A three-dimensional cardiac mapping method and system
By enhancing, registering and morphological analysis of cardiac ultrasound images, an accurate three-dimensional heart model is generated, which solves the error problems caused by two-dimensional images and low-resolution three-dimensional images in the prior art, and achieves more accurate cardiac marking and diagnosis.
Patent Information
- Application Number
- CN202310987154.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-08-07
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2043-08-07
AI Technical Summary
Existing cardiac diagnosis methods can only provide two-dimensional images or low-resolution three-dimensional images, resulting in large errors in cardiac marking results, and manual marking has great subjectivity, making it difficult to conduct accurate analysis and diagnosis.
By collecting cardiac ultrasound image sequences within multiple cardiac cycles, image enhancement and edge detection processing are performed, image registration is performed based on correlation matching algorithm, and morphological analysis is used to perform stratified mapping of the three-dimensional model to generate more accurate hearts 3D model.
It improves the display clarity and mapping accuracy of the three-dimensional cardiac model, reduces the subjective impact, and provides more accurate diagnosis and treatment effects for heart patients.
Smart Images

Figure CN117011464B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of image mapping, and in particular relates to a three-dimensional cardiac mapping method and system. Background Art
[0002] 3D cardiac mapping is a medical imaging technology that combines multiple 2D medical images, such as ultrasound, CT or MRI images, into a 3D model to comprehensively evaluate the heart. This technology can provide more detailed and accurate information about the structure and function of the heart, thereby helping doctors make more accurate diagnoses and treatment plans. When performing 3D cardiac mapping, doctors use professional software to process and reconstruct multiple 2D images to generate a 3D model with the true morphology and structure of the heart. This 3D model can be rotated, enlarged and reduced, allowing doctors to view various parts of the heart and evaluate the structure and function of the heart.
[0003] Traditional methods for diagnosing heart disease can only provide two-dimensional images or low-resolution three-dimensional images. In addition, the existing three-dimensional cardiac mapping methods in the prior art often simply perform rough mapping of the structural dimensions of the heart, resulting in large errors in the results of cardiac mapping. In addition, manual mapping is highly subjective, making it difficult to accurately analyze and diagnose the heart. Summary of the invention
[0004] The purpose of the embodiments of the present invention is to provide a three-dimensional cardiac mapping method and system, which can solve the technical problems that existing heart disease diagnosis methods can only provide two-dimensional images or low-resolution three-dimensional images, and the existing three-dimensional cardiac mapping methods in the prior art often only simply perform rough mapping of the structural dimensions of the heart, resulting in large errors in the results of cardiac mapping, and manual mapping has a large degree of subjectivity.
[0005] In order to solve the above-mentioned technical problems, the present invention is achieved as follows:
[0006] First aspect
[0007] An embodiment of the present invention provides a method for three-dimensional cardiac mapping, the method comprising:
[0008] S101: Acquire cardiac ultrasound image sequences within a plurality of cardiac cycles, wherein each cardiac ultrasound image sequence includes a plurality of cardiac ultrasound images;
[0009] S102: performing image enhancement and edge detection processing on the cardiac ultrasound image to obtain an optimized cardiac ultrasound image;
[0010] S103: registering the optimized cardiac ultrasound images based on a correlation matching algorithm to ensure that the optimized cardiac ultrasound images are in the same coordinate system;
[0011] S104: performing a three-dimensional reconstruction operation on each registered optimized cardiac ultrasound image to obtain a three-dimensional cardiac model;
[0012] S105: Introduce the heart to use morphological analysis method to perform layered mapping of the three-dimensional heart model;
[0013] S106: Outputting the mapped three-dimensional heart model.
[0014] Second aspect
[0015] An embodiment of the present invention provides a three-dimensional cardiac mapping system, comprising:
[0016] An acquisition module, used for acquiring cardiac ultrasound image sequences within a plurality of cardiac cycles, wherein each cardiac ultrasound image sequence includes a plurality of cardiac ultrasound images;
[0017] A processing module, used for performing image enhancement and edge detection processing on the cardiac ultrasound image to obtain an optimized cardiac ultrasound image;
[0018] A registration module, used for registering the optimized cardiac ultrasound images based on a correlation matching algorithm to ensure that the optimized cardiac ultrasound images are in the same coordinate system;
[0019] A reconstruction module, used for performing three-dimensional reconstruction on each registered optimized cardiac ultrasound image to obtain a three-dimensional heart model;
[0020] A mapping module, used to introduce a cardiac morphological analysis method to perform hierarchical mapping on a three-dimensional cardiac model;
[0021] The output module is used to output the three-dimensional heart model after mapping.
