Automatic identification method and device for pulmonary vein orifice

Abstract

The invention provides an automatic identification method and device for a pulmonary vein orifice, relates to the field of medical image processing, and solves the technical problem of low identification accuracy of the pulmonary vein orifice in a complex scene in the prior art. The method comprises the following steps: acquiring a vertex set and a triangular patch set of a left atrium three-dimensional grid model; calculating a three-dimensional space parameter of each vertex based on the vertex set and the triangular patch set, and generating a feature vector of the corresponding vertex according to the three-dimensional space parameter; and clustering the feature vector of each vertex through a clustering algorithm, and identifying the pulmonary vein orifice based on a clustering result. The method and device are used in the pulmonary vein mouth recognition process.

Description

Technical Field

[0001] This application relates to the field of medical image processing, and in particular to an automatic identification method and apparatus for pulmonary vein orifices. Background Technology

[0002] Atrial fibrillation is the most common arrhythmia in clinical practice. Currently, catheter ablation for pulmonary vein isolation is commonly used to treat atrial fibrillation. Therefore, automated pulmonary vein ostium identification technology is of significant diagnostic value for physicians.

[0003] In the field of medical image processing, existing technologies for identifying pulmonary vein ostia often employ simple distance-based calculations and threshold judgment methods. For example, firstly, the centroid of the entire left atrium is calculated; this step forms the basis for subsequent calculations. Then, the point farthest from the centroid is calculated and marked as a candidate point for a pulmonary vein ostia. Next, it is determined whether the number of candidate points reaches a preset threshold; if so, these candidate points are identified as pulmonary vein ostia. However, this approach only achieves good recognition results under regular left atrium structures. For more complex pulmonary vein ostia branches, it may only identify branch information while missing the pulmonary vein ostia, resulting in low accuracy in complex scenarios. Summary of the Invention

[0004] This application provides an automatic identification method and apparatus for pulmonary vein ostium, which solves the technical problem of low accuracy in pulmonary vein ostium identification in complex scenarios in the prior art.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] In one aspect, an automatic identification method for pulmonary vein orifices is provided, comprising: obtaining a vertex set and a triangular facet set of a three-dimensional mesh model of the left atrium; calculating the three-dimensional spatial parameters of each vertex based on the vertex set and the triangular facet set, and generating a feature vector of the corresponding vertex based on the three-dimensional spatial parameters; clustering the feature vector of each vertex using a clustering algorithm, and identifying the pulmonary vein orifice based on the clustering results.

[0007] Based on the above technical solution, the automatic identification device in this embodiment can acquire the vertex set and triangular facet set of the three-dimensional mesh model of the left atrium. Then, the automatic identification device calculates the three-dimensional spatial parameters of each vertex based on the vertex set and triangular facet set, and generates the feature vector of the corresponding vertex according to the three-dimensional spatial parameters. In this way, the automatic identification device can cluster the feature vectors of each vertex using a clustering algorithm and identify the pulmonary vein orifice based on the clustering results. Compared with related technologies that rely solely on distance and centroid for identification, which fail to consider geometric features and thus lead to inaccurate identification in complex structures, this embodiment can acquire a three-dimensional mesh model, calculate multi-dimensional spatial parameters, and cluster them to comprehensively characterize the geometric features of the pulmonary vein orifice, thereby achieving accurate identification and improving the accuracy of pulmonary vein orifice identification in complex scenarios.

[0008] In conjunction with the first aspect mentioned above, in one possible implementation, the clustering algorithm is the K-Means clustering algorithm, with 5 clusters, of which 4 clusters correspond to the pulmonary vein orifice and 1 cluster corresponds to the left atrium.

[0009] In conjunction with the first aspect mentioned above, in one possible implementation, the identification results of the five cluster categories are rendered using different colors, with the colors of the four pulmonary vein orifices differing from the rendering color of the main body of the left atrium.

[0010] In conjunction with the first aspect mentioned above, in one possible implementation, the three-dimensional spatial parameters include the three-dimensional coordinates of the vertex, the normal vector, the Gaussian curvature, and the mean curvature, and the eigenvector is composed of the three-dimensional coordinates, the three components of the normal vector, the mean curvature, and the Gaussian curvature.

