Multi-feature state data visualization monitoring system and method based on three-dimensional ultrasound

Through three-dimensional ultrasound feature data acquisition, projection imaging and equalization enhancement technology, intuitive images are generated, solving the problems of large amount of data and low diagnostic efficiency in three-dimensional ultrasound images, and improving diagnostic accuracy and efficiency.

CN118415676BActive Publication Date: 2024-11-08GUANGZHOU SONOSTAR TECH CO LTD
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202410889998.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-04
Publication Date
2024-11-08
Estimated Expiration
2044-07-04

AI Technical Summary

Technical Problem

The large amount of data information in three-dimensional ultrasound images leads to low diagnostic efficiency and low accuracy. Relying solely on image morphological information is not enough for accurate diagnosis, and other characteristic information such as blood flow conditions and tissue hardness are needed.

Method used

A multi-feature state data visual monitoring system based on three-dimensional ultrasound, including a three-dimensional ultrasound feature data acquisition module, a projection imaging module, a graph equalization enhancement module and a visual presentation module. By acquiring three-dimensional ultrasound feature data, projection imaging, identification analysis and equalization are carried out. Enhanced, generate intuitive images for visual rendering.

Benefits of technology

It improves doctors' understanding of the dynamic changes in patients' structures, promotes faster and more accurate diagnosis, helps to develop more effective treatment plans, and improves the efficiency and accuracy of medical diagnosis and monitoring.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118415676B_ABST
    Figure CN118415676B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of ultrasonic image processing technology, and specifically to a multi-feature state data visualization monitoring system and method based on three-dimensional ultrasound. The system includes a three-dimensional ultrasound feature data acquisition module, a projection imaging module, a graph equalization enhancement module, and a visualization presentation module; the three-dimensional ultrasound feature data acquisition module is used to acquire three-dimensional ultrasound feature data; the projection imaging module is used to perform projection imaging of the three-dimensional ultrasound feature data according to the coronal reference plane and the projection depth to generate a projection graph; the graph equalization enhancement module is used to identify and analyze the projection graph, identify the image features corresponding to the target three-dimensional ultrasound feature data in the projection graph, and perform equalization enhancement on the image features to obtain a first image; the visualization presentation module is used to visualize the first image. The present invention can improve the efficiency and accuracy of medical diagnosis and monitoring.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of ultrasonic image processing, and in particular to a multi-feature state data visualization monitoring system and method based on three-dimensional ultrasound. Background Art

[0002] In the field of medical diagnosis and monitoring, accurately and intuitively displaying the dynamic changes of the patient's body structure is crucial for early diagnosis of diseases, formulation of treatment plans, and evaluation of treatment effects. Although traditional two-dimensional ultrasound imaging technology is widely used in clinical practice, it has limitations in displaying complex structures and tiny lesions. In recent years, with the rapid development of medical imaging technology, three-dimensional ultrasound imaging technology has gradually become an important tool for medical diagnosis and monitoring by virtue of its ability to provide three-dimensional, intuitive, and multi-angle medical image information.

[0003] However, there are still some challenges in relying solely on 3D ultrasound images for diagnosis and monitoring. First, 3D ultrasound images contain a large amount of information, and doctors need to spend a lot of time and energy to interpret and analyze this data, which to some extent affects the efficiency and accuracy of diagnosis. Secondly, for some diseases or lesions, relying solely on the morphological information of the image may not be enough for accurate diagnosis, and other characteristic information, such as blood flow, tissue hardness, etc., must also be combined.

[0004] In order to solve these problems, a multi-feature state data visualization monitoring system based on three-dimensional ultrasound is urgently needed. Summary of the invention

[0005] The purpose of the present invention is to provide a multi-feature state data visualization monitoring system and method based on three-dimensional ultrasound: at least to solve the problem in existing solutions that when analyzing three-dimensional ultrasound images, the amount of data information is large and the dynamic changes of the patient's body structure cannot be intuitively understood, resulting in low diagnostic efficiency and low accuracy.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] On the one hand, a multi-feature state data visualization monitoring system based on three-dimensional ultrasound includes a three-dimensional ultrasound feature data acquisition module, a projection imaging module, a graph equalization enhancement module, and a visualization presentation module;

