A method, apparatus, and storage medium for segmenting an aneurysm

Abstract

The application discloses a method, device and storage medium for segmenting an aneurysm. The method comprises the following steps: generating a blood vessel graph structure according to a blood vessel segmentation mask, wherein the blood vessel graph structure at least comprises leaf nodes containing radius attributes; determining an initial path node inside the aneurysm according to a positioning point; screening a target path from the initial path node to the leaf node, and sorting the target path according to an average radius to form a path pair; restoring a path through the aneurysm based on the path pair to obtain a restored path; and segmenting the aneurysm based on the restored path to obtain an aneurysm segmentation result. The scheme can guarantee stable segmentation of a large aneurysm, stably obtain the peripheral blood vessel condition of the aneurysm, and improve the accuracy and reliability of aneurysm segmentation.

Description

Technical Field

[0001] This application generally relates to the field of medical image processing technology. More specifically, this application relates to a method, apparatus, and computer-readable storage medium for segmenting aneurysms. Background Technology

[0002] In the medical field, accurate segmentation of aneurysms is crucial for the diagnosis, treatment planning, and follow-up of neurosurgical diseases. Multimodal vascular imaging, such as digital subtraction angiography (“DSA”), CT angiography (“CTA”), and magnetic resonance angiography (“MRA”), provides important evidence for aneurysm detection; however, accurately segmenting aneurysms from these images remains a challenging task.

[0003] In existing technologies, intracranial aneurysms are characterized by diverse shapes and complex necks. Both manual segmentation and deep learning models present significant technical challenges. Specifically, manual segmentation is time-consuming, labor-intensive, and reliant on physician experience, while deep learning models, when processing aneurysms, are prone to incomplete segmentation of the aneurysm and may mistakenly segment the parent artery as an aneurysm, leading to inaccurate segmentation results and impacting clinical diagnosis and treatment planning.

[0004] In view of this, this application provides a method for segmenting aneurysms to ensure stable segmentation of large aneurysms and to stably obtain information about the surrounding blood vessels of the aneurysm, thereby improving the accuracy and reliability of aneurysm segmentation. Summary of the Invention

[0005] In order to at least address one or more of the technical problems mentioned above, this application proposes a scheme for segmenting aneurysms in several aspects.

[0006] In a first aspect, this application provides a method for segmenting an aneurysm, comprising: generating a vascular map structure based on a vascular segmentation mask, wherein the vascular map structure includes at least leaf nodes containing radius attributes; determining initial path nodes inside the aneurysm based on positioning points; filtering target paths from the initial path nodes to the leaf nodes, and sorting the target paths according to average radius to form path pairs; reconstructing the path through the aneurysm based on the path pairs to obtain a reconstructed path; and segmenting the aneurysm based on the reconstructed path to obtain an aneurysm segmentation result.

[0007] In some embodiments, the target path from the initial path node to the leaf node is filtered by the following operations: traversing the set of paths from the initial path node to the leaf node; calculating the length or average radius of each path in the set of paths; and filtering the target path from the initial path node to the leaf node based on the length or average radius of each path.

[0008] In some embodiments, filtering the target path from the initial path node to the leaf node based on the length or average radius of each path includes: filtering out paths from the path set whose length is less than a length threshold or whose average radius is less than a radius threshold, in order to obtain the target path from the initial path node to the leaf node.

[0009] In some embodiments, the vascular map structure further includes edge nodes with radius attributes. Reconstructing the path through the aneurysm based on the path pair to obtain the reconstructed path includes: performing edge node removal and interpolation operations on the path pair to obtain new path points; generating spheres with all points on the path pair after adding new path points as centers and according to the corresponding radii; and performing a union operation on the spheres to reconstruct the path through the aneurysm to obtain the reconstructed path.

[0010] In some embodiments, the path pairs are edge node removed by the following operation: taking the first point on each path in the path pair as the starting point; removing edge nodes on each path in the path pair whose distance from the corresponding starting point is less than the radius of the corresponding starting point, thereby removing edge nodes from the path pairs.

[0011] In some embodiments, the path pair interpolation operation is performed by adding a target number of points containing a target radius between the first points on each path in the path pair after removing edge nodes.