[0011] In conjunction with the first aspect mentioned above, in one possible implementation, the normal vector of a vertex is determined by a weighted calculation based on the normal vectors of the triangular facets in the vertex's neighborhood; the Gaussian curvature is determined based on the included angle of the vertex and the local area of ​​the vertex; and the mean curvature is determined based on the length of the adjacent edge of the vertex, the angle of the opposite corner of the adjacent edge, and the local area of ​​the vertex in the triangular facets in the vertex's neighborhood.

[0012] In conjunction with the first aspect above, in one possible implementation, the local area of ​​a vertex is any of the following: the area of ​​the Thiessen polygon, the mixed area, or the area of ​​the centroid.

[0013] In conjunction with the first aspect mentioned above, in one possible implementation, the normal vector of a vertex satisfies the following formula:

[0014]

[0015] Where N(v) is the set of triangular faces in the neighborhood of a vertex. Let w be the normal vector of the triangular facet f. fLet f be the weighting coefficient of the triangular facet. Let be the normal vector of the vertex;

[0016] Gaussian curvature satisfies the following formula:

[0017]

[0018] Where K(v) is the Gaussian curvature of vertex v, A is the local area of ​​vertex v, and θ j The angle of the j-th included angle of the vertex;

[0019] The mean curvature satisfies the following formula:

[0020]

[0021] Where H is the mean curvature, A is the local area of ​​vertex v, and (v, v) i Let α be an adjacent edge of the vertex. i β i It is the angle opposite the diagonal of the adjacent side.

[0022] In conjunction with the first aspect mentioned above, in one possible implementation, the feature vector of each vertex is standardized using the following formula:

[0023]

[0024] Where x is the eigenvalue in the eigenvector, μ is the mean of the eigenvalues ​​in the dataset, σ is the standard deviation of the eigenvalues ​​in the dataset, and z is the eigenvalue after standardization.

[0025] Secondly, an automatic identification device is provided, comprising: a communication unit and a processing unit; the communication unit is used to acquire the vertex set and triangular facet set of a three-dimensional mesh model of the left atrium; the processing unit is used to calculate the three-dimensional spatial parameters of each vertex based on the vertex set and triangular facet set, and generate the feature vector of the corresponding vertex according to the three-dimensional spatial parameters; the processing unit is used to cluster the feature vector of each vertex through a clustering algorithm, and identify the pulmonary vein orifice based on the clustering results.

[0026] Thirdly, this application provides an automatic identification device, comprising: a processor and a storage medium; the storage medium includes instructions, and the processor is configured to execute the instructions to implement the method of any of the above embodiments. This automatic identification device may be an electronic device or a chip within an electronic device.

[0027] Fourthly, this application provides a computer-readable storage medium storing instructions that, when executed on an automatic identification device, cause the automatic identification device to perform the method described in any of the above embodiments.

[0028] Fifthly, this application provides a computer program product containing instructions that, when run on an automatic identification device, cause the automatic identification device to perform the method described in any of the above embodiments.

[0029] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments. Attached Figure Description

[0030] Figure 1 A system architecture diagram of an automatic pulmonary vein orifice identification system provided in this application embodiment;

[0031] Figure 2 A flowchart illustrating an automatic identification method for pulmonary vein orifices provided in an embodiment of this application;

[0032] Figure 3 A structural diagram of a three-dimensional mesh model of the left atrium provided in an embodiment of this application;

[0033] Figure 4 A structural diagram of another three-dimensional mesh model of the left atrium provided in this application embodiment;

[0034] Figure 5 This is a schematic diagram of the structure of an automatic identification device provided in an embodiment of this application;

[0035] Figure 6 This is a schematic diagram of the hardware structure of an automatic identification device provided in an embodiment of this application. Detailed Implementation

[0036] In the description of this application, unless otherwise stated, " / " means "or," for example, A / B can mean A or B. The "and / or" in this document 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 alone, A and B simultaneously, and B alone. Furthermore, "at least one" means one or more, and "multiple" means two or more. The terms "first," "second," etc., do not limit the quantity or order of execution, and "first," "second," etc., do not necessarily imply differences.