[0022] In the embodiment of the present invention, the collected cardiac ultrasound image is subjected to image enhancement and edge detection processing to make the contrast of the cardiac ultrasound image stronger and the display effect better. Then, the optimized cardiac ultrasound image is registered to avoid artifacts in the process of reconstructing the cardiac three-dimensional model, thereby improving the display clarity of the established cardiac three-dimensional model. Finally, the established cardiac three-dimensional model is automatically layered mapped using the morphological analysis method to improve the mapping effect of the details and overall structure of the cardiac three-dimensional structure, avoid the subjective influence of the mapping, provide a more accurate cardiac three-dimensional model for analyzing the patient's condition, and provide better treatment effects for patients with heart disease. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] Figure 1 is a flow chart of a three-dimensional cardiac mapping method provided by an embodiment of the present invention;
[0024] Figure 2 It is a structural schematic diagram of a three-dimensional cardiac mapping system provided by an embodiment of the present invention.
[0025] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION
[0026] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all 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.
[0027] In conjunction with the accompanying drawings, a three-dimensional cardiac mapping method and system provided by the embodiment of the present invention will be described in detail through specific embodiments and application scenarios.
[0028] Embodiment 1
[0029] Reference Figure 1 , showing a schematic flow chart of a method for three-dimensional cardiac mapping provided by an embodiment of the present invention;
[0030] An embodiment of the present invention provides a three-dimensional cardiac mapping method, the method comprising:
[0031] S101: Acquire cardiac ultrasound image sequences within a plurality of cardiac cycles, wherein each cardiac ultrasound image sequence includes a plurality of cardiac ultrasound images.
[0032] It should be noted that the steps of collecting cardiac ultrasound image sequences within multiple cardiac cycles are to obtain multiple cardiac ultrasound images for subsequent processing to obtain more information and data, so as to have a more comprehensive understanding of the structure and function of the heart. Collecting image sequences within multiple cardiac cycles can improve the reliability and accuracy of the data, thereby better assessing the heart condition and disease state. Scientific sampling methods can improve the accuracy of the final established three-dimensional heart model and avoid excessive errors caused by too little sampling.
[0033] S102: Perform image enhancement and edge detection processing on the cardiac ultrasound image to obtain an optimized cardiac ultrasound image.
[0034] It should be noted that the acquired cardiac ultrasound images have certain noise and fuzziness due to the influence of various uncertain factors in the acquisition process, which will affect the subsequent data analysis and processing. Image enhancement processing can enhance the contrast and clarity of the image and improve the image quality. Edge detection processing can help accurately locate and extract the contour and edge information of the heart, providing a basis for subsequent three-dimensional reconstruction and morphological analysis.
[0035] In a possible implementation, S102 specifically includes:
[0036] S1021: Perform image enhancement on each cardiac ultrasound image through histogram equalization processing to obtain an enhanced image G(x,y):
[0037]
[0038] Where G(x,y) represents the pixel value of the enhanced image, H(i,j) represents the pixel value at the coordinate (i,j) in the original image, and M and N represent the width and height of the image respectively;
[0039] S1022: Perform Sobel operator edge detection on the enhanced image to extract edge information G of the enhanced image x and G y :
[0040]
[0041]
[0042] Among them, G x and G y They represent the gradients of the enhanced image in the horizontal and vertical directions after edge detection, respectively. The symbol * represents the convolution operation, and I represents the enhanced image.
[0043] S1023: Calculate and optimize the cardiac ultrasound image G according to the gradients of the enhanced image in the horizontal and vertical directions after edge detection:
[0044]
[0045] S1024: Outputting the optimized cardiac ultrasound image G.
[0046] S103: Registering the optimized cardiac ultrasound images based on a correlation matching algorithm to ensure that the optimized cardiac ultrasound images are in the same coordinate system.
[0047] Image registration refers to the process of aligning multiple images of the same scene taken from different perspectives, different positions or different times so that they can perfectly overlap in the same coordinate system. In other words, two or more images are transformed in a certain way so that they overlap in the same spatial position. By registering the optimized cardiac ultrasound images, they can be aligned, so as to more accurately compare and analyze medical images and improve the effect of medical image processing.
