Interlayer cavity separation method and device based on clustering algorithm, equipment and medium

Abstract

The invention relates to an interlayer cavity separation method and device based on a clustering algorithm, equipment and a medium, and the method comprises the steps: extracting a vascular interlayer inner diaphragm model and a target vascular model based on a to-be-processed CTA image; converting the vascular interlayer inner membrane model into a grid model, and extracting a first surface patch and a second surface patch which are continuous and have the largest area; aiming at each voxel grid on the target blood vessel model, determining a grid point, closest to the first surface patch and the second surface patch, of the voxel grid; direction vectors of the voxel grids and the grid points are calculated, and feature vectors are constructed by the direction vectors and the space coordinates of the grid points; the feature vectors corresponding to the voxel grids are subjected to clustering analysis, an interlayer separation result is obtained, the problem that time and labor are consumed by manual labeling is solved, meanwhile, the method is clear in principle, and interlayer separation precision is improved.

Description

Technical Field

[0001] This application relates to the technical field of medical image processing, and particularly to a method, device, equipment, and medium for separating sandwich cavities based on a clustering algorithm. Background Art

[0002] The separation of vascular sandwich cavities has always been one of the difficult problems in vascular model extraction. Since there may be a large number of flow channels between the sandwich cavities, and the development of the intimal flap is affected by CT enhancement, it may be unclear. For some complex sandwich models, the sandwich may be distorted, which greatly increases the difficulty of distinguishing the true and false cavities. At present, there are mainly two types of methods for separating sandwich cavities. One is based on manual annotation, and its main disadvantage is that it requires a lot of time and effort; the other is mainly based on deep learning model segmentation methods, and its main disadvantages are as follows: 1. It depends on a large number of training sets and gold standards; 2. The universality is insufficient, and the data trained in one training set is difficult to adapt to images with large differences; 3. Deep learning is a black box, and its application in the medical field requires more caution. Summary of the Invention

[0003] Based on this, it is necessary to provide a method, device, equipment, and medium for separating sandwich cavities based on a clustering algorithm for the above technical problems.

[0004] In a first aspect, an embodiment of the present application provides a method for separating sandwich cavities based on a clustering algorithm, and the method includes:

[0005] Based on the CTA image to be processed, extract the vascular sandwich intimal flap model and the target vascular model;

[0006] Convert the vascular sandwich intimal flap model into a mesh model, and extract the two consecutive and largest-area first patch and second patch therefrom;

[0007] For each voxel grid on the target vascular model, determine the grid point on the first patch and the second patch that is closest to it; calculate the direction vector between the voxel grid and the grid point, and construct a feature vector with the spatial coordinates of the grid point;

[0008] Perform clustering analysis on the feature vectors corresponding to each voxel grid to obtain the sandwich separation result.

[0009] In one of the embodiments, the converting the vascular sandwich intimal flap model into a mesh model and extracting the two consecutive and largest-area first patch and second patch therefrom includes:

[0010] Obtain the normal vector of each triangular patch in the mesh model;

[0011] Divide the mesh model into multiple continuous patches based on the normal vectors of each of the triangular patches;

[0012] Select the two patches with the largest areas from the multiple continuous patches to obtain a first patch and a second patch.

[0013] In one embodiment, the dividing the mesh model into multiple continuous patches based on the normal vectors of each of the triangular patches includes:

[0014] Calculate the included angle between the normal vectors of each triangular patch and its adjacent triangular patches;

[0015] If the included angle of the normal vectors is within the threshold range, determine that the triangular patch and its adjacent triangular patch are the same continuous patch.

[0016] In one embodiment, for each voxel grid on the target blood vessel model, determining the grid points on the first patch and the second patch that are closest to it; calculating the direction vector between the voxel grid and the grid point includes:

[0017] Convert the voxel coordinates of each voxel grid on the target blood vessel model into spatial coordinates;

[0018] Based on the spatial coordinates, calculate the distances between the voxel grid and all grid points on the first patch and the second patch to determine the grid points on the first patch and the second patch that are closest to it;

[0019] Based on the spatial coordinates of the voxel grid and the spatial coordinates of the grid point, calculate the direction vector between the voxel grid and the closest grid point.