[0037] It should be noted that, in this application, the terms "exemplary" or "for example" are used to indicate that something is being described as an example, illustration, or illustration. Any embodiment or design described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0038] In the field of medical image processing, accurate identification of pulmonary vein ostia is crucial for the diagnosis and treatment of heart diseases. Currently, existing technologies for pulmonary vein ostia identification mostly employ simple distance-based calculation and threshold judgment methods. The specific implementation process is as follows: First, the centroid of the entire left atrium is calculated; this step forms the basis for subsequent calculations. Then, the point farthest from the centroid is calculated and marked as a candidate point for a pulmonary vein ostia. Next, it is determined whether the number of candidate points for pulmonary vein ostia reaches a preset threshold. If the threshold is reached, these candidate points are identified as pulmonary vein ostia and marked with a special color; if the threshold is not reached, the process returns to the step of calculating the next farthest point to continue the search.

[0039] However, this existing method has several drawbacks. First, it only considers the positional features of the three-dimensional heart, which is too one-sided. In the actual heart structure, the heart is an extremely complex three-dimensional organ, and the distribution and morphology of pulmonary veins are diverse and complex. Second, when there are too many points for a particular pulmonary vein, it will significantly affect the calculation of the centroid. Because the calculation of the centroid depends on the positional information of all points, too many points for a particular pulmonary vein will cause the centroid position to shift, thus affecting the final identification result of the pulmonary vein orifice. This leads to a significant reduction in the accuracy and reliability of this method when faced with complex heart structures and pulmonary vein distributions. In clinical applications, inaccurate pulmonary vein orifice identification may lead to misdiagnosis by doctors, affecting the formulation of subsequent treatment plans, and may even cause operational errors in some interventional treatments, posing unnecessary risks to patients. Therefore, developing a more accurate and reliable automatic pulmonary vein orifice identification method is urgently needed.

[0040] In view of this, this application provides an automatic identification method for pulmonary vein orifices. The automatic identification device can acquire the vertex set and triangular facet set of a three-dimensional mesh model of the left atrium. Then, the automatic identification device calculates the three-dimensional spatial parameters of each vertex based on the vertex set and triangular facet set, and generates the feature vector of the corresponding vertex according to the three-dimensional spatial parameters. In this way, the automatic identification device can cluster the feature vectors of each vertex using a clustering algorithm, and identify the pulmonary vein orifice based on the clustering results. Compared with the identification schemes in related technologies that are based only on distance and centroid, which do not consider geometric features, resulting in inaccurate identification in complex structures, this application embodiment can acquire a three-dimensional mesh model, calculate multi-dimensional spatial parameters and cluster them to comprehensively characterize the geometric features of the pulmonary vein orifice, thereby achieving accurate identification and improving the identification accuracy of the pulmonary vein orifice in complex scenes.

[0041] The embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0042] The automatic identification method for pulmonary vein orifices provided in this application embodiment can be applied to, for example... Figure 1 In the automatic identification system for pulmonary vein orifices shown, such as Figure 1 As shown, the automatic identification system for the pulmonary vein orifice includes: a data acquisition device 101 and an automatic identification device 102.

[0043] The data acquisition device 101 and the automatic identification device 102 are connected by a communication link, which can be a wired communication link or a wireless communication link. This application does not limit the type of communication link.

[0044] In some embodiments, the acquisition device 101 is used to acquire model data of the three-dimensional mesh model of the left atrium.

[0045] For example, the model data may include data related to the vertices and triangular facets that constitute the three-dimensional mesh model of the left atrium.

[0046] The acquisition device 101 is also used to send the acquired model data to the automatic identification device 102. The automatic identification device 102 is used to receive the model data from the acquisition device 101.

[0047] The automatic identification device 102 is used to acquire the vertex set and triangular facet set of the three-dimensional mesh model of the left atrium, calculate the three-dimensional spatial parameters of each vertex based on the vertex set and triangular facet set, generate the feature vector of the corresponding vertex according to the three-dimensional spatial parameters, cluster the feature vector of each vertex through a clustering algorithm, and identify the pulmonary vein orifice based on the clustering results.

[0048] For example, the automatic identification device 102 can be a server, including:

[0049] The processor can be a general-purpose central processing unit (CPU), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present application.

[0050] A transceiver can be any type of transceiver used to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area network (WLAN), etc.

