Heart chamber three-dimensional reconstruction method based on echocardiography and related device

Abstract

The invention discloses a heart chamber three-dimensional reconstruction method based on an echocardiogram and a related device, and relates to the technical field of artificial intelligence and three-dimensional reconstruction, three-dimensional point cloud data is generated based on the echocardiogram of a heart chamber to be reconstructed, normalization processing is performed on the three-dimensional point cloud data, uniform sampling is performed on a preset three-dimensional area, and the three-dimensional reconstruction result is obtained. And obtaining a plurality of query points, carrying out normalization processing on the three-dimensional coordinates of all the query points, taking the normalized point cloud data and the normalized three-dimensional coordinates of each query point as input, and utilizing the trained occupation function prediction model to obtain an occupation result of each query point. And performing three-dimensional reconstruction on the to-be-reconstructed heart chamber based on the normalized three-dimensional coordinates of all the query points and the occupancy result, so that the three-dimensional reconstruction of the heart chamber can be simply, conveniently and efficiently completed, and a doctor is helped to accurately, intuitively and quantitatively analyze the heart function of a patient through an echocardiogram.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence and three-dimensional reconstruction technology, and in particular to a method and related device for three-dimensional reconstruction of cardiac chambers based on echocardiography. Background Art

[0002] Echocardiography is one of the most commonly used imaging methods in cardiac examinations. It uses ultrasonic scanning to observe the heart structure and blood flow through the human skin and muscles, and to clarify the function and integrity of the heart chambers and large blood vessels. Obtaining a three-dimensional model of the heart chamber on an echocardiogram can help doctors more accurately quantify and analyze the patient's heart function, such as measuring ventricular volume and ejection fraction. However, echocardiography is an ultrasonic image with high noise and sparse sampling, and it is difficult to directly obtain a three-dimensional model of the heart chamber from an echocardiogram. It is an effective method to mark the anatomical structure position points on the echocardiogram, convert the two-dimensional coordinates of the anatomical structure position points into a three-dimensional coordinate system to form a three-dimensional point cloud, and reconstruct the three-dimensional model of the heart chamber based on the three-dimensional point cloud.

[0003] At present, the three-dimensional reconstruction method of cardiac chambers based on echocardiography is mainly a knowledge-based reconstruction algorithm (KBR). This knowledge-based reconstruction algorithm uses a piecewise smooth subdivision surface (PSSS) algorithm to fine-tune a template mesh based on a three-dimensional point cloud, and uses the template mesh to fit the three-dimensional point cloud to reconstruct a three-dimensional model of the cardiac chamber. However, this knowledge-based reconstruction algorithm requires the structural features of each point, each edge and each face of the template mesh to be labeled, which not only requires professional knowledge but is also time-consuming and labor-intensive.

[0004] Based on this, there is an urgent need for a technology that can simply and efficiently reconstruct a three-dimensional model of the heart chamber. Summary of the invention

[0005] The purpose of the present application is to provide a method and related device for three-dimensional reconstruction of heart chambers based on echocardiography, which can easily and efficiently reconstruct a three-dimensional model of the heart chambers.

[0006] To achieve the above objectives, this application provides the following solutions:

[0007] In a first aspect, the present application provides a method for three-dimensional reconstruction of a heart chamber based on echocardiography, the method for three-dimensional reconstruction of a heart chamber based on echocardiography comprising:

[0008] Generate three-dimensional point cloud data based on the echocardiogram of the heart chamber to be reconstructed; the three-dimensional point cloud data includes a plurality of three-dimensional points and the three-dimensional coordinates and category of each three-dimensional point; the three-dimensional point is an anatomical structure position point of the heart chamber to be reconstructed, and the category is the anatomical structure category of the anatomical structure position point;

[0009] Normalizing the three-dimensional point cloud data to obtain normalized point cloud data; the three-dimensional coordinates of the center point of the normalized point cloud data are the coordinate origin, and the three-dimensional coordinates of each three-dimensional point of the normalized point cloud data are within a preset range;

[0010] Uniformly sampling a preset three-dimensional area to obtain a plurality of query points, and normalizing the three-dimensional coordinates of all the query points to obtain normalized three-dimensional coordinates of each query point; the normalized three-dimensional coordinates of the center point of all the query points are the coordinate origin, and the normalized three-dimensional coordinates are within a preset range;

[0011] Taking the normalized point cloud data and the normalized three-dimensional coordinates of each query point as input, using the trained occupancy function prediction model to obtain an occupancy result of each query point; the occupancy result includes that the query point is located inside the heart chamber to be reconstructed, and that the query point is located outside the heart chamber to be reconstructed;

[0012] Performing three-dimensional reconstruction of the heart chamber to be reconstructed based on the normalized three-dimensional coordinates and occupancy results of all the query points to obtain an initial three-dimensional model of the heart chamber to be reconstructed;

[0013] The initial three-dimensional model is denormalized to obtain a three-dimensional model of the heart chamber to be reconstructed.

[0014] Optionally, the trained occupancy function prediction model includes an encoder, a fusion module and a decoder connected in sequence;

[0015] The encoder is used to process the normalized point cloud data to obtain point cloud features;

[0016] The fusion module is used to process the point cloud features and the normalized three-dimensional coordinates of each query point to obtain fusion features;

[0017] The decoder is used to process the fused features to obtain an occupancy result of each query point.

[0018] Optionally, the encoder includes a plurality of first multi-layer perceptron pooling modules and a multi-layer perceptron connected in sequence; the first multi-layer perceptron pooling module includes a multi-layer perceptron and a pooling layer connected in sequence;

[0019] The fusion module includes a second multi-layer perceptron pooling module and a multi-layer perceptron connected in sequence, and the second multi-layer perceptron pooling module includes a multi-layer perceptron and a pooling layer connected in parallel; or, the fusion module includes a feature projection layer, a segmentation network, a feature query layer and a pooling layer connected in sequence; wherein the feature projection layer is used to project the point cloud features onto the xoy plane, the xoz plane and the yoz plane respectively to obtain three plane vectors; the segmentation network is used to process the three plane vectors to obtain three plane features; the feature query layer is used to determine the query point feature of each query point based on the normalized three-dimensional coordinates of each query point and the three plane features;

[0020] The decoder includes a plurality of multi-layer perceptrons connected in sequence.

