Intracardiac ultrasonic three-dimensional imaging method and device based on orthogonal array micro phased array

Abstract

The application relates to the technical field of ultrasonic three-dimensional imaging, and discloses an intracardiac ultrasonic three-dimensional imaging method and device based on an orthogonal array micro phased array, which comprises the following steps: acquiring an initial ultrasonic image pair, a structure auxiliary image and a texture auxiliary image; constructing an ultrasonic three-dimensional image group by analyzing the structure auxiliary image, the texture auxiliary image and the initial ultrasonic image pair; and performing image fitting on the ultrasonic three-dimensional image group to obtain a comprehensive ultrasonic three-dimensional image. It can be seen that the application can model from the structure and texture angles by acquiring a first ultrasonic image and a second ultrasonic image, so that the three-dimensional imaging process fully considers the structure and texture characteristics; and the four ultrasonic three-dimensional images are combined to perform image fitting, the level of the comprehensive ultrasonic three-dimensional image is enriched, the robustness of the three-dimensional image in feature expression is improved, and thus the accuracy of the intracardiac ultrasonic three-dimensional image is further improved on the basis of the application of the orthogonal ultrasonic probe.

Description

Technical Field

[0001] This invention relates to the field of ultrasound three-dimensional imaging technology, and in particular to a method and apparatus for intracardiac ultrasound three-dimensional imaging based on orthogonal array micro phased array. Background Technology

[0002] Currently, commonly used cardiac imaging methods include digital subtraction angiography (DSA), transthoracic echocardiography (TTE), and transesophageal echocardiography (TEE). DSA is a radiological technique that can cause iatrogenic harm to patients and clinicians, and its planar projection cannot accurately provide a three-dimensional view. TTE uses a low-frequency ultrasound transducer and is susceptible to artifacts due to rib interference. TEE requires inserting the imaging probe into the esophagus, which can damage the esophageal mucosa and cause esophagitis. Furthermore, TEE requires anesthesia and multidisciplinary collaboration.

[0003] Intracardiac ultrasound (ICE) offers advantages such as high resolution, minimal rib interference, no radiation, and significantly reduced surgical time. Currently, 3D ICE imaging technology is expensive and suffers from lower resolution, poor elevation-angle imaging, and low-quality planar imaging. Furthermore, the technology for generating 3D images from 2D images is still not fully developed.

[0004] The heart is a complex three-dimensional structure. Modern cardiac 3D ultrasound uses high-quality, standardized orthogonal two-dimensional sections to ensure that the 3D data can contain the complete heart structure. For example, to evaluate the left ventricle based on the acquisition of ultrasound images based on the anatomical structure, the apical two-chamber view and the apical four-chamber view are used. These two views are roughly orthogonal in space. This method is often seen in TTE, which uses orthogonal ultrasound probes to acquire the required images. However, due to the limited space in the heart, the application of orthogonal ultrasound probes is lacking in ICE.

[0005] Furthermore, the existing method of using two-dimensional intracardiac ultrasound images to perform three-dimensional ultrasound imaging does not yield accurate three-dimensional ultrasound images. Summary of the Invention

[0006] The purpose of this invention is to provide a method and device for intracardiac ultrasound three-dimensional imaging based on orthogonal array micro phased array, so as to realize the application of orthogonal ultrasound probes in intracardiac ultrasound three-dimensional imaging, and further improve the accuracy of intracardiac ultrasound three-dimensional images on this basis.

[0007] The first aspect of this invention discloses a method for three-dimensional intracardiac ultrasound imaging based on an orthogonal array micro-phased array, the method comprising: Acquire an initial pair of ultrasound images, which is obtained through an orthogonal array of micro phased arrays; The initial ultrasound image pair includes a first ultrasound image and a second ultrasound image, wherein the first ultrasound image is used to represent cardiac structural features and the second ultrasound image is used to represent cardiac texture features; Based on the initial ultrasound image pair, an initial three-dimensional ultrasound image is obtained; Obtain structure-aided images and texture-aided images; A structure-assisted 3D image is constructed based on the structure-assisted image and the first ultrasound image; a texture-assisted 3D image is constructed based on the texture-assisted image and the second ultrasound image; and a first auxiliary ultrasound 3D image is obtained based on the structure-assisted image and the texture-assisted image. Image fitting is performed on the set of ultrasound three-dimensional images to obtain a comprehensive ultrasound three-dimensional image. The set of ultrasound three-dimensional images includes the structure-assisted three-dimensional image, the texture-assisted three-dimensional image, the initial ultrasound three-dimensional image, and the first auxiliary ultrasound three-dimensional image.

[0008] As an optional implementation, in the first aspect of the invention, before acquiring the structure-assisted image and the texture-assisted image, the method further includes: Determine the initial observation pose corresponding to the initial ultrasound image pair, the initial observation pose being used to acquire the initial ultrasound image pair; The initial ultrasound three-dimensional image is divided into grids to obtain multiple grid blocks. Based on the initial observation pose, a first confidence level is determined for each grid block. The first confidence level is used to measure the degree of information deviation between the grid block and the actual corresponding area of ​​the heart. Based on the first confidence level corresponding to all the grid blocks, an auxiliary observation pose is determined, which is used to obtain the structure-assisted image and the texture-assisted image.

[0009] As another optional implementation, in the first aspect of the invention, the method further includes: Based on the auxiliary observation pose, a second confidence level is determined for each grid block. The first confidence level is then updated based on the second confidence level to obtain a third confidence level. An image update operation is performed, comprising: obtaining an auxiliary ultrasound image pair based on the third confidence level of all the grid blocks; obtaining a second auxiliary ultrasound 3D image based on the auxiliary ultrasound image pair; and updating the current structure-assisted 3D image and the current texture-assisted 3D image based on the auxiliary ultrasound image pair, so that the current composite ultrasound 3D image is image-fitted with the second auxiliary ultrasound 3D image, the updated structure-assisted 3D image, and the updated texture-assisted 3D image to obtain an updated composite ultrasound 3D image. Based on the third confidence level, determine whether the updated integrated ultrasound 3D image meets the preset update conditions: When it is determined that the integrated ultrasound three-dimensional image meets the preset update conditions, the image update operation is retried until the integrated ultrasound three-dimensional image no longer meets the preset update conditions. When it is determined that the integrated ultrasound 3D image does not meet the preset update conditions, the current integrated ultrasound 3D image is determined to be the target ultrasound 3D image.