[0012] In some embodiments, the operation of segmenting the aneurysm based on the restored path to obtain the aneurysm segmentation result includes: performing a union operation on the restored path to obtain a connected component; and segmenting the aneurysm based on the distance from the location point to the connected component to obtain the aneurysm segmentation result.

[0013] In some embodiments, the operation of segmenting the aneurysm based on the distance from the location point to the connected domain and obtaining the aneurysm segmentation result includes: in response to the minimum distance from the target location point to the target connected domain, determining the target connected domain as the aneurysm segmentation result.

[0014] In a second aspect, this application provides an apparatus including a processor and a memory, wherein the memory stores computer instructions for segmenting aneurysms, which, when executed by the processor, cause one or more embodiments of the first aspect to be implemented.

[0015] In a third aspect, this application provides a computer-readable storage medium having stored thereon computer program instructions for segmenting aneurysms, which, when executed by one or more processors, cause one or more embodiments of the first aspect to be implemented.

[0016] Based on the above-described scheme for optimizing the neck surface of aneurysms, this embodiment generates a vascular map structure containing at least leaf nodes with radius attributes according to a vascular segmentation mask. Initial path nodes within the aneurysm are determined based on positioning points, and target paths from these initial path nodes to the leaf nodes are identified. Path pairs based on the target paths are used to reconstruct the path traversing the aneurysm for segmentation. This accurately presents the vascular topology and size characteristics, ensuring that the segmentation logic conforms to anatomical features, focusing on the main path set closely related to the aneurysm morphology, and avoiding the mis-inclusion of the carrier artery. Path reconstruction allows for the reconstruction of the connection between the aneurysm and surrounding vessels, fitting the spatial morphological contour of the aneurysm, and achieving complete segmentation of large intracranial aneurysms. This effectively solves the problems of incomplete aneurysm segmentation and mis-segmentation of the carrier artery in existing technologies, thereby stably acquiring the vascular conditions surrounding the aneurysm and providing reliable image segmentation results for clinical diagnosis and treatment planning. Attached Figure Description

[0017] The above and other objects, features, and advantages of exemplary embodiments of this application will become readily understood by reading the following detailed description with reference to the accompanying drawings. In the drawings, several embodiments of this application are illustrated by way of example and not limitation, and the same or corresponding reference numerals denote the same or corresponding parts, wherein:

[0018] Figure 1 This is an exemplary flowchart illustrating a method for segmenting an aneurysm according to an embodiment of this application;

[0019] Figure 2 This is an exemplary schematic diagram illustrating a vascular map structure according to an embodiment of this application;

[0020] Figure 3 This is an exemplary flowchart illustrating the determination of a target path according to an embodiment of this application;

[0021] Figure 4 This is an exemplary flowchart illustrating the reconstruction of the path through the aneurysm and the segmentation of the aneurysm based on path pairs according to an embodiment of this application;

[0022] Figure 5 This is an exemplary structural block diagram illustrating a device according to an embodiment of this application. Detailed Implementation

[0023] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this application. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0024] It should be understood that the terms "comprising" and "including" used in the specification and claims of this application indicate the presence of the described features, integrals, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0025] It should also be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application. As used in this specification and claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this specification and claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations.

[0026] As used in this specification and claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if [described condition or event] is detected" may be interpreted, depending on the context, as "once determined," "in response to determination," "once [described condition or event] is detected," or "in response to detection of [described condition or event]."

[0027] The specific embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0028] Figure 1 This is an exemplary flowchart illustrating a method 100 for segmenting an aneurysm according to an embodiment of this application. Figure 1 As shown, the method 100 includes: step S101: generating a vascular map structure based on a vascular segmentation mask, wherein the vascular map structure includes at least leaf nodes containing radius attributes; step S102: determining initial path nodes inside the aneurysm based on the positioning points; step S103: filtering target paths from the initial path nodes to the leaf nodes, and sorting the target paths according to their average radius to form path pairs; step S104: reconstructing the path through the aneurysm based on the path pairs to obtain the reconstructed path; and step S105: segmenting the aneurysm based on the reconstructed path to obtain the aneurysm segmentation result.