[0008] The three-dimensional ultrasound feature data acquisition module is used to acquire three-dimensional ultrasound feature data, wherein the three-dimensional ultrasound feature data includes target three-dimensional ultrasound feature data and non-target three-dimensional ultrasound feature data, and the three-dimensional ultrasound feature data is medical image data obtained by three-dimensional ultrasound imaging technology;

[0009] The projection imaging module is used to perform projection imaging on the three-dimensional ultrasonic feature data to generate a projection image;

[0010] The image equalization and enhancement module is used to identify and analyze the projection image, identify the image features corresponding to the target three-dimensional ultrasound feature data in the projection image, and perform equalization and enhancement on the image features to obtain a first image;

[0011] The visualization presentation module is used to perform visualization presentation on the first image.

[0012] Furthermore, the projection imaging module is used to perform projection imaging on the three-dimensional ultrasound feature data according to the coronal reference plane and the projection depth, and generating the projection image specifically includes the following process:

[0013] Acquire three-dimensional ultrasound volume data based on the three-dimensional ultrasound feature data, where the three-dimensional ultrasound volume data is the three-dimensional structure information of the target area of ​​the human body;

[0014] Determine the distance between the reference plane and the plane of the human target area based on the three-dimensional structure information of the human target area , and based on distance Generate coronal reference planes;

[0015] Based on coronal reference plane and projection depth Generate projection map by averaging composite functions , the average synthesis function is as follows:

[0016] ;

[0017] in, In the projection diagram The gray value of a pixel, The first projection plane of the three-dimensional ultrasound feature data The depth of each position from the reference plane is The intensity value of the voxel at .

[0018] Furthermore, the image equalization enhancement module is used to identify and analyze the projection image, and identifying the image features corresponding to the target three-dimensional ultrasound feature data in the projection image specifically includes the following processes:

[0019] pass Wavelet obtains the phase of the projection image at multiple scales;

[0020] The consistency of the local directional phase is determined. If the local directional phase is consistent with the preset phase, the local part is the image feature corresponding to the target three-dimensional ultrasound feature data. If the local directional phase is inconsistent with the preset phase, the local part is not the image feature corresponding to the target three-dimensional ultrasound feature data. The calculation formula of the local directional phase is as follows:

[0021] ;

[0022] in, is the local directional phase in the projection image, Indicates that the wavelet The even symmetric part and the odd symmetric part in the scale direction, Indicates that the wavelet is in a specific The even and odd symmetric parts of the scale direction, represents the amplitude of the wavelet response at the corresponding scale and direction, is a tiny constant that prevents the denominator from being zero, represents the noise threshold, is a weighting factor based on frequency spreading.

[0023] Furthermore, performing equalization enhancement on the image features to obtain the first image specifically includes the following process:

[0024] Input image features ,in, is the node set representing the target three-dimensional ultrasound feature data in the image feature, , is the edge set representing non-target 3D ultrasound feature data in the image features, , the number of edges is ;

[0025] Get the feature matrix of the node as , is the feature dimension, The eigenvector of , the adjacency matrix of the node is , the degree matrix is ;

[0026] Will and Input Graph Neural Network Encoder , output embedding matrix , , specifically:

[0027] Sampling two adaptive enhancement functions Generate micrograph views , ,in, is a collection of topology-level enhancement functions and attribute-level enhancement functions:

[0028] Through the encoder network with the same weights Generate embedding matrix ;

[0029] Through the encoder network with the same weights Generate embedding matrix ;

[0030] For topological enhancement, we remove edges from the graph according to their importance and use degree centrality as a method to measure node centrality: we sample a modified subset of the input graph. The probability set definition formula is as follows:

[0031] ;

[0032] in, To enhance the edge set in the view, To delete an edge The probability of degree of importance;

[0033] Edge centrality is defined as the average of the centrality scores of two adjacent nodes as follows:

[0034] ;

[0035] in, For edge The centrality is used to indicate the influence of the importance between two connected nodes. , represents the node centrality measure;

[0036] Calculate the probability of each edge based on the centrality of each edge: Set To reduce the impact of dense nodes, after normalization, the value is converted into probability through the conversion formula. The conversion formula is as follows:

[0037] ;

[0038] in, is a hyperparameter whose purpose is to control the overall probability of deleting edges; yes The maximum value of yes The average value of , used to limit the maximum value of probability;

[0039] For attribute level enhancement: Calculate measurement nodes based on the first formula The size of the eigenvalue in the dth dimension , the first formula is as follows:

[0040] ;

[0041] in, For Node Features, represents the node centrality measure;

[0042] The probability of attribute representation features enhanced at the node attribute level is generated by the second formula , the second formula is as follows:

[0043] ;

[0044] in, , for The maximum value of for The average value of Hyperparameters to control the overall size of feature enhancement;

[0045] Perform topology-level and node-level attribute enhancement to generate two enhanced views and , complete the equalization enhancement, and obtain the enhanced view and Fuse into the first image.

