Three-dimensional intracardiac ultrasonic imaging image enhancement method and system

Abstract

The invention provides a three-dimensional intracardiac ultrasonic imaging image enhancement method and system, and belongs to the technical field of image processing, and the method comprises the steps: obtaining a region, containing a weak signal, of a three-dimensional intracardiac ultrasonic image; performing local contrast enhancement on the region containing the weak signal to obtain a first enhanced ultrasonic image; performing dimension reduction processing on the first enhanced ultrasonic image to obtain a key feature vector of the first enhanced ultrasonic image; and performing image reconstruction based on the key feature vector to obtain a second enhanced ultrasonic imaging image. According to the method, the quality of the weak signal area in the three-dimensional intracardiac ultrasound image is effectively improved from acquisition of the weak signal area to local enhancement and then to reconstruction based on the key features, so that the three-dimensional intracardiac ultrasound image is clearer and more accurate, doctors can more accurately observe the internal structure and lesion condition of the heart, and the accuracy of the diagnosis is improved. High-quality image results are provided for doctors, the diagnosis time is shortened, and the diagnosis efficiency is improved.

Description

Technical Field

[0001] This application relates to the field of image processing technology, specifically a method and system for enhancing three-dimensional intracardiac ultrasound imaging images. Background Technology

[0002] Intracardiac ultrasound imaging is an advanced imaging technique that uses a miniature ultrasound probe placed at the tip of a catheter and inserted into the heart chamber via a vein or artery to achieve real-time, high-quality imaging and hemodynamic measurement of the heart and its adjacent tissues.

[0003] Current intracardiac ultrasound imaging has the following problems in the image enhancement process:

[0004] Early cardiac lesions may only manifest as weak signal changes. If these weak signals are not effectively enhanced, information about the lesion can easily be lost, leading to missed diagnoses. During three-dimensional intracardiac ultrasound imaging, due to limitations of the equipment itself and interference from human tissue, images are often contaminated with a significant amount of noise, especially in low signal intensity regions. This noise has a more pronounced effect, severely reducing image quality and readability. A low signal-to-noise ratio causes detailed information in the image to be overwhelmed by noise, making the image appear blurry or even distorted, affecting the doctor's accurate judgment of cardiac structure and lesions.

[0005] Therefore, overcoming the aforementioned technical problems and defects has become a key issue that needs to be addressed. Summary of the Invention

[0006] To overcome the aforementioned problems in the prior art, this application provides a three-dimensional intracardiac ultrasound imaging image enhancement method and system, which adopts the following technical solution:

[0007] In a first aspect, this application provides a method for enhancing three-dimensional intracardiac ultrasound imaging images, including:

[0008] Acquire regions containing weak signals in three-dimensional intracardiac ultrasound images;

[0009] Local contrast enhancement is performed on regions containing weak signals to obtain a first enhanced ultrasound image;

[0010] The first enhanced ultrasound image is subjected to dimensionality reduction processing to obtain the key feature vector of the first enhanced ultrasound image;

[0011] Image reconstruction is performed based on key feature vectors to obtain a second enhanced ultrasound imaging image.

[0012] Furthermore, regions containing weak signals in three-dimensional intracardiac ultrasound images are acquired, including:

[0013] The three-dimensional intracardiac ultrasound image is decomposed into multiple scales to obtain each frequency sub-band. Based on the energy distribution of different frequency sub-bands, the region containing weak signals is determined.

[0014] Furthermore, the regions containing weak signals are identified, including:

[0015] The three-dimensional intracardiac ultrasound image is filtered by a low-pass filter and a high-pass filter to obtain the first image.

[0016] The first image is downsampled to obtain the first-level low-frequency coefficients and first-level high-frequency coefficients of the three-dimensional intracardiac ultrasound image at different scales.

[0017] The first-level low-frequency coefficients are subjected to a second wavelet transform to obtain the second-level low-frequency coefficients; this process is repeated iteratively until a preset number of iterations is reached, thus completing the multi-scale decomposition of the three-dimensional intracardiac ultrasound image.

[0018] Obtain the frequency sub-bands obtained from multi-scale decomposition, and determine the regions containing weak signals based on the energy distribution of different frequency sub-bands.

[0019] Further, local contrast enhancement is performed on the region containing the weak signal to obtain a first enhanced ultrasound image, including:

[0020] Local contrast enhancement is achieved in regions containing weak signals by contrast-limited adaptive histogram equalization. By increasing the contrast between the weak signal and the background, a three-dimensional intracardiac ultrasound image with enhanced signal is obtained.

