Three-dimensional reconstruction and lesion detection system for breast ultrasonic image

Abstract

The invention discloses a three-dimensional reconstruction and lesion detection system for a mammary gland ultrasonic image, which comprises an ultrasonic data acquisition unit, a mammary gland ultrasonic image preprocessing module, a three-dimensional reconstruction module, a lesion detection and classification module, a data storage and management module and a report generation and display interaction module, the ultrasonic data acquisition unit is used for acquiring breast ultrasonic images, the breast ultrasonic image preprocessing module is used for image preprocessing, the three-dimensional reconstruction module is used for image three-dimensional reconstruction, the lesion detection and classification module is used for detecting and classifying breast lesions, and the data storage and management module is used for storing and managing data and detection reports. And the report generation and display interaction module is used for providing a report and an interaction interface. According to the three-dimensional reconstruction and lesion detection system for the mammary gland ultrasonic image, a mammary gland ultrasonic image three-dimensional modeling algorithm based on tomography is provided for three-dimensional reconstruction of the mammary gland image; and a mammary gland lesion detection algorithm based on the fuzzy neural network is provided to detect and identify mammary gland lesions.

Description

Technical Field

[0001] The invention relates to the fields of tomography, three-dimensional reconstruction and fuzzy neural network, and in particular to a three-dimensional reconstruction and lesion detection system for breast ultrasound images. Background Art

[0002] Tomographic imaging technology and three-dimensional reconstruction technology are imaging technologies that use multi-angle scanning to obtain information on the internal structure of an object. They aim to solve the problem that traditional two-dimensional images in breast ultrasound images are difficult to fully display the deep structure of breast tissue. Through tomographic imaging technology and three-dimensional reconstruction technology, multi-level information in the breast is collected from different angles to reconstruct three-dimensional breast images, allowing the system to reconstruct the internal tissue structure of the breast intuitively and clearly. Tomographic imaging technology provides the core image acquisition and reconstruction means, which can greatly improve the resolution and accuracy of internal breast images, and provide a more reliable foundation for subsequent lesion identification and precise treatment.

[0003] Fuzzy neural network technology is an intelligent algorithm that combines fuzzy logic and neural networks. It aims to solve the problems of insufficient accuracy and adaptability of traditional algorithms in dealing with breast lesion detection. Since the lesion areas in breast ultrasound images vary greatly in size, shape and density, fuzzy neural networks process different lesion characteristics through fuzzification to better cope with complex data and improve the robustness and sensitivity of lesion detection, so that the system can automatically identify lesion tissue, accurately judge the type of lesion, reduce the subjective influence of doctors, and thus improve the accuracy and consistency of diagnosis.

[0004] However, the existing three-dimensional reconstruction and lesion detection system for breast ultrasound images has difficulty in displaying the three-dimensional structure of the deep breast, resulting in missed detection and misjudgment of lesions. At the same time, the lack of three-dimensional reconstruction function limits the three-dimensional observation and analysis of breast tissue. In terms of lesion detection, traditional systems have difficulty in accurately responding to complex breast tissue differences, often have low sensitivity to lesion detection, and are easily interfered by noise, leading to the risk of misdiagnosis and missed diagnosis. Summary of the invention

[0005] The purpose of the present invention is to provide a three-dimensional reconstruction and lesion detection system for breast ultrasound images, so as to solve the problem that the existing three-dimensional reconstruction and lesion detection system for breast ultrasound images proposed in the above background technology is difficult to display the three-dimensional structure of the deep breast, resulting in missed detection and misjudgment of lesions. At the same time, the system lacks three-dimensional reconstruction function, which limits the three-dimensional observation and analysis of breast tissue. In terms of lesion detection, traditional systems find it difficult to accurately cope with complex breast tissue differences, often have low sensitivity to lesion detection, and are easily interfered by noise, resulting in the risk of misdiagnosis and missed diagnosis.

[0006] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a three-dimensional reconstruction and lesion detection system for breast ultrasound images, comprising an ultrasound data acquisition unit, a breast ultrasound image preprocessing module, a three-dimensional reconstruction module, a lesion detection and classification module, a data storage and management module, and a report generation and display interaction module, characterized in that: the ultrasound data acquisition unit is used to collect breast ultrasound image data to ensure the acquisition of high-quality original image information and provide a basis for subsequent processing; the breast ultrasound image preprocessing module is used to perform preprocessing operations such as filtering and denoising, enhancing contrast, and maintaining image edges on the collected ultrasound images to ensure image clarity and quality and the accuracy of subsequent lesion detection; the three-dimensional reconstruction module includes an image registration unit and a three-dimensional modeling unit; the image registration unit is used to spatially align ultrasound images acquired from different viewing angles and time points to ensure consistency and comparability between images and provide accurate image data for three-dimensional modeling; the three-dimensional modeling unit proposes a method based on tomography. The three-dimensional modeling algorithm of breast ultrasound images is used to construct a three-dimensional model based on the registered two-dimensional ultrasound images to ensure that the three-dimensional structure of breast tissue and lesions can be accurately presented and analyzed. The lesion detection and classification module includes a feature extraction unit and a classification recognition unit. The feature extraction unit is used to extract key information from the breast ultrasound image, including breast morphology, texture and boundary features, to ensure that rich local and global feature data are provided for classification. The classification recognition unit proposes a breast lesion detection algorithm based on fuzzy neural network to classify and identify breast lesions according to the extracted features, to ensure that the system accurately detects and effectively distinguishes breast lesions. The data storage and management module is used to store and manage the patient's ultrasound image data and test reports to ensure the security, reliability and efficient access of the data. The report generation and display interaction module is used to generate a test report and provide a user interaction interface so that users can view reports and images in real time to ensure accurate communication of test results and convenience of user operation.

[0007] Preferably, the ultrasound data acquisition unit acquires ultrasound image data of the breast region by using an ultrasound probe and an imaging device, thereby ensuring that the collected image information is accurate and complete, and providing original image data for subsequent processing.