[0021] Optionally, generating three-dimensional point cloud data based on an echocardiogram of the heart chamber to be reconstructed specifically includes:

[0022] Determining the two-dimensional coordinates of each anatomical structure location point based on an echocardiogram of the heart chamber to be reconstructed;

[0023] For each of the anatomical structure position points, the two-dimensional coordinates of the anatomical structure position point are transformed using the three-dimensional posture information of the ultrasound probe when the echocardiogram is generated to obtain the three-dimensional coordinates of the anatomical structure position point; the anatomical structure position point is recorded as a three-dimensional point, the three-dimensional coordinates of the anatomical structure position point are marked as the three-dimensional coordinates of the three-dimensional point, and the anatomical structure category of the anatomical structure position point is recorded as the category of the three-dimensional point, and all of the three-dimensional points and the three-dimensional coordinates and category of each of the three-dimensional points are combined into three-dimensional point cloud data.

[0024] Optionally, before taking the normalized point cloud data and the normalized three-dimensional coordinates of each query point as input and obtaining the occupancy result of each query point using the trained occupancy function prediction model, the echocardiography-based three-dimensional reconstruction method of the cardiac chamber further includes:

[0025] Acquire a data set; the data set includes a plurality of sample normalized point cloud data and a sample initial three-dimensional model corresponding to each of the sample normalized point cloud data;

[0026] For each of the sample normalized point cloud data, a sampling area is determined based on the sample normalized point cloud data, and the sampling area is randomly sampled to obtain a plurality of sample query points; for each of the sample query points, an actual occupancy result of the sample query point is determined based on the three-dimensional coordinates of the sample query point and the sample initial three-dimensional model corresponding to the sample normalized point cloud data;

[0027] The sample normalized point cloud data and the three-dimensional coordinates of each sample query point are used as input, and the actual occupancy result of each sample query point is used as a label to train the initial occupancy function prediction model to obtain a trained occupancy function prediction model.

[0028] Optionally, performing three-dimensional reconstruction on the heart chamber to be reconstructed based on the normalized three-dimensional coordinates and occupancy results of all the query points to obtain an initial three-dimensional model of the heart chamber to be reconstructed specifically includes:

[0029] The normalized three-dimensional coordinates and occupancy results of all the query points are used as input, and the marching cube algorithm is used to perform three-dimensional reconstruction on the heart chamber to be reconstructed, so as to obtain an initial three-dimensional model of the heart chamber to be reconstructed.

[0030] In a second aspect, the present application provides a device for three-dimensional reconstruction of a cardiac chamber based on echocardiography, wherein the device comprises:

[0031] A point cloud generation module, for generating three-dimensional point cloud data based on an echocardiogram of a heart chamber to be reconstructed; the three-dimensional point cloud data comprises a plurality of three-dimensional points and a three-dimensional coordinate and a category of each three-dimensional point; the three-dimensional point is an anatomical structure position point of the heart chamber to be reconstructed, and the category is an anatomical structure category of the anatomical structure position point;

[0032] A normalization module, used for normalizing the three-dimensional point cloud data to obtain normalized point cloud data; the three-dimensional coordinates of the center point of the normalized point cloud data are the coordinate origin, and the three-dimensional coordinates of each three-dimensional point of the normalized point cloud data are within a preset range;

[0033] A query point determination module is used to uniformly sample a preset three-dimensional area to obtain a plurality of query points, and normalize the three-dimensional coordinates of all the query points to obtain the normalized three-dimensional coordinates of each query point; the normalized three-dimensional coordinates of the center point of all the query points are the coordinate origin, and the normalized three-dimensional coordinates are within a preset range;

[0034] a model prediction module, configured to use the normalized point cloud data and the normalized three-dimensional coordinates of each query point as input, and obtain an occupancy result of each query point using a trained occupancy function prediction model; the occupancy result includes that the query point is located inside the heart chamber to be reconstructed, and that the query point is located outside the heart chamber to be reconstructed;

[0035] A three-dimensional reconstruction module, used for performing three-dimensional reconstruction of the heart chamber to be reconstructed based on the normalized three-dimensional coordinates and occupancy results of all the query points to obtain an initial three-dimensional model of the heart chamber to be reconstructed;

[0036] The model recovery module is used to perform a denormalization process on the initial three-dimensional model to obtain a three-dimensional model of the heart chamber to be reconstructed.

[0037] In a third aspect, the present application provides a computer device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement any one of the above-described methods for three-dimensional reconstruction of cardiac chambers based on echocardiography.

[0038] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned methods for three-dimensional reconstruction of cardiac chambers based on echocardiography.

[0039] In a fifth aspect, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for three-dimensional reconstruction of cardiac chambers based on echocardiography.

[0040] According to the specific embodiments provided in this application, this application discloses the following technical effects:

[0041] The present application provides a method and related device for three-dimensional reconstruction of a heart chamber based on echocardiography, generates three-dimensional point cloud data based on the echocardiogram of the heart chamber to be reconstructed, normalizes the three-dimensional point cloud data to obtain normalized point cloud data, uniformly samples a preset three-dimensional area to obtain multiple query points, and normalizes the three-dimensional coordinates of all query points to obtain the normalized three-dimensional coordinates of each query point, takes the normalized point cloud data and the normalized three-dimensional coordinates of each query point as input, uses a trained occupancy function prediction model to obtain the occupancy result of each query point, performs three-dimensional reconstruction of the heart chamber to be reconstructed based on the normalized three-dimensional coordinates and occupancy results of all query points to obtain an initial three-dimensional model of the heart chamber to be reconstructed, denormalizes the initial three-dimensional model to obtain the three-dimensional model of the heart chamber to be reconstructed, does not need to introduce a template mesh, and does not need to label the template mesh, thereby eliminating the need for professional knowledge and time-consuming and labor-intensive labeling work, and can simply and efficiently complete the three-dimensional reconstruction of the heart chamber, helping doctors to accurately, intuitively, and quantitatively analyze the patient's heart function through echocardiography. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0043] Figure 1 This is a diagram of the application environment of a method for three-dimensional reconstruction of cardiac chambers based on echocardiography provided in Example 1 of the present application.