[0046] Furthermore, the visual presentation module is used to visually present the first image, including the following process:

[0047] The ultrasonic probe coordinate system is introduced to represent the coordinate position of the pixel points in a frame of the ultrasonic image in the first image. The top midpoint of the first image is taken as the origin of the ultrasonic probe coordinate system. Each pixel point in the first image has a unique coordinate representation. The unique coordinates of each point in the ultrasonic probe coordinate system are , through the coordinate system transformation, the three-dimensional coordinate value of the pixel point in the coordinate system is obtained , the coordinate transformation formula is as follows:

[0048] ;

[0049] in, is a conversion matrix, which depends on the relative positions between pixels of the first image and can be freely preset.

[0050] On the other hand, a multi-feature state data visualization monitoring method based on three-dimensional ultrasound includes:

[0051] Acquire three-dimensional ultrasound feature data, wherein the three-dimensional ultrasound feature data includes target three-dimensional ultrasound feature data and non-target three-dimensional ultrasound feature data, and the three-dimensional ultrasound feature data is medical image data obtained by three-dimensional ultrasound imaging technology;

[0052] Performing projection imaging on the three-dimensional ultrasound feature data according to the coronal reference plane and the projection depth to generate a projection map;

[0053] Performing recognition analysis on the projection image, identifying image features corresponding to the target three-dimensional ultrasonic feature data in the projection image, and performing equalization enhancement on the image features to obtain a first image;

[0054] The first image is visually presented.

[0055] Compared with the existing solutions, the present invention achieves the following beneficial effects:

[0056] The present invention obtains three-dimensional ultrasonic feature data, projects the three-dimensional ultrasonic feature data according to the coronal reference plane and the projection depth, generates a projection map, identifies and analyzes the projection map, identifies the image features corresponding to the target three-dimensional ultrasonic feature data in the projection map, and performs equalization enhancement on the image features to obtain a first image, and visualizes the first image. The multi-feature state data can be presented to doctors in an intuitive and easy-to-understand manner, helping doctors to understand the dynamic changes of the patient's body structure more quickly and accurately, so as to make more accurate diagnoses and formulate more effective treatment plans, which can improve the efficiency and accuracy of medical diagnosis and monitoring and provide rich data support for medical research. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] 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 recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0058] Figure 1 is a system block diagram of a multi-feature state data visualization monitoring system based on three-dimensional ultrasound according to an embodiment of the present invention;

[0059] Figure 2 This is a workflow diagram of a three-dimensional ultrasound-based multi-feature state data visualization monitoring system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] In addition, the described features, structures or characteristics may be combined in one or more example embodiments in any suitable manner. In the following description, many specific details are provided to provide a full understanding of the example embodiments of the present disclosure. However, those skilled in the art will appreciate that the technical solutions of the present disclosure may be practiced while omitting one or more of the specific details, or other methods, components, steps, etc. may be adopted. In other cases, well-known structures, methods, implementations or operations are not shown or described in detail to avoid obscuring various aspects of the present disclosure.

[0062] This embodiment provides a multi-feature state data visualization monitoring system based on three-dimensional ultrasound. Figure 1 is a system block diagram of a multi-feature state data visualization monitoring system based on three-dimensional ultrasound according to an embodiment of the present invention. Figure 1 As shown, the system includes a three-dimensional ultrasound feature data acquisition module, a projection imaging module, an image equalization enhancement module and a visualization presentation module;

[0063] The three-dimensional ultrasound feature data acquisition module is used to acquire three-dimensional ultrasound feature data, wherein the three-dimensional ultrasound feature data includes target three-dimensional ultrasound feature data and non-target three-dimensional ultrasound feature data, and the three-dimensional ultrasound feature data is medical image data obtained by three-dimensional ultrasound imaging technology;

[0064] The projection imaging module is used to perform projection imaging on the three-dimensional ultrasonic feature data to generate a projection image;

[0065] The image equalization and enhancement module is used to identify and analyze the projection image, identify the image features corresponding to the target three-dimensional ultrasound feature data in the projection image, and perform equalization and enhancement on the image features to obtain a first image;

[0066] The visualization presentation module is used to perform visualization presentation on the first image.