[0010] As another optional implementation, in the first aspect of the invention, the method further includes: The structure-assisted 3D image and the texture-assisted 3D image are compared and analyzed to obtain the first difference parameter and the second difference parameter; Based on the first difference parameter and the second difference parameter, the framework weight parameters are obtained; Wherein, the first difference parameter is used to measure the difference in image quality between the structure-assisted 3D image and the texture-assisted 3D image, and the second difference parameter is used to measure the difference in information quality between the structure-assisted 3D image and the texture-assisted 3D image, wherein the information quality includes the clarity of the heart contour details and the proportion of key heart structures in the image; Furthermore, the method for acquiring the integrated ultrasound three-dimensional image includes: Based on the aforementioned framework weight parameters, image fitting is performed on the ultrasound three-dimensional image group to obtain a comprehensive ultrasound three-dimensional image.

[0011] As another optional implementation, in the first aspect of the invention, the method further includes: The initial ultrasound three-dimensional image and the first auxiliary ultrasound three-dimensional image are compared and analyzed to obtain the third difference parameter and the fourth difference parameter; Based on the third and fourth difference parameters, the regional weight parameters are obtained; The third difference parameter is used to measure the overall confidence level difference between the initial observation pose and the auxiliary observation pose. The overall confidence level includes the density of high-confidence grid blocks and the combined first confidence level of all grid blocks. The fourth difference parameter is used to measure the difference in the inverse influence between the initial ultrasound 3D image and the auxiliary ultrasound 3D image. The inverse influence includes the degree of underfitting or overfitting caused by the ultrasound 3D image during the fitting and updating process.

[0012] And, the step of performing image fitting on the ultrasound three-dimensional image group based on the framework weight parameters to obtain a comprehensive ultrasound three-dimensional image includes: Based on the framework weight parameters and the region weight parameters, the ultrasound three-dimensional image group is fitted to obtain a comprehensive ultrasound three-dimensional image.

[0013] As another optional implementation, in the first aspect of the invention, determining the auxiliary observation pose based on the first confidence level corresponding to all the grid blocks includes: Based on the first confidence level corresponding to all the grid blocks, multiple unknown grid blocks are obtained, wherein the value of the first confidence level corresponding to the unknown grid blocks is less than a preset confidence threshold; All the unknown grid blocks are evaluated and analyzed to obtain the prediction effect score corresponding to all observation poses in the heart. The observation pose with the highest prediction effect score is determined as the auxiliary observation pose. The prediction effect score is used to measure the observation value of the target observation pose.

[0014] As another optional implementation, in the first aspect of the present invention, the method for obtaining the prediction effect score includes: A first effect score is obtained based on the number of unknown grid blocks acquired from the observed pose. A second effect score is obtained based on the image quality parameters of the ultrasound image pair corresponding to the observed pose. A third effect score is obtained by predicting the number of high-confidence grid blocks corresponding to the observed pose. A fourth effect score is obtained by predicting the confidence change of all grid blocks based on the observed pose. A predicted effect score corresponding to the target observed pose is obtained based on the first effect score, the second effect score, the third effect score, and the fourth effect score.

[0015] A second aspect of the present invention discloses an intracardiac ultrasound three-dimensional imaging device based on an orthogonal array micro phased array, the device comprising: An image acquisition module is used to acquire an initial pair of ultrasound images, which are obtained through an orthogonal array micro phased array; wherein, the initial pair of ultrasound images includes a first ultrasound image and a second ultrasound image, the first ultrasound image being used to represent cardiac structural features and the second ultrasound image being used to represent cardiac texture features; An initial imaging module is used to obtain an initial three-dimensional ultrasound image based on the initial ultrasound image pair; An auxiliary imaging module is used to acquire a structural auxiliary image and a texture auxiliary image; construct a structural auxiliary three-dimensional image based on the structural auxiliary image and the first ultrasound image; construct a texture auxiliary three-dimensional image based on the texture auxiliary image and the second ultrasound image; and obtain a first auxiliary ultrasound three-dimensional image based on the structural auxiliary image and the texture auxiliary image. The integrated imaging module is used to fit the ultrasound three-dimensional image group to obtain an integrated ultrasound three-dimensional image. The ultrasound three-dimensional image group includes the structure-assisted three-dimensional image, the texture-assisted three-dimensional image, the initial ultrasound three-dimensional image, and the first auxiliary ultrasound three-dimensional image.

[0016] As an optional implementation, in a second aspect of the invention, the apparatus further includes: Grid zoning module, used for Before the auxiliary imaging module acquires the structure auxiliary image and the texture auxiliary image Figure 1 The initial observation pose corresponding to the initial ultrasound image pair is determined, and the initial observation pose is used to acquire the initial ultrasound image pair; the initial ultrasound three-dimensional image is divided into grids to obtain multiple grid blocks; based on the initial observation pose, the first confidence level corresponding to each grid block is determined, and the first confidence level is used to measure the degree of information deviation between the grid block and the actual corresponding area of ​​the heart; The pose prediction module is used to determine the auxiliary observation pose based on the first confidence level corresponding to all the grid blocks before the auxiliary imaging module acquires the structure-assisted image and the texture-assisted image. The auxiliary observation pose is used to obtain the structure-assisted image and the texture-assisted image.

[0017] As another optional implementation, in a second aspect of the invention, the apparatus further includes: An image update module is used to determine a second confidence level for each grid block based on the auxiliary observation pose, update the first confidence level according to the second confidence level to obtain a third confidence level, and perform an image update operation, which includes: obtaining auxiliary ultrasound image pairs according to the third confidence levels of all the grid blocks; obtaining a second auxiliary ultrasound 3D image according to the auxiliary ultrasound image pairs; and updating the current structure-assisted 3D image and the current texture-assisted 3D image according to the auxiliary ultrasound image pairs, so that the current composite ultrasound 3D image is image-fitted with the second auxiliary ultrasound 3D image, the updated structure-assisted 3D image, and the updated texture-assisted 3D image to obtain an updated composite ultrasound 3D image. The update judgment module is used to determine whether the updated integrated ultrasound three-dimensional image meets the preset update conditions based on the third confidence level: when it is determined that the integrated ultrasound three-dimensional image meets the preset update conditions, the image update operation is re-triggered until the integrated ultrasound three-dimensional image does not meet the preset update conditions; when it is determined that the integrated ultrasound three-dimensional image does not meet the preset update conditions, the current integrated ultrasound three-dimensional image is determined to be the target ultrasound three-dimensional image.

