A blood vessel separation method and system

Abstract

This invention provides a method and system for blood vessel separation. In one aspect, this invention first acquires real-time tracking path information of the original blood vessel image and performs a first topological analysis on the real-time tracking path information to generate an initial segmentation result for the blood vessel. Then, based on the initial segmentation result, the blood vessel centerline is extracted, and according to a preset algorithm, a second topological analysis is performed on the blood vessel topological information based on the blood vessel centerline to generate a final segmentation result for the blood vessel. Therefore, the technical solution provided by this invention separates blood vessels through a two-step separation method, effectively improving the separation speed and efficiency.

Description

[0001] This application is a divisional application of the case filed on May 9, 2017, with application number 201710322757.6 and invention title "A method and system for separating blood vessels". Technical Field

[0002] This invention relates to the field of digital medical technology, and in particular to a method and system for separating blood vessels. Background Technology

[0003] With the continuous development of surgical techniques, precision surgery places higher demands on computer-aided medical imaging systems. In hepatobiliary surgery, surgeons need a detailed understanding of the diseased areas of the liver and their relationship with blood vessels before surgery. Utilizing computer-aided 3D imaging systems and liver segmentation technology, surgeons can gain a clear, intuitive, and three-dimensional understanding of the relationships between various tissues within the liver before surgery. Furthermore, they can determine whether surgery is feasible based on the automatic liver segmentation results, allowing surgeons to make detailed plans before surgery and precisely remove cancerous tissue while minimizing damage to healthy tissue during the procedure.

[0004] Precise segmentation of the portal vein and hepatic vein is one of the fundamental and valuable aspects of liver segmentation. However, during venous and delayed phase scanning, the contrast of the portal vein and hepatic vein is low and the noise is high. In addition, due to the volume effect, relatively close portal vein and hepatic vein segments may adhere during separation, causing parts or even the entirety of one vascular system to be identified as another vascular system. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a method and system for separating blood vessels to solve the problem of low accuracy and efficiency in blood vessel segmentation in the prior art.

[0006] On one hand, embodiments of the present invention provide a method for separating blood vessels, the method comprising:

[0007] Real-time tracking path information of the original blood vessel image is obtained through tracking;

[0008] A first topological analysis is performed on the real-time tracking path information to generate initial segmentation results of blood vessels;

[0009] Extract the vessel centerline based on the initial segmentation results;

[0010] According to a preset algorithm, a second topology analysis is performed on the vascular topology information based on the vascular centerline to generate the final segmentation result of the vascular system.

[0011] In addition to the aspects and any possible implementations described above, a further implementation is provided, which involves performing a second topological analysis on the vascular topological information based on the vascular centerline according to a preset algorithm to generate the final segmentation result of the vascular system, specifically including:

[0012] The parameter information of the blood vessel segments corresponding to each of the blood vessel centerlines is calculated, and the blood vessel topology based on the blood vessel centerlines is stored as an undirected graph;

[0013] After searching for connected paths in the undirected graph based on preset marker points, a second topological analysis is performed on the connected paths based on the parameter information using a preset algorithm to generate the final segmentation result of the blood vessels.

[0014] In addition to the aspects described above and any possible implementation, a further implementation is provided, wherein the parameter information includes one or more of the following: the average radius of the vessel segment, the average tangential direction of the vessel segment, the radii at both ends of the vessel segment, and the tangential directions at both ends of the vessel segment.

[0015] In addition to the aspects and any possible implementations described above, an implementation is further provided in which the first topology analysis and the second topology analysis include vascular path analysis and vascular bifurcation analysis.

[0016] In addition to the aspects described above and any possible implementations, a further implementation is provided, wherein the method further includes:

[0017] The correspondence between each pixel point of the blood vessel and the center line of the blood vessel is stored separately.

[0018] In addition to the aspects described above and any possible implementations, an implementation is further provided in which the tracking employs one or more of the following methods: ridge tracking, minimum cost path tracking, blood vessel cross-section model tracking, and tubular structure model tracking.

[0019] On the other hand, embodiments of the present invention provide a blood vessel separation system, the system comprising:

[0020] The acquisition unit is used to acquire real-time tracking path information of the original blood vessel image through tracking;

[0021] The first processing unit is used to perform a first topological analysis on the real-time tracking path information to generate an initial segmentation result of the blood vessels;

[0022] Extraction unit, used to extract the blood vessel centerline based on the initial segmentation result;

[0023] The second processing unit is used to perform a second topology analysis on the vascular topology information based on the vascular centerline according to a preset algorithm, and generate the final segmentation result of the vascular system.