[0048] It should be noted that in the process of optimizing cardiac ultrasound images, due to the influence of factors such as human breathing and heartbeat, there may be slight position and morphological changes between different images. If no registration is performed, it may cause inaccuracy and inconsistency in the data. Therefore, through the registration operation based on the correlation matching algorithm, multiple images can be placed in the same coordinate system, ensuring the consistency and accuracy of the data, and providing a better data basis for subsequent three-dimensional reconstruction and morphological analysis.
[0049] In a possible implementation manner, S103 specifically includes:
[0050] S1031: Select an optimized cardiac ultrasound image as a reference image, and use it as the origin of the coordinate system to establish a plane rectangular coordinate system;
[0051] S1032: Selecting one of the remaining optimized ultrasound images as an image to be aligned;
[0052] S1033: normalizing the reference image and the image to be aligned to obtain a normalized reference image and a normalized image to be aligned;
[0053] S1034: Calculate the similarity between the normalized reference image and the image to be aligned based on a correlation matching algorithm:
[0054]
[0055] Among them, I ref (x,y),I mov (x, y) represent the reference image and the image to be aligned respectively. They represent the means of the normalized reference image and the normalized image to be aligned, respectively, and (tx,ty) represents the relative displacement between the reference image and the image to be aligned;
[0056] S1035: Calculate the target relative displacement when the similarity is maximum;
[0057] S1036: translating the image to be aligned using the target displacement to complete the registration;
[0058] S1037: Repeat S1032-S1036 to register the remaining images to be aligned.
[0059] S104: Performing a three-dimensional reconstruction operation on each registered optimized cardiac ultrasound image to obtain a three-dimensional cardiac model.
[0060] It should be noted that the steps of performing 3D reconstruction on the registered cardiac ultrasound images are as follows. Through 3D reconstruction, multiple 2D images can be combined into a 3D heart model, so as to more intuitively understand the structure and function of the heart. At the same time, 3D reconstruction can also provide more geometric morphological information and spatial position information, which is helpful for further morphological analysis and quantitative evaluation of the patient's heart, and improves the effectiveness of targeted treatment.
[0061] In a possible implementation, S104 specifically includes:
[0062] S1041: extracting feature points from the registered optimized cardiac ultrasound image, wherein the feature points include ventricular wall feature points and cardiac valve feature points, to obtain a feature point set;
[0063] S1042: Convert the feature point set into a three-dimensional point cloud data set X:
[0064] X={x1,x2,...,x i}
[0065]
[0066] Among them, x i is the feature point q in the feature point set i The three-dimensional coordinates of
[0067] S1043: Use triangulation algorithm to convert 3D point cloud data into triangulated mesh data M:
[0068] M={m1,m2,...,m i}
[0069] m i =[x k ,x p ,x q ]
[0070] x k ,x p ,x q ∈X
[0071] Among them, each triangle m i Corresponding to three 3D point cloud data x k ,x p ,x q ;
[0072] S1044: Select different materials and textures to optimize and compress the triangular mesh data to obtain a three-dimensional model of the heart.
[0073] S105: Introduce the heart and use the morphological analysis method to perform layered mapping on the three-dimensional heart model.
[0074] Among them, morphological analysis is an image analysis method that can be used to analyze and describe the shape and structure in an image. It extracts the morphological information of the image, such as contours, corners, holes, morphological features, etc., through a series of morphological operations, such as dilation, erosion, opening, and closing operations.
[0075] In medical image processing, morphological analysis is often used to analyze and describe the morphological structure of biological tissues, thereby helping doctors diagnose diseases and evaluate treatment effects. In cardiac image processing, morphological analysis can be used to extract the morphological features of the heart, such as the size of the heart chamber, myocardial thickness, the location and thickness of the ventricular septum, etc. This information can help doctors determine the health of the heart and diagnose heart disease.
