Left ventricle motion prediction method, system and device based on triangulation, and medium

Abstract

The invention provides a left ventricular motion prediction method, system and device based on triangulation and a medium, and relates to the technical field of medical image processing, and the method comprises the steps: obtaining a left ventricular intima contour image, and extracting a key point set and coordinate information from the left ventricular intima contour image; processing the left ventricular intimal contour image by using a VGG16 network model, and extracting feature information of a key point set; constructing a graph structure in combination with a triangulation method, and capturing structure information of the key point set; aggregating features through a graph convolutional neural network model to obtain embedded information of the key point set; carrying out feature matching by using a Sinkhorn algorithm to obtain a diastolic-systolic deformation relationship of the left ventricular intimal contour; and finally, predicting the motion of the left ventricle according to the diastolic-systolic deformation relation of the left ventricular intimal contour to obtain a left ventricular motion prediction result. According to the method, the structure information between the key points is constructed by combining the triangulation method and the Sinkhorn algorithm, and the accuracy of feature matching is improved, so that the accuracy of left ventricle motion prediction is improved.

Description

Technical Field

[0001] The present application relates to the technical field of medical image processing, and in particular to a left ventricular motion prediction method, system, device and medium based on triangulation. Background Art

[0002] Cardiac medical image processing technology plays a vital role in the early diagnosis, treatment planning and disease monitoring of heart disease, and can provide key information about the structure and functional status of the heart. However, existing technologies such as generalized robust point matching, iterative closest point and thin plate spline-based robust point matching, although effective in some cases, often overemphasize point features and ignore the topological relationship between key points, resulting in abnormal corresponding predictions between myocardial contours. In addition, although image registration-based methods can integrate local and global information, they are computationally intensive and time-consuming when processing high-dimensional data; feature tracking-based methods may fall into local optimal solutions; graph matching-based methods reduce computational costs but may ignore global geometric structures. Therefore, existing technologies face challenges in processing cardiac images, and more accurate and robust solutions are urgently needed to improve the accuracy of left ventricular motion prediction based on triangulation. Summary of the invention

[0003] The present application provides a left ventricular motion prediction method, system, device and medium based on triangulation to solve one or more technical problems existing in the prior art and at least provide beneficial options or create conditions.

[0004] On the one hand, the present application provides a left ventricular motion prediction method based on triangulation, comprising the following steps: Obtain left ventricular endocardial contour images; According to the left ventricular endocardial contour image, coordinate information of a key point set is obtained; the key point set includes an end-diastolic key point subset and an end-systolic key point subset; According to the left ventricular endocardium contour image and the coordinate information of the key point set, feature processing is performed using a VGG16 network model to obtain feature information of the key point set; According to the coordinate information and feature information of the key point set, a graph construction process is performed in combination with a triangulation method to obtain structural information of the key point set; According to the structural information and feature information of the key point set, a graph convolutional neural network model is used to perform feature aggregation to obtain embedded information of the key point set; According to the embedded information and coordinate information of the key point set, feature matching is performed in combination with the Sinkhorn algorithm to obtain the diastolic-systolic deformation relationship of the left ventricular endocardial contour; The diastolic-systolic movement of the left ventricular endocardial contour is predicted according to the diastolic-systolic deformation relationship of the left ventricular endocardial contour to obtain a left ventricular movement prediction result.

[0005] Further, the feature processing is performed using a VGG16 network model based on the left ventricular endocardium contour image and the coordinate information of the key point set to obtain the feature information of the key point set, including: According to the left ventricular endocardial contour image, feature processing is performed using the VGG16 network model to obtain an initial feature tensor; According to the initial feature tensor and the coordinate information of the key point set, in combination with a bilinear interpolation method, feature information of the key point set is obtained.

[0006] Furthermore, the graph construction process is performed based on the coordinate information and feature information of the key point set in combination with a triangulation method to obtain the structural information of the key point set, including: Obtaining a distance matrix according to the coordinate information and feature information of the key point set; the distance matrix is ​​used to characterize the distance between each key point in the key point set; According to the distance matrix, combined with the triangulation method, a weighted adjacency matrix of the key point set is obtained as structural information; the triangulation method is used to establish connections between key point pairs in the key point set whose distance does not exceed two units.

[0007] Furthermore, the step of performing feature aggregation using a graph convolutional neural network model based on the structural information and feature information of the key point set to obtain the embedded information of the key point set includes: According to the structural information and feature information of the key point set, the in-graph aggregation features of the key point set are obtained by utilizing the in-graph convolution mechanism of the graph convolutional neural network model; According to the structural information and feature information of the key point set, the cross-graph aggregation features of the key point set are obtained by utilizing the cross-graph convolution mechanism of the graph convolutional neural network model and combining with the similarity matrix; Embedding information of the key point set is obtained according to the intra-graph aggregation features and cross-graph aggregation features of the key point set.

[0008] Further, the embedding information of the key point set includes end-diastolic embedding information and end-systolic embedding information; The embedding information and coordinate information of the key point set are combined with the Sinkhorn algorithm to perform feature matching to obtain the diastolic-systolic deformation relationship of the left ventricular endocardial contour, including: Calculating the similarity between the end-diastolic embedded information and the end-systolic embedded information to obtain a score matrix; According to the score matrix, feature matching is performed in combination with the Sinkhorn algorithm to obtain a matching matrix; The diastolic-systolic deformation relationship of the left ventricular endocardial contour is obtained according to the comprehensive information of the matching matrix and the key point set.

[0009] Furthermore, the feature matching is performed according to the score matrix in combination with the Sinkhorn algorithm to obtain a matching matrix, including: Iteratively normalizing the score matrix using the Sinkhorn algorithm to obtain a converged double random matrix; According to the converged double random matrix, the matching matrix is ​​obtained; in the matching matrix, only one element in each row and each column is 1, and all other elements are 0; The matching matrix is ​​optimized by minimizing the negative log loss.

[0010] Furthermore, the diastolic-systolic deformation relationship of the left ventricular endocardial contour is obtained based on the comprehensive information of the matching matrix and the key point set, including: Obtaining a deformation function according to the comprehensive information of the matching matrix and the key point set; According to the deformation function, the diastolic-systolic deformation relationship of the left ventricular endocardium contour is obtained.