[0020] In one embodiment, the expression form of the feature vector V is as follows:

[0021] V = (D, , , , T);

[0022] ;

[0023] where D is the direction vector between the voxel grid and the grid point, x0, y0, z0 are the spatial coordinates of the voxel grid, x1, y1, z1 are the spatial coordinates of the grid point, and when T = 1, it means the grid point is on the first patch, and when T = 2, it means the grid point is on the second patch.

[0024] In one embodiment, the extracting the intimal flap model of the aortic dissection based on the to-be-processed CTA image includes:

[0025] Extract an initial vascular model based on the CTA image to be processed;

[0026] Perform endolemma filling on the initial vascular model based on morphological closing operation to obtain a first target vascular model;

[0027] Subtract the first target vascular model from the initial vascular model and take the largest connected component to obtain a vascular dissection endolemma model.

[0028] In one embodiment, the extracting the target vascular model based on the CTA image to be processed includes:

[0029] Extract the centerline of the first target vascular model;

[0030] Extract the target points closest to each point on the vascular dissection endolemma model on the centerline to form a target centerline;

[0031] Determine the target vascular model based on the target centerline and the first target vascular model.

[0032] In a second aspect, an embodiment of the present application further provides a device for separating a dissection cavity based on a clustering algorithm, and the device includes:

[0033] A first extraction module, configured to extract a vascular dissection endolemma model and a target vascular model based on the CTA image to be processed;

[0034] A second extraction module, configured to convert the vascular dissection endolemma model into a mesh model and extract two consecutive and largest first and second meshes;

[0035] A feature vector construction module, configured to determine the grid points closest to the first and second meshes for each voxel on the target vascular model; calculate the direction vector between the voxel and the grid point, and construct a feature vector with the spatial coordinates of the grid point;

[0036] A cavity separation module, configured to perform clustering analysis on the feature vectors corresponding to the voxels to obtain a dissection separation result.

[0037] In a third aspect, an embodiment of the present application further provides a computer device, including a memory and a processor, where a computer program is stored in the memory, and the processor is configured to run the computer program to execute the method as described in the first aspect above.

[0038] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, where a computer program is stored in the storage medium, and the computer program, when executed by a processor, implements the method as described in the first aspect above.

[0039] The above-mentioned method, device, equipment and medium for separating the sandwich cavity based on the clustering algorithm extract the vascular dissection intimal flap model and the target vascular model based on the CTA image to be processed; convert the vascular dissection intimal flap model into a mesh model, and extract the two continuous and largest-area first and second patches therefrom; for each voxel grid on the target vascular model, determine the grid points on the first patch and the second patch that are closest to it; calculate the direction vector between the voxel grid and the grid point, and construct a feature vector with the spatial coordinates of the grid point; perform clustering analysis on the feature vectors corresponding to each voxel grid to obtain the sandwich separation result. Thus, the separation of the cavity of the sandwich is realized based on the traditional segmentation method, which solves the problem of time-consuming and laborious manual annotation, does not require a large amount of data sets as the training set of the deep learning network, and the principle of the traditional method is clear, improving the accuracy of cavity separation.

[0040] The details of one or more embodiments of the present application are set forth in the following drawings and description to make the other features, objects, and advantages of the present application more concise and understandable. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments and descriptions thereof are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings:

[0042] Figure 1 is a hardware structure block diagram of a terminal device for the method of separating the sandwich cavity based on the clustering algorithm in an embodiment;

[0043] Figure 2 is a flowchart of the method of separating the sandwich cavity based on the clustering algorithm in an embodiment;

[0044] Figure 3 is a structure block diagram of a device for separating the sandwich cavity based on the clustering algorithm in an embodiment;

[0045] Figure 4 is a schematic diagram of the structure of a computer device in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0046] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be described and explained below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0047] Obviously, the accompanying drawings in the following description are only some examples or embodiments of the present application. For those of ordinary skill in the art, without creative efforts, the present application can also be applied to other similar scenarios based on these drawings. In addition, it can also be understood that although the efforts made in such a development process may be complex and lengthy, for those of ordinary skill in the art related to the content disclosed in the present application, some design, manufacturing, or production changes based on the technical content disclosed in the present application are only conventional technical means and should not be understood as the content disclosed in the present application being insufficient.