[0067] In summary, the present invention obtains three-dimensional ultrasound feature data, projects the three-dimensional ultrasound feature data according to the coronal reference plane and the projection depth, and generates a projection map; the projection map is identified and analyzed to identify the image features corresponding to the target three-dimensional ultrasound feature data in the projection map, and the image features are equalized and enhanced to obtain a first image, and the first image is visualized. The multi-feature state data can be displayed to doctors in an intuitive and easy-to-understand manner, helping doctors to understand the dynamic changes of the patient's body structure more quickly and accurately, so as to make more accurate diagnoses and formulate more effective treatment plans, which can improve the efficiency and accuracy of medical diagnosis and monitoring and provide rich data support for medical research.

[0068] In some embodiments, Figure 2is a workflow diagram of a multi-feature state data visualization monitoring system based on three-dimensional ultrasound according to an embodiment of the present invention. Figure 2 As shown, the projection imaging module is used to perform projection imaging on the three-dimensional ultrasound feature data according to the coronal reference plane and the projection depth, and generating the projection image specifically includes the following steps:

[0069] Step S101: Acquire three-dimensional ultrasound volume data based on three-dimensional ultrasound feature data, where the three-dimensional ultrasound volume data is three-dimensional structural information of a human target region. The human target region may include lungs, spine, etc. The target three-dimensional ultrasound feature data is the three-dimensional structural information of the human target region to be diagnosed, and the non-target three-dimensional ultrasound feature data is the three-dimensional structural information of the human target region not to be diagnosed.

[0070] Step S102: Determine the distance between the reference plane and the plane of the human body target area based on the three-dimensional structure information of the human body target area , and based on distance Generate a coronal reference plane; the reference plane can be the near-viewing plane where the human skin is located. The coronal reference plane, also known as the coronal plane or frontal plane, is a plane that divides the body into two parts, front and back, along the left-right direction of the human body. In DICOM format medical images such as CT or MRI, the coronal plane image reflects the longitudinal section along the left-right direction of the human body, dividing the body into the front and back. This plane is very important in medical imaging because it allows doctors to observe the patient's internal anatomical structure from a specific angle.

[0071] Step S103: Based on the coronal reference plane and projection depth Generate projection map by averaging composite functions , the average synthesis function is as follows:

[0072] ;

[0073] in, In the projection diagram The gray value of a pixel, The first projection plane of the three-dimensional ultrasound feature data The depth of each position from the reference plane is The intensity value of the voxel at .

[0074] In some embodiments, the image equalization enhancement module is used to identify and analyze the projection image, and identifying the image features corresponding to the target three-dimensional ultrasound feature data in the projection image specifically includes the following process:

[0075] pass Wavelet obtains the phase of the projection image at multiple scales. Wavelet is a filter that is a An improvement on filters, which in signal processing analyze both the spatial and frequency characteristics of a signal. Filters are a fundamental signal analysis technique that can describe a signal in terms of its local frequency response and have many applications in signal processing. Any application of filters or other wavelet basis functions can be derived from filter. Filters are widely used in image processing, pattern recognition and other fields. In particular, they perform well in primitive operations such as edge detection and can effectively mark the edges of images.

[0076] The consistency of the local directional phase is determined. If the local directional phase is consistent with the preset phase, the local part is the image feature corresponding to the target three-dimensional ultrasound feature data. If the local directional phase is inconsistent with the preset phase, the local part is not the image feature corresponding to the target three-dimensional ultrasound feature data. The calculation formula of the local directional phase is as follows:

[0077] ;

[0078] in, is the local directional phase in the projection image, Indicates that the wavelet The even symmetric part and the odd symmetric part in the scale direction, Indicates that the wavelet is in a specific The even and odd symmetric parts of the scale direction, represents the amplitude of the wavelet response at the corresponding scale and direction, is a tiny constant that prevents the denominator from being zero, represents the noise threshold, is a weighting factor based on frequency spreading.