[0008] Preferably, the breast ultrasound image preprocessing module ensures that image quality is improved by performing preprocessing operations such as filtering and noise reduction, contrast enhancement, and image edge preservation, thereby providing clear and accurate breast ultrasound image data for subsequent three-dimensional reconstruction and lesion detection.

[0009] Preferably, the three-dimensional reconstruction module includes an image registration unit, which compares ultrasound images acquired at different viewing angles and time points through precise image registration technology, adjusts the position and angle of the ultrasound image, ensures that the images can be accurately superimposed, provides preparation for three-dimensional modeling, and ensures the accuracy and consistency of subsequent three-dimensional models.

[0010] Preferably, the three-dimensional reconstruction module includes a three-dimensional modeling unit, which proposes a three-dimensional modeling algorithm for breast ultrasound images based on tomography to construct a three-dimensional model of breast tissue by integrating the aligned two-dimensional image data, thereby ensuring the accurate construction and efficient rendering of the three-dimensional model, so that the system can stereoscopically display and accurately locate the breast lesion area.

[0011] Specifically, the breast ultrasound image three-dimensional modeling algorithm based on tomography is as follows: First, breast ultrasound image information is obtained from multiple angles through tomography technology, and the internal structure of the object is reconstructed to obtain the pressure field information under a given sound source, frequency and complex value sound velocity. The specific formula is expressed as follows:

[0012]

[0013] Among them, U represents the pressure field, l represents the Laplace operator, C represents the complex-valued sound speed, Δ(Ω) represents the sound source term, and Ω represents the angular frequency. The specific formula is expressed as follows:

[0014] Ω=2πf

[0015] Among them, f represents the frequency. By simulating the propagation of ultrasonic waves in three-dimensional space, the foundation is laid for the subsequent reconstruction of the sound velocity distribution. Then, the finite difference method is used to divide space and time into small, finite intervals, and then the derivatives are solved on these intervals. The continuous partial differential equations are discretized into a set of solvable algebraic equations to simulate the propagation of waves in three-dimensional space, and the sound source terms at the corresponding grid points are obtained by calculating the pressure distribution under given sound sources and medium properties. The specific formula is expressed as:

[0016]

[0017] Among them, Δ(Ω) i,j,k It is represented as the sound source term at the grid point (i, j, k), U i,j,k The pressure field value at the grid point (i, j, k), Δx 2 , Δy 2 , Δz 2They are respectively represented as the spatial step lengths along the x, y, and z directions, x, y, and z respectively represent the breast ultrasound information in the horizontal direction, the breast ultrasound information in the vertical direction, and the breast ultrasound information in the depth direction, i, j, and k respectively represent the direction indexes along the horizontal direction, the vertical direction, and the depth direction, which are used to access and calculate the value of each point in the three-dimensional space grid. Each index represents a corresponding grid point, which together define the position in the three-dimensional space. Secondly, after obtaining the initial pressure field, a cost function E is defined to measure the difference between the simulated wave field and the observed wave field, and the sound speed C is iteratively updated to minimize the cost function. The specific formula of the cost function is:

[0018]

[0019] Among them, E(Ω,C) represents the cost function, e represents the residual, H represents the conjugate operation, and the specific calculation formula of e(Ω,C) is expressed as:

[0020] e(Ω,C)=U obs (Ω,C)-D obs (Ω,C true )

[0021] Among them, U obs Represented as simulated wave field, D obs Represented as the observed wave field, C true Expressed as the true speed of sound, the iterative update formula of the speed of sound is expressed as:

[0022]

[0023] Among them, C (p+1) Expressed as the speed of sound at the p+1th iteration, C (p) It represents the speed of sound at the pth iteration, α represents the iterative update step size, It is expressed as the gradient of the cost function. By iteratively updating the sound velocity, the optimal sound velocity distribution can be obtained, thereby realizing the three-dimensional modeling of breast tissue. Secondly, after iteratively updating the sound velocity and obtaining the optimal sound velocity distribution, the three-dimensional reconstruction of the breast ultrasound image is performed to obtain the three-dimensional sound velocity map of the breast tissue. The three-dimensional wave field simulation is performed using the optimized sound velocity model, and the propagation of the sound wave is evaluated at each grid point to obtain the detailed three-dimensional structure of the breast tissue. The specific formula is expressed as follows:

[0024]

[0025] Among them, C opt It is represented by the sound speed after iterative update optimization, G(i,j,k;Ω,C opt) is expressed as a Green's function in three-dimensional space, representing the wave field generated by the point source at the origin at the grid point (i, j, k), considering the attenuation and phase change of the wave propagating from the sound source to the receiving point, N is expressed as the number of grid points along each spatial dimension, and finally, after completing the three-dimensional reconstruction, it is compared with the known sound velocity distribution to ensure the robustness and accuracy of the algorithm in processing actual breast ultrasound images. The specific formula is expressed as:

[0026]

[0027] Among them, E final Expressed as the final cost function value, e final It is expressed as the final residual. The three-dimensional equation is solved by the finite difference method, and the sound velocity model is iteratively optimized to achieve accurate three-dimensional reconstruction of breast tissue. After simulating the propagation of breast ultrasound in three-dimensional space, the simulation and actual observed wave fields are compared, and the sound velocity distribution is continuously updated until they match, thereby achieving accurate three-dimensional reconstruction of breast tissue.

[0028] Preferably, the lesion detection and classification module includes a feature extraction unit, which extracts key features that are helpful for lesion identification by analyzing the properties of shape, texture and signal distribution in the ultrasound image, thereby ensuring that sufficient decision-making information is provided for subsequent classification and identification of breast lesions.

[0029] Preferably, the lesion detection and classification module includes a classification and recognition unit, which proposes a breast lesion detection algorithm based on a fuzzy neural network, classifies and identifies lesions in breast images by reducing artifacts in ultrasound images and extracting rich local detail features as well as global feature information of the image, thereby ensuring that the system accurately recognizes and classifies breast ultrasound images.