[0011] On the other hand, the present application provides a left ventricular motion prediction system based on triangulation, including: a data acquisition module, a coordinate acquisition module, a feature processing module, a graph construction module, a feature aggregation module, a feature matching module and a deformation prediction module; The data acquisition module is used to acquire the left ventricular endocardial contour image; The coordinate acquisition module is used to obtain the coordinate information of the key point set according to the left ventricular endocardial contour image; the key point set includes an end-diastolic key point subset and an end-systolic key point subset; The feature processing module is used to perform feature processing using a VGG16 network model according to the left ventricular endocardial contour image and the coordinate information of the key point set to obtain feature information of the key point set; The graph construction module is used to perform graph construction processing based on the coordinate information and feature information of the key point set in combination with a triangulation method to obtain the structural information of the key point set; The feature aggregation module is used to perform feature aggregation using a graph convolutional neural network model according to the structural information and feature information of the key point set to obtain embedded information of the key point set; The feature matching module is used to perform feature matching based on the embedded information and coordinate information of the key point set in combination with the Sinkhorn algorithm to obtain the diastolic-systolic deformation relationship of the left ventricular endocardial contour; The deformation prediction module is used to predict the diastolic-systolic motion of the left ventricular endocardial contour according to the diastolic-systolic deformation relationship of the left ventricular endocardial contour to obtain a left ventricular motion prediction result.

[0012] On the other hand, the present application provides a left ventricular motion prediction device based on triangulation, comprising: a processor and a memory; the memory is used to store a program; When the program is executed by the processor, the processor implements the aforementioned left ventricular motion prediction method based on triangulation.

[0013] On the other hand, the present application provides a computer-readable storage medium storing a program executable by a processor, wherein the program executable by the processor is used to implement the aforementioned left ventricular motion prediction method based on triangulation when executed by the processor.

[0014] The beneficial effects of the present application are as follows: the present application provides a left ventricular motion prediction method based on triangulation, comprising: acquiring a left ventricular endocardial contour image; obtaining coordinate information of a key point set based on the left ventricular endocardial contour image; the key point set comprising an end-diastolic key point subset and an end-systolic key point subset; performing feature processing using a VGG16 network model based on the left ventricular endocardial contour image and the coordinate information of the key point set to obtain feature information of the key point set; performing graph construction processing based on the coordinate information and feature information of the key point set in combination with a triangulation method to obtain structural information of the key point set; performing feature aggregation using a graph convolutional neural network model based on the structural information and feature information of the key point set to obtain embedded information of the key point set; performing feature matching based on the embedded information and coordinate information of the key point set in combination with a Sinkhorn algorithm to obtain a diastolic-systolic deformation relationship of the left ventricular endocardial contour; predicting the diastolic-systolic motion of the left ventricular endocardial contour based on the diastolic-systolic deformation relationship of the left ventricular endocardial contour to obtain a left ventricular motion prediction result. This application combines the triangulation method and the Sinkhorn algorithm to construct structural information between key points, improve the accuracy of feature matching, and thus improve the accuracy of left ventricular motion prediction. This application also provides corresponding devices, systems, and media, and the beneficial effects of the devices, systems, and media are similar to those of the method, and will not be repeated here.

[0015] Other features and advantages of the present application will be described in the following description, and partly become apparent from the description, or understood by practicing the present application. The purpose and other advantages of the present application can be realized and obtained by the structures specifically pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0017] Figure 1 is a flow chart of a left ventricular motion prediction method based on triangulation provided by the present application; Figure 2 It is a schematic diagram of the principle of determining the coordinate information, feature information and structure information of a set of key points provided by the present application; Figure 3 It is a principle diagram of obtaining the left ventricular motion prediction result according to the coordinate information, feature information and structure information of the key point set provided by the present application; Figure 4 is a structural diagram of a left ventricular motion prediction system based on triangulation provided by the present application; Figure 5 It is a structural diagram of the left ventricular motion prediction device based on triangulation provided in this application. DETAILED DESCRIPTION

[0018] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with 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.

[0019] The present application is further described below in conjunction with the accompanying drawings and specific embodiments. The described embodiments should not be regarded as limiting the present application, and all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0020] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0022] Cardiovascular diseases have an effective impact on the structure and function of the heart, especially the morphology and function of the left ventricle. As the key chamber for pumping blood, the normal operation of the left ventricle is essential for maintaining heart function. However, common cardiovascular diseases such as coronary heart disease and hypertension can cause abnormalities in the structure of the left ventricle, such as myocardial hypertrophy or dilatation, which in turn affects the contraction and relaxation function of the heart. Therefore, early and accurate prediction of left ventricular motion is of great significance for the diagnosis and treatment of heart disease. With the advancement of medical imaging technologies such as magnetic resonance imaging and computed tomography, computer-aided diagnosis has played an important role in medical imaging research. Traditionally, medical experts rely on personal experience to interpret medical images and provide diagnostic reports, but this method is easily affected by subjective factors and may lead to misdiagnosis or missed diagnosis. By introducing computer-aided technology, the error rate can be significantly reduced and help medical experts analyze the condition more accurately. In recent years, research on combining computer technology with medical imaging has become a hot area, aiming to improve diagnostic accuracy and treatment effects.

[0023] In the task of left ventricular motion prediction, most of the existing technologies optimize matching and prediction performance through multi-view feature integration, shape-aware loss functions, etc., but they all have some shortcomings. Among them, the image registration-based method is computationally intensive and time-consuming when processing high-dimensional data; traditional feature tracking methods such as the iterative nearest point method may fall into the local optimal solution, resulting in suboptimal correspondence; among the feature tracking methods based on graph matching, the deformable graph matching method reduces the computational cost, but over-focuses on the local structure and ignores the global geometric information; the random depth graph matching method introduces a hierarchical attention mechanism to reduce the impact of noise, but increases the computational complexity and time overhead. Therefore, the above limitations affect the application effect of the existing technology in left ventricular contour matching and motion prediction.

[0024] In view of the problems and defects existing in the related art, the embodiment of the present application provides a left ventricular motion prediction method, system, device and medium based on triangulation. First, the left ventricular endocardial contour image and the coordinate information of the key point set are obtained. These key points are used to characterize the left ventricular endocardial contour. Then, the VGG16 network model is used for feature processing to obtain the feature information of the key point set, and then the triangulation method is used to construct a graph according to the feature information and coordinate information of the key point set to obtain the structural information of the key point set. Then, the graph convolutional neural network model is used for feature aggregation and the Sinkhorn algorithm is used for feature matching to obtain the diastolic-systolic deformation relationship of the left ventricular endocardial contour; according to the diastolic-systolic deformation relationship of the left ventricular endocardial contour, the diastolic-systolic motion of the left ventricular endocardial contour is predicted to obtain the left ventricular motion prediction result. The embodiment of the present application not only improves the quality of feature representation, but also enhances the ability to capture local and global structural information, and achieves more accurate and smooth left ventricular motion prediction.