[0051] Memory can be read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions, random access memory (RAM) or other types of dynamic storage devices capable of storing information and instructions, electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed discs, laser discs, optical discs, universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto. Memory can exist independently and be connected to the processor via communication lines. Memory can also be integrated with the processor.

[0052] The execution device for the automatic identification method of pulmonary vein orifice provided in this application can be Figure 1 The automatic identification device 102 is shown. The execution device can also be the central processing unit (CPU) of the electronic device, or a control module within the electronic device for executing the automatic identification method for the pulmonary vein orifice. This embodiment of the application uses the automatic identification device executing the automatic identification method for the pulmonary vein orifice as an example to illustrate the automatic identification method for the pulmonary vein orifice provided in this embodiment.

[0053] It should be noted that the various embodiments of this application can be referenced or learned from each other. For example, the same or similar steps, method embodiments, system embodiments and device embodiments can be referenced from each other without limitation.

[0054] Figure 2 This is a flowchart illustrating an automatic identification method for pulmonary vein orifices provided in an embodiment of this application. Figure 2 As shown, the method includes the following steps:

[0055] Step 201: Obtain the vertex set and triangular facet set of the three-dimensional mesh model of the left atrium.

[0056] For example, the three-dimensional mesh model of the left atrium can be represented as a three-dimensional mesh LA = (V, E), where V represents the set of all vertices, E represents the set of all triangular faces, and N represents the number of vertices. The coordinates of each vertex are (x, y, z). Each triangular face can be represented by its corresponding 3 vertices.

[0057] Step 202: Calculate the three-dimensional spatial parameters of each vertex based on the vertex set and the triangular facet set, and generate the feature vector of the corresponding vertex according to the three-dimensional spatial parameters.

[0058] In some embodiments, the three-dimensional spatial parameters include the three-dimensional coordinates of the vertex, the normal vector, the mean curvature, and the Gaussian curvature, and the eigenvector is composed of the three-dimensional coordinates, the three components of the normal vector, the mean curvature, and the Gaussian curvature.

[0059] For example, the normal vector of a vertex can be represented as The Gaussian curvature can be represented as k1, and the mean curvature can be represented as k2. The feature vector can be represented as F(x,y,z,vx,vy,vz,k1,k2), thus obtaining a dataset M with dimension N*8.

[0060] It should be noted that the four pulmonary vein orifices form a protruding branch shape relative to the left atrium. Therefore, the normal vector and curvature will change significantly on the protruding curved surface. The embodiments of this application can identify the pulmonary veins based on the distribution patterns of these changes, thereby improving the accuracy of identification.

[0061] Step 203: Cluster the feature vectors of each vertex using a clustering algorithm, and identify the pulmonary vein openings based on the clustering results.

[0062] In some embodiments, the clustering algorithm is the K-Means clustering algorithm, with 5 clusters, of which 4 clusters correspond to the pulmonary vein orifices and 1 cluster corresponds to the left atrium. In this embodiment, classifying the pulmonary vein orifices and the left atrium based on heart structure can effectively improve clustering accuracy.

[0063] For example, the identification results of the five cluster categories can be rendered in different colors, with the colors of the four pulmonary vein orifices differing from the rendered color of the main body of the left atrium. Alternatively, the colors of the four pulmonary vein orifices can also be different.

[0064] For example, in this embodiment of the application, K-Means clustering can be performed using the KMeans method in the Python machine learning library sklearn. Specifically, the automatic identification device can execute the following function:

[0065] y=KMeans(n_clusters=5, init=”k-means++”, max_iter=500, tol=1e-5; random_state=100).fi t(M2)

[0066] Where n_cluters represents the number of clusters, and the remaining values ​​are hyperparameter values. The maximum number of iterations max_iter is set to 500, and the error threshold tol is set to le-5. Since the KMeans algorithm is quite sensitive to the initial state, this method can make the selection of the initial cluster centers more reasonable and speed up the clustering convergence.

[0067] Set random_state = 100. The prediction result is y, with a dimension of N*1, and the value range of y is 0, 1, 2, 3, 4. These represent 5 classes, each represented by a different color. This allows the 5 classes of points in the LA to be labeled with their corresponding colors and rendered, with the four pulmonary vein orifices appearing in different colors.