[0024] As described above and in any possible implementation, a further implementation is provided, wherein the second processing unit is specifically used for:

[0025] The parameter information of the blood vessel segments corresponding to each of the blood vessel centerlines is calculated, and the blood vessel topology based on the blood vessel centerlines is stored as an undirected graph;

[0026] After searching for connected paths in the undirected graph based on preset marker points, a second topological analysis is performed on the connected paths based on the parameter information using a preset algorithm to generate the final segmentation result of the blood vessels.

[0027] In addition to the aspects and any possible implementations described above, an implementation is further provided in which the first topology analysis and the second topology analysis include vascular path analysis and vascular bifurcation analysis.

[0028] In addition to the aspects described above and any possible implementations, an implementation is further provided in which the system further includes:

[0029] The storage unit is used to store the correspondence between each blood vessel pixel and the blood vessel centerline.

[0030] One of the above technical solutions has the following beneficial effects:

[0031] In this embodiment of the invention, during the initial segmentation process, by analyzing the local puff information of the blood vessels, extremely obvious vascular adhesion points are separated. After the initial segmentation is completed, by analyzing the global topological information of the blood vessels, path information and bifurcation information are used to further separate the vascular adhesion points. This embodiment of the invention effectively improves the separation speed and efficiency of blood vessels through a two-step separation method. Attached Figure Description

[0032] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 This is a schematic flowchart of the blood vessel separation method provided in an embodiment of the present invention;

[0034] Figure 2 Pre-separation blood vessel image for an embodiment of the present invention;

[0035] Figure 3 This is an image of the separated blood vessels according to an embodiment of the present invention;

[0036] Figure 4This is a functional block diagram of the blood vessel separation system provided in the embodiments of the present invention. Detailed Implementation

[0037] To better understand the technical solution of the present invention, the embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0038] It should be understood that the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0039] The terminology used in the embodiments of this invention is for the purpose of describing particular embodiments only and is not intended to limit the invention. The singular forms “a,” “the,” and “the” as used in the embodiments of this invention and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0040] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.

[0041] Depending on the context, the word "if" as used here can be interpreted as "when," "when," "in response to determination," or "in response to detection." Similarly, depending on the context, the phrase "if determination" or "if detection (of the stated condition or event)" can be interpreted as "when determination," "in response to determination," "when detection (of the stated condition or event)," or "in response to detection (of the stated condition or event)."

[0042] Please refer to Figure 1 This is a schematic flowchart of the blood vessel separation method provided in an embodiment of the present invention, as shown below. Figure 1 As shown, the method includes the following steps:

[0043] Step S101: Real-time tracking path information of the original blood vessel image is obtained by tracking.

[0044] Specifically, in this embodiment of the invention, a blood vessel tracking algorithm is used to obtain real-time tracking path information of the original blood vessel image. The principle of the blood vessel tracking algorithm is as follows:

[0045] After selecting the tracking starting point based on the original vascular image, the radius, coordinates, and direction of the vascular segment where the tracking starting point is located are determined, and an initial vascular model is established. Starting from the tracking starting point, the initial vascular model is fitted and matched with the neighboring region located at the tracking starting point to optimize the initial vascular model. Then, the real-time tracking path information such as the vascular radius, vascular direction, vascular contrast, and vascular matching degree of the vascular segment where the tracking starting point is located after optimization is further determined. Then, the vascular model is moved forward, and the real-time tracking path information at the next vascular location is determined using the same method as described above.

[0046] Step S102: Perform a first topological analysis on the real-time tracking path information to generate an initial segmentation result of the blood vessels.