[0025] First, the implementation steps of the left ventricular motion prediction method based on triangulation provided in the embodiment of the present application will be described in detail below with reference to the accompanying drawings.

[0026] The left ventricular motion prediction method based on triangulation proposed in the embodiment of the present application can be applied to a terminal, a server, or software running in a terminal or a server. The terminal can be a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content distribution networks, and big data and artificial intelligence platforms.

[0027] Reference Figure 1 The implementation process of the left ventricular motion prediction method based on triangulation provided in the embodiment of the present application may include but is not limited to the following steps.

[0028] Step 101: Acquire a left ventricular endocardial contour image.

[0029] In step 101, the left ventricular endocardial contour image is obtained to provide raw data for subsequent analysis. The endocardial contour image of the heart is an intuitive representation of the internal structure of the heart, especially the left ventricle. The changes in shape and position during the cardiac cycle are crucial for diagnosing cardiovascular diseases. These images obtained by medical imaging techniques such as MRI or CT scanning are the basis for left ventricular motion analysis.

[0030] Step 102: Obtain coordinate information of a set of key points based on the left ventricular endocardium contour image.

[0031] It should be noted that the key point set includes the end-diastolic key point subset and the end-systolic key point subset. The contour of the left ventricular endocardium can reflect the morphological changes of the heart at different stages of the cardiac cycle (such as end-diastole and end-systole). By analyzing the changes in these contours, the functional state of the heart can be evaluated, including the contractility of the myocardium and the changes in ventricular volume. Many cardiovascular diseases can cause abnormalities in cardiac structure and function, which are usually reflected in the contour of the left ventricular endocardium. For example, diseases such as myocardial infarction and cardiomyopathy can cause local or overall myocardial movement to weaken or disappear, thereby changing the normal contour of the left ventricular endocardium. Therefore, accurately identifying and matching the left ventricular endocardium contour can help to detect and diagnose these diseases at an early stage.

[0032] In step 102, key points and their coordinate information are extracted from the left ventricular endocardial contour image. These key points are usually located at prominent positions of the contour, such as vertices, edge intersections, etc. The selection of key points is very important for accurately tracking heart movement. Dividing the key points into two subsets, end-diastole and end-systole, helps to compare the changes in heart morphology in different cardiac stages, thereby better understanding heart function.

[0033] Step 103, based on the left ventricular endocardium contour image and the coordinate information of the key point set, feature processing is performed using the VGG16 network model to obtain feature information of the key point set.

[0034] It should be noted that the VGG16 network model is a deep convolutional neural network consisting of 13 convolutional layers and 3 fully connected layers, and is well-known for its excellent performance in image classification tasks. The VGG16 network model can extract deep features from the left ventricular endocardium contour image, which can capture the complex structural information in the image.

[0035] In step 103, the VGG16 network model is used to automatically extract deep features in the left ventricular endocardium contour image to obtain feature information of the key point set. Compared with manually designed features, the VGG16 network model can capture more complex and more representative feature patterns, which is very beneficial to improving matching accuracy and robustness.

[0036] Step 104 , based on the coordinate information and feature information of the key point set, a graph is constructed in combination with a triangulation method to obtain structural information of the key point set.

[0037] In step 104, a triangulation method is introduced to establish the connection relationship between the key points, forming a graph that can reflect the topological structure of the left ventricular endocardium contour. This method not only considers the directly adjacent key points, but also considers the influence of key points at a longer distance, thereby more comprehensively representing the spatial structure of the heart contour and improving the accuracy of subsequent matching tasks.

[0038] Step 105, based on the structural information and feature information of the key point set, a graph convolutional neural network model is used to perform feature aggregation to obtain the embedded information of the key point set.

[0039] It should be noted that the graph convolutional neural network model is a deep learning model specifically designed to process graph structured data. Unlike traditional convolutional neural networks, the graph convolutional neural network model can perform feature extraction and information propagation in non-Euclidean space. It defines the convolution operation through the adjacency matrix and key point feature matrix of the graph, so that the features of each key point not only contain its own information, but also integrate the features of its neighboring key points. This mechanism can effectively capture the local and global relationships between key points and is suitable for tasks such as key point classification, graph classification, and link prediction.

[0040] In step 105, a graph convolutional neural network model is used to perform feature aggregation, and the structural information and feature information of the key point set are fused to generate richer embedded information. The graph convolutional neural network model can effectively capture the relationship between key points and reflect the topological structure of the graph. By propagating and aggregating information along edges and key points, local and global relationship information can be fully captured. The embedded information generated in this way not only contains the features of the key points, but also takes into account its position in the overall structure and its relationship with other key points. This provides a more comprehensive and accurate feature representation for subsequent key point matching.

[0041] Step 106, based on the embedded information and coordinate information of the key point set, feature matching is performed in combination with the Sinkhorn algorithm to obtain the diastolic-systolic deformation relationship of the left ventricular endocardium contour.

[0042] In step 106, based on the embedding information and coordinate information obtained in the previous steps, the distribution matrix between the feature points is calculated in combination with the Sinkhorn algorithm. This step ensures the one-to-one matching relationship of the feature points, avoids the problem of repeated matching or missing matching of feature points, and improves the accuracy and consistency of the prediction of the diastolic-systolic deformation relationship of the left ventricular endocardial contour.

[0043] Step 107, predicting the diastolic-systolic motion of the left ventricular endocardial contour according to the diastolic-systolic deformation relationship of the left ventricular endocardial contour, and obtaining a left ventricular motion prediction result.

[0044] In step 107, the movement of the left ventricle is predicted based on the diastolic-systolic deformation relationship of the left ventricular endocardial contour. The high-precision and robust matching results obtained in the above steps can more accurately track the changes of the left ventricle from diastolic to systolic state, and then evaluate its functional state. This is of great significance for the early diagnosis and treatment of heart disease and can provide valuable reference information for clinicians.