[0029] First, in step S101, a vascular map structure is generated based on the vascular segmentation mask. In some implementation scenarios, the vascular binarized image extracted from medical images (such as DSA, CTA) can be obtained by using methods such as threshold segmentation and deep learning, marking the vascular region as 1 and the background as 0, thus obtaining the vascular segmentation mask.

[0030] In other implementations, a vascular graph structure can be generated from a vascular segmentation mask using segmentation tools (such as sknw, a Python library focused on building and analyzing networks from skeleton images). This vascular graph structure includes leaf nodes (nodes with only one adjacent node) and edge nodes (the remaining nodes), each with a radius attribute. The radius is the shortest distance from the node to the vascular surface, determined by calculating the Euclidean distance from the node to the edge of the vascular mask in 3D space. As an example, if the vascular graph structure G contains m leaf nodes, denoted as n1 to nm, and edges are represented by (nj, nk), where 1 <= j, k <= m, then there are L edge nodes on the edge (nj, nk), denoted as e1 to eL, with radii r1 to rL.

[0031] In other implementation scenarios, the length of the edge (nj, nk) can be determined. If the length of the edge (nj, nk) is less than 10mm or less than (rj+rk), a new point nm+1 is added. The new point is located at the center of nj and nk. All adjacent points of the original nj and nk are set as adjacent points of nm+1 to generate the vascular map structure. The generated vascular map structure quantifies the thickness of blood vessels through the radius attribute, and the leaf nodes locate the ends of blood vessels, providing an accurate topological and geometric basis for subsequent path analysis and avoiding misjudgment of aneurysm boundaries due to fuzzy vascular structures.

[0032] Next, in step S102, the initial path nodes within the aneurysm are determined based on the location points. In some implementation scenarios, the location points [x0, y0, z0] can be marked on the medical image by the user through interactive methods (such as mouse clicks), or the location points can be generated by automatic detection algorithms (such as key point detection based on aneurysm features). Based on the generated location points, the Euclidean distances from all leaf nodes n1 to nm in the vascular structure map G to the location points are calculated, and the node np corresponding to the minimum distance is found as the initial path node within the aneurysm. Thus, by determining the initial node based on the location points, it is ensured that the segmentation starting point is located in the core region of the aneurysm, avoiding incomplete segmentation caused by the offset of the starting point, and improving the alignment of the segmentation results with clinical needs.

[0033] Based on the initial path nodes within the aneurysm determined above, in step S103, target paths from the initial path nodes to leaf nodes are selected, and the target paths are sorted according to their average radius to form path pairs. In some embodiments, the target paths from the initial path nodes to leaf nodes can be selected by the following operation: traversing the set of paths from the initial path nodes to leaf nodes, calculating the length or average radius of each path in the path set, and selecting the target paths from the initial path nodes to leaf nodes according to the length or average radius of each path.

[0034] In some implementation scenarios, we can first start from the initial path node np and use, for example, breadth-first search or depth-first search to traverse the vascular structure graph to obtain the set W of all paths from the initial node np to the leaf nodes. Next, we calculate the total length and average radius (the arithmetic mean of the radii of the nodes along the path) of each path. The total length is the sum of the lengths of all edges, and the edge length is calculated using the differences in node coordinates; the aforementioned average radius is the arithmetic mean of the radii of the nodes along the path. Further, in some embodiments, paths with a length less than a length threshold or an average radius less than a radius threshold are filtered out from the path set to obtain the target path from the initial path node to the leaf node.

[0035] In some implementation scenarios, the aforementioned length threshold can be, for example, 80 mm, and the aforementioned radius threshold can be, for example, 1 mm. For example, paths with a length less than 80 mm or an average radius less than 1 mm will be filtered out from the path set to obtain the target path W'. After obtaining the target path W', the paths in the target path W' are sorted in descending order of average radius. For example, the paths in W' are denoted as w1 to wf, and the average radii are denoted as r1 to rf, where rw1>rw2>...>rwf. Adjacent paths (wi, wi+1) are then paired sequentially. Based on this, through dual screening of length and average radius, small branches and noisy paths are excluded, focusing on the main paths related to the aneurysm body and avoiding missegmentation of the aneurysm-bearing artery. By sorting and pairing paths by radius, it is ensured that the path pairs can characterize the main inflow / outflow channels of the aneurysm, providing a reliable set of paths for reconstructing the aneurysm morphology.