[0068] In one example, such as Figure 3 The diagram shown is a structural diagram of a three-dimensional mesh model of the left atrium provided in an embodiment of this application. It includes four pulmonary vein orifices with prominent branches. Based on the automatic identification method for pulmonary vein orifices provided in this embodiment, the entire three-dimensional mesh model has 34,704 vertices and 69,404 triangular faces. The value of y ranges from 0 to 4. These represent five categories, thus dividing the three-dimensional mesh model into five parts. Part 1, Part 2, Part 3, and Part 4 correspond to the four pulmonary vein orifices, respectively, while Part 5 corresponds to the main body of the left atrium.

[0069] In yet another example, such as Figure 4The diagram shown is a structural diagram of another three-dimensional mesh model of the left atrium provided in this embodiment of the application. It includes four pulmonary vein orifices, each with numerous and intricate branches, making the entire three-dimensional mesh model quite complex. Based on the automatic identification method for pulmonary vein orifices provided in this embodiment, the entire three-dimensional mesh model can be determined to have 381,060 vertices and 761,402 triangular faces. The value of y ranges from 0 to 4. These represent five categories, thus dividing the three-dimensional mesh model into five parts. Parts 1, 2, 3, and 4 correspond to the four pulmonary vein orifices, and part 5 corresponds to the main body of the left atrium.

[0070] As can be seen from the above examples, the automatic identification method for pulmonary vein openings provided in this application embodiment can also accurately identify pulmonary vein openings in complex scenarios.

[0071] Based on the above technical solution, the automatic identification device in this embodiment can acquire the vertex set and triangular facet set of the three-dimensional mesh model of the left atrium. Then, the automatic identification device calculates the three-dimensional spatial parameters of each vertex based on the vertex set and triangular facet set, and generates the feature vector of the corresponding vertex according to the three-dimensional spatial parameters. In this way, the automatic identification device can cluster the feature vectors of each vertex using a clustering algorithm and identify the pulmonary vein orifice based on the clustering results. Compared with related technologies that rely solely on distance and centroid for identification, which fail to consider geometric features and thus lead to inaccurate identification in complex structures, this embodiment can acquire a three-dimensional mesh model, calculate multi-dimensional spatial parameters, and cluster them to comprehensively characterize the geometric features of the pulmonary vein orifice, thereby achieving accurate identification and improving the accuracy of pulmonary vein orifice identification in complex scenarios.

[0072] As one possible implementation, the normal vector of the vertex in the above three-dimensional spatial parameters is determined by weighted calculation based on the normal vectors of the triangular facets in the vertex's neighborhood, the Gaussian curvature is determined based on the included angle of the vertex and the local area of ​​the vertex, and the average curvature is determined based on the length of the adjacent side of the vertex, the angle of the opposite corner of the adjacent side, and the local area of ​​the vertex in the triangular facets in the vertex's neighborhood.

[0073] In some embodiments, the local area of ​​a vertex is any one of the following: the area of ​​a Thiessen polygon (also known as a Voronoi region), the mixed area, or the area of ​​the centroid.

[0074] In some embodiments, the normal vector of a vertex satisfies the following formula:

[0075]

[0076] Where N(v) is the set of triangular faces in the neighborhood of a vertex. Let w be the normal vector of the triangular facet f. f Let f be the weighting coefficient of the triangular facet. Let be the normal vector of the vertex.

[0077] In some embodiments, the Gaussian curvature satisfies the following formula:

[0078]

[0079] Where K(v) is the Gaussian curvature of vertex v, A is the local area of ​​vertex v, and θ j Let be the angle of the j-th included angle of the vertex.

[0080] In some embodiments, the mean curvature satisfies the following formula:

[0081]

[0082] Where H is the mean curvature, A is the local area of ​​vertex v, and (v, v) i Let α be an adjacent edge of the vertex. i β i It is the angle opposite the diagonal of the adjacent side.

[0083] Furthermore, the obtained feature vectors can be processed in the embodiments of this application to avoid the influence of numerical range differences on the clustering results and improve the stability of the algorithm.

[0084] As one possible implementation, the feature vector of each vertex is standardized using the following formula:

[0085]

[0086] Where x is the eigenvalue in the eigenvector, μ is the mean of the eigenvalues ​​in the dataset, σ is the standard deviation of the eigenvalues ​​in the dataset, and z is the eigenvalue after standardization.