[0045] In some embodiments of the present application, reference Figure 2In step 103, based on the left ventricular endocardial contour image and the coordinate information of the key point set, the VGG16 network model is used to perform feature processing to obtain the feature information of the key point set, including but not limited to the following steps.

[0046] Step 201, based on the left ventricular endocardium contour image, feature processing is performed using the VGG16 network model to obtain an initial feature tensor.

[0047] In step 201, the VGG16 network model is used to automatically learn the rich visual features in the left ventricular endocardial contour image as the initial feature tensor, including texture, edges and other complex patterns, thereby providing a highly accurate and comprehensive feature description. These high-quality initial feature tensors provide a solid foundation for subsequent graph construction, feature aggregation and matching, and effectively improve the accuracy and robustness of left ventricular contour matching and motion prediction.

[0048] Step 202, based on the initial feature tensor and the coordinate information of the key point set, the feature information of the key point set is obtained in combination with the bilinear interpolation method.

[0049] It should be noted that bilinear interpolation is a commonly used interpolation technique in image processing, which is used to predict the pixel values ​​of non-grid points in an image. This method is calculated based on the known pixel values ​​of the four nearest neighbors around the target position. Specifically, the two pixel values ​​on both sides of the target position are first linearly interpolated in the horizontal direction to obtain two intermediate values; then the two intermediate values ​​are linearly interpolated again in the vertical direction to finally obtain the pixel value of the target position. Bilinear interpolation can generate smooth and continuous images by considering the influence of the four surrounding pixels, which is suitable for operations such as image scaling, rotation and deformation.

[0050] In step 202, by performing bilinear interpolation on the feature tensor output by the VGG16 network model, the feature map is precisely aligned with the key point coordinates, thereby generating a feature vector at each key point position, and obtaining more refined and accurate key point feature information. This not only improves the detail of feature representation, but also ensures that the feature information is highly consistent with the actual position of the key point, providing a solid foundation for subsequent feature matching and motion prediction.

[0051] In some embodiments of the present application, when performing feature processing, the output of the second convolution of the fourth layer and the first convolution of the fifth layer of the VGG16 network model are selected as the initial feature tensor. The reason is that the features of these intermediate layers can capture the transition information from local details to high-level patterns. The lower-level features mainly capture local information such as the edges and textures of the image, while the higher-level features gradually transition to capturing more abstract parts of the object. The fourth and fifth layers are in the middle of the VGG16 network model, which not only retains sufficient spatial details but also contains a certain degree of abstract information, which is suitable for the left ventricular contour matching task. In addition, the features of the fourth and fifth layers of the VGG16 network model have achieved a good balance between generalization and specialization, avoiding the overfitting problem that may be caused by deeper layers and the lack of generalization ability that may be caused by shallower layers. Therefore, the selection of these two layers of feature representation can provide a rich and accurate information basis for subsequent analysis.

[0052] Optionally, according to the left ventricular endocardial contour image and the coordinate information of the key point set, in combination with the VGG16 network model and the bilinear interpolation method, the implementation process of obtaining the feature information of the key point set includes but is not limited to the following steps.

[0053] First, the left ventricular endocardial contour image Input into the VGG16 network model to get the initial feature tensor ; Then, using bilinear interpolation , according to each key point Coordinate information of In the initial feature tensor Interpolation to get the key points Feature information , satisfying the following formula (1): (1).

[0054] The above two steps work together to first extract the deep features of the heart image through the VGG16 network, and then use bilinear interpolation to accurately assign these features to each key point, thereby generating high-quality key point feature information. This process ensures that the feature information is both rich and accurate, providing strong support for the subsequent graph construction and feature aggregation.

[0055] In some embodiments of the present application, reference Figure 2 In step 104, the graph is constructed based on the coordinate information and feature information of the key point set in combination with the triangulation method to obtain the structural information of the key point set, including but not limited to the following steps.

[0056] Step 301, obtaining a distance matrix according to the coordinate information and feature information of the key point set.

[0057] It should be noted that the distance matrix is ​​used to represent the distance between each key point in the key point set.

[0058] Step 301, quantify the spatial relationship between the key points in the key point set by the distance between them to obtain a distance matrix. By calculating the distance between the key points, a preliminary spatial topological structure can be established, which helps to more accurately describe the relative positions between the key points in subsequent steps.

[0059] Optionally, the Euclidean distance is used to calculate the distance between key points in the key point set.

[0060] Step 302: According to the distance matrix and in combination with the triangulation method, a weighted adjacency matrix of the key point set is obtained as structural information.

[0061] It should be noted that the triangulation method is used to establish connections between key point pairs in the key point set whose distance does not exceed two units. In the key point set, the distance between key points includes coordinate distance and feature distance. Coordinate distance refers to the distance between two key points in the coordinate system. Feature distance refers to the distance between two key points in the feature space, and feature distance is usually used to measure the similarity of two key points in the feature space.

[0062] Optionally, the calculation method of the coordinate distance includes Euclidean distance, Manhattan distance and Chebyshev distance, and the calculation method of the feature distance includes Euclidean distance and cosine similarity.

[0063] In step 302, a triangulation method is used to establish connections between key point pairs in the key point set whose distance does not exceed two units, and a weighted adjacency matrix is ​​formed as the structural information of the key point set. The triangulation method not only considers the direct connection between adjacent key points, but also considers the indirect connection between key points that are far apart but still relevant. This construction method can better capture the local and global topological relationships between key points. The weighted adjacency matrix represents the connection strength between key points, where the weight reflects the similarity or distance between key points. Such structural information provides important topological relationship support for subsequent feature aggregation and matching, which helps to improve the accuracy and robustness of left ventricular contour matching and motion prediction.

[0064] Through the above two steps, the embodiment of the present application can effectively construct the structural information of the key point set, which not only enhances the ability to capture local features, but also considers the global structural information, thereby providing a solid foundation for subsequent feature aggregation and matching tasks. This method overcomes the limitations of traditional methods that overemphasize point features and ignore the topological relationship between points, and improves the overall matching accuracy.

[0065] In some embodiments of the present application, reference Figure 3 In step 105, based on the structural information and feature information of the key point set, the graph convolutional neural network model is used to perform feature aggregation to obtain the embedded information of the key point set, and the implementation process includes but is not limited to the following steps.

[0066] Step 401, based on the structural information and feature information of the key point set, the in-graph aggregation features of the key point set are obtained by utilizing the in-graph convolution mechanism of the graph convolutional neural network model.