[0036] Further, in step S104, the path through the aneurysm is reconstructed based on the path pair to obtain the reconstructed path. In some embodiments, edge node removal and interpolation operations are performed on the path pair to obtain new path points. A sphere is generated centered on all points in the path pair after adding the new path points, and then a union operation is performed on the spheres to reconstruct the path through the aneurysm and obtain the reconstructed path. In some embodiments, edge node removal can be performed on the path pair by taking the first point on each path in the path pair as the starting point and removing edge nodes on each path that are less than the radius of the corresponding starting point. In other embodiments, interpolation can be performed on the path pair by adding a target number of points containing a target radius between the first points on each path in the path pair after removing edge nodes.

[0037] Specifically, for the path pair (wi, wi+1), taking the starting node np1 (radius rp) of wi as an example, remove the edge nodes on wi whose distance from the starting node np1 is less than rp (i.e., proximal nodes located inside the aneurysm). Similarly, process the starting node of wi+1 to obtain the truncated path starting points eyi and eyi+1. Next, between eyi and eyi+1, generate D new points using linear interpolation based on the Euclidean distance D(eyi, eyi+1). The radius of each new point is set to (ri+ri+1) / 2, where ri and ri+1 are the radii of eyi and eyi+1, respectively. Thus, the path pair after adding the new path points can be obtained, and the total number of points in the path pair after adding the new path points is Li+Li+1-yi-yi+1+D. By generating spheres centered on all points in the path pair after adding the new path points according to the corresponding radii, and then performing a union operation on the spheres, the path through the aneurysm can be reconstructed to obtain the restored path. Among them, redundant nodes inside the aneurysm are removed by edge node removal, adjacent paths are smoothly connected by interpolation operation, and the spatial connection morphology of the aneurysm and the parent artery is accurately restored by three-dimensional spherical union, avoiding segmentation gaps caused by path discontinuity and improving the integrity of the aneurysm outline.

[0038] Finally, in step S105, the aneurysm is segmented based on the restored path to obtain the aneurysm segmentation result. In some embodiments, a connected component can be obtained by performing a union operation on the restored path, and the aneurysm can be segmented based on the distance from the location point to the connected component to obtain the aneurysm segmentation result. Specifically, in some embodiments, the target connected component is determined as the aneurysm segmentation result in response to the minimum distance from the target location point to the target connected component. As an example, a logical NOT operation (1-vessel_seg) is performed on the restored path vessel_seg, and a logical AND operation is performed with the original vascular segmentation mask to obtain n connected components, each corresponding to a region in the vascular network not covered by the restored path. Then, by calculating the shortest distance from the location point to each connected component (taking the minimum Euclidean distance from all points in the connected component to the location point), the connected component j with the smallest distance is found and determined as the aneurysm segmentation result. Based on this, connected components are filtered according to the distance of the positioning points to ensure that the segmentation result is the region closest to the aneurysm core, avoiding misidentification of distal vessels as aneurysms; morphological processing eliminates segmentation noise, making the segmentation result more in line with clinical diagnostic requirements, and providing an accurate basis for aneurysm volume calculation, aneurysm neck analysis, etc.

[0039] As described above, the embodiments of this application generate a vascular graph structure containing leaf nodes with radius attributes based on a vascular segmentation mask. This accurately characterizes the topological structure and size features of blood vessels, providing a precise geometric basis for subsequent path analysis. By determining the initial path nodes inside the aneurysm based on the positioning points, the vascular path can be explored starting from the core region of the aneurysm, ensuring the accuracy of the segmentation starting point. By screening the target paths from the initial path nodes to the leaf nodes and sorting them by average radius to form path pairs, irrelevant small branches and noisy paths can be effectively filtered out, focusing on the aneurysm-related paths that carry the main blood flow and avoiding missegmentation of the aneurysm-bearing artery.