[0048] When the term "embodiment" is mentioned in the present application, it means that the specific features, structures, or characteristics described in combination with the embodiment can be included in at least one embodiment of the present application. The appearance of this phrase at various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those of ordinary skill in the art explicitly and implicitly understand that the embodiments described in the present application can be combined with other embodiments without conflict.

[0049] Unless otherwise defined, the technical terms or scientific terms involved in the present application should have the ordinary meaning understood by those with ordinary skills in the technical field to which the present application belongs. The terms "a", "an", "one", "the", and similar words involved in the present application do not indicate a limitation in quantity and can represent a singular or plural number. The terms "include", "comprise", "have", and any variations thereof involved in the present application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may further include unlisted steps or units, or may further include other steps or units inherent to these processes, methods, products, or devices. The terms "connect", "be connected", "couple", and similar words involved in the present application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The term "plurality" involved in the present application refers to two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships can exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after. The terms "first", "second", "third", etc. involved in the present application are only used to distinguish similar objects and do not represent a specific order for the objects.

[0050] The method embodiment provided in this embodiment can be executed on a terminal, a computer, or a similar computing device. For example, it runs on a terminal. Figure 1is a hardware structure block diagram of a terminal of the sandwich cavity separation method based on clustering algorithm of this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) processor 102 and memory 104 for storing data, wherein processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0051] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the sandwich cavity separation method based on the clustering algorithm in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories can be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0052] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by a communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, RF) module, which is used to communicate with the Internet wirelessly.

[0053] The present invention provides a method for separating sandwich cavities based on a clustering algorithm, and the method is applied to Figure 1 The terminal in is used as an example to illustrate. Figure 2 As shown, the method comprises the following steps:

[0054] Step 201: extracting a vascular dissection intimal sheet model and a target blood vessel model based on the CTA image to be processed.

[0055] Specifically, the original angiography image is obtained, which is the CTA image to be processed. In the embodiment of the present invention, the blood vessel model in the CTA image is extracted. Specifically, it can be achieved by: performing threshold segmentation on the blood vessel model to mark the area of the blood vessel model with the HU value range within the preset threshold range; using a morphological erosion algorithm to remove the small connected areas of bones and blood vessels in the area of the blood vessel model, and extracting the connected area where the blood vessels are located to remove the bone area, thereby obtaining the blood vessel area; using a morphological dilation algorithm to compensate the blood vessel area to obtain the initial blood vessel model. Then, based on the morphological closing operation, the intimal flap of the initial blood vessel model is filled to obtain the first target blood vessel model, and the centerline of the first target blood vessel model is extracted. The difference between the first target blood vessel model and the initial blood vessel model is taken and the largest connected domain is obtained to obtain the blood vessel dissection intimal flap model.

[0056] For each point on the blood vessel dissection intimal flap model, find the point on the centerline that is closest to it. Eventually, a continuous target centerline on the centerline can be obtained. Using this target centerline, further extract only the blood vessel model near the target centerline to remove the interference of the far blood vessel model on the segmentation process, and obtain the target blood vessel model, which is the model for which dissection is required.

[0057] Step 202: Convert the blood vessel dissection intimal flap model into a mesh model, and extract the two consecutive and largest-area first face and second face.

[0058] Step 203: For each voxel grid on the target blood vessel model, determine the grid point on the first face and the second face that is closest to it; calculate the direction vector between the voxel grid and the grid point, and construct a feature vector with the spatial coordinates of the grid point.

[0059] Step 204: Perform clustering analysis on the feature vectors corresponding to each voxel grid to obtain the dissection result.

[0060] Specifically, a binary classification clustering algorithm is performed on the feature vectors corresponding to all voxel grids on the target blood vessel model. For example, the k-means algorithm is used for clustering, and the clustering result is the dissection result.

[0061] In the above-mentioned method for separating the sandwich cavity based on the clustering algorithm, the vascular dissection intimal flap model and the target blood vessel model are extracted from the CTA image to be processed; the vascular dissection intimal flap model is converted into a mesh model, and the two continuous and largest-area first patch and second patch are extracted therefrom; for each voxel grid on the target blood vessel model, the grid points closest to the first patch and the second patch are determined; the direction vector between the voxel grid and the grid point is calculated, and a feature vector is constructed with the spatial coordinates of the grid point; clustering analysis is performed on the feature vectors corresponding to the voxel grids to obtain the sandwich separation result. Thus, the separation of the cavity of the sandwich is realized based on the traditional segmentation method, which solves the problem of time-consuming and laborious manual annotation, does not require a large amount of data sets as the training set of the deep learning network, and the principle of the traditional method is clear, improving the accuracy of sandwich separation.