[0030] Specifically, the fuzzy neural network-based breast lesion detection algorithm is as follows: first, the key features of the breast ultrasound image obtained by the feature extraction unit are further extracted for subsequent fuzzy neural network input, the co-occurrence matrix of the key feature area is calculated, and the entropy information, uniformity information, contrast information and maximum co-occurrence matrix elements of the key features of the breast ultrasound image are extracted based on this matrix. The co-occurrence matrix element calculation formula is expressed as:

[0031]

[0032] Among them, P is represented by the co-occurrence matrix, which represents the matrix of grayscale co-occurrence frequency under a specific distance d and angle θ between pixels in the breast ultrasound image, d is represented by the distance between pixels, which represents the distance between pixel pairs considered when calculating the co-occurrence matrix in the breast ultrasound image, θ is represented by the angle, which represents the angle between pixel pairs considered when calculating the co-occurrence matrix in the breast ultrasound image, a and b represent the grayscale values ​​of two pixels in the breast ultrasound image, f represents the grayscale function, k represents the row number of the position coordinates in the breast ultrasound image, l represents the column number of the position coordinates in the breast ultrasound image, D represents the set of pixel points when calculating the co-occurrence matrix, δ represents the Kronecker function, cos represents the cosine function, sin represents the sine function, and the specific formula for entropy calculation is expressed as:

[0033]

[0034] Among them, H represents entropy information, which represents the final calculated value to measure the uncertainty of regional information in breast ultrasound images, i, j represents the index of rows and columns in the co-occurrence matrix, and p ij It is expressed as the probability of gray level i and gray level j appearing simultaneously in the co-occurrence matrix, log is expressed as a logarithmic function, and entropy information can quantify the distribution uniformity of pixel intensity values ​​in the image area. The specific calculation formula of uniformity information is expressed as:

[0035]

[0036] Among them, U represents the uniformity information of the breast ultrasound image, which represents the final calculated value to measure the consistency of pixel intensity in the image area. The specific formula of the contrast information of the breast ultrasound image is expressed as:

[0037]

[0038] By calculating the contrast information of breast ultrasound images, the areas with large pixel intensity changes are identified. The specific formula of the maximum co-occurrence matrix element is expressed as:

[0039]

[0040] Among them, MCM is expressed as the maximum co-occurrence matrix element. Then, the fuzzy neural network is constructed using the extracted breast ultrasound image features, including entropy information, uniformity information, contrast information and maximum co-occurrence matrix element information as the input of the fuzzy neural network. The specific formula of the fuzzy neural network input layer is expressed as:

[0041] I=[ΔH, ΔU, ΔC, ΔMCM]

[0042] Among them, I represents the input vector, which contains the difference value of the extracted breast ultrasound image features, ΔH represents the entropy difference, ΔU represents the uniformity difference, ΔC represents the contrast difference, ΔMCM represents the maximum co-occurrence matrix element difference, and the specific formula of the fuzzy layer is expressed as follows:

[0043]

[0044] Among them, O k It is represented as the fuzzy output of the kth feature, k is the index of the number of breast ultrasound image features, I k It is represented as the input value of the kth feature of the organism, min(I k ) represents the minimum value of all input values ​​of the kth feature, max(I k ) is expressed as the maximum value of all input values ​​of the kth feature, and the specific formula of the maximum fuzzy neuron layer is expressed as:

[0045]

[0046] Among them, S zk It is represented as the output of the zth neuron to the kth input feature, z is the index of the number of neurons in the fuzzy neural network, μ zk Expressed as a property function, used to measure the input O k The degree of membership in the zth fuzzy neuron, O k Represented as the fuzzy output of the kth feature, c z It is expressed as the center value of the zth neuron, which represents the input value when the neuron is most active, σ z It is expressed as the standard deviation of the zth neuron, which controls the width of the membership function. The specific formula of the fuzzy decision layer is expressed as:

[0047]

[0048] Among them, D v It is expressed as the maximum output value of the vth type of breast lesions. The types of breast lesions include benign and malignant. The specific formula of the final output layer is expressed as:

[0049]

[0050] Among them, Y represents the final classification result, D 1 Denotes the maximum output value of the malignant category, D 2It is expressed as the maximum output value of the benign category, otherwise is expressed as a conditional statement. The constructed fuzzy neural network can detect breast lesions by utilizing the extracted breast feature differences, and effectively detect and distinguish malignant tumors from benign tissues. The method based on fuzzy neural network has significant advantages in dealing with uncertainty and nonlinear problems, and can effectively and accurately detect breast lesions.

[0051] Preferably, the data storage and management module stores the ultrasound image data and test results collected and processed by the system by constructing and maintaining a database, thereby ensuring the integrity, security and efficient retrieval of the data.

[0052] Preferably, the report generation and display interaction module automatically generates a test report and provides a user interface, so that the user can view and analyze the test results in real time, thereby ensuring accurate communication of test information and convenience of user operation.

[0053] Compared with the prior art, the present invention has the following beneficial effects:

[0054] The three-dimensional modeling unit proposes a three-dimensional modeling algorithm for breast ultrasound images based on tomography. The algorithm first uses tomography technology to obtain ultrasound image information of the internal structure of the breast from multiple angles, and calculates the pressure field distribution under a given sound source, frequency and complex sound speed by simulating the propagation of ultrasound in three-dimensional space. This process discretizes space and time through the finite difference method, converts the partial differential equation into a solvable algebraic equation, simulates the propagation of ultrasound in the three-dimensional space of the breast, and accurately estimates the sound source term at each grid point. The gradually generated pressure field distribution provides a solid foundation for the reconstruction of the sound speed distribution. The algorithm then defines a cost function to measure the difference between the simulated wave field and the observed wave field, and iteratively updates the sound speed distribution to minimize the cost function, thereby obtaining the optimal sound speed. The optimized sound velocity model not only effectively simulates the propagation of breast ultrasound, but also provides accurate data support for three-dimensional reconstruction. After obtaining the optimal sound velocity distribution, the Green's function is further used to evaluate the sound wave propagation at each grid point to achieve detailed three-dimensional modeling of breast tissue. In addition, by comparing with the actual observation data, the robustness and high precision of the three-dimensional modeling are ensured. This process can iteratively optimize the model to reduce the residual and optimize the final cost function value, so that the reconstruction result is more in line with the actual structure. In short, based on this three-dimensional reconstruction model, the system can evaluate the location and nature of breast lesions at higher resolution and accuracy, which improves the accuracy and efficiency of breast lesion detection. The high-precision three-dimensional modeling achieved by this algorithm provides strong support for the early detection and treatment of breast diseases.