[0067] In step 401, the key points within the end-diastolic key point subset and the end-systolic key point subset are feature aggregated through the intra-graph convolution mechanism of the graph convolutional neural network model. The intra-graph convolution mechanism can effectively capture the local relationship between key points and integrate this relationship information into the feature representation of the key points. The intra-graph aggregated features generated in this way not only contain the features of the key points themselves, but also take into account the influence of their neighboring key points, thereby enhancing the discriminability of the features. This step ensures that the feature information within the key point subset is fully integrated and enhanced.

[0068] Optionally, the intra-graph convolution mechanism of the graph convolutional neural network model satisfies the following formula (2): (2); In formula (2), the edge set is obtained according to the weighted adjacency matrix of the key point set: , Indicates key points With key points There is a connection between For key points No. Layer embedding information; Indicates key points No. Layer embedding information, Indicates key points No. Layer embedding information, , ; represents the feature aggregation function along the key points, represents the feature aggregation function along the edge; and Together with the key points There are key points of connection No. Layer embedding information and key points No. Layer embedding information Aggregation to get key points No. Layer embedding information .

[0069] Step 402, based on the structural information and feature information of the key point set, the cross-graph convolution mechanism of the graph convolutional neural network model is utilized in combination with the similarity matrix to obtain the cross-graph aggregation features of the key point set.

[0070] In this step, the cross-graph convolution mechanism of the graph convolutional neural network model is combined with the similarity matrix to perform feature aggregation on the end-diastolic key point subset and the end-systolic key point subset. The cross-graph convolution mechanism can propagate and aggregate information across different graph structures, thereby capturing the global relationship between different key point subsets. The similarity matrix is ​​used to measure the similarity between key points in different graphs, which helps to selectively transmit and integrate information across graphs. The cross-graph aggregation features generated in this way not only enhance the feature representation within a single graph, but also consider the association between different graphs, further improving the richness and robustness of the features.

[0071] Optionally, the cross-graph convolution mechanism of the graph convolutional neural network model satisfies the following formula (3): (3): In formula (3), Represents the cross-graph convolution function, which is used to aggregate cross-graph information. It first aggregates the information in the previous layer and then uses the similarity matrix To emphasize the features of similar keypoints and weight the features of neighboring keypoints to better capture the local and global relationships between keypoints, and then perform another round of information aggregation. Similarity matrix Represents the end-diastolic keypoint subset of the keypoint set Key points in and the end-systolic keypoint subset Key Points It is updated using a weight matrix and implemented as an exponential function to ensure that all member values ​​are non-negative and better capture the local and global relationships between key points. Satisfies the following formula (4): (4); In formula (4), represents the similarity function, It can be a similarity function based on Euclidean distance or a cosine similarity function.

[0072] Step 403: Obtain embedding information of the key point set according to the in-graph aggregation features and cross-graph aggregation features of the key point set.

[0073] In step 403, the in-graph aggregate features and cross-graph aggregate features are combined to generate the final embedding information. By combining the in-graph and cross-graph aggregate features, the embedding information not only includes the detailed features within the end-diastolic key point subset and the end-systolic key point subset, but also considers the global relationship between different subsets. This comprehensive embedding information provides a more comprehensive and accurate basis for subsequent key point matching, which helps to improve matching accuracy and robustness.

[0074] The above three steps work together to first enhance local features through the intra-graph convolution mechanism, then introduce global information through the cross-graph convolution mechanism, and finally generate high-quality embedded information. This approach ensures the comprehensiveness and accuracy of feature information and provides a solid foundation for left ventricular motion prediction based on triangulation.

[0075] In some embodiments of the present application, the embedded information of the key point set includes end-diastolic embedded information and end-systolic embedded information. Figure 3 In step 106, based on the embedded information and coordinate information of the key point set, the Sinkhorn algorithm is combined to perform feature matching to obtain the diastolic-systolic deformation relationship of the left ventricular endocardial contour, and the implementation process includes but is not limited to the following steps.

[0076] Step 501, calculating the similarity between the end-diastolic embedded information and the end-systolic embedded information to obtain a score matrix.

[0077] In step 501, the similarity between the end-diastolic embedded information and the end-systolic embedded information is calculated using methods such as inner product or cosine similarity to obtain a score matrix, in which each element represents the similarity between the key point subsets at the corresponding positions of the two time points. This score matrix reflects the similarity between key point pairs at different time points.

[0078] Step 502: Perform feature matching based on the score matrix in combination with the Sinkhorn algorithm to obtain a matching matrix.

[0079] It should be noted that the Sinkhorn algorithm is an iterative method based on optimal transmission theory, which is used to generate a double random matrix to ensure that each key point has a unique and optimal matching relationship at different time points. The algorithm gradually converges to a stable double random matrix by alternating the rows and columns of the normalized matrix so that the sum of each row and column is 1. The reason for choosing the Sinkhorn algorithm for feature matching is that it can ensure the uniqueness and consistency of the matching and avoid repeated or missed matching. In addition, the Sinkhorn algorithm takes into account global information, improves the accuracy and robustness of the matching, and performs well in processing low-quality images or abnormal contours. Although it involves an iterative process, it has high computational efficiency and is suitable for large-scale data processing. It can also be used in combination with a variety of similarity metrics to provide a flexible matching scheme. These characteristics make the Sinkhorn algorithm suitable for feature matching tasks in left ventricular motion estimation based on deep learning.

[0080] In step 502, the score matrix is ​​processed using the Sinkhorn algorithm to generate a matching matrix, which effectively solves the uniqueness and consistency problems of key points, avoids repeated matching or missing matching, and thus improves the accuracy and reliability of matching. The matching matrix reflects the mapping relationship between key points at different time points, which is the key to understanding cardiac motion, especially the myocardial displacement and deformation that need to be tracked when evaluating cardiac function.

[0081] Step 503: Obtain the diastolic-systolic deformation relationship of the left ventricular endocardium contour according to the matching matrix and the coordinate information of the key point set.

[0082] It should be noted that the diastolic-systolic deformation relationship describes how the inner membrane contour of the left ventricle changes shape during a complete cardiac cycle, which is very important for diagnosing heart diseases. For example, abnormal deformation patterns may be manifestations of certain pathological conditions, such as myocardial infarction or ventricular wall motion disorder. Therefore, accurately estimating this deformation relationship is of great significance for clinical applications.