[0018] A third aspect of the present invention discloses an apparatus comprising a memory and a processor, the apparatus comprising: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute some or all of the steps in the intracardiac ultrasound three-dimensional imaging method based on orthogonal array micro phased array as described in any of the first aspects of the present invention.

[0019] The fourth aspect of the present invention discloses a computer storage device storing computer instructions, which, when invoked, are used to execute some or all of the steps in the intracardiac ultrasound three-dimensional imaging method based on orthogonal array micro phased array as described in any of the first aspects of the present invention.

[0020] Compared with the prior art, the present invention has the following beneficial effects: Because existing technologies lack applications of orthogonal ultrasound probes in intracardiac ultrasound imaging, the initial ultrasound image pair obtained in this invention is achieved through an orthogonal array of miniature phased arrays. The initial ultrasound image pair includes a first ultrasound image and a second ultrasound image, ensuring that the three-dimensional imaging process fully considers structural and textural features. By acquiring structural and texture auxiliary images and constructing corresponding auxiliary 3D images, and combining the initial ultrasound 3D image with the first auxiliary ultrasound 3D image, image fitting is performed on these four types of ultrasound 3D images, which enriches the hierarchy of the comprehensive ultrasound 3D image and improves the robustness of the 3D image in feature representation. Thus, the accuracy of intracardiac ultrasound 3D images is further improved based on the application of orthogonal ultrasound probes. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 2 This is a schematic flowchart of a three-dimensional intracardiac ultrasound imaging method based on an orthogonal array micro phased array disclosed in an embodiment of the present invention; Figure 3 This is a schematic diagram of the structure of an intracardiac ultrasound three-dimensional imaging device based on an orthogonal array micro phased array disclosed in an embodiment of the present invention; Figure 4 This is a schematic diagram of another intracardiac ultrasound three-dimensional imaging device based on an orthogonal array micro phased array disclosed in an embodiment of the present invention; Figure 1 This is a schematic diagram of an ultrasonic imaging method based on an orthogonal array micro phased array disclosed in an embodiment of the present invention. Detailed Implementation

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

[0024] The terms "first," "second," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, apparatus, product, or end that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or ends.

[0025] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0026] This invention discloses a method and apparatus for intracardiac ultrasound three-dimensional imaging based on an orthogonal array micro phased array, which can further improve the accuracy of intracardiac ultrasound three-dimensional images based on the application of orthogonal ultrasound probes. Detailed descriptions follow.

[0027] Example 1 Please see Figure 1 , Figure 1 This is a schematic flowchart of a three-dimensional intracardiac ultrasound imaging method based on an orthogonal array micro-phased array disclosed in an embodiment of the present invention. Figure 1 The described intracardiac ultrasound three-dimensional imaging method based on orthogonal array micro-phased array can be applied to intracardiac ultrasound three-dimensional imaging devices based on orthogonal array micro-phased array. For example... Figure 4 As shown, the intracardiac ultrasound three-dimensional imaging method based on orthogonal array micro phased array can include the following operations: Step 101: Obtain the initial ultrasound image pair.

[0028] In this embodiment of the invention, the initial ultrasound image pair is obtained through an orthogonal array of micro-phased arrays. The orthogonal micro-phased array can be an orthogonal dual-plane phased array structure, using transducer elements as array elements, which can obtain ultrasound images of the cardiac structure with a dual-layer field of view. The specific method of image acquisition is as follows: Figure 2 As shown. The initial ultrasound image pair can be a pair of ultrasound video data containing multiple frames of ultrasound images, or it can be two mutually orthogonal ultrasound images, or it can be a set of multiple pairs of ultrasound images used to identify the heart. The embodiments of the present invention are not limited to this.

[0029] In this embodiment of the invention, the initial ultrasound image pair includes a first ultrasound image and a second ultrasound image. The image content of the first and second ultrasound images can be orthogonal in three-dimensional space. Because the heart is a complex three-dimensional structure, existing technologies for cardiac ultrasound imaging often employ methods based on anatomical structures, such as utilizing the apical two-chamber and apical four-chamber views. These two views are roughly orthogonal in space, and high-quality, standardized orthogonal two-dimensional views ensure that the three-dimensional data can encompass the complete cardiac structure. Therefore, this embodiment of the invention follows the existing approach of analyzing the three-dimensional structure of the heart using orthogonal two-dimensional images, performing subsequent three-dimensional imaging and analysis operations based on the acquired initial ultrasound image pair.

[0030] Furthermore, by employing the orthogonal array micro-phased array in this embodiment of the invention, based on the acquisition of orthogonal two-dimensional images, it can be ensured that the first ultrasound image and the second ultrasound image can be acquired simultaneously, thereby avoiding problems such as asynchronous cardiac cycles or cardiac position shifts caused by respiratory movements that accompany secondary scanning. The first and second ultrasound images may be acquired asynchronously in terms of timing. For example, in this embodiment of the invention, the two images may focus on different content. To obtain higher image quality, such as capturing relevant key features, the two images can be acquired at their respective optimal times. This embodiment of the invention does not impose any limitations on this.

[0031] In this embodiment of the invention, the first ultrasound image can be used to represent cardiac structural features, and the second ultrasound image can be used to represent cardiac texture features. Different cardiac features can be obtained from the two ultrasound images by adjusting different frequencies. These frequencies can be dynamically adjusted based on the relative spatial relationship between the probe and the heart to improve the image quality of the acquired ultrasound images. This embodiment of the invention does not limit this approach.

[0032] Step 102: Obtain the initial three-dimensional ultrasound image based on the initial ultrasound image pair; In this embodiment of the invention, the ultrasound three-dimensional image can be a three-dimensional model of the heart built in three-dimensional space. The three-dimensional model can include vertices, lines connecting the vertices, surfaces formed by the lines, textures, and materials. The ultrasound three-dimensional image can also be a static image of the three-dimensional model at a certain angle or a static image with depth information of the target object. The ultrasound three-dimensional image can also be a dynamic three-dimensional model. This embodiment of the invention does not limit the scope of the invention.

[0033] In this embodiment of the invention, the method for obtaining a three-dimensional ultrasound image from an ultrasound image pair can be a method based on a three-dimensional reconstruction algorithm to reconstruct a three-dimensional model from a two-dimensional cross-section, or a three-dimensional reconstruction method based on deep learning. The three-dimensional reconstruction algorithm includes, but is not limited to, spline interpolation based on B-splines for smooth surface reconstruction and statistical algorithms based on typical shape changes of the target object. The deep learning-based three-dimensional reconstruction method can be a volume regression network that directly predicts a three-dimensional voxel mesh from a two-dimensional image, or a multi-view fusion method that integrates two-dimensional images from multiple angles.