[0055] 1. The classification and recognition unit proposes a breast lesion detection algorithm based on fuzzy neural network. Through the in-depth analysis of breast ultrasound image features, effective lesion detection is achieved. The key features of breast ultrasound images are obtained in the feature extraction unit, and the co-occurrence matrix is ​​calculated. The in-depth feature information of entropy, uniformity, contrast and maximum co-occurrence matrix elements is extracted from it. The construction of the co-occurrence matrix reflects the spatial relationship between pixels and captures the local and global information of image details. Entropy information measures the uncertainty of pixel intensity in the image area, uniformity information provides pixel consistency measurement, contrast reveals the intensity variation range of the image area, and the maximum co-occurrence matrix elements help determine the significant feature points of the image. The calculated eigenvalues ​​are normalized through the input layer of the fuzzy neural network, and the input vector is constructed and fuzzified to capture the difference in eigenvalues. The fuzzy neuron layer uses the membership function to fuzzify each input feature to maximize the reflection of the activity level of different features. Through the fuzzy decision layer, the classification results of benign and malignant lesions are finally output. The key to the breast lesion detection algorithm based on fuzzy neural network lies in the fuzzy neural network's ability to handle feature uncertainty, which is particularly suitable for fuzzy and nonlinear feature data in breast ultrasound images, enabling the system to significantly improve detection accuracy and classification effects, and facilitate the effective detection and differentiation of malignant and benign lesions. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The invention is further illustrated by the accompanying drawings, but the embodiments in the accompanying drawings do not constitute any limitation to the invention. A person skilled in the art can obtain other drawings based on the following drawings without creative work.

[0057] Figure 1 It is a schematic diagram of the structure of the present invention. DETAILED DESCRIPTION

[0058] 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.

[0059] See also Figure 1The present invention provides a three-dimensional reconstruction and lesion detection system for breast ultrasound images, including an ultrasound data acquisition unit, a breast ultrasound image preprocessing module, a three-dimensional reconstruction module, a lesion detection and classification module, a data storage and management module, and a report generation and display interaction module, characterized in that: the ultrasound data acquisition unit is used to collect breast ultrasound image data to ensure the acquisition of high-quality original image information and provide a basis for subsequent processing; the breast ultrasound image preprocessing module is used to perform preprocessing operations such as filtering and denoising, enhancing contrast, and maintaining image edges on the collected ultrasound images to ensure image clarity and quality and the accuracy of subsequent lesion detection; the three-dimensional reconstruction module includes an image registration unit and a three-dimensional modeling unit; the image registration unit is used to spatially align ultrasound images acquired from different viewing angles and time points to ensure consistency and comparability between images and provide accurate image data for three-dimensional modeling; the three-dimensional modeling unit proposes a breast ultrasound based on tomography. The image three-dimensional modeling algorithm is used to construct a three-dimensional model based on the registered two-dimensional ultrasound image to ensure that the three-dimensional structure of breast tissue and lesions can be accurately presented and analyzed. The lesion detection and classification module includes a feature extraction unit and a classification recognition unit. The feature extraction unit is used to extract key information from the breast ultrasound image, including breast morphology, texture and boundary features, to ensure that rich local and global feature data are provided for classification. The classification recognition unit proposes a breast lesion detection algorithm based on fuzzy neural network to classify and identify breast lesions according to the extracted features, to ensure that the system accurately detects and effectively distinguishes breast lesions. The data storage and management module is used to store and manage the patient's ultrasound image data and test reports, to ensure the security, reliability and efficient access of the data. The report generation and display interaction module is used to generate test reports and provide a user interaction interface, so that users can view reports and images in real time, to ensure the accurate communication of test results and the convenience of user operation.

[0060] See also Figure 1 Furthermore, the ultrasound data acquisition unit obtains ultrasound image data of the breast area by using an ultrasound probe and an imaging device, ensuring that the collected image information is accurate and complete, and providing original image data for subsequent processing.

[0061] See also Figure 1 Furthermore, the breast ultrasound image preprocessing module ensures that the image quality is improved by performing preprocessing operations such as filtering and noise reduction, contrast enhancement, and image edge preservation, thereby providing clear and accurate breast ultrasound image data for subsequent three-dimensional reconstruction and lesion detection.

[0062] See also Figure 1Furthermore, the 3D reconstruction module includes an image registration unit, which compares ultrasound images acquired at different viewing angles and time points through precise image registration technology, adjusts the position and angle of the ultrasound image, ensures that the images can be accurately superimposed, provides preparation for 3D modeling, and ensures the accuracy and consistency of subsequent 3D models.

[0063] See also Figure 1 Furthermore, the 3D reconstruction module includes a 3D modeling unit, which proposes a 3D modeling algorithm for breast ultrasound images based on tomography, and constructs a 3D model of breast tissue by integrating the aligned 2D image data, thereby ensuring the accurate construction and efficient rendering of the 3D model, so that the system can stereoscopically display and accurately locate the breast lesion area.