[0079] Furthermore, performing equalization enhancement on the image features to obtain the first image specifically includes the following process:

[0080] Input image features ,in, is the node set representing the target three-dimensional ultrasound feature data in the image feature, , is the edge set representing non-target 3D ultrasound feature data in the image features, , the number of edges is ;

[0081] Get the feature matrix of the node as , is the feature dimension, The eigenvector of , the adjacency matrix of the node is , the degree matrix is ;

[0082] Will and Input Graph Neural Network Encoder , output embedding matrix , , specifically:

[0083] Sampling two adaptive enhancement functions Generate micrograph views , ,in, is a collection of topology-level enhancement functions and attribute-level enhancement functions:

[0084] Through the encoder network with the same weights Generate embedding matrix ;

[0085] Through the encoder network with the same weights Generate embedding matrix ;

[0086] For topological enhancement, we remove edges from the graph according to their importance and use degree centrality as a method to measure node centrality: we sample a modified subset of the input graph. The probability set definition formula is as follows:

[0087] ;

[0088] in, To enhance the edge set in the view, To delete an edge The probability of degree of importance;

[0089] Edge centrality is defined as the average of the centrality scores of two adjacent nodes as follows:

[0090] ;

[0091] in, For edge The centrality is used to indicate the influence of the importance between two connected nodes. , represents the node centrality measure;

[0092] Calculate the probability of each edge based on the centrality of each edge: Set To reduce the impact of dense nodes, after normalization, the value is converted into probability through the conversion formula. The conversion formula is as follows:

[0093] ;

[0094] in, is a hyperparameter whose purpose is to control the overall probability of deleting edges; yes The maximum value of yes The average value of , used to limit the maximum value of probability;

[0095] For attribute level enhancement: Calculate measurement nodes based on the first formula The size of the eigenvalue in the dth dimension , the first formula is as follows:

[0096] ;

[0097] in, For Node Features, represents the node centrality measure;

[0098] The probability of attribute representation features enhanced at the node attribute level is generated by the second formula , the second formula is as follows:

[0099] ;

[0100] in, , for The maximum value of for The average value of Hyperparameters to control the overall size of feature enhancement;

[0101] Perform topology-level and node-level attribute enhancement to generate two enhanced views and , complete the equalization enhancement, and obtain the enhanced view and Fuse into the first image.

[0102] In some embodiments, an ultrasound probe coordinate system is introduced to represent the coordinate position of a pixel point in a frame of ultrasound image in the first image, wherein the ultrasound probe coordinate system is a mathematical framework for describing the position and direction of the ultrasound probe relative to a reference point or reference surface. In an ultrasound imaging system, the probe coordinate system is crucial for accurately interpreting and positioning ultrasound images. The top midpoint of the first image is taken as the origin of the ultrasound probe coordinate system. Each pixel point in the first image has a unique coordinate representation. The unique coordinates of each point in the ultrasound probe coordinate system are , through the coordinate system transformation, the three-dimensional coordinate value of the pixel point in the coordinate system is obtained , the coordinate transformation formula is as follows:

[0103] ;

[0104] in, is a conversion matrix, which depends on the relative positions between pixels of the first image and can be freely preset.

[0105] The embodiment of the present invention further provides a method for visualizing monitoring of multi-feature state data based on three-dimensional ultrasound, the method comprising:

[0106] Acquire three-dimensional ultrasound feature data, wherein the three-dimensional ultrasound feature data includes target three-dimensional ultrasound feature data and non-target three-dimensional ultrasound feature data, and the three-dimensional ultrasound feature data is medical image data obtained by three-dimensional ultrasound imaging technology;

[0107] Performing projection imaging on the three-dimensional ultrasound feature data according to the coronal reference plane and the projection depth to generate a projection map;

[0108] Performing recognition analysis on the projection image, identifying image features corresponding to the target three-dimensional ultrasonic feature data in the projection image, and performing equalization enhancement on the image features to obtain a first image;

[0109] The first image is visually presented.

[0110] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0111] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0112] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0113] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only for some logical functions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0114] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0115] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program codes.