[0021] Furthermore, the first enhanced ultrasound image undergoes dimensionality reduction processing, including:

[0022] The signal-enhanced three-dimensional intracardiac ultrasound image is unfolded into a two-dimensional matrix, and the mean vector of the matrix is ​​calculated. The mean vector is then subtracted from each row of the matrix to obtain the centered matrix.

[0023] Calculate the covariance matrix of the centered matrix; perform eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and corresponding eigenvectors;

[0024] Arrange the eigenvalues ​​in descending order; select the k largest eigenvalues ​​and their corresponding eigenvectors, where k is the number of dimensions to be retained after dimensionality reduction.

[0025] Further, the key feature vectors of the first enhanced ultrasound image are obtained, including:

[0026] The selected k feature vectors are arranged into a feature vector matrix. The centered matrix is ​​multiplied by the feature vector matrix to obtain the dimension-reduced matrix, which is the information represented by the extracted key feature vectors.

[0027] Furthermore, image reconstruction is performed based on key feature vectors to obtain a second enhanced ultrasound imaging image, including:

[0028] Multiply the dimension-reduced matrix by the transpose of the eigenvector moments to obtain the back projection matrix;

[0029] Add the mean vector to each row of the back projection matrix to obtain the reconstructed two-dimensional matrix.

[0030] Based on the dimensions of the original three-dimensional intracardiac ultrasound image, the reconstructed two-dimensional matrix is ​​rearranged into a three-dimensional array to obtain the reconstructed three-dimensional intracardiac ultrasound image.

[0031] Secondly, this application also provides a three-dimensional intracardiac ultrasound imaging image enhancement system, comprising:

[0032] The weak signal region acquisition module is used to acquire regions containing weak signals in three-dimensional intracardiac ultrasound images;

[0033] The first image enhancement module is used to perform local contrast enhancement on the region containing weak signals to obtain a first enhanced ultrasound image;

[0034] The key feature vector extraction module is used to perform dimensionality reduction processing on the first enhanced ultrasound image to obtain the key feature vector of the first enhanced ultrasound image.

[0035] The second image enhancement module is used to reconstruct the image based on key feature vectors and obtain a second enhanced ultrasound imaging image.

[0036] Thirdly, this application provides an electronic device, comprising:

[0037] One or more processors; a memory; and one or more computer programs, wherein the one or more computer programs are stored in the memory, and the one or more computer programs include instructions that, when executed by the device, cause the device to perform the method as described in the first aspect.

[0038] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when run on a computer, causes the computer to perform the method described in the first aspect.

[0039] Fifthly, this application provides a computer program that, when executed by a computer, performs the method described in the first aspect.

[0040] In one possible design, the program in the fifth aspect can be stored wholly or partially on a storage medium packaged with the processor, or it can be stored wholly or partially on a memory not packaged with the processor.

[0041] This application has the following beneficial effects:

[0042] 1. This application obtains regions containing weak signals in three-dimensional intracardiac ultrasound images. Focusing on these weak signal regions improves the acquisition of lesion information within them, reducing the probability of missed diagnoses. Simultaneously, it can precisely improve the image quality of weak signal regions, reducing the waste of computational resources.

[0043] 2. This application obtains a first enhanced ultrasound image by locally enhancing the contrast of regions containing weak signals. This local contrast enhancement highlights the detailed information in the weak signal regions, making previously difficult-to-observe tissue structures clearer and more discernible.

[0044] 3. This application obtains the key feature vector of the first enhanced ultrasound image by performing dimensionality reduction processing on the first enhanced ultrasound image; the dimensionality reduction processing of this application can remove redundant information in the image, reduce the computational complexity in the process of extracting key features, and help to grasp the main feature information of the image.

[0045] 4. This application obtains a second enhanced ultrasound imaging image by reconstructing the image based on key feature vectors. By reconstructing the image based on key feature vectors and incorporating the mean vector, this application can restore the original position of the data, making the reconstructed three-dimensional intracardiac ultrasound image closer to the original image, reducing noise, and providing doctors with higher-quality image data for accurate diagnosis of child labor.