[0034] Step 103: Obtain the structure-aided image and the texture-aided image.

[0035] In this embodiment of the invention, structural auxiliary images and texture auxiliary images can be acquired in pairs. The acquisition method can be the same as that used to acquire the initial pair of ultrasound images, employing an orthogonal micro-phased array to obtain new orthogonal cross-sectional images of the heart, i.e., acquiring a new pair of auxiliary ultrasound images. This acquisition method ensures that each pair of images can be acquired simultaneously, reducing interference caused by differences in temporal information. These two ultrasound images can also be acquired separately, using methods such as transthoracic echocardiography or transesophageal echocardiography; this embodiment of the invention does not limit the specific methods used.

[0036] Step 104: Construct a structure-assisted 3D image based on the structure-assisted image and the first ultrasound image; construct a texture-assisted 3D image based on the texture-assisted image and the second ultrasound image; obtain the first auxiliary ultrasound 3D image based on the structure-assisted image and the texture-assisted image. In this embodiment of the invention, three types of ultrasound three-dimensional images are constructed. The structure-assisted image and the first ultrasound image focus on the structural features of the heart. Therefore, the structure-assisted three-dimensional image constructed based on these two images can provide a richer representation of the heart's structural features in three-dimensional space. Similarly, the texture-assisted three-dimensional image focuses on the texture features of the heart. The first auxiliary ultrasound three-dimensional image focuses on the differences between it and the initial ultrasound three-dimensional image. These differences can be reflected by the spatial relative relationship between the spatial location regions of the heart corresponding to the two auxiliary images and the regions corresponding to the initial ultrasound image. The spatial relative relationship is measured based on the completeness of the initial ultrasound three-dimensional image, which is not limited in this embodiment of the invention.

[0037] Step 105: Perform image fitting on the ultrasound three-dimensional image group to obtain a comprehensive ultrasound three-dimensional image.

[0038] In this embodiment of the invention, the ultrasound three-dimensional image group includes a structure-assisted three-dimensional image, a texture-assisted three-dimensional image, an initial ultrasound three-dimensional image, and a first auxiliary ultrasound three-dimensional image. The fitting process for the three-dimensional image can follow the approach of generating three-dimensional images from two-dimensional images, continuing to use spline interpolation. Based on the weight relationship between the four surfaces, a contour passing through the surfaces or a complete three-dimensional image that infinitely approximates each surface according to the weight relationship can be obtained. The fitting method can also employ parametric spline interpolation fitting, such as NURBS, or point cloud reconstruction methods based on three-dimensional point clouds, such as Poisson reconstruction, or voxel reconstruction methods based on three-dimensional voxels, or methods based on deep learning. This embodiment of the invention does not limit the specific methods used.

[0039] As can be seen, the embodiments of the present invention acquire initial ultrasound image pairs through orthogonal array micro phased array, which allows the three-dimensional imaging process to fully consider structural and texture features. By acquiring structural auxiliary images and texture auxiliary images, corresponding auxiliary three-dimensional images are constructed. Image fitting is performed on four types of ultrasound three-dimensional images, which enriches the hierarchy of the comprehensive ultrasound three-dimensional image and improves the robustness of the three-dimensional image in feature representation. Thus, the accuracy of intracardiac ultrasound three-dimensional images is further improved based on the application of orthogonal ultrasound probes.

[0040] The purpose of acquiring structural and texture-assisted images is to further supplement the initial three-dimensional ultrasound image using these two auxiliary ultrasound images. Due to the spatial limitations of intracardiac ultrasound image acquisition, intracardiac ultrasound images often cannot present a complete cross-sectional image of the heart. The initial ultrasound image pair acquired based on an orthogonal micro-phased array can accurately reflect the image of the cardiac region detected by the probe. In an optional embodiment, the image of regions other than the cardiac location corresponding to the initial ultrasound image pair is further considered to determine whether the image corresponds to the actual cardiac region. In this optional embodiment, before acquiring the structural and texture-assisted images as described above, the method may further include: Determine the initial observation pose corresponding to the initial ultrasound image pair; The initial ultrasound 3D image is divided into grids to obtain multiple grid blocks. Based on the initial observation pose, the first confidence level corresponding to each grid block is determined. The auxiliary observation pose is determined based on the first confidence level corresponding to all grid blocks.

[0041] In this optional embodiment, the observation pose may include the coordinates of the observation point corresponding to the ultrasound image, the observation angle for acquiring the ultrasound image, and the observation direction. The initial observation pose is used to acquire an initial ultrasound image pair; that is, the orthogonal micro-phased array probe can acquire an initial ultrasound image pair based on this initial observation pose. Since intracardiac ultrasound images limit the observation points for acquiring ultrasound images to the inside of the heart, the acquired ultrasound images are often partial images of a cross-section of the heart. Furthermore, the initial three-dimensional ultrasound image obtained based on the initial ultrasound image pair can be an ellipsoid reconstructed from a two-dimensional image. This three-dimensional image has the basic characteristics of the heart and can be used for basic three-dimensional cardiac analysis. While the accuracy of the heart region corresponding to the image pair is high, other regions may deviate from the actual heart condition due to a lack of actual data. The three-dimensional ultrasound image can also be a complete three-dimensional image reconstructed from a two-dimensional image using a deep learning model based on experience, but experience still differs from reality. Therefore, in this optional embodiment, a confidence level is introduced for further consideration.

[0042] In this optional embodiment, the three-dimensional image is divided into grid blocks, wherein the size and shape of the grid blocks are not limited in this optional embodiment. A first confidence level is used to measure the degree of information deviation between the grid blocks and the actual corresponding area of ​​the heart. Specifically, the confidence level can be measured in the following ways: I. Measurement based on density: Density refers to the density of data points corresponding to an image relative to the target grid. Within or near a grid block, the more original data points an image corresponds to, the higher its confidence level.

[0043] Second, image quality can be measured. Image quality can be judged by factors such as sharpness, signal-to-noise ratio, presence of artifacts, and whether the cross-section is standard. For example, the confidence level of a block with a clear image, high signal-to-noise ratio, and standard cross-section should be higher than that of a block with a blurry image or artifacts.