[0062] In one embodiment, the converting the vascular dissection intimal flap model into a mesh model and extracting the two continuous and largest-area first patch and second patch therefrom includes the following steps:

[0063] Step 301, obtain the normal vector of each triangular patch in the mesh model.

[0064] Step 302, divide the mesh model into multiple continuous patches based on the normal vectors of the triangular patches.

[0065] Step 303, select the two patches with the largest area from the multiple continuous patches to obtain the first patch and the second patch.

[0066] In this application, for each triangular patch of the mesh model, its normal vector can be calculated, and then whether the two patches are continuous is defined by analyzing the change in the included angle of the normal vectors of adjacent patches. After analysis, several continuous patches can be obtained (each continuous patch includes multiple triangular patches with smaller included angle changes), and then the two patches with the largest area are taken, namely the first patch and the second patch.

[0067] The first patch and the second patch actually represent the two surfaces of the intimal flap, and the definition of the sandwich is actually based on the intimal flap connecting the flow cavity. Therefore, it is possible to judge whether a point in the flow cavity belongs to the true cavity or the false cavity based on the relationship between each point in the flow cavity and the two surfaces of the intimal flap.

[0068] In one embodiment, the dividing the mesh model into multiple continuous patches based on the normal vectors of the triangular patches includes the following content: calculate the included angle between the normal vectors of each triangular patch and its adjacent triangular patch; if the included angle of the normal vectors is within the threshold range, determine that the triangular patch and its adjacent triangular patch are the same continuous patch.

[0069] In this application, if the included angle between the normal vectors of a triangular patch and its adjacent triangular patches is within a threshold range, for example, less than a certain angle, it indicates that the included angle change between the triangular patch and its adjacent triangular patches is small, and then it is defined as a continuous patch. Through the above method, the mesh model can be divided into multiple continuous patches, and then the two patches with the largest areas can be selected from them.

[0070] In one embodiment, for each voxel grid on the target blood vessel model, determine the grid points on the first patch and the second patch that are closest to it; calculating the direction vector between the voxel grid and the grid points includes the following:

[0071] Step 401, convert the voxel coordinates of each voxel grid on the target blood vessel model into spatial coordinates.

[0072] A voxel grid is the basic discretized representation unit of a three-dimensional medical image (such as CTA). In the dissection task, the voxel grid is the basic unit for calculation and modeling, and its geometric and spatial information directly determines the accuracy of intimal flap extraction, feature calculation, and clustering results. Convert the voxel coordinates of each voxel grid into spatial coordinates (x, y, z).

[0073] Step 402, based on the spatial coordinates, calculate the distances between the voxel grid and all grid points on the first patch and the second patch to determine the grid points on the first patch and the second patch that are closest to it.

[0074] Specifically, based on the spatial coordinates of the voxel grid and the spatial coordinates of the grid points, calculate the distances between the voxel grid and all grid points on the first patch and the second patch to determine the grid points on the first patch and the second patch that are closest to it. When the closest grid point is on the first patch, mark it as 1, and when the closest grid point is on the second patch, mark it as 2.

[0075] Step 403, based on the spatial coordinates of the voxel grid and the spatial coordinates of the grid points, calculate the direction vector between the voxel grid and the closest grid point.

[0076] In one embodiment, the expression form of the feature vector V is as follows:

[0077] V = (D, , , , T);

[0078] ;

[0079] Wherein, D is the direction vector from the voxel grid to the grid point closest to it, x0, y0, z0 are the spatial coordinates of the voxel grid, x1, y1, z1 are the spatial coordinates of the grid point, when T = 1, it means the grid point is on the first patch, and when T = 2, it means the grid point is on the second patch.