[0087] The foregoing mainly describes the solutions of the embodiments of this application from the perspective of device implementation. It is understood that each device, such as an automatic identification device, includes at least one of the hardware structures and software modules corresponding to the execution of each function in order to achieve the above-mentioned functions. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in a hardware or computer software-driven manner depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0088] This application embodiment can divide the automatic identification device into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0089] When using integrated units, Figure 5 A possible structural schematic diagram of the automatic identification device (referred to as automatic identification device 50) involved in the above embodiments is shown. The automatic identification device 50 includes a processing unit 501 and a communication unit 502, and may also include a storage unit 503. Figure 5 The structural diagram shown can be used to illustrate the structure of the automatic identification device involved in the above embodiments.

[0090] when Figure 5 The schematic diagram shown illustrates the structure of the automatic identification device involved in the above embodiments. The processing unit 501 is used to control and manage the operation of the automatic identification device, the communication unit 502 is used for the automatic identification device to communicate with other devices, and the storage unit 503 is used to store the program code and data of the automatic identification device.

[0091] For example, communication unit 502 is used to obtain the vertex set and triangular facet set of the three-dimensional mesh model of the left atrium;

[0092] The processing unit 501 is used to calculate the three-dimensional spatial parameters of each vertex based on the vertex set and the triangular facet set, and generate the feature vector of the corresponding vertex according to the three-dimensional spatial parameters.

[0093] The processing unit 501 is used to cluster the feature vectors of each vertex using a clustering algorithm, and to identify the pulmonary vein orifice based on the clustering results.

[0094] In one possible implementation, the clustering algorithm is the K-Means clustering algorithm, with 5 clusters, of which 4 clusters correspond to the pulmonary vein orifice and 1 cluster corresponds to the left atrium.

[0095] In one possible implementation, the identification results of the five cluster categories are rendered in different colors, with the colors of the four pulmonary vein orifices being different from the rendering color of the main body of the left atrium.

[0096] In one possible implementation, the three-dimensional spatial parameters include the three-dimensional coordinates of the vertex, the normal vector, the Gaussian curvature, and the mean curvature, and the eigenvector is composed of the three-dimensional coordinates, the three components of the normal vector, the mean curvature, and the Gaussian curvature.

[0097] In one possible implementation, the vertex normal vector is determined by a weighted average of the normal vectors of the triangular facets in the vertex's neighborhood; the Gaussian curvature is determined based on the included angle of the vertex and the local area of ​​the vertex; and the mean curvature is determined based on the length of the adjacent edge of the vertex, the angle of the opposite corner of the adjacent edge, and the local area of ​​the vertex in the triangular facets in the vertex's neighborhood.

[0098] In one possible implementation, the local area of ​​a vertex is any of the following: the area of ​​the Thiessen polygon, the mixed area, or the area of ​​the centroid.

[0099] In one possible implementation, the normal vector of a vertex satisfies the following formula:

[0100]

[0101] Where N(v) is the set of triangular faces in the neighborhood of a vertex. Let w be the normal vector of the triangular facet f. f Let f be the weighting coefficient of the triangular facet. Let be the normal vector of the vertex;

[0102] Gaussian curvature satisfies the following formula:

[0103]

[0104] Where K(v) is the Gaussian curvature of vertex v, A is the local area of ​​vertex v, and θ j The angle of the j-th included angle of the vertex;

[0105] The mean curvature satisfies the following formula:

[0106]

[0107] Where H is the mean curvature, A is the local area of ​​vertex v, and (v, v) i Let α be an adjacent edge of the vertex. i β i It is the angle opposite the diagonal of the adjacent side.

[0108] In one possible implementation, the feature vector of each vertex is standardized using the following formula:

[0109]

[0110] Where x is the eigenvalue in the eigenvector, μ is the mean of the eigenvalues ​​in the dataset, σ is the standard deviation of the eigenvalues ​​in the dataset, and z is the eigenvalue after standardization.