[0076] In a possible implementation manner, S105 specifically includes:
[0077] S1051: Import the 3D heart model and divide it into layers according to the structure:
[0078] M l =x∈M:α l ≤H(x)<α l+1
[0079] Among them, M represents the three-dimensional model of the heart, M l represents the heart structure of the first layer, H(x) represents the maximum height of the heart 3D model in 3D space, α l and α l+1 They represent the height thresholds of the lth layer and the l+1th layer of the three-dimensional heart model respectively;
[0080] S1052: Preliminarily mark the structures at each level based on cardiac anatomical knowledge to obtain preliminary marking results;
[0081] S1053: Based on the preliminary marking, each level is refined and marked using a morphological analysis algorithm to obtain a refined marking result S' l :
[0082]
[0083] Among them, B represents the preset structural element, that is, a binary matrix, and the symbol Represents the morphological operation operator, S l Indicates preliminary marking results;
[0084] S1054: The preliminary labeling result and the refined labeling result are combined to obtain the final labeling S of the entire heart three-dimensional model:
[0085]
[0086] Wherein, n represents the number of divided cardiac structure layers.
[0087] In actual application, those skilled in the art can set the number of cardiac structure layers according to actual needs. The more layers, the more accurate the mapping results. However, in the mapping process, the more cardiac structure layers, the better, because the more cardiac structure layers, the longer the marking time. The appropriate cardiac structure can be selected according to the required mapping accuracy of the three-dimensional cardiac model to improve the efficiency and accuracy of three-dimensional cardiac mapping.
[0088] It should be noted that in hierarchical mapping, the three-dimensional heart model will be divided into multiple different levels according to the different anatomical structures and functions of the heart, and each level will be labeled and annotated. These labels and annotations can be used to study and analyze the heart structure, function and related diseases in more depth. The high-quality three-dimensional heart model information obtained through the previous steps has not been fully utilized. Through hierarchical mapping, we can further explore more information in the model, conduct a more comprehensive and in-depth analysis of the structure, function and disease of the heart, and carefully divide and label the different structures and parts of the model, which will help improve the accuracy and credibility of the model.
[0089] S106: Outputting the mapped three-dimensional heart model.
[0090] In the embodiment of the present invention, the collected cardiac ultrasound image is subjected to image enhancement and edge detection processing to make the contrast of the cardiac ultrasound image stronger and the display effect better. Then, the optimized cardiac ultrasound image is registered to avoid artifacts in the process of reconstructing the cardiac three-dimensional model, thereby improving the display clarity of the established cardiac three-dimensional model. Finally, the established cardiac three-dimensional model is automatically layered mapped using the morphological analysis method to improve the mapping effect of the details and overall structure of the cardiac three-dimensional structure, avoid the subjective influence of the mapping, provide a more accurate cardiac three-dimensional model for analyzing the patient's condition, and provide better treatment effects for patients with heart disease.
[0091] Embodiment 2
[0092] Reference Figure 2 , showing a schematic structural diagram of a three-dimensional cardiac mapping system provided in an embodiment of the present invention.
[0093] A three-dimensional cardiac mapping system 20, comprising:
[0094] An acquisition module 201 is used to acquire cardiac ultrasound image sequences within multiple cardiac cycles, wherein each cardiac ultrasound image sequence includes multiple cardiac ultrasound images;
[0095] The processing module 202 is used to perform image enhancement and edge detection processing on the cardiac ultrasound image to obtain an optimized cardiac ultrasound image;
[0096] A registration module 203, used for registering the optimized cardiac ultrasound images based on a correlation matching algorithm to ensure that the optimized cardiac ultrasound images are in the same coordinate system;
[0097] A reconstruction module 204 is used to perform three-dimensional reconstruction on each registered optimized cardiac ultrasound image to obtain a three-dimensional heart model;
[0098] Mapping module 205, used for introducing the heart to perform layered mapping on the three-dimensional heart model using morphological analysis method;
[0099] The output module 206 is used to output the mapped three-dimensional heart model.
[0100] In a possible implementation, the processing module specifically includes:
[0101] The first processing submodule is used to perform image enhancement on each cardiac ultrasound image through histogram equalization processing to obtain an enhanced image G(x,y):
[0102]
[0103] Where G(x,y) represents the pixel value of the enhanced image, H(i,j) represents the pixel value at the coordinate (i,j) in the original image, and M and N represent the width and height of the image respectively;
[0104] The first extraction submodule is used to perform Sobel operator edge detection on the enhanced image and extract edge information G of the enhanced image. x and G y :
[0105]
[0106]
[0107] Among them, G x and G y They represent the gradients of the enhanced image in the horizontal and vertical directions after edge detection, respectively. The symbol * represents the convolution operation, and I represents the enhanced image.
[0108] The first calculation submodule is used to calculate and optimize the cardiac ultrasound image G according to the gradients of the enhanced image in the horizontal direction and the vertical direction after edge detection:
[0109]
[0110] The output submodule is used to output the optimized cardiac ultrasound image G.