[0047] In this embodiment of the invention, the first topology analysis is based on the analysis of local topology information of the original blood vessel image. Local topology information analysis can be understood as tracing several new blood vessel segments forward from a tracking point, analyzing the blood vessel path information and bifurcation information of these segments, and deriving a local depth detection tree based on the local topology information. The tracking methods for obtaining the first topology analysis include ridge line tracking, minimum cost path tracking, blood vessel cross-section model tracking, and tubular model tracking, among others. One or more of the above tracking methods can be combined to obtain the real-time tracking path information of the original blood vessel image. The ridge line tracking method preprocesses the image through smoothing and filtering to obtain a filtered response image that increases the pixel values ​​in the central region of the blood vessel diameter and decreases the pixel values ​​in the blood vessel boundary region. The blood vessel centerline is then tracked along the ridge direction of the filtered response from an initial point on this image. The minimum cost path method filters or calculates energy in the image, assigns a cost value to adjacent pixels, and searches for the minimum path step-by-step from an initial point on the cost map using dynamic programming, thereby tracing the blood vessel centerline. The vascular cross-section model tracking method typically constructs a 2D vascular cross-section model. Starting from a starting point, it modifies parameters such as radius, contrast, and normal vector, and performs similarity matching with the vascular image to find the most similar position. The center point of the matched model is then used as the center point of the tracked vascular, and the process is repeated. The tubular structure model tracking method constructs a 3D tubular model, typically ellipsoidal or cylindrical. Starting from a starting point, it modifies parameters such as radius, contrast, and diameter direction, and performs similarity matching with the vascular image to find the most similar position. The center point of the matched model is then used as the center point of the tracked vascular, and the process is repeated.

[0048] The tubular structure model tracing method will be used as an example for illustration. In this method, each tubular model represents a node. Tracing the tubular structure forms a series of nodes with discontinuous center points. Then, a directed graph is constructed based on the tracing direction. Each node of the tubular model in the tracing path is a vertex in the directed graph, and the connection relationship between adjacent nodes in the tracing path is an edge in the directed graph. The directed graph is an acyclic tree structure, i.e., a local depth detection tree. Each node in the tree diagram stores at least the vessel radius, vessel direction, vessel contrast, and vessel matching degree of the vessel segment in which the node is located. The connections between nodes store at least the vessel direction deviation information between the parent node and the child node, and the angle information between the branching child nodes.

[0049] It should be noted that the first topological analysis is used to identify obvious vascular adhesion points. For example, obvious vascular adhesion points can be identified using the following strategies:

[0050] 1. Bifurcation Analysis

[0051] Based on local topological information, the angle between the main branch and the sub-branch of each bifurcation is analyzed. When the directional deviation angle of the sub-vessel segments of the two bifurcations is greater than 160 degrees, it is identified as a vascular adhesion point, and path tracing at the adhesion point is interrupted. When the directional deviation angle of the sub-vessel segments of the two bifurcations is greater than 130 degrees, and the matching degree of the two sub-vessel segments at the bifurcation is greater than that of the parent vessel segment (because the parent vessel segment is at the adhesion point, its vessel contrast and matching degree are both low), it is identified as a significant vascular adhesion point, and path tracing at the adhesion point is interrupted.

[0052] 2. Local path analysis

[0053] Based on the local depth detection tree, the rate of change of radius, angle and matching degree of each path from the root node to the leaf node is calculated and compared with preset values. Paths that do not meet the preset conditions are identified as obvious vascular adhesion points, and path tracking at the adhesion points is interrupted.

[0054] After the above steps, the initial segmentation result of the blood vessel (i.e., image mask) is generated by performing the first topological analysis (including bifurcation information and local path information) on the real-time tracking path information.

[0055] Step S103: Extract the center line of the blood vessel based on the initial segmentation result.

[0056] In this embodiment of the invention, the initial segmentation result (i.e., the image mask) is thinned, also known as skeletonization. A centerline composed of continuous pixels is rapidly extracted using an extraction algorithm. This extraction algorithm can be categorized into morphological extraction and level set extraction. Specifically, the principle of the extraction algorithm is as follows: First, the surface of the object on the image mask is symmetrically eroded. Edge pixels that do not satisfy Eulerian invariance and are not simple points are eroded. After erosion, holes are filled in. Finally, the centerlines of each blood vessel in the initial segmentation result can be extracted. Since the extraction algorithm is a commonly used technique in the field, it will not be elaborated further here. After extracting the blood vessel centerlines, the correspondence between each blood vessel pixel and its centerline is stored. Therefore, when a blood vessel pixel is selected, the blood vessel centerline can be directly located.

[0057] Step S104: According to a preset algorithm, perform a second topology analysis on the vascular topology information based on the vascular centerline to generate the final segmentation result of the vascular system.