[0044] Third, measurement is based on prior knowledge. For example, in a block where the approximate thickness of the myocardium is known, the confidence level is higher for blocks that fit within that range.

[0045] In this optional embodiment, the auxiliary observation pose is used to obtain structural and textural auxiliary images. The purpose of acquiring the auxiliary observation pose is to further supplement information on cardiac regions with low confidence. There can be multiple auxiliary observation poses and corresponding pairs of auxiliary ultrasound images; this optional embodiment does not limit this. For the initial 3D ultrasound image, acquiring auxiliary ultrasound images to improve confidence can effectively improve the accuracy of 3D imaging, thereby making the final fitted composite 3D ultrasound image more accurate.

[0046] In an optional embodiment, based on a confidence level measurement method, a new round of auxiliary ultrasound images is acquired on top of the auxiliary ultrasound images, which are then used for continuous updating of the three-dimensional ultrasound images. Therefore, the specific operation of the intracardiac ultrasound three-dimensional imaging method based on orthogonal array micro phased array may also include: Based on the auxiliary observation pose, the second confidence level of each grid block is determined. The first confidence level is then updated based on the second confidence level to obtain the third confidence level. An image update operation is performed, which includes: obtaining auxiliary ultrasound image pairs based on the third confidence of all grid blocks; obtaining a second auxiliary ultrasound 3D image based on the auxiliary ultrasound image pairs; and updating the current structure-assisted 3D image and the current texture-assisted 3D image based on the auxiliary ultrasound image pairs, so that the current composite ultrasound 3D image is image-fitted with the second auxiliary ultrasound 3D image, the updated structure-assisted 3D image, and the updated texture-assisted 3D image to obtain an updated composite ultrasound 3D image. Based on the third confidence level, determine whether the updated integrated ultrasound 3D image meets the preset update conditions: When it is determined that the integrated ultrasound 3D image meets the preset update conditions, the image update operation is triggered again until the integrated ultrasound 3D image no longer meets the preset update conditions. When it is determined that the integrated ultrasound 3D image does not meet the preset update conditions, the current integrated ultrasound 3D image is determined as the target ultrasound 3D image.

[0047] In this optional embodiment, a cyclical update mechanism is introduced based on the confidence level supplementing cardiac information. This mechanism determines whether the comprehensive ultrasound 3D image needs updating; if so, it triggers an image update operation until the comprehensive ultrasound 3D image no longer requires updating. The update conditions can be related to confidence level, criticality, and completeness. Criticality refers to whether the image includes the key structures required for the task, and completeness refers to whether the outline edges displayed in the image are complete. This optional embodiment is not limited in its scope.

[0048] In this optional embodiment, the update condition can be a manually set threshold range, which can constrain the confidence level or values ​​or conditions derived from the confidence level; the update condition can also be a dynamically changing condition based on update requirements, which is continuously adjusted based on factors such as the number of updates, time, and cost to avoid overfitting; the update condition can also be dynamically adjusted based on deep learning to avoid underfitting. This optional embodiment is not limited.

[0049] In this optional embodiment, the second confidence level can be obtained based on the auxiliary observation pose. The confidence level measurement method used in the above embodiments will not be elaborated upon in this optional embodiment. Specifically, the operation of updating the first confidence level to obtain the third confidence level based on the second confidence level can employ an adaptive fusion method. This method specifically includes: prioritizing the use of higher confidence levels for those with large confidence level differences, and prioritizing the use of lower confidence levels for those with smaller differences; a weighted fusion method can also be used, but this optional embodiment is not limited to this method.

[0050] In this optional embodiment, the image update operation is similar to the method described in the above embodiment, which determines the auxiliary observation pose based on the first confidence level and obtains two auxiliary ultrasound images based on the auxiliary observation pose. The difference is that the newly acquired auxiliary ultrasound image pair updates the structure-assisted three-dimensional image and the texture-assisted three-dimensional image. Finally, the image fitting operation can be the surface fitting method used in the above embodiment. This optional embodiment is not limited.

[0051] As can be seen, this optional embodiment can further improve the confidence of ultrasound three-dimensional images through the cyclic update mechanism and the constraint of update conditions, thereby improving the accuracy of ultrasound three-dimensional images.

[0052] The four types of ultrasound 3D images in the ultrasound 3D image set have differences. Direct fitting may amplify negative effects and reduce positive effects. For example, the structure-assisted 3D image is subject to interference from noise or artifacts, and the task requires more texture feature extraction. Direct fitting will amplify this interference, and the sparse representation of structural features reduces the overall ultrasound 3D image's focus on texture. Therefore, to improve the accuracy of the integrated ultrasound 3D image, the fitting process needs to be further refined.

[0053] In an optional embodiment, the accuracy of the fitting operation is improved through weight allocation. Therefore, the specific operation of the intracardiac ultrasound three-dimensional imaging method based on orthogonal array micro phased array may further include: By comparing and analyzing structure-assisted 3D images and texture-assisted 3D images, the first difference parameter and the second difference parameter are obtained. Based on the first difference parameter and the second difference parameter, the framework weight parameters are obtained; The first difference parameter is used to measure the difference in image quality between structure-assisted 3D images and texture-assisted 3D images, and the second difference parameter is used to measure the difference in information quality between structure-assisted 3D images and texture-assisted 3D images. Information quality includes the clarity of the heart contour details and the proportion of key heart structures in the image. In addition, the methods for acquiring comprehensive ultrasound three-dimensional images include: Based on the framework weight parameters, image fitting is performed on the ultrasound three-dimensional image group to obtain a comprehensive ultrasound three-dimensional image.

[0054] In this optional embodiment, image quality is a fundamental attribute of ultrasound 3D images, and high-quality ultrasound 3D images should account for a larger proportion in the fitting process. Image quality variation may include resolution, noise level, penetration, contrast sharpness, overall sharpness, uniformity, and artifact readability; this optional embodiment is not limited to any particular aspect.

[0055] In this optional embodiment, the intervention of the weighting parameter in the fitting process directly affects the generation result of the comprehensive ultrasound 3D image. For example, for the ultrasound 3D image corresponding to the weighting parameter, a weight is assigned to each grid block. During the surface fitting process, with the actual position of the heart as a reference, the result at the same grid position is generated by fitting grid blocks corresponding to multiple ultrasound 3D images. The larger the weight, the stronger the importance of the grid block corresponding to this image, and the surface generated by the fitting process should be as close as possible to this grid block; conversely, the smaller the weight, the smaller the influence of this grid block on the shape of the final surface.

