B true CN117495668B (en) | 2024-03-29 |
Family
ID=89683301
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311854766.1A Active CN117495668B (en) | 2023-12-29 | 2023-12-29 | Method, device and medium for determining a main vessel path and a branch vessel path |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117495668B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110517279A (en) * | 2019-09-20 | 2019-11-29 | 北京深睿博联科技有限责任公司 | Neck vessel centerline extracting method and device |
| CN113516644A (en) * | 2021-07-13 | 2021-10-19 | 天津大学 | Intravascular optical coherence tomography branch blood vessel identification method |
| WO2022199403A1 (en) * | 2021-03-26 | 2022-09-29 | 北京阅影科技有限公司 | Blood vessel centerline extraction method and apparatus |
| CN115775216A (en) * | 2021-09-07 | 2023-03-10 | 上海微创卜算子医疗科技有限公司 | Blood vessel information acquisition method, electronic device and storage medium |
| CN116778486A (en) * | 2023-07-03 | 2023-09-19 | 深圳睿心智能医疗科技有限公司 | Point cloud segmentation method, device, equipment and medium of angiography image |
| CN116843622A (en) * | 2023-05-31 | 2023-10-03 | 深圳睿心智能医疗科技有限公司 | Vascular centerline determination system, device, and storage medium |
| CN117115150A (en) * | 2023-10-20 | 2023-11-24 | 柏意慧心(杭州)网络科技有限公司 | Method, computing device and medium for determining branch vessels |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102016205507A1 (en) * | 2016-04-04 | 2017-10-05 | Siemens Healthcare Gmbh | Method for determining collateral information describing the blood flow in collaterals, medical image recording device, computer program and electronically readable data carrier |
-
2023
- 2023-12-29 CN CN202311854766.1A patent/CN117495668B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110517279A (en) * | 2019-09-20 | 2019-11-29 | 北京深睿博联科技有限责任公司 | Neck vessel centerline extracting method and device |
| WO2022199403A1 (en) * | 2021-03-26 | 2022-09-29 | 北京阅影科技有限公司 | Blood vessel centerline extraction method and apparatus |
| CN113516644A (en) * | 2021-07-13 | 2021-10-19 | 天津大学 | Intravascular optical coherence tomography branch blood vessel identification method |
| CN115775216A (en) * | 2021-09-07 | 2023-03-10 | 上海微创卜算子医疗科技有限公司 | Blood vessel information acquisition method, electronic device and storage medium |
| CN116843622A (en) * | 2023-05-31 | 2023-10-03 | 深圳睿心智能医疗科技有限公司 | Vascular centerline determination system, device, and storage medium |
| CN116778486A (en) * | 2023-07-03 | 2023-09-19 | 深圳睿心智能医疗科技有限公司 | Point cloud segmentation method, device, equipment and medium of angiography image |
| CN117115150A (en) * | 2023-10-20 | 2023-11-24 | 柏意慧心(杭州)网络科技有限公司 | Method, computing device and medium for determining branch vessels |
Non-Patent Citations (3)
| Title |
|---|
| Global LBP Features for Iris Recognition using Blood Vessel Segmentation;Kanchan S. Bhagat.etc;《IEEE》;20161231;全文 * |
| 基于最小代价路径的血管中心线提取;盛惠娟;邓振生;欧阳丽蓉;;计算机工程与应用;20150115(02);全文 * |
| 心血管造影图像中的心血管提取;徐智, 郁道银, 谢洪波, 陈晓冬;中国生物医学工程学报;20031231(01);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117495668A (en) | 2024-02-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8073227B2 (en) | System and method for geometric modeling of tubular structures | |
| US10460204B2 (en) | Method and system for improved hemodynamic computation in coronary arteries | |
| Sun et al. | Graph-based IVUS segmentation with efficient computer-aided refinement | |
| US7953266B2 (en) | Robust vessel tree modeling | |
| US7043290B2 (en) | Method and apparatus for segmentation of an object | |
| US9600890B2 (en) | Image segmentation apparatus, medical image device and image segmentation method | |
| CN109478327B (en) | Method for automatic detection of systemic arteries in Computed Tomography Angiography (CTA) of arbitrary field of view | |
| CN111528871A (en) | Method and system for whole body bone removal and vessel visualization in medical images | |
| JP2009072576A (en) | Method, apparatus and computer program for quantitative bifurcation analysis on angiographic image | |
| WO2017047819A1 (en) | Blood vessel shape analysis device, method for same, and computer software program for same | |
| JP4248399B2 (en) | Automatic branch labeling method | |
| JP2008521461A (en) | Method for measuring tubular organs using knowledge structure mapping | |
| CN108428210B (en) | Blood vessel image reconstruction method and reconstruction device | |
| CN117115150B (en) | Method, computing device and medium for determining branch vessels | |
| Zhao et al. | Automatic retinal vessel segmentation using multi-scale superpixel chain tracking | |
| JP4411075B2 (en) | Branch selection method for probe alignment | |
| KR20160053325A (en) | Method of classifying artery and vein of organ | |
| Wu et al. | Regulated morphology approach to fuzzy shape analysis with application to blood vessel extraction in thoracic CT scans | |
| Ebrahimdoost et al. | Automatic segmentation of pulmonary artery (PA) in 3D pulmonary CTA images | |
| KR101514795B1 (en) | Quantification method of vessel | |
| CN117495668B (en) | Method, device and medium for determining a main vessel path and a branch vessel path | |
| JP7187680B2 (en) | LINE STRUCTURE EXTRACTION APPARATUS AND METHOD, PROGRAM AND TRAINED MODEL | |
| CN117495667B (en) | Method, computing device, and medium for determining a vessel centerline | |
| CN104239874A (en) | Method and device for identifying organ blood vessels | |
| Alom et al. | Automatic slice growing method based 3D reconstruction of liver with its vessels |
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 |