[0064] See also Figure 1 Furthermore, the three-dimensional modeling algorithm of breast ultrasound images based on tomography is as follows: First, breast ultrasound image information is obtained from multiple angles through tomography technology, and the internal structure of the object is reconstructed to obtain the pressure field information under a given sound source, frequency and complex-valued sound velocity. The specific formula is expressed as follows:

[0065]

[0066] Among them, U represents the pressure field, l represents the Laplace operator, C represents the complex-valued sound speed, Δ(Ω) represents the sound source term, and Ω represents the angular frequency. The specific formula is expressed as follows:

[0067] Ω=2πf

[0068] Among them, f represents the frequency. By simulating the propagation of ultrasonic waves in three-dimensional space, the foundation is laid for the subsequent reconstruction of the sound velocity distribution. Then, the finite difference method is used to divide space and time into small, finite intervals, and then the derivatives are solved on these intervals. The continuous partial differential equations are discretized into a set of solvable algebraic equations to simulate the propagation of waves in three-dimensional space, and the sound source terms at the corresponding grid points are obtained by calculating the pressure distribution under given sound sources and medium properties. The specific formula is expressed as:

[0069]

[0070] Among them, Δ(Ω) i,j,k It is represented as the sound source term at the grid point (i, j, k), U i,j,k The pressure field value at the grid point (i, j, k), Δx 2 , Δy 2 , Δz 2They are respectively represented as the spatial step lengths along the x, y, and z directions, x, y, and z respectively represent the breast ultrasound information in the horizontal direction, the breast ultrasound information in the vertical direction, and the breast ultrasound information in the depth direction, i, j, and k respectively represent the direction indexes along the horizontal direction, the vertical direction, and the depth direction, which are used to access and calculate the value of each point in the three-dimensional space grid. Each index represents a corresponding grid point, which together define the position in the three-dimensional space. Secondly, after obtaining the initial pressure field, a cost function E is defined to measure the difference between the simulated wave field and the observed wave field, and the sound speed C is iteratively updated to minimize the cost function. The specific formula of the cost function is:

[0071]

[0072] Among them, E(Ω,C) represents the cost function, e represents the residual, H represents the conjugate operation, and the specific calculation formula of e(Ω,C) is expressed as:

[0073] e(Ω,C)=U obs (Ω,C)-D obs (Ω,C true )

[0074] Among them, U obs Represented as simulated wave field, D obs Represented as the observed wave field, C true Expressed as the true speed of sound, the iterative update formula of the speed of sound is expressed as:

[0075]

[0076] Among them, C (p+1) Expressed as the speed of sound at the p+1th iteration, C (p) It represents the speed of sound at the pth iteration, α represents the iterative update step size, It is expressed as the gradient of the cost function. By iteratively updating the sound velocity, the optimal sound velocity distribution can be obtained, thereby realizing the three-dimensional modeling of breast tissue. Secondly, after iteratively updating the sound velocity and obtaining the optimal sound velocity distribution, the three-dimensional reconstruction of the breast ultrasound image is performed to obtain the three-dimensional sound velocity map of the breast tissue. The three-dimensional wave field simulation is performed using the optimized sound velocity model, and the propagation of the sound wave is evaluated at each grid point to obtain the detailed three-dimensional structure of the breast tissue. The specific formula is expressed as follows:

[0077]

[0078] Among them, C opt It is represented by the sound speed after iterative update optimization, G(i,j,k;Ω,C opt) is expressed as a Green's function in three-dimensional space, representing the wave field generated by the point source at the origin at the grid point (i, j, k), considering the attenuation and phase change of the wave propagating from the sound source to the receiving point, N is expressed as the number of grid points along each spatial dimension, and finally, after completing the three-dimensional reconstruction, it is compared with the known sound velocity distribution to ensure the robustness and accuracy of the algorithm in processing actual breast ultrasound images. The specific formula is expressed as:

[0079]

[0080] Among them, E final Expressed as the final cost function value, e final It is expressed as the final residual. The three-dimensional equation is solved by the finite difference method, and the sound velocity model is iteratively optimized to achieve accurate three-dimensional reconstruction of breast tissue. After simulating the propagation of breast ultrasound in three-dimensional space, the simulation and actual observed wave fields are compared, and the sound velocity distribution is continuously updated until they match, thereby achieving accurate three-dimensional reconstruction of breast tissue.

[0081] See also Figure 1 Furthermore, the lesion detection and classification module includes a feature extraction unit, which extracts key features that are helpful for lesion identification by analyzing the properties of shape, texture and signal distribution in the ultrasound image, thereby ensuring that sufficient decision-making information is provided for subsequent classification and identification of breast lesions.

[0082] See also Figure 1 Furthermore, the lesion detection and classification module includes a classification and recognition unit, which proposes a breast lesion detection algorithm based on a fuzzy neural network, and classifies and recognizes lesions in breast images by reducing artifacts in ultrasound images and extracting rich local detail features and global feature information of the image, thereby ensuring that the system accurately recognizes and classifies breast ultrasound images.

[0083] See also Figure 1 Furthermore, the breast lesion detection algorithm based on fuzzy neural network is as follows: First, the key features of the breast ultrasound image obtained by the feature extraction unit are further extracted for subsequent fuzzy neural network input, the co-occurrence matrix of the key feature area is calculated, and the entropy information, uniformity information, contrast information and maximum co-occurrence matrix elements of the key features of the breast ultrasound image are extracted based on this matrix. The calculation formula of the co-occurrence matrix elements is expressed as:

[0084]

[0085] Among them, P is represented by the co-occurrence matrix, which represents the matrix of grayscale co-occurrence frequency under a specific distance d and angle θ between pixels in the breast ultrasound image, d is represented by the distance between pixels, which represents the distance between pixel pairs considered when calculating the co-occurrence matrix in the breast ultrasound image, θ is represented by the angle, which represents the angle between pixel pairs considered when calculating the co-occurrence matrix in the breast ultrasound image, a and b represent the grayscale values ​​of two pixels in the breast ultrasound image, f represents the grayscale function, k represents the row number of the position coordinates in the breast ultrasound image, l represents the column number of the position coordinates in the breast ultrasound image, D represents the set of pixel points when calculating the co-occurrence matrix, δ represents the Kronecker function, cos represents the cosine function, sin represents the sine function, and the specific formula for entropy calculation is expressed as:

[0086]

[0087] Among them, H represents entropy information, which represents the final calculated value to measure the uncertainty of regional information in breast ultrasound images, i, j represents the index of rows and columns in the co-occurrence matrix, and p ij It is expressed as the probability of gray level i and gray level j appearing simultaneously in the co-occurrence matrix, log is expressed as a logarithmic function, and entropy information can quantify the distribution uniformity of pixel intensity values ​​in the image area. The specific calculation formula of uniformity information is expressed as:

[0088]

[0089] Among them, U represents the uniformity information of the breast ultrasound image, which represents the final calculated value to measure the consistency of pixel intensity in the image area. The specific formula of the contrast information of the breast ultrasound image is expressed as:

[0090]

[0091] By calculating the contrast information of breast ultrasound images, the areas with large pixel intensity changes are identified. The specific formula of the maximum co-occurrence matrix element is expressed as:

[0092]

[0093] Among them, MCM is expressed as the maximum co-occurrence matrix element. Then, the fuzzy neural network is constructed using the extracted breast ultrasound image features, including entropy information, uniformity information, contrast information and maximum co-occurrence matrix element information as the input of the fuzzy neural network. The specific formula of the fuzzy neural network input layer is expressed as:

[0094] I=[ΔH, ΔU, ΔC, ΔMCM]

[0095] Among them, I represents the input vector, which contains the difference value of the extracted breast ultrasound image features, ΔH represents the entropy difference, ΔU represents the uniformity difference, ΔC represents the contrast difference, ΔMCM represents the maximum co-occurrence matrix element difference, and the specific formula of the fuzzy layer is expressed as follows:

[0096]

[0097] Among them, O k It is represented as the fuzzy output of the kth feature, k is the index of the number of breast ultrasound image features, I k It is represented as the input value of the kth feature of the organism, min(I k ) represents the minimum value of all input values ​​of the kth feature, max(I k ) is expressed as the maximum value of all input values ​​of the kth feature, and the specific formula of the maximum fuzzy neuron layer is expressed as:

[0098]

[0099] Among them, S zk It is represented as the output of the zth neuron to the kth input feature, z is the index of the number of neurons in the fuzzy neural network, μ zk Expressed as a property function, used to measure the input O k The degree of membership in the zth fuzzy neuron, O k Represented as the fuzzy output of the kth feature, σ z It is expressed as the center value of the zth neuron, which represents the input value when the neuron is most active, σ z It is expressed as the standard deviation of the zth neuron, which controls the width of the membership function. The specific formula of the fuzzy decision layer is expressed as:

[0100]

[0101] Among them, D v It is expressed as the maximum output value of the vth type of breast lesions. The types of breast lesions include benign and malignant. The specific formula of the final output layer is expressed as:

[0102]

[0103] Among them, Y represents the final classification result, D 1 Denotes the maximum output value of the malignant category, D 2It is expressed as the maximum output value of the benign category, otherwise is expressed as a conditional statement. The constructed fuzzy neural network can detect breast lesions by utilizing the extracted breast feature differences, and effectively detect and distinguish malignant tumors from benign tissues. The method based on fuzzy neural network has significant advantages in dealing with uncertainty and nonlinear problems, and can effectively and accurately detect breast lesions.

[0104] See also Figure 1 Furthermore, the data storage and management module stores the ultrasound image data and test results collected and processed by the system by building and maintaining a database, thereby ensuring the integrity, security and efficient retrieval of the data.

[0105] See also Figure 1 Furthermore, the report generation and display interaction module automatically generates a test report and provides a user interface, so that users can view and analyze the test results in real time, ensuring accurate communication of test information and convenience of user operation.

[0106] During specific use, first, the ultrasound data acquisition unit is used to collect breast ultrasound image data to ensure the acquisition of high-quality original image information and provide a basis for subsequent processing. Secondly, the breast ultrasound image preprocessing module is used to perform preprocessing operations such as filtering and denoising, enhancing contrast and maintaining image edges on the acquired ultrasound images to ensure image clarity and quality and the accuracy of subsequent lesion detection. Then, the 3D reconstruction module includes an image registration unit and a 3D modeling unit. The image registration unit is used to spatially align ultrasound images acquired from different perspectives and time points to ensure consistency and comparability between images and provide accurate image data for 3D modeling. The 3D modeling unit proposes a 3D modeling algorithm for breast ultrasound images based on tomography to construct a 3D model based on the registered 2D ultrasound images to ensure that the three-dimensional structure of breast tissue and lesions can be is accurately presented and analyzed. Secondly, the lesion detection and classification module includes a feature extraction unit and a classification recognition unit. The feature extraction unit is used to extract key information from breast ultrasound images, including breast morphology, texture and boundary features, to ensure that rich local and global feature data are provided for classification. The classification recognition unit proposes a breast lesion detection algorithm based on fuzzy neural network to classify and identify breast lesions according to the extracted features, to ensure that the system can accurately detect and effectively distinguish breast lesions. Finally, the data storage and management module is used to store and manage the patient's ultrasound image data and test reports, to ensure the security, reliability and efficient access of the data. The report generation and display interaction module is used to generate test reports and provide a user interaction interface, so that users can view reports and images in real time, to ensure the accurate communication of test results and the convenience of user operation.