[0116] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. Multi-feature state data visualization monitoring system based on three-dimensional ultrasound, It is characterized in that The system includes a three-dimensional ultrasound feature data acquisition module, a projection imaging module, an image equalization enhancement module, and a visualization presentation module; The three-dimensional ultrasound feature data acquisition module is used to acquire three-dimensional ultrasound feature data, wherein the three-dimensional ultrasound feature data includes target three-dimensional ultrasound feature data and non-target three-dimensional ultrasound feature data, and the three-dimensional ultrasound feature data is medical image data obtained by three-dimensional ultrasound imaging technology; The projection imaging module is used to perform projection imaging on the three-dimensional ultrasonic feature data to generate a projection image; The image equalization and enhancement module is used to identify and analyze the projection image, identify the image features corresponding to the target three-dimensional ultrasound feature data in the projection image, and perform equalization and enhancement on the image features to obtain a first image; The equalization enhancement of the image features to obtain the first image specifically includes the following process: Input image features ,in, is the node set representing the target three-dimensional ultrasound feature data in the image feature, , is the edge set representing non-target 3D ultrasound feature data in the image features, , the number of edges is ; Get the feature matrix of the node as , is the feature dimension, The eigenvector of , the adjacency matrix of the node is , the degree matrix is ; Will and Input Graph Neural Network Encoder , output embedding matrix , , specifically: Sampling two adaptive enhancement functions Generate micrograph views , ,in, is a collection of topology-level enhancement functions and attribute-level enhancement functions: Through the encoder network with the same weights Generate embedding matrix ; Through the encoder network with the same weights Generate embedding matrix ; For topological enhancement, we remove edges from the graph according to their importance and use degree centrality as a method to measure node centrality: we sample a modified subset of the input graph. The probability set definition formula is as follows: ; in, To enhance the edge set in the view, To delete an edge The probability of degree of importance; Edge centrality is defined as the average of the centrality scores of two adjacent nodes as follows: ; in, For edge The centrality is used to indicate the influence of the importance between two connected nodes. , represents the node centrality measure; Calculate the probability of each edge based on the centrality of each edge: Set To reduce the impact of dense nodes, after normalization, the value is converted into probability through the conversion formula. The conversion formula is as follows: ; in, is a hyperparameter whose purpose is to control the overall probability of deleting edges; yes The maximum value of yes The average value of , used to limit the maximum value of probability; For attribute level enhancement: Calculate measurement nodes based on the first formula The size of the eigenvalue in the dth dimension , the first formula is as follows: ; in, For Node Features, represents the node centrality measure; The probability of attribute representation features enhanced at the node attribute level is generated by the second formula , the second formula is as follows: ; in, , for The maximum value of for The average value of Hyperparameters to control the overall size of feature enhancement; Perform topology-level and node-level attribute enhancement to generate two enhanced views and , complete the equalization enhancement, and obtain the enhanced view and Fusing into a first image; The visualization presentation module is used to perform visualization presentation on the first image.

2. The multi-feature state data visualization monitoring system based on three-dimensional ultrasound according to claim 1, It is characterized in that The projection imaging module is used to perform projection imaging on the three-dimensional ultrasound feature data according to the coronal reference plane and the projection depth. The generation of the projection image specifically includes the following processes: Acquire three-dimensional ultrasound volume data based on the three-dimensional ultrasound feature data, where the three-dimensional ultrasound volume data is the three-dimensional structure information of the target area of ​​the human body; Determine the distance between the reference plane and the plane of the human target area based on the three-dimensional structure information of the human target area , and based on distance Generate coronal reference planes; Based on coronal reference plane and projection depth Generate projection map by averaging composite functions , the average synthesis function is as follows: ; in, In the projection diagram The gray value of a pixel, The first The depth of each position from the reference plane is The intensity value of the voxel at .

3. The multi-feature state data visualization monitoring system based on three-dimensional ultrasound according to claim 1, It is characterized in that The image equalization enhancement module is used to identify and analyze the projection image, and identify the image features corresponding to the target three-dimensional ultrasound feature data in the projection image. The process includes: pass Wavelet obtains the phase of the projection image at multiple scales; The consistency of the local directional phase is determined. If the local directional phase is consistent with the preset phase, the local part is the image feature corresponding to the target three-dimensional ultrasound feature data. If the local directional phase is inconsistent with the preset phase, the local part is not the image feature corresponding to the target three-dimensional ultrasound feature data. The calculation formula of the local directional phase is as follows: ; in, is the local directional phase in the projection image, Indicates that the wavelet The even symmetric part and the odd symmetric part in the scale direction, Indicates that the wavelet is in a specific The even and odd symmetric parts of the scale direction, represents the amplitude of the wavelet response at the corresponding scale and direction, is a tiny constant that prevents the denominator from being zero, represents the noise threshold, is a weighting factor based on frequency spreading.