[0111] In a possible implementation, the registration module specifically includes:
[0112] The first selection submodule is used to select an optimized cardiac ultrasound image as a reference image and use it as the origin of the coordinate system to establish a plane rectangular coordinate system;
[0113] A second selection submodule is used to select one of the remaining optimized ultrasound images as an image to be aligned;
[0114] The second processing submodule is used to normalize the reference image and the image to be aligned to obtain a normalized reference image and a normalized image to be aligned;
[0115] The second calculation submodule is used to calculate the similarity between the normalized reference image and the image to be aligned based on a correlation matching algorithm:
[0116]
[0117] Among them, I ref (x,y),I mov (x, y) represent the reference image and the image to be aligned respectively. They represent the means of the normalized reference image and the normalized image to be aligned, respectively, and (tx,ty) represents the relative displacement between the reference image and the image to be aligned;
[0118] The third calculation submodule is used to calculate the relative displacement of the target when the similarity is maximum;
[0119] The translation submodule is used to translate the image to be aligned using the target displacement to complete the registration;
[0120] The repeating submodule is used to repeat S1032-S1036 to register the remaining images to be aligned.
[0121] In a possible implementation, the reconstruction module specifically includes:
[0122] A second extraction submodule is used to extract feature points in the registered optimized cardiac ultrasound image, wherein the feature points include ventricular wall feature points and cardiac valve feature points, to obtain a feature point set;
[0123] The first conversion submodule is used to convert the feature point set into a three-dimensional point cloud data set X:
[0124] X={x1,x2,...,x i}
[0125]
[0126] Among them, x i is the feature point q in the feature point set i The three-dimensional coordinates of
[0127] The second conversion submodule is used to convert the three-dimensional point cloud data into triangular mesh data M using a triangulation algorithm:
[0128] M={m1,m2,...,m i}
[0129] m i =[x k ,x p ,x q ]
[0130] x k ,x p ,x q ∈X
[0131] Among them, each triangle m i Corresponding to three 3D point cloud data x k ,x p ,x q ;
[0132] The acquisition submodule is used to select different materials and textures to optimize and compress the triangular mesh data to obtain a three-dimensional model of the heart.
[0133] In a possible implementation, the mapping module specifically includes:
[0134] The import submodule is used to import the 3D heart model and divide the 3D heart model into layers according to the structure:
[0135] M l =x∈M:α l ≤H(x)<α l+1
[0136] Among them, M represents the three-dimensional model of the heart, M l represents the heart structure of the first layer, H(x) represents the maximum height of the heart 3D model in 3D space, α l and α l+1 They represent the height thresholds of the lth layer and the l+1th layer of the three-dimensional heart model respectively;
[0137] The first mapping submodule is used to perform preliminary mapping of each layer of structure based on cardiac anatomical knowledge to obtain preliminary mapping results;
[0138] The second mapping submodule is used to perform a detailed mapping of each layer based on the preliminary marking using a morphological analysis algorithm to obtain a detailed mapping result S' l :
[0139]
[0140] Among them, B represents the preset structural element, that is, a binary matrix, and the symbol Represents the morphological operation operator, S l Indicates preliminary marking results;
[0141] The merging submodule is used to merge the preliminary mapping results and the refined mapping results to obtain the final mapping S of the entire heart 3D model:
[0142]
[0143] Wherein, n represents the number of divided cardiac structure layers.
[0144] The three-dimensional cardiac mapping system 20 provided in the embodiment of the present invention can implement each process implemented in the above method embodiment, and will not be described again here to avoid repetition.
[0145] In the embodiment of the present invention, the collected cardiac ultrasound image is subjected to image enhancement and edge detection processing to make the contrast of the cardiac ultrasound image stronger and the display effect better. Then, the optimized cardiac ultrasound image is registered to avoid artifacts in the process of reconstructing the cardiac three-dimensional model, thereby improving the display clarity of the established cardiac three-dimensional model. Finally, the established cardiac three-dimensional model is automatically layered mapped using the morphological analysis method to improve the mapping effect of the details and overall structure of the cardiac three-dimensional structure, avoid the subjective influence of the mapping, provide a more accurate cardiac three-dimensional model for analyzing the patient's condition, and provide better treatment effects for patients with heart disease.
[0146] The virtual system in the embodiment of the present invention may be a system, or a component, an integrated circuit, or a chip in a terminal.