[0107] Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments, or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A three-dimensional reconstruction and lesion detection system for breast ultrasound images, characterized in that: The invention comprises an ultrasound data acquisition unit, a breast ultrasound image preprocessing module, a 3D reconstruction module, a lesion detection and classification module, a data storage and management module, and a report generation and display interaction module; wherein the ultrasound data acquisition unit is used to collect breast ultrasound image data, obtain high-quality original image information, and provide a basis for subsequent processing; the breast ultrasound image preprocessing module is used to perform preprocessing operations such as filtering and denoising, contrast enhancement, and image edge preservation on the collected ultrasound images, so as to improve the image clarity and quality and ensure the accuracy of subsequent lesion detection; the 3D reconstruction module comprises an image registration unit and a 3D modeling unit; the image registration unit is used to spatially align ultrasound images acquired from different viewing angles and time points, so that the images have consistency and comparability, and provide accurate image data for 3D modeling; the 3D modeling unit proposes a breast tomography-based The three-dimensional modeling algorithm of breast ultrasound images is used to construct a three-dimensional model based on the registered two-dimensional ultrasound images. The three-dimensional structure of breast tissue and lesions can be accurately presented and analyzed. The lesion detection and classification module includes a feature extraction unit and a classification recognition unit. The feature extraction unit is used to extract key information from breast ultrasound images, including breast morphology, texture and boundary features, and provide rich local and global feature data for classification. The classification recognition unit proposes a breast lesion detection algorithm based on fuzzy neural network for classifying and identifying breast lesions according to the extracted features. The system accurately detects and effectively distinguishes breast lesions. The data storage and management module is used to store and manage the patient's ultrasound image data and test reports, and ensures the security, reliability and efficient access of the data. The report generation and display interaction module is used to generate test reports and provide a user interaction interface.

2. A system for three-dimensional reconstruction and lesion detection of breast ultrasound images according to claim 1, characterized in that: The ultrasound data acquisition unit acquires ultrasound image data of a breast region by using an ultrasound probe and an imaging device.

3. The system for three-dimensional reconstruction and lesion detection of breast ultrasound images according to claim 1, characterized in that: The breast ultrasound image preprocessing module improves image quality by performing preprocessing operations such as filtering and noise reduction, contrast enhancement, and image edge preservation, thereby providing clear and accurate breast ultrasound image data for subsequent three-dimensional reconstruction and lesion detection.

4. The system for three-dimensional reconstruction and lesion detection of breast ultrasound images according to claim 1, characterized in that: The 3D reconstruction module includes an image registration unit and a 3D modeling unit. The image registration unit compares ultrasound images acquired at different viewing angles and time points through precise image registration technology, adjusts the position and angle of the ultrasound image, and accurately superimposes the images to provide preparation for 3D modeling and ensure the accuracy and consistency of subsequent 3D models. The 3D modeling unit proposes a 3D modeling algorithm for breast ultrasound images based on tomography, and constructs a 3D model of breast tissue by integrating the registered 2D image data. The precise construction and efficient rendering of the 3D model enable the system to stereoscopically display and accurately locate the breast lesion area.

5. A system for three-dimensional reconstruction and lesion detection of breast ultrasound images according to claim 4, characterized in that: First, breast ultrasound image information is obtained from multiple angles through tomography technology to reconstruct the internal structure of the object to obtain the pressure field information under a given sound source, frequency and complex-valued sound velocity. The specific formula is expressed as: Among them, U represents the pressure field, l represents the Laplace operator, C represents the complex-valued sound speed, Δ(Ω) represents the sound source term, and Ω represents the angular frequency. The specific formula is expressed as follows: Ω=2πf Among them, f represents the frequency. By simulating the propagation of ultrasonic waves in three-dimensional space, the foundation is laid for the subsequent reconstruction of the sound velocity distribution. Then, the finite difference method is used to divide space and time into small, finite intervals, and then the derivatives are solved on these intervals. The continuous partial differential equations are discretized into a set of solvable algebraic equations to simulate the propagation of waves in three-dimensional space, and the sound source terms at the corresponding grid points are obtained by calculating the pressure distribution under given sound sources and medium properties. The specific formula is expressed as: Among them, Δ(Ω) i,j,k It is represented as the sound source term at the grid point (i, j, k), U i,j,k The pressure field value at the grid point (i, j, k), Δx 2 , Δy 2 , Δz 2 They are respectively represented as the spatial step lengths along the x, y, and z directions, x, y, and z respectively represent the breast ultrasound information in the horizontal direction, the breast ultrasound information in the vertical direction, and the breast ultrasound information in the depth direction, i, j, and k respectively represent the direction indexes along the horizontal direction, the vertical direction, and the depth direction, which are used to access and calculate the value of each point in the three-dimensional space grid. Each index represents a corresponding grid point, which together define the position in the three-dimensional space. Secondly, after obtaining the initial pressure field, a cost function E is defined to measure the difference between the simulated wave field and the observed wave field, and the sound speed C is iteratively updated to minimize the cost function. The specific formula of the cost function is: Among them, E(Ω,C) represents the cost function, e represents the residual, H represents the conjugate operation, and the specific calculation formula of e(Ω,C) is expressed as: e(Ω,C)=U obs (Ω,C)-D obs (Ω,C true ) Among them, U obs Represented as simulated wave field, D obs Represented as the observed wave field, C true Expressed as the true speed of sound, the iterative update formula of the speed of sound is expressed as: Among them, C (p+1) Expressed as the speed of sound at the p+1th iteration, C (p) It represents the speed of sound at the pth iteration, α represents the iterative update step size, It is expressed as the gradient of the cost function. By iteratively updating the sound velocity, the optimal sound velocity distribution can be obtained, thereby realizing the three-dimensional modeling of breast tissue. Secondly, after iteratively updating the sound velocity and obtaining the optimal sound velocity distribution, the three-dimensional reconstruction of the breast ultrasound image is performed to obtain the three-dimensional sound velocity map of the breast tissue. The three-dimensional wave field simulation is performed using the optimized sound velocity model, and the propagation of the sound wave is evaluated at each grid point to obtain the detailed three-dimensional structure of the breast tissue. The specific formula is expressed as follows: Among them, C opt It is represented by the sound speed after iterative update optimization, G(i,j,k;Ω,C opt ) is expressed as a Green's function in three-dimensional space, representing the wave field generated by the point source at the origin at the grid point (i, j, k), considering the attenuation and phase change of the wave propagating from the sound source to the receiving point, N is expressed as the number of grid points along each spatial dimension, and finally, after completing the three-dimensional reconstruction, by comparing with the known sound velocity distribution, the robustness and accuracy of the algorithm in processing actual breast ultrasound images are expressed as follows: Among them, E final Expressed as the final cost function value, e final It is expressed as the final residual. The three-dimensional equation is solved by the finite difference method, and the sound velocity model is iteratively optimized to achieve accurate three-dimensional reconstruction of breast tissue. After simulating the propagation of breast ultrasound in three-dimensional space, the simulation and actual observed wave fields are compared, and the sound velocity distribution is continuously updated until they match, thereby achieving accurate three-dimensional reconstruction of breast tissue.