[0080] In one embodiment, the process of extracting the vascular dissection intimal flap model based on the CTA image to be processed includes: extracting an initial vascular model based on the CTA image to be processed; since the intimal flap is disconnected in the initial vascular model, it is difficult to accurately extract the centerline of the blood vessel. Therefore, through the closing operation of morphological operations, the intimal flap is filled. Specifically, according to the closing operation of morphology, the intimal flap of the initial vascular model is filled to obtain a first target vascular model, and the centerline of the first target vascular model is extracted. Then, by taking the difference between the first target vascular model and the initial vascular model and taking the largest connected component, the vascular dissection intimal flap model is obtained.

[0081] In one embodiment, the process of extracting the target vascular model based on the CTA image to be processed includes: extracting the centerline of the first target vascular model; extracting the target point closest to each point on the vascular dissection intimal flap model on the centerline to form a target centerline; based on the target centerline and the first target vascular model, determining the target vascular model.

[0082] After obtaining the first target vascular model in this application, the centerline of the first target vascular model is extracted. For each point on the vascular dissection intimal flap model, the point on the centerline closest to it is found, and finally a continuous target centerline on the centerline can be obtained. Using this target centerline, further extract only the vascular model near the target centerline to remove the interference of the far - away vascular model on the segmentation process, and obtain the target vascular model, which is the model for which dissection is required.

[0083] It should be noted that the steps shown in the above process or the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer - executable instructions. And although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here.

[0084] In one embodiment, as Figure 3 shown, an embodiment of this application also provides a device for separating the dissection cavity based on a clustering algorithm. The device includes:

[0085] A first extraction module 10, configured to extract a vascular dissection intimal flap model and a target vascular model based on a CTA image to be processed;

[0086] The second extraction module 20 is configured to convert the vascular dissection intimal flap model into a mesh model, and extract two consecutive and largest first and second patches therefrom;

[0087] The feature vector construction module 30 is configured to, for each voxel grid on the target vascular model, determine the grid points on the first and second patches that are closest to it; calculate the direction vector between the voxel grid and the grid point, and construct a feature vector with the spatial coordinates of the grid point;

[0088] The cavity separation module 40 is configured to perform clustering analysis on the feature vectors corresponding to the voxel grids to obtain the dissection separation result.

[0089] In one embodiment, the second extraction module 20 is further configured to: obtain the normal vector of each triangular patch in the mesh model; divide the mesh model into multiple consecutive patches based on the normal vectors of the triangular patches; select the two patches with the largest areas from the multiple consecutive patches to obtain the first and second patches.

[0090] In one embodiment, the second extraction module 20 is further configured to: calculate the included angle between the normal vectors of each triangular patch and its adjacent triangular patch; if the included angle of the normal vectors is within the threshold range, determine that the triangular patch and its adjacent triangular patch are the same consecutive patch.

[0091] In one embodiment, the feature vector construction module 30 is further configured to: convert the voxel coordinates of each voxel grid on the target vascular model into spatial coordinates; calculate the distances between the voxel grid and all grid points on the first and second patches based on the spatial coordinates to determine the grid points on the first and second patches that are closest to it; calculate the direction vector between the voxel grid and the closest grid point based on the spatial coordinates of the voxel grid and the grid point.

[0092] In one embodiment, the expression form of the feature vector V is as follows:

[0093] V = (D, , , , T);

[0094] ;

[0095] where D is the direction vector between the voxel grid and the grid point, x0, y0, z0 are the spatial coordinates of the voxel grid, x1, y1, z1 are the spatial coordinates of the grid point, and when T = 1, it indicates that the grid point is on the first patch, and when T = 2, it indicates that the grid point is on the second patch.

[0096] In one embodiment, the first extraction module 10 is further configured to: extract an initial vascular model based on the CTA image to be processed; perform intimal flap filling on the initial vascular model based on morphological closing operation to obtain a first target vascular model; subtract the first target vascular model from the initial vascular model and take the largest connected component to obtain a vascular dissection intimal flap model.

[0097] In one embodiment, the first extraction module 10 is further configured to: extract the centerline of the first target vascular model; extract the target points closest to each point of the vascular dissection intimal flap model on the centerline to form a target centerline; determine a target vascular model based on the target centerline and the first target vascular model.

[0098] It should be noted that the above-mentioned each module can be a functional module or a program module, and can be implemented by software or hardware. For the modules implemented by hardware, the above-mentioned each module can be located in the same processor; or the above-mentioned each module can also be located in different processors in any combined form.

[0099] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 4 shown. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus.