[0111] The processing unit 501 can be a processor or a controller, and the communication unit 502 can be a communication interface, transceiver, transceiver circuit, transceiver device, etc. The term "communication interface" is a general term and may include one or more interfaces. The storage unit 503 can be a memory. When the automatic identification device 50 is a chip, the processing unit 501 can be a processor or a controller, and the communication unit 502 can be an input interface and / or an output interface, pins, or circuits, etc. The storage unit 503 can be a storage unit within the chip (e.g., a register, cache, etc.) or a storage unit located outside the chip (e.g., read-only memory (ROM), random access memory (RAM, etc.)).

[0112] The communication unit can also be called a transceiver unit. The antenna and control circuit with transceiver functions in the automatic identification device 50 can be considered as the communication unit 502 of the automatic identification device 50, and the processor with processing functions can be considered as the processing unit 501 of the automatic identification device 50. Optionally, the device in the communication unit 502 that implements the receiving function can be considered as a communication unit, which is used to execute the receiving steps in the embodiments of this application. The communication unit can be a receiver, a receiver circuit, etc. The device in the communication unit 502 that implements the transmitting function can be considered as a transmitting unit, which is used to execute the transmitting steps in the embodiments of this application. The transmitting unit can be a transmitter, a transmitter, a transmitting circuit, etc.

[0113] Figure 5 If the integrated units in the process are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this application, in essence, or the parts that contribute to the prior art, or all or part of the technical solutions, can be embodied in the form of software products. These computer software products are stored in a storage medium and include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the methods described in the various embodiments of this application. Storage media for storing computer software products include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory, random access memory, magnetic disks, or optical disks.

[0114] Figure 5 The units in the process can also be called modules; for example, a processing unit can be called a processing module.

[0115] This application also provides a hardware structure diagram of an automatic identification device (referred to as automatic identification device 60), see [link to diagram]. Figure 6The automatic identification device 60 includes a processor 601, and optionally, a memory 602 connected to the processor 601.

[0116] In the first possible implementation, see Figure 6 The automatic identification device 60 also includes a transceiver 603. The processor 601, memory 602, and transceiver 603 are connected via a bus. The transceiver 603 is used to communicate with other devices or communication networks. Optionally, the transceiver 603 may include a transmitter and a receiver. The device in the transceiver 603 that implements the receiving function can be considered as a receiver, which is used to perform the receiving steps in the embodiments of this application. The device in the transceiver 603 that implements the transmitting function can be considered as a transmitter, which is used to perform the transmitting steps in the embodiments of this application.

[0117] Based on the first possible implementation method Figure 6 The structural diagram shown can be used to illustrate the structure of the automatic identification device involved in the above embodiments.

[0118] in, Figure 6 The system chip in the automatic identification device can also be illustrated. In this case, the actions performed by the automatic identification device can be implemented by the system chip. The specific actions performed can be found above and will not be repeated here.

[0119] In implementation, each step of the method provided in this embodiment can be completed by integrated logic circuits in the processor or by instructions in software form. The steps of the method disclosed in the embodiments of this application can be directly manifested as being executed by a hardware processor, or being executed by a combination of hardware and software modules in the processor.

[0120] The processor in this application may include, but is not limited to, at least one of the following: a central processing unit (CPU), a microprocessor, a digital signal processor (DSP), a microcontroller unit (MCU), or an artificial intelligence processor, etc., which are various computing devices that run software. Each computing device may include one or more cores for executing software instructions to perform calculations or processing. The processor may be a separate semiconductor chip or integrated with other circuits into a single semiconductor chip. For example, it may be integrated with other circuits (such as encoding / decoding circuits, hardware acceleration circuits, or various bus and interface circuits) to form a SoC (System-on-a-Chip), or it may be integrated as a built-in processor within an ASIC. The ASIC with the integrated processor may be packaged separately or together with other circuits. In addition to the cores for executing software instructions to perform calculations or processing, the processor may further include necessary hardware accelerators, such as field-programmable gate arrays (FPGAs), PLDs (programmable logic devices), or logic circuits that implement dedicated logic operations.

[0121] The memory in the embodiments of this application may include at least one of the following types: read-only memory (ROM) or other types of static storage devices capable of storing static information and instructions; random access memory (RAM) or other types of dynamic storage devices capable of storing information and instructions; or electrically erasable programmable-only memory (EEPROM). In some scenarios, the memory may also be a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0122] This application also provides a computer-readable storage medium including instructions that, when run on a computer, cause the computer to perform any of the methods described above.