[0058] The embodiments of the present invention further refine step S104, specifically including:

[0059] a) Calculate the parameter information of the blood vessel segment corresponding to each of the blood vessel centerlines, and store the blood vessel topology based on the blood vessel centerlines as an undirected graph;

[0060] In this embodiment of the invention, the second topology analysis is performed based on a second topology structure. The second topology structure is an undirected graph constructed by analyzing the bifurcation points and terminal points extracted from the centerline, using the bifurcation points and terminal points as vertices and the adjacency relationships of nodes as edges. Each edge of the undirected graph stores the average radius and direction of the blood vessel segment, and each vertex of the undirected graph stores the radius and direction of the blood vessel at the node's location.

[0061] b) After searching for connected paths in the undirected graph based on preset marker points, a second topological analysis is performed on the connected paths based on the parameter information using a preset algorithm to generate the final segmentation result of the blood vessels.

[0062] In this embodiment of the invention, the parameter information of the blood vessel segment to be calculated includes the average radius of the blood vessel segment, the average tangent direction of the blood vessel segment, the radii at both ends of the blood vessel segment, and the tangent directions at both ends of the blood vessel segment. After the calculation is completed, the parameter information of each blood vessel segment is stored, and the blood vessel topology based on the blood vessel centerline is stored as an undirected graph. Then, after the user adds preset marker points, a depth-first search algorithm is used to search for connected paths in the undirected graph, and then a second topology analysis is performed on the connected paths. Specifically, after the user sets the preset marker points, the algorithm searches for all connected paths for each pair of marker points, and then analyzes the parameter information stored on these connected paths.

[0063] It should be noted that the second topology analysis includes the following three steps:

[0064] 1) First, find the locations of the minimum radius, maximum front-to-back angle, and maximum front-to-back radius difference in the connected path corresponding to the preset marker point, and identify these edges in the undirected graph as suspected adhesion points.

[0065] 2) Next, determine whether there is a branch at each suspected adhesion point. If there is no branch at the suspected adhesion point, then exclude the suspected adhesion point; if there is a branch at the suspected adhesion point, then perform branch analysis on it using a preset strategy. For example, the following strategy can be used to perform branch analysis on suspected adhesion points:

[0066] a) Determine whether the average angle between the two bifurcated sides is greater than 130 degrees. If so, determine that it is a suspected adhesion point; otherwise, exclude the suspected adhesion point.

[0067] b) Determine whether the average directional angle between the two bifurcated sides is greater than 90 degrees and the directional angle between the nodes at the bifurcation point is greater than 130 degrees. If so, it is determined to be a suspected adhesion point; otherwise, the suspected adhesion point is excluded.

[0068] 3) Finally, determine the final suspected adhesion point. If, after the screening in steps 1) and 2), only one suspected adhesion point remains on each connected path, then that suspected adhesion point is taken as the final suspected adhesion point. If there are multiple suspected adhesion points, then after performing adhesion similarity probability analysis on the multiple suspected adhesion points, the suspected adhesion point with the highest probability is selected as the final suspected adhesion point.

[0069] For example, adhesion similarity probability analysis can be performed by weighting parameters such as radius, angle deviation, and direction of the connected path to calculate the probability of the suspected adhesion point, and then selecting the one with the highest probability from the suspected adhesion points as the final suspected adhesion point of the connected path.

[0070] Figure 2 For the purpose of separating blood vessels in an embodiment of the present invention, Figure 3 This is an image of the separated blood vessels according to an embodiment of the present invention. Please refer to... Figure 2 After the user marks a certain number of hepatic vein points and portal vein points in the vascular image before separation, the separation method of this embodiment of the invention automatically separates the overall vascular image into a vascular image composed of hepatic veins and portal veins, thereby achieving vascular separation.

[0071] The technical solutions of the embodiments of the present invention have the following beneficial effects:

[0072] In this embodiment of the invention, during the initial segmentation process, by analyzing the local puff information of the blood vessels, extremely obvious vascular adhesion points are separated. After the initial segmentation is completed, by analyzing the global topological information of the blood vessels, path information and bifurcation information are used to further separate the vascular adhesion points. This embodiment of the invention effectively improves the separation speed and efficiency of blood vessels through a two-step separation method.

[0073] The technical solution of the present invention will be further explained below in conjunction with specific application scenarios.