[0046] 5. This application effectively improves the quality of weak signal regions in three-dimensional intracardiac ultrasound images by acquiring weak signal regions, local enhancement, and reconstruction based on key features. This makes the three-dimensional intracardiac ultrasound images clearer and more accurate, helping doctors to observe the internal structure and lesions of the heart more accurately, providing doctors with high-quality image results, and helping to shorten the diagnosis time and improve the diagnosis efficiency. Attached Figure Description

[0047] Figure 1 This is an exemplary system architecture diagram to which embodiments of this application can be applied;

[0048] Figure 2 This is a flowchart of a three-dimensional intracardiac ultrasound imaging image enhancement method according to an embodiment of this application;

[0049] Figure 3 This is a flowchart illustrating the multi-scale decomposition of three-dimensional intracardiac ultrasound images according to an embodiment of this application.

[0050] Figure 4 This is a flowchart of the first image enhancement acquisition process according to an embodiment of this application;

[0051] Figure 5 This is a flowchart illustrating the dimensionality reduction process in an embodiment of this application.

[0052] Figure 6 This is a flowchart illustrating the second image enhancement acquisition process according to an embodiment of this application;

[0053] Figure 7 This is a system flowchart of an embodiment of this application;

[0054] Figure 8 This is a schematic diagram of a computer device according to an embodiment of this application. Detailed Implementation

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the terminology used herein in the specification of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having," and any variations thereof, in the specification, claims, and foregoing drawings of this application, are intended to cover non-exclusive inclusion. The terms "first," "second," etc., in the specification, claims, or foregoing drawings of this application are used to distinguish different objects, not to describe a particular order.

[0056] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0057] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0058] like Figure 1 As shown, system architecture 100 may include terminal devices 101, 102, and 103, a network 104, and a server 105. Network 104 serves as the medium for providing communication links between terminal devices 101, 102, and 103 and server 105. Network 104 may include various connection types, such as wired or wireless communication links, or fiber optic cables, etc.

[0059] Users can use terminal devices 101, 102, and 103 to interact with server 105 via network 104 to receive or send messages, etc. Various communication client applications can be installed on terminal devices 101, 102, and 103, such as web browser applications, shopping applications, search applications, instant messaging tools, email clients, social media platform software, etc.

[0060] Terminal devices 101, 102, and 103 can be various electronic devices with displays and support web browsing, including but not limited to smartphones, tablets, e-book readers, MP3 players (Moving Picture Experts Group Audio Layer III), MP4 players (Moving Picture Experts Group Audio Layer IV), laptops, and desktop computers, etc.

[0061] Server 105 can be a server that provides various services, such as a backend server that supports the pages displayed on terminal devices 101, 102, and 103.

[0062] It should be noted that the three-dimensional intracardiac ultrasound imaging image enhancement method provided in this application embodiment is generally executed by a server / terminal device, and correspondingly, the three-dimensional intracardiac ultrasound imaging image enhancement system is generally set in the server / terminal device.

[0063] It should be understood that Figure 1 The number of terminal devices, networks, and servers shown is merely illustrative. Depending on implementation needs, any number of terminal devices, networks, and servers can be included.

[0064] The target object in this application refers to the patient. This application uniformly represents the patient as the target object. By enhancing weak signals, this application can capture weak signals of the target object, thereby improving the information expression capability of the three-dimensional color ultrasound image of the target object.

[0065] Continue to refer to Figure 2 The figure shows a flowchart of a three-dimensional intracardiac ultrasound imaging image enhancement method according to this application. The method includes the following steps:

[0066] Step 201: Obtain the region containing weak signal in the three-dimensional intracardiac ultrasound image.

[0067] In this embodiment of the application, the acquisition of regions containing weak signals in a three-dimensional intracardiac ultrasound image is specifically implemented by: performing multi-scale decomposition on the three-dimensional intracardiac ultrasound image, acquiring each frequency sub-band obtained from the multi-scale decomposition, and determining regions containing weak signals based on the energy distribution of different frequency sub-bands.

[0068] Before processing the three-dimensional intracardiac ultrasound image of the target object, the three-dimensional intracardiac ultrasound image of the target object is acquired based on a preset device. In this embodiment of the application, an ultrasound diagnostic instrument equipped with three-dimensional intracardiac ultrasound imaging can be used to acquire the three-dimensional intracardiac ultrasound image of the target object. The ultrasound diagnostic instrument equipped with three-dimensional intracardiac ultrasound imaging emits ultrasound signals through a probe. The ultrasound signals penetrate the chest wall and enter the heart tissue. When the ultrasound signals encounter different tissue interfaces, they are reflected and scattered. The probe receives the reflected signals and converts them into electrical signals. By analyzing and processing the electrical signals, the image data of multiple two-dimensional planes are reconstructed to generate a three-dimensional intracardiac ultrasound image.