6. The system for three-dimensional reconstruction and lesion detection of breast ultrasound images according to claim 1, characterized in that: The lesion detection and classification module includes a feature extraction unit and a classification recognition unit. The feature extraction unit extracts key features that are helpful for lesion recognition by analyzing the properties of shape, texture and signal distribution in the ultrasound image, and provides sufficient decision-making information for the subsequent classification and recognition of breast lesions. The classification recognition unit proposes a breast lesion detection algorithm based on fuzzy neural network, which classifies and recognizes lesions in breast images by reducing artifacts in ultrasound images and extracting rich local detail features and global feature information of the image. The system accurately recognizes and classifies breast ultrasound images.

7. A system for three-dimensional reconstruction and lesion detection of breast ultrasound images according to claim 6, characterized in that: Firstly, the key features of the breast ultrasound image obtained by the feature extraction unit are further extracted for subsequent fuzzy neural network input, and the co-occurrence matrix of the key feature area is calculated. Based on this matrix, the entropy information, uniformity information, contrast information and maximum co-occurrence matrix elements of the key features of the breast ultrasound image are extracted. The calculation formula of the co-occurrence matrix elements is expressed as: Among them, P is represented by the co-occurrence matrix, which represents the matrix of grayscale co-occurrence frequency under a specific distance d and angle θ between pixels in the breast ultrasound image, d is represented by the distance between pixels, which represents the distance between pixel pairs considered when calculating the co-occurrence matrix in the breast ultrasound image, θ is represented by the angle, which represents the angle between pixel pairs considered when calculating the co-occurrence matrix in the breast ultrasound image, a and b represent the grayscale values ​​of two pixels in the breast ultrasound image, f represents the grayscale function, k represents the row number of the position coordinates in the breast ultrasound image, l represents the column number of the position coordinates in the breast ultrasound image, D represents the set of pixel points when calculating the co-occurrence matrix, δ represents the Kronecker function, cos represents the cosine function, sin represents the sine function, and the specific formula for entropy calculation is expressed as: Among them, H represents entropy information, which represents the final calculated value to measure the uncertainty of regional information in breast ultrasound images, i, j represents the index of rows and columns in the co-occurrence matrix, and p ij It is expressed as the probability of gray level i and gray level j appearing simultaneously in the co-occurrence matrix, log is expressed as a logarithmic function, and entropy information can quantify the distribution uniformity of pixel intensity values ​​in the image area. The specific calculation formula of uniformity information is expressed as: Among them, U represents the uniformity information of the breast ultrasound image, which represents the final calculated value to measure the consistency of pixel intensity in the image area. The specific formula of the contrast information of the breast ultrasound image is expressed as: By calculating the contrast information of breast ultrasound images, the areas with large pixel intensity changes are identified. The specific formula of the maximum co-occurrence matrix element is expressed as: Among them, MCM is expressed as the maximum co-occurrence matrix element. Then, the fuzzy neural network is constructed using the extracted breast ultrasound image features, including entropy information, uniformity information, contrast information and maximum co-occurrence matrix element information as the input of the fuzzy neural network. The specific formula of the fuzzy neural network input layer is expressed as: I=[ΔH,ΔU,ΔC,ΔMCM Among them, I represents the input vector, which contains the difference value of the extracted breast ultrasound image features, ΔH represents the entropy difference, ΔU represents the uniformity difference, ΔC represents the contrast difference, ΔMCM represents the maximum co-occurrence matrix element difference, and the specific formula of the fuzzy layer is expressed as follows: Among them, O k It is represented as the fuzzy output of the kth feature, k is the index of the number of breast ultrasound image features, I k It is represented as the input value of the kth feature of the organism, min(I k ) represents the minimum value of all input values ​​of the kth feature, max(I k ) is expressed as the maximum value of all input values ​​of the kth feature, and the specific formula of the maximum fuzzy neuron layer is expressed as: Among them, S zk It is represented as the output of the zth neuron to the kth input feature, z is the index of the number of neurons in the fuzzy neural network, μ zk Expressed as a property function, used to measure the input O k The degree of membership in the zth fuzzy neuron, O k Represented as the fuzzy output of the kth feature, c z It is expressed as the center value of the zth neuron, which represents the input value when the neuron is most active, σ z It is expressed as the standard deviation of the zth neuron, which controls the width of the membership function. The specific formula of the fuzzy decision layer is expressed as: Among them, D v It is expressed as the maximum output value of the vth type of breast lesions. The types of breast lesions include benign and malignant. The specific formula of the final output layer is expressed as: Among them, Y represents the final classification result, D1 represents the maximum output value of the malignant category, D2 represents the maximum output value of the benign category, otherwise represents the conditional statement. The constructed fuzzy neural network can use the extracted breast feature differences to detect breast lesions, and effectively detect and distinguish malignant tumors and benign tissues. The method based on fuzzy neural network has significant advantages in dealing with uncertainty and nonlinear problems, and can effectively and accurately detect breast lesions.

8. The system for three-dimensional reconstruction and lesion detection of breast ultrasound images according to claim 1, characterized in that: The data storage and management module stores the ultrasound image data and test results collected and processed by the system by building and maintaining a database, ensuring the integrity, security and efficient retrieval of the data.

9. The system for three-dimensional reconstruction and lesion detection of breast ultrasound images according to claim 1, characterized in that: The report generation and display interaction module automatically generates a test report and provides a user interface, so that users can view and analyze test results in real time, accurately convey test information and facilitate user operations.

Images