[0147] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.
Claims
1. A three-dimensional cardiac mapping method, It is characterized in that include: S101: Acquire cardiac ultrasound image sequences within a plurality of cardiac cycles, wherein each of the cardiac ultrasound image sequences includes a plurality of cardiac ultrasound images; S102: performing image enhancement and edge detection processing on the cardiac ultrasound image to obtain an optimized cardiac ultrasound image; S103: registering the optimized cardiac ultrasound images based on a correlation matching algorithm to ensure that the optimized cardiac ultrasound images are in the same coordinate system; S104: performing a three-dimensional reconstruction operation on each registered optimized cardiac ultrasound image to obtain a three-dimensional cardiac model; S105: introducing the heart and performing layered mapping on the three-dimensional heart model using a morphological analysis method; S106: Outputting the mapped three-dimensional heart model; The S104 specifically includes: S1041: extracting feature points from the registered optimized cardiac ultrasound image, wherein the feature points include ventricular wall feature points and cardiac valve feature points, to obtain a feature point set; S1042: Convert the feature point set into a three-dimensional point cloud data set X : ; in, is a feature point in the feature point set q i The three-dimensional coordinates of S1043: Convert the three-dimensional point cloud data into triangular mesh data using a triangulation algorithm M : ; Among them, each triangle m i Corresponding to three 3D point cloud data ; S1044: Select different materials and textures to optimize and compress the triangular mesh data to obtain the three-dimensional model of the heart; The S105 specifically includes: S1051: Import the three-dimensional heart model, and layer the three-dimensional heart model according to the structure: ; in, M represents the three-dimensional model of the heart, Indicates l Layered heart structure, H ( x ) represents the maximum height of the three-dimensional heart model in the three-dimensional space, and Respectively represent the three-dimensional heart model l Layer and l +1 layer height threshold; S1052: Preliminarily mark the structures at each level based on cardiac anatomical knowledge to obtain preliminary marking results; S1053: Based on the preliminary marking, each layer is refined and marked using a morphological analysis algorithm to obtain a refined marking result. : ; in, B Represents the preset structural element, i.e., a binary matrix, symbol represents the morphological operation operator, Indicates the preliminary marking result; S1054: Merge the preliminary labeling result and the refined labeling result to obtain the final labeling of the entire three-dimensional heart model. S : ; Wherein, n represents the number of divided cardiac structure layers.
2. The three-dimensional cardiac mapping method according to claim 1, It is characterized in that The S102 specifically includes: S1021: Perform image enhancement on each of the cardiac ultrasound images through histogram equalization processing to obtain an enhanced image G ( x , y ): ; in, G ( x , y ) represents the pixel value of the enhanced image, H ( i , j ) represents the coordinates in the original image ( i , j ), M and N Respectively represent the width and height of the image; S1022: Perform Sobel operator edge detection on the enhanced image to extract edge information of the enhanced image G x and G y : ; ; in, G x and G y They respectively represent the gradients of the enhanced image in the horizontal direction and the vertical direction after edge detection, and the symbol * represents the convolution operation. I representing the enhanced image; S1023: Calculating the optimized cardiac ultrasound image according to the gradients of the enhanced image in the horizontal direction and the vertical direction after edge detection G : ; S1024: Outputting the optimized cardiac ultrasound image G .
3. The three-dimensional cardiac mapping method according to claim 1, It is characterized in that The S103 specifically includes: S1031: Selecting one of the optimized cardiac ultrasound images as a reference image, and using it as the origin of the coordinate system to establish a plane rectangular coordinate system; S1032: Selecting one of the remaining optimized ultrasound images as an image to be aligned; S1033: normalizing the reference image and the image to be aligned to obtain a normalized reference image and a normalized image to be aligned; S1034: Calculate the similarity between the normalized reference image and the image to be aligned based on a correlation matching algorithm: ; in, , represent the reference image and the image to be aligned respectively, , Respectively represent the mean of the normalized reference image and the normalized image to be aligned, ( ) represents the relative displacement between the reference image and the image to be aligned; S1035: Calculating the target relative displacement when the similarity is maximum; S1036: translating the image to be aligned using the target displacement to complete the registration; S1037: Repeat S1032-S1036 to register the remaining images to be aligned.