[0074] This invention, taking into account the characteristics of portal vein and hepatic vein segmentation results—namely, a limited number of vessel levels and branches, with typically 1-5 adhesion points—proposes a method for rapidly identifying and separating adhesion points between the two vascular systems. During the initial segmentation process, highly obvious vascular adhesion points can be separated by analyzing local vascular information. After the initial segmentation, global vascular topology information is analyzed, and path and bifurcation information are used to further separate the vascular adhesion points. This two-step separation method effectively improves the speed and efficiency of vascular separation in the liver analysis workflow.

[0075] It is understood that the technical solutions of the embodiments of the present invention can also be applied to other application scenarios with relatively simple vascular topologies, such as the separation of cardiovascular arteries and veins; for scenarios with more complex topologies, such as the separation of pulmonary arteries and veins, the technical solutions of the embodiments of the present invention can be used as auxiliary processing means.

[0076] Please refer to Figure 4 This is a functional block diagram of the blood vessel separation system provided in the embodiments of the present invention, as shown below. Figure 4 As shown, the system includes:

[0077] The acquisition unit 410 is used to acquire real-time tracking path information of the original blood vessel image through tracking;

[0078] The first processing unit 420 is used to perform a first topological analysis on the real-time tracking path information to generate an initial segmentation result of the blood vessels;

[0079] Extraction unit 430 is used to extract the blood vessel centerline based on the initial segmentation result;

[0080] The second processing unit 440 is used to perform a second topology analysis on the vascular topology information based on the vascular centerline according to a preset algorithm, and generate the final segmentation result of the vascular system.

[0081] As described above and in any possible implementation, a further implementation is provided, wherein the second processing unit is specifically used for:

[0082] The parameter information of the blood vessel segments corresponding to each of the blood vessel centerlines is calculated, and the blood vessel topology based on the blood vessel centerlines is stored as an undirected graph;

[0083] After searching for connected paths in the undirected graph based on preset marker points, a second topological analysis is performed on the connected paths based on the parameter information using a preset algorithm to generate the final segmentation result of the blood vessels.

[0084] In addition to the aspects described above and any possible implementation, a further implementation is provided, wherein the parameter information includes one or more of the following: the average radius of the vessel segment, the average tangential direction of the vessel segment, the radii at both ends of the vessel segment, and the tangential directions at both ends of the vessel segment.

[0085] In addition to the aspects and any possible implementations described above, an implementation is further provided in which the first topology analysis and the second topology analysis include vascular path analysis and vascular bifurcation analysis.

[0086] In addition to the aspects described above and any possible implementations, an implementation is further provided in which the system further includes:

[0087] The storage unit is used to store the correspondence between each blood vessel pixel and the blood vessel centerline.

[0088] Because each unit in this embodiment can perform Figure 1 For the methods shown, parts not described in detail in this embodiment, please refer to the [examples / descriptions]. Figure 1-3 Related explanations.

[0089] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, servers, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0090] In the embodiments provided by this invention, it should be understood that the disclosed systems, servers, and methods can be implemented in other ways. For example, the server embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between servers or units may be electrical, mechanical, or other forms.

[0091] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0092] In addition, the functional units in various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or hardware plus software functional units.

[0093] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer server (which may be a personal computer, server, or network server, etc.) or processor to execute some steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0094] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for separating blood vessels, characterized in that, The method includes: Real-time tracking path information of the original vascular image is obtained by tracking; the original vascular image includes vascular images of at least two vascular systems; Local topology information is determined based on the real-time tracking path information; the local topology information includes vascular path information and vascular bifurcation information. A first topological analysis is performed on the local topological information to determine the vascular adhesion sites in the original vascular image, and an initial segmentation result is generated that interrupts the path tracing at the vascular adhesion sites. Extract the vessel centerline based on the initial segmentation results; According to a preset algorithm, a second topological analysis is performed on the vascular topological information based on the vascular centerline to generate the final segmentation result of the vascular system. The step of performing a first topological analysis on the local topological information to determine the vascular adhesion sites in the original vascular image includes: The bifurcation information of the blood vessels is analyzed to determine the angle between the corresponding blood vessel segments at each bifurcation point, and the location of the blood vessel adhesion is determined based on the angle between the corresponding blood vessel segments at each bifurcation point; or... A local depth detection tree is determined based on the vascular path information, and the parameter change rate between the root node and leaf node of each path in the local depth detection tree is obtained. The vascular adhesion site is determined based on the parameter change rate.