[0056] As can be seen, this optional embodiment, by comparing and analyzing the two auxiliary three-dimensional images, fully considers their structural and texture-based framework properties, and uses the differences between the two auxiliary ultrasound three-dimensional images to allocate weights in the fitting process, thereby improving the accuracy of the fitting process.

[0057] The framework weight parameter is used to adjust the weight distribution ratio between the structure-assisted 3D image and the texture-assisted 3D image. The differences between the two types of assisted ultrasound 3D images tend to be due to differences in image content caused by different probe frequencies. Compared with the two types of assisted ultrasound 3D images, the differences between the initial ultrasound 3D image and the first assisted ultrasound 3D image are more likely to be due to differences in image content caused by different poses. Therefore, in order to further improve the accuracy of the fitting process, in an optional embodiment, the specific operation of the intracardiac ultrasound 3D imaging method based on orthogonal array micro phased array may also include: The initial ultrasound 3D image and the first auxiliary ultrasound 3D image were compared and analyzed to obtain the third and fourth difference parameters; The regional weight parameters are obtained based on the third and fourth difference parameters; The third difference parameter is used to measure the difference in overall confidence level between the initial observation pose and the auxiliary observation pose. The overall confidence level includes the density of high-confidence grid blocks and the combined first confidence level of all grid blocks. The fourth difference parameter is used to measure the difference in reverse influence between the initial ultrasound 3D image and the auxiliary ultrasound 3D image. The reverse influence includes the degree of underfitting or overfitting caused by the ultrasound 3D image during the fitting and updating process.

[0058] Furthermore, based on the framework weight parameters, image fitting is performed on the ultrasound 3D image group to obtain a comprehensive ultrasound 3D image, including: Based on the framework weight parameters and region weight parameters, image fitting is performed on the ultrasound three-dimensional image group to obtain a comprehensive ultrasound three-dimensional image.

[0059] In this optional embodiment, the confidence level reflects the deviation between the image and the actual information of the heart. The density of the high-confidence grid blocks and the combined level of the first confidence level of the grid blocks can directly reflect the amount and distribution of effective information in the ultrasound three-dimensional image. Therefore, the third difference parameter can reflect the reliability of the ultrasound three-dimensional image.

[0060] In this optional embodiment, the inverse influence degree is obtained through the inverse feedback of the ultrasound 3D image during the fitting and updating process. For example, in the actual fitting process, at a certain location on the heart, among the four ultrasound images, one image has a high confidence level for its grid block, while the other three images have lower confidence levels for their corresponding grid blocks. In this case, the final generated ultrasound 3D image will be underfitted. Overfitting, on the other hand, can occur when four images at the same location have high confidence levels, but three of them have confidence levels for this grid block based on algorithms or experience, while the remaining one is based on actual conditions. Directly fitting all four images will result in overfitting. Furthermore, the inverse influence degree can be obtained through the simulation of the fitting process in "prefitting," and this optional embodiment is not limited to this.

[0061] This optional embodiment can further refine the weight allocation mechanism for the four types of ultrasound three-dimensional images by extending the above embodiments with new weight parameters. Moreover, this weight allocation mechanism is applicable to cyclic update operations, and this optional embodiment does not limit the scope of the embodiments.

[0062] The auxiliary observation pose determines how much effective information can be obtained from the two newly acquired auxiliary ultrasound images. The key to measuring effective information lies in the confidence level of the corresponding grid blocks. Therefore, to improve the quantity and quality of the acquired effective information, in an optional embodiment, the specific operation method for determining the auxiliary observation pose based on the first confidence level corresponding to all grid blocks may include: Based on the first confidence level corresponding to all grid blocks, multiple unknown grid blocks are obtained, and the value of the first confidence level corresponding to the unknown grid blocks is less than the preset confidence threshold. All unknown grid blocks are evaluated and analyzed to obtain the prediction effect score for all observation poses within the heart. The observation pose with the highest prediction effect score is determined as the auxiliary observation pose. The prediction effect score is used to measure the observation value of the target observation pose.

[0063] In this optional embodiment, the prediction performance score can be used to measure the observational value of the predicted pose. This observational value can be reflected in the quantity and quality of effective information obtained from the predicted pose, or the effect of the ultrasound images obtained from the predicted pose on the updating of the ultrasound 3D image. The prediction performance score is used to score each predicted pose, thereby determining whether to use the predicted pose in subsequent observations and, when using these predicted poses, the observation priority among each predicted pose.

[0064] Furthermore, in another optional embodiment, the prediction performance score is further decomposed, and the selection of the auxiliary observation pose is evaluated from multiple perspectives to obtain the observation pose with the highest efficiency, thereby improving the acquisition efficiency and image quality of the auxiliary ultrasound images. Therefore, the above-mentioned method for obtaining the prediction performance score may include: The first effect score is obtained based on the number of unknown grid blocks acquired from the observed pose. The second effect score is obtained based on the image quality parameters of the ultrasound image pair corresponding to the observed pose. The third effect score is obtained by predicting the number of high-confidence grid blocks based on the observed pose. The fourth effect score is obtained by predicting the confidence change of all grid blocks based on the observed pose. The predicted effect score corresponding to the target observed pose is obtained based on the first effect score, the second effect score, the third effect score, and the fourth effect score.

[0065] In this optional embodiment, the predicted effect score can be obtained by direct calculation and fusion of the four effect scores. During this process, the proportion of each score can be dynamically adjusted according to the actual situation. For example, the first effect score is used to acquire cardiac cross-sectional ultrasound images corresponding to low-confidence grid blocks; the more unknown grid blocks that can be acquired, the higher the corresponding first effect score. In the first round of acquiring auxiliary ultrasound images to fit the initial three-dimensional ultrasound image, the auxiliary observation pose obtained based on the first effect score can preferentially acquire a large amount of cardiac-related positional information, therefore the first effect score has a higher proportion in the first round. In subsequent iterative updates, as the unknown information decreases, the first effect score should be reduced accordingly to allow the predicted auxiliary observation pose to play other roles.

[0066] This optional embodiment further refines the predicted effect score through four effect scores, thereby improving the observation efficiency of the auxiliary observation pose, so as to improve the acquisition efficiency and image quality of the auxiliary ultrasound image, thereby improving the image quality and accuracy of the final generated ultrasound three-dimensional image.