[0044] Figure 2 A schematic flow chart of a method for three-dimensional reconstruction of cardiac chambers based on echocardiography provided in Example 1 of the present application.

[0045] Figure 3 This is a schematic diagram of the structure of the trained occupancy function prediction model provided in Example 1 of the present application.

[0046] Figure 4 This is a schematic diagram of the first structure of the fusion module provided in Example 1 of the present application.

[0047] Figure 5 This is a second structural diagram of the fusion module provided in Example 1 of the present application.

[0048] Figure 6 This is a training flowchart of the trained occupancy function prediction model provided in Example 1 of the present application.

[0049] Figure 7 A schematic diagram for comparing the target three-dimensional model and the predicted three-dimensional model provided in Example 1 of the present application.

[0050] Figure 8 A schematic diagram of the functional modules of a cardiac chamber three-dimensional reconstruction device based on echocardiography provided in Example 2 of the present application.

[0051] Fig. 9 A schematic diagram of the structure of a computer device provided in Example 3 of the present application. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0053] Example 1

[0054] The method for three-dimensional reconstruction of cardiac chambers based on echocardiography provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the terminal communicates with the server through the network. The data storage system can store the data that the server needs to process. The data storage system can be set up separately, integrated on the server, or placed on the cloud or other servers. The terminal can send the echocardiogram to be processed to the server. After the server receives the echocardiogram to be processed, for the echocardiogram to be processed, the server generates three-dimensional point cloud data based on the echocardiogram of the heart chamber to be reconstructed, normalizes the three-dimensional point cloud data, obtains normalized point cloud data, uniformly samples the preset three-dimensional area, obtains multiple query points, and normalizes the three-dimensional coordinates of all query points to obtain the normalized three-dimensional coordinates of each query point, takes the normalized point cloud data and the normalized three-dimensional coordinates of each query point as input, uses the trained occupancy function prediction model to obtain the occupancy result of each query point, and performs three-dimensional reconstruction of the heart chamber to be reconstructed based on the normalized three-dimensional coordinates and occupancy results of all query points to obtain the initial three-dimensional model of the heart chamber to be reconstructed, and denormalizes the initial three-dimensional model to obtain the three-dimensional model of the heart chamber to be reconstructed. The server can feed back the obtained three-dimensional model for the echocardiogram to the terminal.

[0055] In addition, in some embodiments, the three-dimensional reconstruction method of the heart chamber based on echocardiography can also be implemented independently by a server or a terminal. For example, the terminal can directly process the echocardiogram to be processed, or the server can obtain the echocardiogram to be processed from the data storage system and process the echocardiogram to be processed.

[0056] The terminal may be, but is not limited to, various desktop computers, laptops, smart phones, tablet computers, IoT devices, and portable wearable devices. The server may be implemented as an independent server or a server cluster consisting of multiple servers, or may be a cloud server.

[0057] like Figure 2 As shown, this embodiment provides a method for three-dimensional reconstruction of cardiac chambers based on echocardiography. The method is executed by a computer device, and can be executed by a computer device such as a terminal or a server alone, or by a terminal and a server together. In the embodiment of the present application, the method is applied to Figure 1 Taking the server in the example as an example, the method for three-dimensional reconstruction of cardiac chambers based on echocardiography includes the following steps:

[0058] S1: Generate three-dimensional point cloud data based on an echocardiogram of a heart chamber to be reconstructed; the three-dimensional point cloud data includes a plurality of three-dimensional points and three-dimensional coordinates and a category of each three-dimensional point; the three-dimensional point is an anatomical structure position point of the heart chamber to be reconstructed, and the category is the anatomical structure category of the anatomical structure position point.

[0059] S2: normalizing the three-dimensional point cloud data to obtain normalized point cloud data; the three-dimensional coordinates of the center point of the normalized point cloud data are the coordinate origin, and the three-dimensional coordinates of each three-dimensional point of the normalized point cloud data are within a preset range.

[0060] S3: uniformly sample the preset three-dimensional area to obtain multiple query points, and normalize the three-dimensional coordinates of all the query points to obtain the normalized three-dimensional coordinates of each query point; the normalized three-dimensional coordinates of the center point of all the query points are the coordinate origin, and the normalized three-dimensional coordinates are within a preset range.

[0061] S4: Using the normalized point cloud data and the normalized three-dimensional coordinates of each query point as input, using the trained occupancy function prediction model to obtain the occupancy result of each query point; the occupancy result includes the query point being located inside the heart chamber to be reconstructed, and the query point being located outside the heart chamber to be reconstructed.

[0062] S5: Perform three-dimensional reconstruction on the heart chamber to be reconstructed based on the normalized three-dimensional coordinates and occupancy results of all the query points to obtain an initial three-dimensional model of the heart chamber to be reconstructed.

[0063] S6: performing a denormalization process on the initial three-dimensional model to obtain a three-dimensional model of the heart chamber to be reconstructed.

[0064] By implementing the above steps S1 to S6, this embodiment uses deep learning technology to fit the implicit function of the three-dimensional structure of the heart chamber to obtain a trained occupancy function prediction model, and uses the trained occupancy function prediction model to realize three-dimensional reconstruction of the heart chamber based on echocardiography. Specifically, the three-dimensional sparse point cloud of the cardiac anatomical structure is used as input, and a neural network is used to fit the occupancy function (Occupancy function, also known as implicit function) of the heart chamber to be reconstructed, and predict whether any query point in the space is inside the heart chamber to be reconstructed, thereby realizing three-dimensional reconstruction of the heart chamber to be reconstructed. There is no need to introduce a template mesh or to label the template mesh, which saves the time-consuming and labor-intensive labeling work that requires professional knowledge. A simple and efficient three-dimensional reconstruction method of the heart chamber based on implicit functions can be proposed for echocardiography, and a three-dimensional model of the heart chamber can be obtained. Doctors can further analyze the three-dimensional model to help doctors accurately, intuitively, and quantitatively analyze the patient's heart function through echocardiography.