[0083] In step 503, the diastolic-systolic deformation relationship of the left ventricular endocardial contour is obtained based on the coordinate information of the matching matrix and the key point set, and the relative movement of each key point in the diastolic and systolic states can be determined, and the change trend of the entire left ventricular endocardial contour can be depicted accordingly.

[0084] In some embodiments of the present application, reference Figure 3 In step 502, feature matching is performed based on the score matrix in combination with the Sinkhorn algorithm to obtain a matching matrix, and the implementation process includes but is not limited to the following steps.

[0085] Step 601, using the Sinkhorn algorithm to iteratively normalize the score matrix to obtain a converged double random matrix.

[0086] In step 601, the score matrix is ​​converted into a double random matrix (i.e., the sum of each row and each column is 1). The Sinkhorn algorithm iteratively adjusts the element values ​​in the score matrix so that the sum of each row and each column of the final matrix is ​​close to 1. This process ensures that each end-diastolic key point matches only one end-systolic key point, and vice versa, thereby avoiding the problem of duplicate matching or missing matching.

[0087] Specifically, the Sinkhorn algorithm gradually approaches the double random condition by alternating normalization operations on the rows and columns of the score matrix. Each iteration brings the matrix closer to satisfying the double random constraint. When the iteration reaches a certain number of times or meets the preset convergence criteria, the score matrix will become a stable double random matrix, which directly reflects the optimal matching possibility between key points.

[0088] Step 602: Obtain a matching matrix based on the converged double random matrix. In the matching matrix, only one element in each row and column is 1, and all other elements are 0.

[0089] In step 602, the double random matrix is ​​converted into a matching matrix, and the probability distribution in the double random matrix is ​​interpreted as the basis for the actual matching decision. Since the elements of the double random matrix represent the possibility of matching, it is necessary to select the most likely matching relationships to construct the final matching matrix. The matching matrix is ​​a binary matrix, in which only one element in each row and column is 1, and all other elements are 0.

[0090] Optionally, a matching matrix is ​​constructed by selecting the maximum value in each row or column of a doubly random matrix to decide which elements should be set to 1.

[0091] Step 603: The matching matrix is ​​optimized by minimizing the negative logarithmic loss.

[0092] In step 603, the matching matrix is ​​further optimized to improve the quality of the matching matrix. Minimizing the negative logarithmic loss is a common optimization strategy that aims to adjust the matching matrix to better conform to the actual cardiac motion pattern.

[0093] By minimizing the negative logarithmic loss function, the matching results can be made more consistent with the expected myocardial motion model and reduce unreasonable matching situations. The optimization process may involve adjusting certain matching decisions in the matching matrix to ensure that the overall matching scheme can minimize the total loss function. This helps to improve the accuracy and reliability of key point matching, especially in the presence of noisy or abnormal data.

[0094] The above three steps together ensure that the conversion from the score matrix to the matching matrix not only satisfies the optimal transmission problem in theory, but also provides high-quality and reliable key point matching results in practice, which is crucial for the subsequent analysis of the diastolic-systolic deformation relationship of the left ventricular endocardial contour.

[0095] In some embodiments of the present application, reference Figure 3 In step 503, the process of obtaining the diastolic-systolic deformation relationship of the left ventricular endocardial contour according to the coordinate information of the matching matrix and the key point set includes but is not limited to the following steps.

[0096] Step 701, obtaining a deformation function according to the matching matrix and the coordinate information of the key point set.

[0097] In step 701, a mathematical model (i.e., a deformation function) is constructed based on the matching results between the key points, and the model can quantify the shape changes of the heart at different time points. The deformation function is a key tool for connecting the left ventricular endocardium contour at the end of diastole and end of systole. It not only reflects the spatial displacement of the key points, but may also include local deformation (such as stretching, compression, etc.). Specifically, the matching matrix provides information on the correspondence between each key point from the end of diastole to the end of systole. These one-to-one matching pairs are the basis for constructing the deformation function. The coordinate information contains the location information, attribute information, and confidence information of the key points. Using this information, the deformation function can be defined more accurately to ensure that it can truly reflect the actual movement pattern of the heart endocardium.

[0098] Step 702: Obtain the diastolic-systolic deformation relationship of the left ventricular endocardium contour according to the deformation function.

[0099] In step 702, the position of the key points on the left ventricular endocardial contour is reconstructed using a deformation function. By applying the deformation function to all key points, the diastolic-systolic deformation relationship of the left ventricular endocardial contour can be obtained. Based on the diastolic-systolic deformation relationship of the left ventricular endocardial contour, a series of quantitative analyses can be performed, such as calculating the thickness change, volume change rate, strain and strain rate of the myocardial wall. These parameters are crucial for evaluating the heart's pumping efficiency and detecting potential heart disease lesions.

[0100] Specifically, first, based on the matching matrix and the coordinate information of the key points, a deformation function is constructed, which describes the spatial displacement of each key point from the end of diastole to the end of systole. Commonly used deformation functions include affine transformation, thin plate spline or radial basis function, which are used to accurately quantify the movement path of each key point on the left ventricular endocardial contour.

[0101] Next, the deformation function is applied to all points of the entire left ventricular endocardial contour, not just the key points, to achieve modeling of continuous deformation of the endocardial surface. For points that are not directly involved in the matching, an interpolation method is used to predict their movement paths to ensure the integrity of the deformation model. This step generates a detailed pattern of changes in the left ventricular endocardial contour during the cardiac cycle, namely the diastolic-systolic deformation relationship.

[0102] Using these deformation relationships, a series of quantitative motion parameters are calculated, such as displacement field (specific moving direction and distance of each point), strain rate (local myocardial stretching or compression), volume change (estimate the volume change of the left ventricle during the cardiac cycle to calculate the ejection fraction EF), and wall thickness change (observe the change of myocardial wall thickness over time). The above parameters are integrated to generate a comprehensive left ventricular motion estimation report. Finally, by comparing and cross-validating with clinical standard measurement results, the deformation function and its related parameters are continuously optimized to improve the accuracy of the model.

[0103] Optionally, the process of performing feature matching based on the coordinate information and embedded information of the key point set in combination with the Sinkhorn algorithm to obtain the diastolic-systolic deformation relationship of the left ventricular endocardial contour includes but is not limited to the following steps.

[0104] First, calculate the end-diastolic embedding information and end-systolic embedded information The similarity between them is used to obtain the score matrix . Scoring Matrix Satisfies the following formula (5): (5); In formula (5), represents the similarity function, It can be a similarity function based on Euclidean distance or a cosine similarity function.