[0100] Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a method for separating a sandwich cavity based on a clustering algorithm. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad provided on the outer shell of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0101] Those skilled in the art can understand, Figure 4The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0102] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in any of the above embodiments of the sandwich cavity separation method based on the clustering algorithm are implemented.

[0103] Those of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.

[0104] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0105] The above embodiments only represent several implementation manners of this application, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of the patent of this application should be subject to the appended claims.

Claims

1. A method for separating an interlayer cavity based on a clustering algorithm, characterized in that, The method includes: Based on the CTA image to be processed, extracting a vascular dissection intimal flap model and a target blood vessel model; Converting the vascular dissection intimal flap model into a mesh model, and extracting two consecutive and largest-area first patches and second patches therefrom; For each voxel grid on the target blood vessel model, determining the grid points on the first patch and the second patch that are closest to it; calculating the direction vector between the voxel grid and the grid point, and constructing a feature vector with the spatial coordinates of the grid point; Performing clustering analysis on the feature vectors corresponding to each voxel grid to obtain a dissection separation result.

2. The method according to claim 1, wherein The converting the vascular dissection intimal flap model into a mesh model and extracting two consecutive and largest-area first patches and second patches therefrom includes: Obtaining the normal vector of each triangular patch in the mesh model; Based on the normal vectors of the triangular patches, dividing the mesh model into multiple consecutive patches; Selecting two patches with the largest area from the multiple consecutive patches to obtain a first patch and a second patch.

3. The method according to claim 2, wherein The dividing the mesh model into multiple consecutive patches based on the normal vectors of the triangular patches includes: Calculating the included angle between the normal vectors of each triangular patch and its adjacent triangular patches; If the included angle of the normal vectors is within the threshold range, determining that the triangular patch and its adjacent triangular patch are in the same consecutive patch.

4. The method according to claim 1, wherein The for each voxel grid on the target blood vessel model, determining the grid points on the first patch and the second patch that are closest to it; calculating the direction vector between the voxel grid and the grid point includes: Converting the voxel coordinates of each voxel grid on the target blood vessel model into spatial coordinates; Based on the spatial coordinates, calculating the distances between the voxel grid and all grid points on the first patch and the second patch to determine the grid points on the first patch and the second patch that are closest to it; Based on the spatial coordinates of the voxel grid and the spatial coordinates of the grid point, calculating the direction vector between the voxel grid and the closest grid point.

5. The method according to claim 4, wherein The expression form of the feature vector V is as follows: V = (D, , , , T); ； Where D is the direction vector between the voxel grid and the grid point, x0, y0, z0 are the spatial coordinates of the voxel grid, x1, y1, z1 are the spatial coordinates of the grid point, when T = 1, it means the grid point is located on the first patch, and when T = 2, it means the grid point is located on the second patch.

6. The method according to claim 1, characterized in that The extracting the vascular dissection intimal flap model based on the CTA image to be processed includes: Based on the CTA image to be processed, extracting an initial blood vessel model; Performing intimal flap filling on the initial blood vessel model based on morphological closing operation to obtain a first target blood vessel model; Taking the difference between the first target blood vessel model and the initial blood vessel model and taking the largest connected component to obtain a vascular dissection intimal flap model.

7. The method according to claim 6, wherein The extracting the target blood vessel model based on the CTA image to be processed includes: Extracting the centerline of the first target blood vessel model; Extracting the target points closest to each point on the vascular dissection intimal flap model on the centerline to form a target centerline; Determine a target blood vessel model based on the target center line and the first target blood vessel model.

8. A sandwich cavity separation device based on a clustering algorithm, characterized in that, The device includes: A first extraction module, configured to extract a blood vessel dissection intimal flap model and a target blood vessel model based on a CTA image to be processed; A second extraction module, configured to convert the blood vessel dissection intimal flap model into a mesh model, and extract two consecutive and largest-area first patches and second patches therefrom; A feature vector construction module, configured to, for each voxel grid on the target blood vessel model, determine the grid point on the first patch and the second patch that is closest to it; calculate the direction vector between the voxel grid and the grid point, and construct a feature vector with the spatial coordinates of the grid point; A cavity separation module, configured to perform clustering analysis on the feature vectors corresponding to the voxel grids to obtain a dissection separation result.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images