[0065] In S1, the heart chambers to be reconstructed may be the left atrium, the right atrium, the left ventricle, and the right ventricle.

[0066] In S1, three-dimensional point cloud data is generated based on the echocardiogram of the heart chamber to be reconstructed, specifically including: determining the two-dimensional coordinates of each anatomical structure position point based on the echocardiogram of the heart chamber to be reconstructed; for each anatomical structure position point, using the three-dimensional posture information of the ultrasound probe when generating the echocardiogram, coordinate transformation is performed on the two-dimensional coordinates of the anatomical structure position point to obtain the three-dimensional coordinates of the anatomical structure position point. The anatomical structure position point is recorded as a three-dimensional point, the three-dimensional coordinates of the anatomical structure position point are recorded as the three-dimensional coordinates of the three-dimensional point, and the anatomical structure category of the anatomical structure position point is recorded as the category of the three-dimensional point, and all three-dimensional points and the three-dimensional coordinates and category of each three-dimensional point are composed into three-dimensional point cloud data.

[0067] This embodiment first uses an ultrasonic device to collect an echocardiogram of the heart chamber to be reconstructed, and in the process of collecting the echocardiogram, uses a sensor to collect the movement of the ultrasonic probe of the ultrasonic device to obtain the three-dimensional posture information of the ultrasonic probe. Then, the key anatomical structure position points are marked on the 2D echocardiogram to obtain the two-dimensional coordinates of each anatomical structure position point. Finally, the two-dimensional coordinates of each anatomical structure position point are transformed into a three-dimensional coordinate system through the recorded three-dimensional posture information to obtain the three-dimensional coordinates of each anatomical structure position point, and the anatomical structure category information of each anatomical structure position point is recorded at the same time to obtain three-dimensional point cloud data.

[0068] Considering that an echocardiogram at one angle may not be able to fully display all anatomical structure locations, this embodiment may acquire multiple views at different angles when acquiring an echocardiogram, so as to facilitate determination of the two-dimensional coordinates of all anatomical structure locations.

[0069] Among them, the anatomical structure location points can be determined according to user needs. As an example, for the right ventricle, the anatomical structure location points include seven types: tricuspid valve ring, right ventricular septum, right ventricular endocardium, base, apex, pulmonary valve ring, and right ventricular septum edge.

[0070] The anatomical structure category of each anatomical structure location point is recorded in the form of a one-hot code.

[0071] In S2, the three-dimensional point cloud data is normalized, specifically including: translating and scaling the three-dimensional point cloud data, and recording the translation parameters and scaling parameters. The preset range can be [-1, 1]. Of course, other preset ranges of values ​​can be selected according to needs, and this embodiment does not impose any limitation on this.

[0072] In S3, the preset three-dimensional area can be a voxel grid of (32, 32, 32), and each voxel grid corresponds to a query point. Of course, voxel grids of other resolutions can be selected as needed, and other types of three-dimensional areas can be selected as needed. By uniformly sampling the three-dimensional area, multiple query points can be obtained. This embodiment does not impose any limitation on this.

[0073] In S3, the three-dimensional coordinates of all query points are normalized, specifically including: translating and scaling the three-dimensional coordinates of all query points to obtain the normalized three-dimensional coordinates of each query point, and the preset range of the normalized three-dimensional coordinates is the same as the preset range of the three-dimensional coordinates of each three-dimensional point of the normalized point cloud data.

[0074] In S4, the trained occupancy function prediction model is used to extract point cloud feature information and predict the OCC value of the query point in space. OCC is a binary variable. If OCC is equal to 1, it means that the query point is in the heart chamber to be reconstructed. If OCC is equal to 0, it means that the query point is not in the heart chamber to be reconstructed. Figure 3 As shown, the trained occupancy function prediction model includes an encoder, a fusion module and a decoder connected in sequence. The encoder is used to process the normalized point cloud data and extract the point cloud features. The fusion module is used to process the point cloud features and the normalized three-dimensional coordinates of each query point to obtain the fused features. The decoder is used to process the fused features, predict the OCC value of each query point, and obtain the occupancy result of each query point.

[0075] Among them, the input of the encoder is normalized point cloud data (np, 3+c), which is concatenated from the three-dimensional coordinates of all three-dimensional points of the normalized point cloud data (np, 3) and the unique hot codes (np, c) of the categories of all three-dimensional points, where np is the number of three-dimensional points in the normalized point cloud data, 3 is the number of three-dimensional coordinates of the three-dimensional points, and c is the number of categories of the three-dimensional points. The output of the encoder is point cloud features (np, d), and d is the feature dimension of the three-dimensional points.

[0076] The encoder includes a plurality of first multi-layer perceptron pooling modules and a multi-layer perceptron (MLP) connected in sequence, the first multi-layer perceptron pooling module includes a multi-layer perceptron and a pooling layer connected in sequence, and the working process of the first multi-layer perceptron pooling module is as follows: the first multi-layer perceptron pooling module is divided into two parts, one part is the MLP of the channel dimension, which is used to extract the local features (np, d) of all three-dimensional points in the normalized point cloud data, and the other part is the pooling layer of the point dimension, which is used to extract the d-dimensional global features (d) of the local features (np, d) of all three-dimensional points output by the MLP, and the global features are copied np times and spliced ​​to the local features of each three-dimensional point respectively to obtain features of size (np, 2*d). The last multi-layer perceptron processes the features of size (np, 2*d) to obtain point cloud features (np, d).

[0077] The input of the fusion module is the point cloud features (np, d) extracted by the encoder and the normalized three-dimensional coordinates (nq, 3) of all query points, where nq is the number of query points, and the output of the fusion module is the fused features (nq, d).

[0078] This embodiment provides two fusion module structures, the first one uses global pooling + splicing to extract features, and the second one uses planar convolution to extract features.