[0105] Second, the scoring matrix Iterative normalization is performed through the Sinkhorn algorithm, iterative After times, we get the converged double random matrix , the sum of each row and column of the doubly random matrix is ​​1, matching the matrix The iterative process of the Sinkhorn algorithm satisfies the following formula (6): (6; In formula (6), the initial matrix , Indicates the number of iterations; and are two normalization factors, respectively adjusting The rows and columns of is the normalization factor Iteration The result of the Indicated by The diagonal matrix formed by Normalization factor Iteration The result of the Indicated by The diagonal matrix formed by The iterative process satisfies the following formula (7): (7); The iterative process satisfies the following formula (8): (8).

[0106] Then, the matching matrix is ​​optimized by minimizing the negative logarithmic loss , minimizing the negative log loss The following formula (9) is satisfied: (9); Ideally, the matching matrix It should be a permutation matrix, meaning that each keypoint in the end-diastolic keypoint subset corresponds to only one keypoint in the end-systolic keypoint subset, and the matching matrix Elements Represents the key points in the end-diastolic key point subset Key points from the end-systolic key point subset Match, otherwise 0. The matching matrix obtained by the Sinkhorn algorithm After optimization, it is close to a permutation matrix, but it is not completely a strict permutation matrix, because the result of the Sinkhorn algorithm may contain some non-zero non-integer values. However, in practical applications, this approximation is usually sufficient to determine the one-to-one correspondence between key points.

[0107] Then, according to the matching matrix The coordinate information of the key point set is used to determine the matching key point pairs in the key point set and obtain the deformation function. The change of the deformation function is the result of the superposition of the changes along the x-axis and y-axis directions. Taking the x-axis direction as an example, the deformation function The following formula (10) is satisfied: (10); In formula (10), the current position Refers to the specific location in the image that needs to be deformed; From the current location To the deformed position, Indicates the number of key points; It is the key point location, yes The weight coefficient of is the effective radius, which determines the influence range of the key point and is calculated based on the Euclidean distance; is the radial basis function, which calculates the contribution of each key point to the deformation. The following formula (11) is satisfied: (15); In formula (11), Represents the normalized distance, indicating the current position arrive Distance and effective radius The ratio of hour, Forced to 0, which means that keypoints outside the effective radius of the control point will not be affected by that keypoint.

[0108] Optionally, the radial basis function It is based on Wendland's C2 function.

[0109] In summary, the embodiments of the present application can provide the following technical effects.

[0110] The left ventricular motion prediction method based on triangulation proposed in the embodiment of the present application effectively improves the accuracy and efficiency of left ventricular motion prediction. First, feature extraction of cardiac images at the end of diastole and end of systole is performed through the VGG16 network, with special attention paid to the feature representation of the deep convolutional layer, and the geometric structure information is enhanced in combination with the bilinear interpolation method, providing accurate and detailed feature description for subsequent steps. Then, the topological structure of the key point set of the left ventricular endocardial contour is constructed by the triangulation method, which not only captures the feature information of the adjacent nodes, but also attaches importance to the importance of the distant nodes, and optimizes the accuracy and robustness of the key point matching. In addition, the application of the graph convolutional neural network model enhances the ability of cross-graph information fusion, and effectively reflects the topological structure of the graph by propagating embedded information along the edge of the graph. At the same time, the similarity matrix is ​​used to achieve efficient cross-graph information propagation, which improves the overall adaptability and performance of the model. These technical means work together to ensure that every link in the process from image input to feature extraction to graph construction can operate efficiently, providing a solid foundation for cardiac motion analysis.

[0111] On the basis of achieving efficient feature processing and key point matching, the method further optimizes the similarity matrix through the Sinkhorn algorithm, generates accurate node correspondence, and then constructs a deformation function to accurately map the diastolic-systolic deformation relationship of the left ventricular endocardial contour, providing a reliable basis for the motion estimation of the left ventricular endocardial contour. Finally, based on the diastolic-systolic deformation relationship of the left ventricular endocardial contour, the diastolic-systolic motion of the left ventricular endocardial contour is predicted to obtain the left ventricular motion prediction result. Therefore, the left ventricular motion prediction method based on triangulation proposed in the embodiment of the present application not only improves the accuracy, robustness and efficiency of left ventricular motion prediction.

[0112] Secondly, refer to Figure 4 The left ventricular motion prediction system based on triangulation provided in the embodiment of the present application includes: a data acquisition module 801, a coordinate acquisition module 802, a feature processing module 803, a graph construction module 804, a feature aggregation module 805, a feature matching module 806 and a deformation prediction module 807.

[0113] The data acquisition module 801 is used to acquire the left ventricular endocardium contour image.

[0114] The coordinate acquisition module 802 is used to obtain the coordinate information of the key point set according to the left ventricular endocardial contour image. The key point set includes an end-diastolic key point subset and an end-systolic key point subset.

[0115] The feature processing module 803 is used to perform feature processing using the VGG16 network model according to the left ventricular endocardium contour image and the coordinate information of the key point set to obtain the feature information of the key point set.

[0116] The graph construction module 804 is used to perform graph construction processing based on the coordinate information and feature information of the key point set in combination with a triangulation method to obtain the structural information of the key point set.

[0117] The feature aggregation module 805 is used to perform feature aggregation based on the structural information and feature information of the key point set using a graph convolutional neural network model to obtain the embedded information of the key point set.

[0118] The feature matching module 806 is used to perform feature matching based on the embedded information and coordinate information of the key point set in combination with the Sinkhorn algorithm to obtain the diastolic-systolic deformation relationship of the left ventricular endocardium contour.

[0119] The deformation prediction module 807 is used to predict the diastolic-systolic motion of the left ventricular endocardial contour according to the diastolic-systolic deformation relationship of the left ventricular endocardial contour, and obtain a left ventricular motion prediction result.

[0120] On the other hand, referring to Figure 5The left ventricular motion prediction device based on triangulation provided in the embodiment of the present application includes: a processor and a memory. The memory is used to store programs.

[0121] When the program is executed by the processor, the processor implements the aforementioned left ventricular motion prediction method based on triangulation.

[0122] In addition, an embodiment of the present application provides a computer-readable storage medium, in which a program executable by a processor is stored. When the program executable by the processor is executed by the processor, it is used to implement the aforementioned left ventricular motion prediction method based on triangulation.