[0040] Furthermore, by reconstructing the path through the aneurysm based on path pairs, and through edge node removal and interpolation operations, the morphological contour of the aneurysm can be accurately fitted, restoring its connection relationship with surrounding vessels. Finally, based on the restored path segmentation, the aneurysm region can be accurately separated through connected component analysis and distance judgment of localization points. This achieves complete segmentation of large intracranial aneurysms with diverse shapes and complex necks, effectively solving the problems of incomplete aneurysm segmentation and misinclusion of the carrier artery in the segmentation results in existing technologies. This provides stable information on the surrounding vessels of the aneurysm, offering reliable imaging evidence for clinical diagnosis and treatment. In some implementation scenarios, erosion and dilation operations can also be performed on the aneurysm segmentation results to remove noise, smooth the contour, and preserve the main structure.

[0041] Figure 2 This is an exemplary schematic diagram illustrating a vascular map structure according to an embodiment of this application. For example... Figure 2 As shown, the vascular map structure can include leaf nodes (e.g., indicated by arrow A in the figure) and edge nodes (e.g., indicated by arrow B in the figure). As previously mentioned, the vascular map structure can be generated by constructing a skeleton network from the vascular segmentation mask using tools such as sknw. Based on the generated vascular map structure and localization points, the target paths from the initial path nodes to the leaf nodes are determined, and path pairs are identified. Then, the path through the aneurysm is reconstructed based on the path pairs. The aneurysm is segmented by reconstructing the path, and the aneurysm segmentation result is obtained.

[0042] Figure 3 This is an exemplary flowchart illustrating the determination of a target path according to an embodiment of this application. Figure 3 As shown, in step S301, the location point is obtained. In some implementation scenarios, the location point can be obtained by marking the location point on the medical image or by automatically detecting key points of the aneurysm features. Next, in step S302, the Euclidean distance from the location point to all leaf nodes in the vascular structure map G is calculated, and in step S303, the node corresponding to the minimum distance is determined as the initial path node inside the aneurysm.

[0043] Based on the initial path nodes obtained above, in step S304, the path set W from the initial path nodes to the leaf nodes is traversed. In step S305, the length or average radius of each path in the path set is calculated, and in step S306, paths with a length less than 80 mm or an average radius less than 1 mm are filtered out from the path set to obtain the target path W'. According to the target path W', the paths in the target path W' are sorted in descending order of average radius, and adjacent paths (wi, wi+1) are sequentially paired to form path pairs, thereby reconstructing the path through the aneurysm to segment the aneurysm.

[0044] Figure 4 This is an exemplary flowchart illustrating a path-pair-based reconstruction of the path through an aneurysm and segmentation of the aneurysm according to an embodiment of this application. Figure 4 As shown, in step S401, edge node removal and interpolation operations are performed on the path pairs to obtain new path points. Specifically, taking the first point on each path in the path pair as the starting point, edge nodes on each path in the path pair whose distance from the corresponding starting point is less than the radius of the corresponding starting point are removed to perform edge node removal on the path pairs. Then, a target number of points containing the target radius are added between the first points on each path in the path pair after edge node removal to perform interpolation on the path pairs. The target number is D new points generated by linear interpolation using Euclidean distance D(eyi,eyi+1), and the target radius is (ri+ri+1) / 2.

[0045] In step S402, spheres are generated centered on all points of the path pair after adding the new path point, according to the corresponding radii. In step S403, a union operation is performed on the spheres to reconstruct the path through the aneurysm. Based on the obtained reconstructed path, in step S404, a union operation is performed on the reconstructed path to obtain connected components. Further, in step S405, the shortest distance from the location point to each connected component is calculated. In step S406, the connected component j with the smallest distance is determined as the aneurysm segmentation result.

[0046] Figure 5 This is an exemplary structural block diagram illustrating a device 500 according to an embodiment of this application. It is understood that the device 500 may include the apparatus of the embodiments of this application, and the device implementing the solution of this application may be a single device (e.g., a computing device) or a multifunctional device including various peripheral devices.