[0079] like Figure 4 As shown, it is a schematic diagram of the first structure, the fusion module includes a second multi-layer perceptron pooling module and a multi-layer perceptron connected in sequence, and the second multi-layer perceptron pooling module includes a multi-layer perceptron and a pooling layer connected in parallel. At this time, the working process of the fusion module is: first, the point cloud feature (np, d) is maximized pooled in the point dimension to obtain a d-dimensional global feature vector (d); then, the normalized three-dimensional coordinates (nq, 3) of all query points are extracted using the MLP of the channel dimension to obtain a feature vector (nq, d); finally, the d-dimensional global feature vector is copied nq times, spliced ​​onto the feature vector (nq, d), and the dimension is reduced to d using the MLP to obtain a fused feature (nq, d).

[0080] like Figure 5As shown, it is a schematic diagram of the second structure. The fusion module includes a feature projection layer, a segmentation network, a feature query layer and a pooling layer which are connected in sequence. The feature projection layer is used to project the point cloud features onto the xoy plane, the xoz plane and the yoz plane respectively to obtain three plane vectors. The segmentation network is used to process the three plane vectors to obtain three plane features. The feature query layer is used to determine the query point features of each query point based on the normalized three-dimensional coordinates of each query point and the three plane features. At this time, the working process of the fusion module is as follows: first, according to the three-dimensional coordinates of each three-dimensional point in the three-dimensional point cloud data, the point cloud features (np, d) are projected onto the xoy, xoz, and yoz planes (the resolution h*w uses 32*32) to obtain three plane vectors 3*(h, w, d); then the three plane vectors are processed using a segmentation network (such as UNet) to extract the three plane features 3*(h, w, d); finally, the query point features (nq, 3, d) of all query points are extracted according to the projection position of each query point on the xoy, xoz, and yoz planes, and the query point features of all query points are pooled using a pooling layer to obtain the fused features (nq, d) of all query points on the three planes.

[0081] The feature projection process includes: each 3D point in the point cloud feature has a 3D coordinate (x, y, z) and a d-dimensional feature. For each 3D point, the process of projecting the 3D point to the xoy plane is:

[0082] Initialize the features of the xoy plane to a three-dimensional matrix with a shape of (32*32*d) and all values ​​​​are 0. According to the three-dimensional coordinates (x, y, z) of the three-dimensional point, the three-dimensional point is vertically mapped to the xoy plane to obtain the projection point of the three-dimensional point on the xoy plane. The specific process of vertical mapping is: set the z coordinate of the three-dimensional point to 0, and translate and scale the values ​​of the x coordinate and y coordinate to [0, 31]. Since the xoy plane is a 32*32 two-dimensional grid, its coordinate points are integers of [0, 31], and the coordinates of the projection point of the three-dimensional point on the xoy plane may be decimals, so the coordinates of the projection point are rounded or interpolated to obtain the coordinates of the projection point after rounding (x0, y0), then the feature of the xoy plane at (x0, y0) is the d-dimensional feature of the three-dimensional point. When performing the above operations on all 3D points in the point cloud features, there may be multiple 3D points corresponding to the same position on the xoy plane. At this time, the features of these 3D points are averaged to obtain the features of this position, so that the features of each position on the xoy plane can be obtained to form the plane vector of the xoy plane.

[0083] The projection process of the xoz and yoz planes is the same as the above process and will not be repeated here.

[0084] Among them, the feature query process includes: determining the projection position of each query point on the xoy, xoz, yoz plane according to the projection process in the feature projection process, and selecting the average value of the features of the projection position on the xoy, xoz, yoz plane as the query point feature of the query point.

[0085] The input of the decoder is the fused feature (nq, d), and the output of the decoder is the OCC value (nq, 1) of all query points. The OCC value represents the occupancy result of the query point.

[0086] The decoder consists of several multi-layer perceptrons connected in sequence.

[0087] In S5, the heart chamber to be reconstructed is three-dimensionally reconstructed based on the normalized three-dimensional coordinates and occupancy results of all query points to obtain an initial three-dimensional model of the heart chamber to be reconstructed, specifically including: taking the normalized three-dimensional coordinates and occupancy results of all query points as input, using the marching cube algorithm to perform three-dimensional reconstruction on the heart chamber to be reconstructed to obtain an initial three-dimensional model of the heart chamber to be reconstructed.

[0088] In S6, the initial three-dimensional model is denormalized, specifically using translation parameters and scaling parameters to process the initial three-dimensional model. For example, if the three-dimensional point cloud data is translated to the right by 1, the initial three-dimensional model is translated to the left by 1; if the three-dimensional point cloud data is reduced by 10 times, the initial three-dimensional model is enlarged by 10 times to restore the size and posture and obtain the three-dimensional model of the heart chamber to be reconstructed.

[0089] like Figure 6 As shown, before taking the normalized point cloud data and the normalized three-dimensional coordinates of each query point as input and using the trained occupancy function prediction model to obtain the occupancy result of each query point, the method for three-dimensional reconstruction of the cardiac chamber based on echocardiography of this embodiment further includes:

[0090] (1) Obtain a data set, where the data set includes a plurality of sample normalized point cloud data and a sample initial three-dimensional model corresponding to each sample normalized point cloud data.

[0091] In this embodiment, the three-dimensional point cloud data and the real three-dimensional model (i.e., the target three-dimensional model) of the target heart chamber (i.e., the heart structure) are first obtained. The process of obtaining the three-dimensional point cloud data is the same as the process of obtaining the three-dimensional point cloud data of the heart chamber to be reconstructed, and will not be repeated here. The real three-dimensional model represents the real model of the target heart chamber represented by the three-dimensional point cloud data, and its shape and posture are consistent with the target heart chamber structure represented by the three-dimensional point cloud data.

[0092] In order to facilitate model training, all 3D point cloud data and their corresponding real 3D models are normalized to the same size and position through translation and scaling, and the translation parameters and scaling parameters used for translation and scaling are recorded, which are then used to restore the size and pose of the predicted initial 3D model. At this point, multiple sample normalized point cloud data and the sample initial 3D model corresponding to each sample normalized point cloud data can be obtained to obtain a data set.