[0067] Example 2 Please see Figure 2 , Figure 2This is a schematic diagram of the structure of an intracardiac ultrasound three-dimensional imaging device based on an orthogonal array micro phased array, as disclosed in an embodiment of the present invention. Figure 3 As shown, the intracardiac ultrasound three-dimensional imaging device based on orthogonal array micro phased array may include: The image acquisition module 201 is used to acquire an initial ultrasound image pair, which is obtained by an orthogonal array micro phased array; wherein, the initial ultrasound image pair includes a first ultrasound image and a second ultrasound image, the first ultrasound image is used to represent cardiac structural features, and the second ultrasound image is used to represent cardiac texture features. The initial imaging module 202 is used to obtain an initial three-dimensional ultrasound image based on the initial ultrasound image pair; The auxiliary imaging module 203 is used to acquire a structure-assisted image and a texture-assisted image; construct a structure-assisted three-dimensional image based on the structure-assisted image and a first ultrasound image; construct a texture-assisted three-dimensional image based on the texture-assisted image and a second ultrasound image; and obtain a first auxiliary ultrasound three-dimensional image based on the structure-assisted image and the texture-assisted image. The integrated imaging module 204 is used to perform image fitting on the ultrasound three-dimensional image group to obtain an integrated ultrasound three-dimensional image. The ultrasound three-dimensional image group includes a structure-assisted three-dimensional image, a texture-assisted three-dimensional image, an initial ultrasound three-dimensional image, and a first auxiliary ultrasound three-dimensional image.

[0068] In an optional embodiment, the device further includes: The grid partitioning module is used to determine the initial observation pose corresponding to the initial ultrasound image pair before acquiring the structure-assisted image and texture-assisted image in the above-mentioned auxiliary imaging. The initial observation pose is used to acquire the initial ultrasound image pair. The initial ultrasound three-dimensional image is divided into grids to obtain multiple grid blocks. Based on the initial observation pose, the first confidence level corresponding to each grid block is determined. The first confidence level is used to measure the degree of information deviation between the grid block and the actual corresponding area of ​​the heart. The pose prediction module is used to determine the auxiliary observation pose based on the first confidence level corresponding to all grid blocks before acquiring the structure-assisted image and texture-assisted image through the aforementioned auxiliary imaging. The auxiliary observation pose is used to obtain the structure-assisted image and texture-assisted image.

[0069] In an optional embodiment, the intracardiac ultrasound three-dimensional imaging device based on orthogonal array micro phased array may further include: The image update module is used to determine the second confidence level of each grid block based on the auxiliary observation pose, update the first confidence level according to the second confidence level to obtain the third confidence level, and perform an image update operation, which includes: obtaining auxiliary ultrasound image pairs according to the third confidence levels of all grid blocks; obtaining a second auxiliary ultrasound 3D image according to the auxiliary ultrasound image pairs; and updating the current structure auxiliary 3D image and the current texture auxiliary 3D image according to the auxiliary ultrasound image pairs, so that the current composite ultrasound 3D image is image-fitted with the second auxiliary ultrasound 3D image, the updated structure auxiliary 3D image, and the updated texture auxiliary 3D image to obtain the updated composite ultrasound 3D image. The update judgment module is used to determine whether the updated comprehensive ultrasound 3D image meets the preset update conditions based on the third confidence level: when it is determined that the comprehensive ultrasound 3D image meets the preset update conditions, the image update operation is re-triggered until the comprehensive ultrasound 3D image does not meet the preset update conditions; when it is determined that the comprehensive ultrasound 3D image does not meet the preset update conditions, the current comprehensive ultrasound 3D image is determined to be the target ultrasound 3D image.

[0070] Example 3 Please see Figure 3 , Figure 3 This is a schematic diagram of the structure of a device including a memory and a processor, as disclosed in an embodiment of the present invention. ​ As shown, the intracardiac ultrasound three-dimensional imaging device based on orthogonal array micro phased array may include: Memory 301 storing executable program code; Processor 302 coupled to memory 301; The processor 302 calls the executable program code stored in the memory 301 to execute some or all of the steps in any of the intracardiac ultrasound three-dimensional imaging methods based on orthogonal array micro phased array in Embodiment 1 of the present invention.

[0071] Example 4 This invention discloses a computer storage device that stores computer instructions. When these computer instructions are invoked, they are used to execute some or all of the steps in any of the intracardiac ultrasound three-dimensional imaging methods based on orthogonal array micro phased array disclosed in Embodiment 1 of this invention.

[0072] The device embodiments described above are merely illustrative. The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple grid modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any inventive effort.

[0073] Through the detailed description of the above embodiments, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0074] Finally, it should be noted that the above embodiments are merely preferred embodiments of the present invention and are only used to illustrate the technical solutions of the present invention, not to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for three-dimensional intracardiac ultrasound imaging based on orthogonal array micro-phased array, characterized in that, The method includes: Acquire an initial pair of ultrasound images, which is obtained through an orthogonal array of micro phased arrays; The initial ultrasound image pair includes a first ultrasound image and a second ultrasound image, wherein the first ultrasound image is used to represent cardiac structural features and the second ultrasound image is used to represent cardiac texture features; Based on the initial ultrasound image pair, an initial three-dimensional ultrasound image is obtained; Obtain structure-aided images and texture-aided images; A structure-assisted 3D image is constructed based on the structure-assisted image and the first ultrasound image; a texture-assisted 3D image is constructed based on the texture-assisted image and the second ultrasound image; and a first auxiliary ultrasound 3D image is obtained based on the structure-assisted image and the texture-assisted image. Image fitting is performed on the set of ultrasound three-dimensional images to obtain a comprehensive ultrasound three-dimensional image. The set of ultrasound three-dimensional images includes the structure-assisted three-dimensional image, the texture-assisted three-dimensional image, the initial ultrasound three-dimensional image, and the first auxiliary ultrasound three-dimensional image.

2. The intracardiac ultrasound three-dimensional imaging method based on orthogonal array micro phased array according to claim 1, characterized in that, Before acquiring the structure-assisted image and the texture-assisted image, the method further includes: Determine the initial observation pose corresponding to the initial ultrasound image pair, the initial observation pose being used to acquire the initial ultrasound image pair; The initial ultrasound three-dimensional image is divided into grids to obtain multiple grid blocks. Based on the initial observation pose, a first confidence level is determined for each grid block. The first confidence level is used to measure the degree of information deviation between the grid block and the actual corresponding area of ​​the heart. Based on the first confidence level corresponding to all the grid blocks, an auxiliary observation pose is determined, which is used to obtain a structure-assisted image and a texture-assisted image.