2. The blood vessel separation method according to claim 1, characterized in that, The step of determining the location of vascular adhesion based on the included angle between the corresponding vascular segments of the branch at the bifurcation point includes: If the angle between the corresponding vascular segments at the bifurcation point is greater than 160 degrees, then the bifurcation point is determined to be the location of the vascular adhesion.

3. The blood vessel separation method according to claim 2, characterized in that, The method further includes: If the angle between the corresponding vascular segments of the branch at the bifurcation point is greater than 130 degrees, and the matching degree of each vascular segment of the branch at the bifurcation point is greater than the matching degree of the parent vascular segment, then the bifurcation point is determined to be the vascular adhesion point.

4. The blood vessel separation method according to claim 1, characterized in that, The step of determining the local depth detection tree based on the vascular path information includes: The nodes corresponding to the tubular model are determined from the vascular path information; Using the nodes corresponding to the tubular model as vertices and the connections between adjacent nodes as edges, a directed graph is constructed according to the tracking direction to serve as the local depth detection tree.

5. The method for separating blood vessels according to claim 1, characterized in that, The step of performing a second topological analysis on the vascular topological information based on the vascular centerline according to a preset algorithm to generate the final segmentation result of the vascular system specifically includes: The parameter information of the blood vessel segments corresponding to each of the blood vessel centerlines is calculated, and the blood vessel topology based on the blood vessel centerlines is stored as an undirected graph; After searching for connected paths in the undirected graph based on preset marker points, a second topological analysis is performed on the connected paths based on the parameter information using a preset algorithm to generate the final segmentation result of the blood vessels.

6. The blood vessel separation method according to claim 5, characterized in that, The vascular topology based on the vascular centerline is stored as an undirected graph, including: The bifurcation point and terminal point are determined based on the described vascular topology; The undirected graph is constructed and stored using the bifurcation point and the end point as vertices and the adjacency relationship of the nodes as edges.

7. The method for separating blood vessels according to claim 5, characterized in that, The step of performing a second topology analysis on the connected path based on the parameter information using a preset algorithm to obtain the final segmentation result includes: The suspected adhesion points are determined based on the parameter information of the connected path corresponding to the preset marker points; Determine whether there is a fork at the suspected adhesion site; if a fork is found, determine the final suspected adhesion site among the suspected adhesion sites. The path tracing at the final suspected adhesion point is interrupted to obtain the final segmentation result.

8. The method for separating blood vessels according to claim 7, characterized in that, The step of identifying the final suspected adhesion site among the suspected adhesion sites includes: Determine whether the included angle between the average directions of the two bifurcated sides of the suspected adhesion site is greater than 130 degrees; When the average angle between the two bifurcated sides of the suspected adhesion point is greater than 130 degrees. If there is only one suspected adhesion point on the connected path, then the suspected adhesion point is determined to be the final suspected adhesion point.

9. The method for separating blood vessels according to claim 8, characterized in that, The method further includes: If there are multiple suspected adhesion points on the connected path, then an adhesion similarity probability analysis is performed on the multiple suspected adhesion points, and the suspected adhesion point with the highest adhesion similarity probability is determined as the final suspected adhesion point.

10. A blood vessel separation system, characterized in that, The system includes: The acquisition unit is used to acquire real-time tracking path information of the original vascular image by tracking; the original vascular image includes vascular images of at least two vascular systems; The first processing unit is used to determine local topology information based on the real-time tracking path information; the local topology information includes blood vessel path information and blood vessel bifurcation information; perform a first topology analysis on the local topology information to determine the blood vessel adhesion points in the original blood vessel image, and generate an initial segmentation result that interrupts the path tracking at the blood vessel adhesion points; Extraction unit, used to extract the blood vessel centerline based on the initial segmentation result; The second processing unit is used to perform a second topological analysis on the vascular topological information based on the vascular centerline according to a preset algorithm, and generate the final segmentation result of the vascular. The first processing unit is specifically used for: The blood vessel bifurcation information is analyzed to determine the angle between the blood vessel segments corresponding to the sub-branches at each bifurcation point, and the blood vessel adhesion point is determined based on the angle between the blood vessel segments corresponding to the sub-branches at the bifurcation point; or, a local depth detection tree is determined based on the blood vessel path information, and the parameter change rate between the root node and leaf node of each path in the local depth detection tree is obtained, and the blood vessel adhesion point is determined based on the parameter change rate.

Images