[0093] (2) For each sample normalized point cloud data, a sampling area is determined based on the sample normalized point cloud data, and the sampling area is randomly sampled to obtain multiple sample query points; for each sample query point, the actual occupancy result of the sample query point is determined based on the three-dimensional coordinates of the sample query point and the sample initial three-dimensional model corresponding to the sample normalized point cloud data.

[0094] Training data sampling includes sampling the data set for model training. Specifically, firstly, nq sample query points are densely sampled in space, where the space is the sampling area. The sampling area can be an area that completely contains the sample normalized point cloud data as the model input data (nq, 3); then the occupancy function value OCC(nq) of these nq sample query points is obtained.

[0095] (3) Using the sample normalized point cloud data and the three-dimensional coordinates of each sample query point as input, and the actual occupancy result of each sample query point as a label, the initial occupancy function prediction model is trained to obtain a trained occupancy function prediction model.

[0096] In this embodiment, a point cloud implicit function prediction model of an encoding-decoding structure is first built, that is, an initial occupancy function prediction model is built, which has a structure exactly the same as the trained initial occupancy function prediction model, and then the initial occupancy function prediction model is trained. Specifically, the above-mentioned sample normalized point cloud data and the three-dimensional coordinates and OCC values ​​of the sample query points are used to train the initial occupancy function prediction model.

[0097] After obtaining the trained initial occupancy function prediction model, model reasoning and mesh extraction can be performed. Specifically, in the reasoning process, firstly, a sufficient number of query points are uniformly sampled in space, and the query points are normalized. The query points are input into the trained occupancy function prediction model together with the normalized point cloud data obtained after normalization of the three-dimensional point cloud data to obtain the OCC value of each query point; then, the predicted mesh model is extracted through the marching cube algorithm, that is, the initial three-dimensional model is obtained; finally, according to the recorded translation parameters and scaling parameters, the mesh model is restored to the actual size and posture to obtain the three-dimensional model.

[0098] The three-dimensional reconstruction method of this embodiment first collects three-dimensional point cloud data and a target three-dimensional model of a real heart structure as a data set, then builds an initial occupancy function prediction model, and trains the initial occupancy function prediction model so that it can predict whether an input query point is inside the heart structure, and finally, uses the trained occupancy function prediction model to predict the result, and extracts a mesh based on the prediction result to complete the three-dimensional model reconstruction. This embodiment provides a set of automated method frameworks for reconstructing heart structure on echocardiograms. Unlike existing methods, the three-dimensional model of the heart structure is reconstructed using an implicit function prediction model based on an encoding-decoding structure, which can avoid complex manual feature design and still ensure sufficient accuracy and robustness on sparse and high-noise point clouds.

[0099] Taking the right ventricle 3D reconstruction as an example, it specifically includes the following contents:

[0100] Step 1: Acquire the 3D point cloud data of the heart structure and the target 3D model.

[0101] (1) The process of acquiring three-dimensional point cloud data is as follows: first, ultrasound equipment is used to collect echocardiograms, and 7-15 views from different angles are collected for each case, and the three-dimensional posture information of the ultrasound probe is obtained by using a sensor. Then, the two-dimensional coordinates of the anatomical structure position points are marked on the 2D echocardiogram (np, 2). The anatomical structure position points specifically include: tricuspid valve ring, right ventricular septum, right ventricular endocardium, base, apex, pulmonary valve ring, right ventricular septum edge, etc. Finally, the two-dimensional coordinates are transformed into three-dimensional space through the recorded three-dimensional posture information, and the coordinate points of different views of the same heart at the same stage are merged to obtain a three-dimensional point cloud (np, 3). In addition, the anatomical structure category of each three-dimensional point is recorded in the form of a unique hot code (np, 7).

[0102] (2) The target three-dimensional model can be a three-dimensional representation form such as mesh and voxel. As an example, this embodiment uses a triangular mesh, which is composed of vertices (V: (nv, 3)), edges (E: (ne, 2)) and faces (F: (nf, 3)). The V matrix has a shape of nv rows and 3 columns, representing the three-dimensional coordinates of nv vertices, and each row is the three-dimensional coordinate of a vertex. The E matrix has a shape of ne rows and 2 columns, representing ne edges. The line connecting two vertices is an edge. The two values ​​in each row are the subscripts of the two vertices corresponding to this edge, and the subscript refers to the row number of the vertex in the V matrix. The F matrix has a shape of nf rows and 3 columns, representing nf faces. A face is a triangle formed by the lines connecting three vertices. The three values ​​in each row are the subscripts of the three vertices of the triangle in the V matrix.

[0103] To facilitate subsequent training, all 3D point cloud data and target 3D models are normalized to [-1, 1] through translation and scaling, and the translation parameters and scaling parameters are recorded.

[0104] Step 2: Construct training data (sample query point-OCC) pairs by sampling. First, randomly sample 2048 points in the coordinate range of [-1.1, 1.1] as sample query points. Then, according to the target 3D model, obtain the OCC values ​​of these sample query points. The OCC of the sample query points inside the target 3D model is 1, and the OCC of the sample query points outside the target 3D model is 0.

[0105] Step 3: Train the initial occupancy function prediction model. The specific configuration is: use adam as the optimizer, the initial learning rate is 0.001, the batch size is 32, and the loss function uses binary cross entropy.

[0106] Step 4: Use the model trained above to predict and extract the mesh on the test set. As an example, first construct a (32, 32, 32) voxel grid, input its normalized 3D coordinates into the trained occupancy function prediction model, and obtain the OCC value of the voxel in the grid. Then use the marching cube algorithm to extract the corresponding mesh. Finally, restore the mesh to its true size and pose based on the recorded translation and scaling parameters. The final predicted 3D model is as follows: Figure 7 As shown, the black grid is the predicted three-dimensional model, the white grid is the target three-dimensional model, and the white points are three-dimensional point cloud data. Obviously, the predicted three-dimensional model obtained by the three-dimensional reconstruction method of this embodiment has high accuracy.