[0047] like Figure 5As shown, the device of this application may further include a central processing unit (“CPU”) 511, which may be a general-purpose CPU, a dedicated CPU, or other information processing and program execution unit. Further, the device 500 may also include a mass storage 512 and a read-only memory (“ROM”) 513, wherein the mass storage 512 may be configured to store various types of data, including various vascular map structures, initial path nodes, target paths, path pairs, restored paths, aneurysm segmentation results, algorithm data, intermediate results, and various programs required to run the device 500. The ROM 513 may be configured to store power-on self-tests for the device 500, initialization of various functional modules in the system, drivers for the system's basic input / output, and data and instructions required to boot the operating system.

[0048] Optionally, device 500 may also include other hardware platforms or components, such as the tensor processing unit (“TPU”) 514, graphics processing unit (“GPU”) 515, field-programmable gate array (“FPGA”) 516, and machine learning unit (“MLU”) 517 shown. It is understood that although various hardware platforms or components are shown in device 500, they are merely exemplary and not limiting, and those skilled in the art can add or remove appropriate hardware as needed. For example, device 500 may implement the method for segmenting aneurysms of this application by including only a CPU, associated storage devices, and interface devices.

[0049] In some embodiments, to facilitate data transmission and interaction with external networks, the device 500 of this application further includes a communication interface 518, through which it can connect to a local area network / wireless local area network (“LAN / WLAN”) 505, and further through the LAN / WLAN to connect to a local server 506 or to the Internet (“Internet”) 507. Alternatively or additionally, the device 500 of this application can also directly connect to the Internet or cellular network via the communication interface 518 based on wireless communication technology, such as wireless communication technology based on 3G (“3G”), 4G (“4G”), or 5G (“5G”). In some application scenarios, the device 500 of this application can also access the server 508 and database 509 of an external network as needed to obtain various known algorithms, data, and modules, and can remotely store various data, such as various data or instructions for presenting vascular map structures, initial path nodes, target paths, path pairs, restored paths, aneurysm segmentation results, etc.

[0050] Peripherals of device 500 may include a display device 502, an input device 503, and a data transmission interface 504. In one embodiment, the display device 502 may include, for example, one or more speakers and / or one or more visual displays, configured to provide voice prompts and / or display images and videos for the purpose of segmenting aneurysms according to this application. The input device 503 may include, for example, a keyboard, mouse, microphone, posture capture camera, and other input buttons or controls, configured to receive audio data input and / or user commands. The data transmission interface 504 may include, for example, a serial interface, parallel interface, or Universal Serial Bus interface (“USB”), Small Computer System Interface (“SCSI”), Serial ATA, FireWire (“FireWire”), PCI Express, and High Definition Multimedia Interface (“HDMI”), configured for data transmission and interaction with other devices or systems. According to the scheme of this application, the data transmission interface 504 can receive aneurysm images acquired from CT or MRI equipment and transmit aneurysm images or various other types of data or results to device 500.

[0051] The CPU 511, mass storage 512, ROM 513, TPU 514, GPU 515, FPGA 516, MLU 517, and communication interface 518 of the device 500 of this application can be interconnected via bus 519, and can interact with peripheral devices through this bus. In one embodiment, the CPU 511 can control other hardware components in the device 500 and its peripheral devices through this bus 519.

[0052] The above combination Figure 5 A device that can be used to execute this application is described. It should be understood that the device structure or architecture described herein is merely exemplary, and the implementation method and implementation entity of this application are not limited thereto, but can be changed without departing from the spirit of this application.

[0053] Based on the foregoing description in conjunction with the accompanying drawings, those skilled in the art will understand that the embodiments of this application can also be implemented by software programs. Therefore, this application also provides a computer-readable storage medium storing computer-readable instructions for segmenting aneurysms. When executed by one or more processors, these computer-readable instructions can be used to implement the embodiments of this application in conjunction with the accompanying drawings. Figure 1 The method described is for segmenting aneurysms.

[0054] It should be noted that although the operations of the method of this application are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in that specific order, or that all the operations shown must be performed to achieve the desired result. On the contrary, the steps depicted in the flowchart can be performed in a different order. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step, and / or one step may be broken down into multiple steps.