3. The intracardiac ultrasound three-dimensional imaging method based on orthogonal array micro phased array according to claim 2, characterized in that, The method further includes: Based on the auxiliary observation pose, a second confidence level is determined for each grid block. The first confidence level is then updated based on the second confidence level to obtain a third confidence level. An image update operation is performed, comprising: obtaining an auxiliary ultrasound image pair based on the third confidence level of all the grid blocks; obtaining a second auxiliary ultrasound 3D image based on the auxiliary ultrasound image pair; and updating the current structure-assisted 3D image and the current texture-assisted 3D image based on the auxiliary ultrasound image pair, so that the current composite ultrasound 3D image is image-fitted with the second auxiliary ultrasound 3D image, the updated structure-assisted 3D image, and the updated texture-assisted 3D image to obtain an updated composite ultrasound 3D image. Based on the third confidence level, determine whether the updated integrated ultrasound 3D image meets the preset update conditions: When it is determined that the integrated ultrasound three-dimensional image meets the preset update conditions, the image update operation is retried until the integrated ultrasound three-dimensional image no longer meets the preset update conditions. When it is determined that the integrated ultrasound 3D image does not meet the preset update conditions, the current integrated ultrasound 3D image is determined to be the target ultrasound 3D image.

4. The intracardiac ultrasound three-dimensional imaging method based on orthogonal array micro phased array according to claim 2, characterized in that, The method further includes: The structure-assisted 3D image and the texture-assisted 3D image are compared and analyzed to obtain the first difference parameter and the second difference parameter; Based on the first difference parameter and the second difference parameter, the framework weight parameters are obtained; Wherein, the first difference parameter is used to measure the difference in image quality between the structure-assisted 3D image and the texture-assisted 3D image, and the second difference parameter is used to measure the difference in information quality between the structure-assisted 3D image and the texture-assisted 3D image, wherein the information quality includes the clarity of the heart contour details and the proportion of key heart structures in the image; Furthermore, the method for acquiring the integrated ultrasound three-dimensional image includes: Based on the aforementioned framework weight parameters, image fitting is performed on the ultrasound three-dimensional image group to obtain a comprehensive ultrasound three-dimensional image.

5. The intracardiac ultrasound three-dimensional imaging method based on orthogonal array micro phased array according to claim 4, characterized in that, The method further includes: The initial ultrasound three-dimensional image and the first auxiliary ultrasound three-dimensional image are compared and analyzed to obtain the third difference parameter and the fourth difference parameter; Based on the third and fourth difference parameters, the regional weight parameters are obtained; The third difference parameter is used to measure the overall confidence level difference between the initial observation pose and the auxiliary observation pose. The overall confidence level includes the density of high-confidence grid blocks and the combined first confidence level of all grid blocks. The fourth difference parameter is used to measure the difference in the inverse influence between the initial ultrasound 3D image and the auxiliary ultrasound 3D image. The inverse influence includes the degree of underfitting or overfitting caused by the ultrasound 3D image during the fitting and updating process. And, the step of performing image fitting on the ultrasound three-dimensional image group based on the framework weight parameters to obtain a comprehensive ultrasound three-dimensional image includes: Based on the framework weight parameters and the region weight parameters, the ultrasound three-dimensional image group is fitted to obtain a comprehensive ultrasound three-dimensional image.

6. The intracardiac ultrasound three-dimensional imaging method based on orthogonal array micro phased array according to claim 3, characterized in that, The step of determining the auxiliary observation pose based on the first confidence level corresponding to all the grid blocks includes: Based on the first confidence level corresponding to all the grid blocks, multiple unknown grid blocks are obtained, wherein the value of the first confidence level corresponding to the unknown grid blocks is less than a preset confidence threshold; All the unknown grid blocks are evaluated and analyzed to obtain the prediction effect score corresponding to all observation poses in the heart. The observation pose with the highest prediction effect score is determined as the auxiliary observation pose. The prediction effect score is used to measure the observation value of the target observation pose.

7. The intracardiac ultrasound three-dimensional imaging method based on orthogonal array micro phased array according to claim 6, characterized in that, The method for obtaining the prediction performance score includes: A first effect score is obtained based on the number of unknown grid blocks acquired from the observed pose. A second effect score is obtained based on the image quality parameters of the ultrasound image pair corresponding to the observed pose. A third effect score is obtained by predicting the number of high-confidence grid blocks corresponding to the observed pose. A fourth effect score is obtained by predicting the confidence change of all grid blocks based on the observed pose. A predicted effect score corresponding to the target observed pose is obtained based on the first effect score, the second effect score, the third effect score, and the fourth effect score.

8. A three-dimensional intracardiac ultrasound imaging device based on an orthogonal array micro-phased array, characterized in that, The device includes: An image acquisition module is used to acquire an initial pair of ultrasound images, which are obtained through an orthogonal array micro phased array; wherein, the initial pair of ultrasound images includes a first ultrasound image and a second ultrasound image, the first ultrasound image being used to represent cardiac structural features and the second ultrasound image being used to represent cardiac texture features; An initial imaging module is used to obtain an initial three-dimensional ultrasound image based on the initial ultrasound image pair; An auxiliary imaging module is used to acquire a structural auxiliary image and a texture auxiliary image; construct a structural auxiliary three-dimensional image based on the structural auxiliary image and the first ultrasound image; construct a texture auxiliary three-dimensional image based on the texture auxiliary image and the second ultrasound image; and obtain a first auxiliary ultrasound three-dimensional image based on the structural auxiliary image and the texture auxiliary image. The integrated imaging module is used to fit the ultrasound three-dimensional image group to obtain an integrated ultrasound three-dimensional image. The ultrasound three-dimensional image group includes the structure-assisted three-dimensional image, the texture-assisted three-dimensional image, the initial ultrasound three-dimensional image, and the first auxiliary ultrasound three-dimensional image.

9. An apparatus comprising a memory and a processor, characterized in that, The device includes: Memory containing executable program code; A processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the intracardiac ultrasound three-dimensional imaging method based on orthogonal array micro phased array as described in any one of claims 1-7.

10. A computer storage device, characterized in that, The computer storage device stores computer instructions, which, when executed by a processor, implement the intracardiac ultrasound three-dimensional imaging method based on orthogonal array micro phased array as described in any one of claims 1-7 or the intracardiac ultrasound three-dimensional imaging method based on orthogonal array micro phased array as described in any one of claims 8-10.

Images