[0123] Similarly, the contents of the above method embodiments are all applicable to system embodiments, device embodiments and medium embodiments. The functions specifically implemented by the system embodiments, device embodiments and medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0124] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0125] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the described embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A left ventricular motion prediction method based on triangulation, characterized in that: The steps include: Obtain left ventricular endocardial contour images; According to the left ventricular endocardial contour image, coordinate information of a key point set is obtained; the key point set includes an end-diastolic key point subset and an end-systolic key point subset; According to the left ventricular endocardium contour image and the coordinate information of the key point set, feature processing is performed using a VGG16 network model to obtain feature information of the key point set; According to the coordinate information and feature information of the key point set, a graph construction process is performed in combination with a triangulation method to obtain structural information of the key point set; According to the structural information and feature information of the key point set, a graph convolutional neural network model is used to perform feature aggregation to obtain embedded information of the key point set; According to the embedded information and coordinate information of the key point set, feature matching is performed in combination with the Sinkhorn algorithm to obtain the diastolic-systolic deformation relationship of the left ventricular endocardial contour; The diastolic-systolic movement of the left ventricular endocardial contour is predicted according to the diastolic-systolic deformation relationship of the left ventricular endocardial contour to obtain a left ventricular movement prediction result.

2. The left ventricular motion prediction method based on triangulation according to claim 1, characterized in that: The feature processing is performed using the VGG16 network model according to the left ventricular endocardial contour image and the coordinate information of the key point set to obtain the feature information of the key point set, including: According to the left ventricular endocardial contour image, feature processing is performed using the VGG16 network model to obtain an initial feature tensor; According to the initial feature tensor and the coordinate information of the key point set, in combination with a bilinear interpolation method, feature information of the key point set is obtained.

3. The left ventricular motion prediction method based on triangulation according to claim 1, characterized in that: The step of performing graph construction processing based on the coordinate information and feature information of the key point set in combination with a triangulation method to obtain structural information of the key point set includes: Obtaining a distance matrix according to the coordinate information and feature information of the key point set; the distance matrix is ​​used to characterize the distance between each key point in the key point set; According to the distance matrix, combined with the triangulation method, a weighted adjacency matrix of the key point set is obtained as structural information; the triangulation method is used to establish connections between key point pairs in the key point set whose distance does not exceed two units.

4. The left ventricular motion prediction method based on triangulation according to claim 1, characterized in that: The step of performing feature aggregation using a graph convolutional neural network model according to the structural information and feature information of the key point set to obtain the embedded information of the key point set includes: According to the structural information and feature information of the key point set, the in-graph aggregation features of the key point set are obtained by utilizing the in-graph convolution mechanism of the graph convolutional neural network model; According to the structural information and feature information of the key point set, the cross-graph aggregation features of the key point set are obtained by utilizing the cross-graph convolution mechanism of the graph convolutional neural network model and combining with the similarity matrix; Embedding information of the key point set is obtained according to the intra-graph aggregation features and cross-graph aggregation features of the key point set.

5. The left ventricular motion prediction method based on triangulation according to claim 1, characterized in that: The embedding information of the key point set includes end-diastolic embedding information and end-systolic embedding information; The embedding information and coordinate information of the key point set are combined with the Sinkhorn algorithm to perform feature matching to obtain the diastolic-systolic deformation relationship of the left ventricular endocardial contour, including: Calculating the similarity between the end-diastolic embedded information and the end-systolic embedded information to obtain a score matrix; According to the score matrix, feature matching is performed in combination with the Sinkhorn algorithm to obtain a matching matrix; The diastolic-systolic deformation relationship of the left ventricular endocardial contour is obtained according to the comprehensive information of the matching matrix and the key point set.

6. The left ventricular motion prediction method based on triangulation according to claim 5, characterized in that: The step of performing feature matching according to the score matrix and in combination with the Sinkhorn algorithm to obtain a matching matrix includes: Iteratively normalizing the score matrix using the Sinkhorn algorithm to obtain a converged double random matrix; According to the converged double random matrix, the matching matrix is ​​obtained; in the matching matrix, only one element in each row and each column is 1, and all other elements are 0; The matching matrix is ​​optimized by minimizing the negative log loss.

7. The left ventricular motion prediction method based on triangulation according to claim 5, characterized in that: The step of obtaining the diastolic-systolic deformation relationship of the left ventricular endocardial contour according to the comprehensive information of the matching matrix and the key point set includes: Obtaining a deformation function according to the comprehensive information of the matching matrix and the key point set; According to the deformation function, the diastolic-systolic deformation relationship of the left ventricular endocardium contour is obtained.

8. A left ventricular motion prediction system based on triangulation, characterized in that: include: Data acquisition module, coordinate acquisition module, feature processing module, graph construction module, feature aggregation module, feature matching module and deformation prediction module; The data acquisition module is used to acquire the left ventricular endocardial contour image; The coordinate acquisition module is used to obtain the coordinate information of the key point set according to the left ventricular endocardial contour image; the key point set includes an end-diastolic key point subset and an end-systolic key point subset; The feature processing module is used to perform feature processing using a VGG16 network model according to the left ventricular endocardial contour image and the coordinate information of the key point set to obtain feature information of the key point set; The graph construction module is used to perform graph construction processing based on the coordinate information and feature information of the key point set in combination with a triangulation method to obtain the structural information of the key point set; The feature aggregation module is used to perform feature aggregation using a graph convolutional neural network model according to the structural information and feature information of the key point set to obtain embedded information of the key point set; The feature matching module is used to perform feature matching based on the embedded information and coordinate information of the key point set in combination with the Sinkhorn algorithm to obtain the diastolic-systolic deformation relationship of the left ventricular endocardial contour; The deformation prediction module is used to predict the diastolic-systolic motion of the left ventricular endocardial contour according to the diastolic-systolic deformation relationship of the left ventricular endocardial contour to obtain a left ventricular motion prediction result.

9. A left ventricular motion prediction device based on triangulation, characterized in that: include: Processor and memory; The memory is used to store programs; When the program is executed by the processor, the processor implements the left ventricular motion prediction method based on triangulation as claimed in any one of claims 1 to 7.

10. A computer-readable storage medium storing a program executable by a processor, characterized in that: The program executable by the processor is used to implement the left ventricular motion prediction method based on triangulation as claimed in any one of claims 1 to 7 when executed by the processor.

Images