[0107] The embodiment of the present application also provides an application scenario, which applies the above-mentioned three-dimensional reconstruction method of the heart chamber based on echocardiography. Specifically, the three-dimensional reconstruction method of the heart chamber based on echocardiography provided in this embodiment can be applied in the three-dimensional reconstruction publishing scenario of the heart chamber. The three-dimensional reconstruction publishing scenario of the heart chamber includes an image acquisition link, a three-dimensional reconstruction link and a publishing link. The image acquisition link is used to obtain an echocardiogram of the heart chamber to be reconstructed, the three-dimensional reconstruction link is used to obtain a three-dimensional model of the heart chamber to be reconstructed based on the echocardiogram, and the publishing link is used to publish the three-dimensional model. The three-dimensional reconstruction method of the heart chamber based on echocardiography provided in this embodiment belongs to the three-dimensional reconstruction link.

[0108] Example 2

[0109] Based on the same inventive concept, the embodiment of the present application also provides a device for three-dimensional reconstruction of cardiac chambers based on echocardiography for implementing the above-mentioned method for three-dimensional reconstruction of cardiac chambers based on echocardiography. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above-mentioned method, so the specific limitations in the embodiment of the device for three-dimensional reconstruction of cardiac chambers based on echocardiography provided below can refer to the limitations of the method for three-dimensional reconstruction of cardiac chambers based on echocardiography above, and will not be repeated here.

[0110] like Figure 8 As shown, this embodiment provides a three-dimensional reconstruction device of a heart chamber based on echocardiography, and the three-dimensional reconstruction device of a heart chamber based on echocardiography includes:

[0111] The point cloud generation module M1 is used to generate three-dimensional point cloud data based on the echocardiogram of the heart chamber to be reconstructed; the three-dimensional point cloud data includes multiple three-dimensional points and the three-dimensional coordinates and category of each three-dimensional point; the three-dimensional point is the anatomical structure position point of the heart chamber to be reconstructed, and the category is the anatomical structure category of the anatomical structure position point.

[0112] The normalization module M2 is used to normalize the three-dimensional point cloud data to obtain normalized point cloud data; the three-dimensional coordinates of the center point of the normalized point cloud data are the coordinate origin, and the three-dimensional coordinates of each three-dimensional point of the normalized point cloud data are within a preset range.

[0113] The query point determination module M3 is used to uniformly sample the preset three-dimensional area to obtain multiple query points, and normalize the three-dimensional coordinates of all the query points to obtain the normalized three-dimensional coordinates of each query point; the normalized three-dimensional coordinates of the center point of all the query points are the coordinate origin, and the normalized three-dimensional coordinates are within a preset range.

[0114] The model prediction module M4 is used to use the normalized point cloud data and the normalized three-dimensional coordinates of each query point as input, and use the trained occupancy function prediction model to obtain the occupancy result of each query point; the occupancy result includes that the query point is located inside the heart chamber to be reconstructed, and that the query point is located outside the heart chamber to be reconstructed.

[0115] The three-dimensional reconstruction module M5 is used to perform three-dimensional reconstruction on the heart chamber to be reconstructed based on the normalized three-dimensional coordinates and occupancy results of all the query points to obtain an initial three-dimensional model of the heart chamber to be reconstructed.

[0116] The model recovery module M6 is used to perform a denormalization process on the initial three-dimensional model to obtain a three-dimensional model of the heart chamber to be reconstructed.

[0117] Example 3

[0118] In an exemplary embodiment, a computer device is provided. The computer device may be a server or a terminal. The internal structure diagram thereof may be as follows: Fig. 9 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store echocardiograms. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a three-dimensional reconstruction method of a heart chamber based on an echocardiogram is implemented.

[0119] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0120] In an exemplary embodiment, a computer device is also provided, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the echocardiography-based three-dimensional reconstruction method of the cardiac chamber described in Example 1.

[0121] Example 4

[0122] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for three-dimensional reconstruction of cardiac chambers based on echocardiography described in Example 1 is implemented.

[0123] Example 5

[0124] An embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the method for three-dimensional reconstruction of a cardiac chamber based on echocardiography described in Example 1.

[0125] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0126] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0127] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A method for three-dimensional reconstruction of cardiac chambers based on echocardiography, characterized in that: The method for three-dimensional reconstruction of cardiac chambers based on echocardiography comprises: Generate three-dimensional point cloud data based on the echocardiogram of the heart chamber to be reconstructed; the three-dimensional point cloud data includes a plurality of three-dimensional points and the three-dimensional coordinates and category of each three-dimensional point; the three-dimensional point is an anatomical structure position point of the heart chamber to be reconstructed, and the category is the anatomical structure category of the anatomical structure position point; Normalizing the three-dimensional point cloud data to obtain normalized point cloud data; the three-dimensional coordinates of the center point of the normalized point cloud data are the coordinate origin, and the three-dimensional coordinates of each three-dimensional point of the normalized point cloud data are within a preset range; Uniformly sampling a preset three-dimensional area to obtain a plurality of query points, and normalizing the three-dimensional coordinates of all the query points to obtain normalized three-dimensional coordinates of each query point; the normalized three-dimensional coordinates of the center point of all the query points are the coordinate origin, and the normalized three-dimensional coordinates are within a preset range; Taking the normalized point cloud data and the normalized three-dimensional coordinates of each query point as input, using the trained occupancy function prediction model to obtain an occupancy result of each query point; the occupancy result includes that the query point is located inside the heart chamber to be reconstructed, and that the query point is located outside the heart chamber to be reconstructed; Performing three-dimensional reconstruction of the heart chamber to be reconstructed based on the normalized three-dimensional coordinates and occupancy results of all the query points to obtain an initial three-dimensional model of the heart chamber to be reconstructed; The initial three-dimensional model is denormalized to obtain a three-dimensional model of the heart chamber to be reconstructed.