4. The multi-feature state data visualization monitoring system based on three-dimensional ultrasound according to claim 1, It is characterized in that The visual presentation module is used to visually present the first image, including the following process: The ultrasonic probe coordinate system is introduced to represent the coordinate position of the pixel points in a frame of the ultrasonic image in the first image. The top midpoint of the first image is taken as the origin of the ultrasonic probe coordinate system. Each pixel point in the first image has a unique coordinate representation. The unique coordinates of each point in the ultrasonic probe coordinate system are , through the coordinate system transformation, the three-dimensional coordinate value of the pixel point in the coordinate system is obtained , the coordinate transformation formula is as follows: ; in, is a conversion matrix, which depends on the relative positions between pixels of the first image and can be freely preset.

5. Multi-feature state data visualization monitoring method based on three-dimensional ultrasound, It is characterized in that Methods include: Acquire three-dimensional ultrasound feature data, wherein the three-dimensional ultrasound feature data includes target three-dimensional ultrasound feature data and non-target three-dimensional ultrasound feature data, and the three-dimensional ultrasound feature data is medical image data obtained by three-dimensional ultrasound imaging technology; Performing projection imaging on the three-dimensional ultrasound feature data according to the coronal reference plane and the projection depth to generate a projection map; Performing recognition analysis on the projection image, identifying image features corresponding to the target three-dimensional ultrasonic feature data in the projection image, and performing equalization enhancement on the image features to obtain a first image; The equalization enhancement of the image features to obtain the first image specifically includes the following process: Input image features ,in, is the node set representing the target three-dimensional ultrasound feature data in the image feature, , is the edge set representing non-target 3D ultrasound feature data in the image features, , the number of edges is ; Get the feature matrix of the node as , is the feature dimension, The eigenvector of , the adjacency matrix of the node is , the degree matrix is ; Will and Input Graph Neural Network Encoder , output embedding matrix , , specifically: Sampling two adaptive enhancement functions Generate micrograph views , ,in, is a collection of topology-level enhancement functions and attribute-level enhancement functions: Through the encoder network with the same weights Generate embedding matrix ; Through the encoder network with the same weights Generate embedding matrix ; For topological enhancement, we remove edges from the graph according to their importance and use degree centrality as a method to measure node centrality: we sample a modified subset of the input graph. The probability set definition formula is as follows: ; in, To enhance the edge set in the view, To delete an edge The probability of degree of importance; Edge centrality is defined as the average of the centrality scores of two adjacent nodes as follows: ; in, For edge The centrality is used to indicate the influence of the importance between two connected nodes. , represents the node centrality measure; Calculate the probability of each edge based on the centrality of each edge: Set To reduce the impact of dense nodes, after normalization, the value is converted into probability through the conversion formula. The conversion formula is as follows: ; in, is a hyperparameter whose purpose is to control the overall probability of deleting edges; yes The maximum value of yes The average value of , used to limit the maximum value of probability; For attribute level enhancement: Calculate measurement nodes based on the first formula The size of the eigenvalue in the dth dimension , the first formula is as follows: ; in, For Node Features, represents the node centrality measure; The probability of attribute representation features enhanced at the node attribute level is generated by the second formula , the second formula is as follows: ; in, , for The maximum value of for The average value of Hyperparameters to control the overall size of feature enhancement; Perform topology-level and node-level attribute enhancement to generate two enhanced views and , complete the equalization enhancement, and obtain the enhanced view and Fusing into a first image; The first image is visually presented.

Citation Information

Patent Citations

  • Three-dimensional ultrasonic spinal data based sagittal plane projection imaging method

    CN109965910A

  • Non-contact heart three-dimensional mapping method and system

    CN116703882A

  • System and method for three-dimensional space management and visualization of ultrasound data ("SonoDEX")

    US20060020204A1

  • KR20190141326A