[0055] It should be understood that when the terms "first," "second," "third," and "fourth," etc., are used in the claims, specification, and drawings of this application, they are used only to distinguish different objects and not to describe a specific order. The terms "comprising" and "including" as used in the specification and claims of this application indicate the presence of the described features, integrals, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or collections thereof.

[0056] It should also be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the application. As used in this specification and claims, the singular forms “a,” “an,” and “the” are intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this specification and claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes such combinations.

[0057] Although the embodiments of this application are described above, the content is merely an example adopted for the purpose of facilitating understanding of this application and is not intended to limit the scope and application scenarios of this application. Any person skilled in the art described in this application may make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in this application, but the scope of patent protection of this application shall still be determined by the scope defined in the appended claims.

[0058] Furthermore, the collection and acquisition of various data in this application comply with relevant laws and regulations and are authorized by the data providers. Any organization or individual that needs to obtain external data shall obtain authorization in accordance with the law and ensure data security, and shall not illegally collect, use, process, or transmit unauthorized or unprotected data, nor shall it illegally buy, sell, provide, or disclose unauthorized or unprotected data.

Claims

1. A method for dividing an aneurysm, comprising: A vascular graph structure is generated based on a vascular segmentation mask, wherein the vascular graph structure includes at least leaf nodes containing radius attributes; The initial path nodes inside the aneurysm are determined based on the location points; Filter the target paths from the initial path node to the leaf node, and sort the target paths according to their average radius to form path pairs; Based on the described path, the path through the aneurysm is reconstructed to obtain the reconstructed path; The aneurysm is segmented based on the restored path to obtain the aneurysm segmentation result. The vascular map structure further includes edge nodes with radius attributes. Based on the path pair, the path through the aneurysm is reconstructed, and the reconstructed path is obtained by: Perform edge node removal and interpolation operations on the path pairs to obtain new path points; Generate spheres centered on all path points of the path pair after adding the new path point, according to the corresponding radii. A union operation is performed on the spheres to reconstruct the path through the aneurysm and obtain the reconstructed path.

2. The method of claim 1, wherein the target path from the initial path node to the leaf node is filtered by the following operation: Traverse the set of paths from the initial path node to the leaf node; Calculate the length or average radius of each path in the path set; The target path from the initial path node to the leaf node is selected based on the length or average radius of each path.

3. The method according to claim 2, wherein filtering the target path from the initial path node to the leaf node based on the length or average radius of each path includes: Paths whose length is less than a length threshold or whose average radius is less than a radius threshold are filtered out from the path set to obtain the target path from the initial path node to the leaf node.

4. The method of claim 1, wherein edge nodes are removed from the path pair by the following operation: The first point on each path in the path pair is taken as the starting point; Remove edge nodes from each path in the path pair whose radius from the corresponding starting point is less than that of the corresponding starting point, in order to perform edge node removal on the path pair.

5. The method of claim 1, wherein the path pair interpolation operation is performed by: Add a target number of points containing the target radius between the first point on each path in the path pair after removing edge nodes, to perform an interpolation operation on the path pair.

6. The method according to claim 1, wherein segmenting the aneurysm based on the restored path to obtain the aneurysm segmentation result includes: Perform a union operation on the restored path to obtain the connected components; The aneurysm is segmented based on the distance from the location point to the connected domain, and the aneurysm segmentation result is obtained.

7. The method according to claim 6, wherein segmenting the aneurysm based on the distance from the positioning point to the connected domain, and obtaining the aneurysm segmentation result includes: In response to the minimum distance from the target location point to the target connected region, the target connected region is determined as the aneurysm segmentation result.

8. An apparatus comprising: processor; as well as A memory having stored computer instructions for segmenting aneurysms, which, when executed by a processor, cause the method according to any one of claims 1-7 to be implemented.

9. A computer-readable storage medium having stored thereon computer program instructions for segmenting an aneurysm, the computer program instructions, when executed by one or more processors, causing the method according to any one of claims 1-7 to be implemented.

Images