2. The method for three-dimensional reconstruction of cardiac chambers based on echocardiography according to claim 1, characterized in that: The trained occupancy function prediction model includes an encoder, a fusion module and a decoder connected in sequence; The encoder is used to process the normalized point cloud data to obtain point cloud features; The fusion module is used to process the point cloud features and the normalized three-dimensional coordinates of each query point to obtain fusion features; The decoder is used to process the fused features to obtain an occupancy result of each query point.

3. The method for three-dimensional reconstruction of cardiac chambers based on echocardiography according to claim 2, characterized in that: The encoder includes a plurality of first multi-layer perceptron pooling modules and a multi-layer perceptron connected in sequence; the first multi-layer perceptron pooling module includes a multi-layer perceptron and a pooling layer connected in sequence; The fusion module includes a second multi-layer perceptron pooling module and a multi-layer perceptron connected in sequence, and the second multi-layer perceptron pooling module includes a multi-layer perceptron and a pooling layer connected in parallel; or, the fusion module includes a feature projection layer, a segmentation network, a feature query layer and a pooling layer connected in sequence; wherein the feature projection layer is used to project the point cloud features onto the xoy plane, the xoz plane and the yoz plane respectively to obtain three plane vectors; the segmentation network is used to process the three plane vectors to obtain three plane features; the feature query layer is used to determine the query point feature of each query point based on the normalized three-dimensional coordinates of each query point and the three plane features; The decoder includes a plurality of multi-layer perceptrons connected in sequence.

4. The method for three-dimensional reconstruction of cardiac chambers based on echocardiography according to claim 1, characterized in that: Generate 3D point cloud data based on the echocardiogram of the heart chamber to be reconstructed, including: Determining the two-dimensional coordinates of each anatomical structure location point based on the echocardiogram of the heart chamber to be reconstructed; For each of the anatomical structure position points, the two-dimensional coordinates of the anatomical structure position point are transformed using the three-dimensional posture information of the ultrasound probe when the echocardiogram is generated to obtain the three-dimensional coordinates of the anatomical structure position point; the anatomical structure position point is recorded as a three-dimensional point, the three-dimensional coordinates of the anatomical structure position point are marked as the three-dimensional coordinates of the three-dimensional point, and the anatomical structure category of the anatomical structure position point is recorded as the category of the three-dimensional point, and all of the three-dimensional points and the three-dimensional coordinates and category of each of the three-dimensional points are combined into three-dimensional point cloud data.

5. The method for three-dimensional reconstruction of cardiac chambers based on echocardiography according to claim 1, characterized in that: Before using the normalized point cloud data and the normalized three-dimensional coordinates of each query point as input and obtaining the occupancy result of each query point using the trained occupancy function prediction model, the echocardiogram-based three-dimensional reconstruction method of the cardiac chamber further includes: Acquire a data set; the data set includes a plurality of sample normalized point cloud data and a sample initial three-dimensional model corresponding to each of the sample normalized point cloud data; For each of the sample normalized point cloud data, a sampling area is determined based on the sample normalized point cloud data, and the sampling area is randomly sampled to obtain a plurality of sample query points; for each of the sample query points, an actual occupancy result of the sample query point is determined based on the three-dimensional coordinates of the sample query point and the sample initial three-dimensional model corresponding to the sample normalized point cloud data; The sample normalized point cloud data and the three-dimensional coordinates of each sample query point are used as input, and the actual occupancy result of each sample query point is used as a label to train the initial occupancy function prediction model to obtain a trained occupancy function prediction model.

6. The method for three-dimensional reconstruction of cardiac chambers based on echocardiography according to claim 1, characterized in that: Performing three-dimensional reconstruction of the heart chamber to be reconstructed based on the normalized three-dimensional coordinates and occupancy results of all the query points to obtain an initial three-dimensional model of the heart chamber to be reconstructed, specifically including: The normalized three-dimensional coordinates and occupancy results of all the query points are used as input, and the marching cube algorithm is used to perform three-dimensional reconstruction on the heart chamber to be reconstructed, so as to obtain an initial three-dimensional model of the heart chamber to be reconstructed.

7. A device for three-dimensional reconstruction of cardiac chambers based on echocardiography, characterized in that: The cardiac chamber three-dimensional reconstruction device based on echocardiography comprises: A point cloud generation module, for generating three-dimensional point cloud data based on an echocardiogram of a heart chamber to be reconstructed; the three-dimensional point cloud data comprises a plurality of three-dimensional points and a three-dimensional coordinate and a category of each three-dimensional point; the three-dimensional point is an anatomical structure position point of the heart chamber to be reconstructed, and the category is an anatomical structure category of the anatomical structure position point; A normalization module, used for normalizing the three-dimensional point cloud data to obtain normalized point cloud data; the three-dimensional coordinates of the center point of the normalized point cloud data are the coordinate origin, and the three-dimensional coordinates of each three-dimensional point of the normalized point cloud data are within a preset range; A query point determination module is used to uniformly sample a preset three-dimensional area to obtain a plurality of query points, and normalize the three-dimensional coordinates of all the query points to obtain the normalized three-dimensional coordinates of each query point; the normalized three-dimensional coordinates of the center point of all the query points are the coordinate origin, and the normalized three-dimensional coordinates are within a preset range; a model prediction module, configured to use the normalized point cloud data and the normalized three-dimensional coordinates of each query point as input, and obtain an occupancy result of each query point using a trained occupancy function prediction model; the occupancy result includes that the query point is located inside the heart chamber to be reconstructed, and that the query point is located outside the heart chamber to be reconstructed; A three-dimensional reconstruction module, used for performing three-dimensional reconstruction of the heart chamber to be reconstructed based on the normalized three-dimensional coordinates and occupancy results of all the query points to obtain an initial three-dimensional model of the heart chamber to be reconstructed; The model recovery module is used to perform a denormalization process on the initial three-dimensional model to obtain a three-dimensional model of the heart chamber to be reconstructed.

8. A computer device comprising: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the method for three-dimensional reconstruction of cardiac chambers based on echocardiography as described in any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for three-dimensional reconstruction of cardiac chambers based on echocardiography described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method for three-dimensional reconstruction of cardiac chambers based on echocardiography described in any one of claims 1 to 6 is implemented.

Images