[0123] This application also provides a computer program product containing instructions that, when run on a computer, cause the computer to perform any of the methods described above.

[0124] This application also provides a chip including a processor and an interface circuit. The interface circuit is coupled to the processor. The processor is used to run computer programs or instructions to implement the above-described method. The interface circuit is used to communicate with other modules outside the chip.

[0125] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks (SSDs)).

[0126] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, the disclosure, and the appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude multiple instances. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0127] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the spirit and scope of this application. Accordingly, this specification and drawings are merely exemplary illustrations of this application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from the spirit and scope of this application. Thus, if such modifications and modifications of this application fall within the scope of the claims of this application and their equivalents, this application is also intended to include such modifications and modifications.

Claims

1. An automatic identification method for pulmonary vein orifices, characterized in that, include: Obtain the vertex set and triangle set of the three-dimensional mesh model of the left atrium; The three-dimensional spatial parameters of each vertex are calculated based on the vertex set and the triangular facet set, and the feature vector of the corresponding vertex is generated according to the three-dimensional spatial parameters. The feature vectors of each vertex are clustered using a clustering algorithm, and the pulmonary vein orifice is identified based on the clustering results.

2. The method according to claim 1, characterized in that, The clustering algorithm is the K-Means clustering algorithm, with 5 clusters, of which 4 clusters correspond to the pulmonary vein orifice and 1 cluster corresponds to the main body of the left atrium.

3. The method according to claim 2, characterized in that, The identification results of the five cluster categories are rendered in different colors, with the colors of the four pulmonary vein orifices being different from the rendering color of the main body of the left atrium.

4. The method according to claim 1, characterized in that, The three-dimensional spatial parameters include the three-dimensional coordinates of the vertex, the normal vector, the Gaussian curvature, and the mean curvature. The eigenvector is composed of the three-dimensional coordinates, the three components of the normal vector, the mean curvature, and the Gaussian curvature.

5. The method according to claim 4, characterized in that, The normal vector of the vertex is determined by a weighted calculation based on the normal vectors of the triangular facets in the vertex's neighborhood; the Gaussian curvature is determined based on the included angle of the vertex and the local area of ​​the vertex; the average curvature is determined based on the length of the adjacent edge of the vertex, the angle of the opposite diagonal of the adjacent edge, and the local area of ​​the vertex in the triangular facets in the vertex's neighborhood.

6. The method according to claim 5, characterized in that, The local area of ​​the vertex is any one of the following: the area of ​​the Thiessen polygon, the mixed area, or the area of ​​the centroid.

7. The method according to claim 5, characterized in that, The normal vector of the vertex satisfies the following formula: Where N(v) is the set of triangular faces in the neighborhood of the vertex. Let w be the normal vector of the triangular facet f. f Let f be the weighting coefficient of the triangular facet. Let be the normal vector of the vertex; The Gaussian curvature satisfies the following formula: Where K(v) is the Gaussian curvature of vertex v, A is the local area of ​​vertex v, and θ j The angle of the j-th included angle of the vertex; The average curvature satisfies the following formula: Where H is the average curvature, A is the local area of ​​vertex v, (v, v) i ) represents the adjacent edge of the vertex, α i β i The angle is the diagonal of the adjacent side.

8. The method according to claim 1, characterized in that, The feature vector of each vertex is standardized using the following formula: Where x is the eigenvalue in the eigenvector, μ is the mean of the eigenvalues ​​in the dataset, σ is the standard deviation of the eigenvalues ​​in the dataset, and z is the eigenvalue after standardization.

9. An automatic identification device, characterized in that, The device includes: a communication unit and a processing unit; The communication unit is used to acquire the vertex set and triangular facet set of the three-dimensional mesh model of the left atrium; The processing unit is used to calculate the three-dimensional spatial parameters of each vertex based on the vertex set and the triangular facet set, and generate the feature vector of the corresponding vertex according to the three-dimensional spatial parameters. The processing unit is used to cluster the feature vectors of each vertex using a clustering algorithm, and to identify the pulmonary vein openings based on the clustering results.

10. An automatic identification device, characterized in that, include: A processor and a communication interface; the communication interface is coupled to the processor, the processor being used to run computer programs or instructions to implement the automatic identification method as described in any one of claims 1-8.

Images