4. A three-dimensional cardiac mapping system, It is characterized in that include: An acquisition module, used for acquiring cardiac ultrasound image sequences within a plurality of cardiac cycles, wherein each of the cardiac ultrasound image sequences comprises a plurality of cardiac ultrasound images; A processing module, used for performing image enhancement and edge detection processing on the cardiac ultrasound image to obtain an optimized cardiac ultrasound image; A registration module, used for registering the optimized cardiac ultrasound images based on a correlation matching algorithm to ensure that the optimized cardiac ultrasound images are in the same coordinate system; A reconstruction module, used for performing three-dimensional reconstruction on each registered optimized cardiac ultrasound image to obtain a three-dimensional heart model; A mapping module, used for introducing a heart and performing layered mapping on the three-dimensional heart model by using a morphological analysis method; An output module, used for outputting a three-dimensional heart model after mapping; The reconstruction module specifically includes: A second extraction submodule is used to extract feature points in the registered optimized cardiac ultrasound image, wherein the feature points include ventricular wall feature points and cardiac valve feature points, to obtain a feature point set; The first conversion submodule is used to convert the feature point set into a three-dimensional point cloud data set. X : ; in, is a feature point in the feature point set q i The three-dimensional coordinates of The second conversion submodule is used to convert the three-dimensional point cloud data into triangular mesh data using a triangulation algorithm. M : ; Among them, each triangle m i Corresponding to three 3D point cloud data ; An acquisition submodule, used for selecting different materials and textures to optimize and compress the triangular mesh data to obtain the three-dimensional model of the heart; The mapping module specifically includes: The import submodule is used to import the three-dimensional heart model and to layer the three-dimensional heart model according to the structure: ; in, M represents the three-dimensional model of the heart, Indicates l Layered heart structure, H ( x ) represents the maximum height of the three-dimensional heart model in the three-dimensional space, and Respectively represent the three-dimensional heart model l Layer and l +1 layer height threshold; The first labeling submodule is used to preliminarily label the structures at each level based on cardiac anatomical knowledge to obtain a preliminary labeling result; The second marking submodule is used to refine the marking of each layer based on the preliminary marking using the morphological analysis algorithm to obtain the refined marking results. : ; in, B Represents the preset structural element, i.e., a binary matrix, symbol represents the morphological operation operator, Indicates the preliminary marking result; A merging submodule is used to merge the preliminary marking result and the refined marking result to obtain the final marking of the entire three-dimensional heart model. S : ; Wherein, n represents the number of divided cardiac structure layers.
5. The three-dimensional cardiac mapping system according to claim 4, It is characterized in that The processing module specifically includes: The first processing submodule is used to perform image enhancement on each of the cardiac ultrasound images through histogram equalization processing to obtain an enhanced image G ( x , y ): ; in, G ( x , y ) represents the pixel value of the enhanced image, H ( i , j ) represents the coordinates in the original image ( i , j ), M and N Respectively represent the width and height of the image; The first extraction submodule is used to perform Sobel operator edge detection on the enhanced image to extract edge information of the enhanced image. G x and G y : ; ; in, G x and G y They respectively represent the gradients of the enhanced image in the horizontal direction and the vertical direction after edge detection, and the symbol * represents the convolution operation. I representing the enhanced image; The first calculation submodule is used to calculate the optimized cardiac ultrasound image according to the gradients of the enhanced image in the horizontal direction and the vertical direction after edge detection. G : ; An output submodule, used to output the optimized cardiac ultrasound image G .
6. The three-dimensional cardiac mapping system according to claim 5, It is characterized in that The registration module specifically includes: A first selection submodule is used to select one of the optimized cardiac ultrasound images as a reference image and use it as the origin of the coordinate system to establish a plane rectangular coordinate system; A second selection submodule is used to select one of the remaining optimized ultrasound images as an image to be aligned; A second processing submodule, used for normalizing the reference image and the image to be aligned to obtain a normalized reference image and a normalized image to be aligned; The second calculation submodule is used to calculate the similarity between the normalized reference image and the image to be aligned based on a correlation matching algorithm: ; in, , represent the reference image and the image to be aligned respectively, , Respectively represent the mean of the normalized reference image and the normalized image to be aligned, ( ) represents the relative displacement between the reference image and the image to be aligned; A third calculation submodule is used to calculate the target relative displacement when the similarity is maximum; A translation submodule, used to translate the image to be aligned using the target displacement to complete the registration; The repeating submodule is used to repeat S1032-S1036 to register the remaining images to be aligned.