[0069] After acquiring a three-dimensional intracardiac ultrasound image of the target object, the image will contain some noise, including speckle noise and Gaussian noise. Therefore, denoising processing is required. Denoising can be performed using linear filtering methods such as mean filtering, median filtering, and Gaussian filtering, as well as nonlinear filtering methods such as nonlocal mean filtering. The denoised image is then normalized, mapping the pixel values ​​of the three-dimensional intracardiac ultrasound image to the [0, 1] interval to ensure data consistency. Linear normalization can be used during the normalization process of the three-dimensional intracardiac ultrasound image, i.e. ,in It is the raw data. It is the data with the largest pixel value. It is the data with the smallest pixel value. It is the normalized pixel value.

[0070] In this embodiment of the application, the three-dimensional intracardiac ultrasound image is decomposed into multiple scales to identify the weak signal characteristics and distribution range of different scale frequency sub-bands. Wavelet transform can be used to decompose the three-dimensional intracardiac color ultrasound image into sub-images of different scales, and each scale sub-image has different levels of detail information.

[0071] In this embodiment of the application, multi-scale decomposition is performed on the three-dimensional intracardiac ultrasound image. Please refer to [link / reference]. Figure 3 The specific implementation steps include:

[0072] Step 31: Filter the three-dimensional intracardiac ultrasound image using a low-pass filter and a high-pass filter to obtain the first image.

[0073] Step 32: Downsample the first image to obtain the first-order low-frequency coefficients and first-order high-frequency coefficients at different scales of the three-dimensional intracardiac ultrasound image. This application reduces the amount of data through downsampling while highlighting features at different scales.

[0074] Step 33: Perform a second wavelet transform on the first-level low-frequency coefficients to obtain the second-level low-frequency coefficients; iterate in this way until a preset number of iterations is reached to complete the multi-scale decomposition of the three-dimensional intracardiac ultrasound image. This application can perform multi-scale decomposition of the image by iteratively performing wavelet transform on the low-frequency coefficients. Each decomposition can decompose the image at different scales, thereby obtaining fine feature information.

[0075] Step 34: Obtain the frequency sub-bands obtained from the multi-scale decomposition. Based on the energy distribution of different frequency sub-bands, determine the regions containing weak signals. A frequency sub-band is a portion of the signal decomposed into different frequency ranges after wavelet transform. Each frequency sub-band represents the characteristics of the signal within a specific frequency range, and includes both low-frequency and high-frequency sub-bands.

[0076] This application uses wavelet transform to iterate low-frequency coefficients, which can enhance the characteristics of weak signals in low-frequency coefficients, increase the detection probability of weak signals in low-frequency signals, and enhance the contrast between heart tissue and surrounding areas, making the boundaries of heart structure clearer. This is beneficial for detecting minute lesions and helps doctors diagnose early symptoms in target subjects.

[0077] In this application, the low-frequency subband obtained by wavelet transform mainly contains large-scale structural information of the heart, while the high-frequency subband contains detailed information and possible weak signals.

[0078] In this embodiment of the application, determining the region containing weak signals based on the energy distribution of different frequency sub-bands includes:

[0079] The energy values ​​of different frequency sub-bands are obtained. In this embodiment, the energy values ​​of different frequency sub-bands are obtained based on a preset formula, which is as follows: ,in Indicates the first The energy carried by a person's height Indicates the first The first of the sub-bands The wavelet coefficients in this application include low-frequency coefficients and high-frequency coefficients.

[0080] The energy values ​​of different frequency sub-bands are compared with preset energy values. When the energy value of a sub-band is lower than the preset energy value and the wavelet coefficient of the sub-band is lower than the preset coefficient threshold, it is determined that the three-dimensional spatial region corresponding to the sub-band contains a weak signal.

[0081] In this embodiment, a preset energy value is set based on the statistical characteristics of different sub-band energies. The preset coefficient threshold is selected by the distribution range of the statistical coefficient amplitude.

[0082] Step 202: Perform local contrast enhancement on the region containing weak signals to obtain a first enhanced ultrasound image.

[0083] Contrast-limited adaptive histogram equalization is a technique used to enhance image contrast.

[0084] In this embodiment, contrast-limited adaptive histogram equalization is used to locally enhance the contrast of regions containing weak signals. By increasing the contrast between the weak signals and the background, a signal-enhanced three-dimensional intracardiac ultrasound image is obtained.

[0085] In this embodiment, contrast-limited adaptive histogram equalization is used to locally enhance the contrast of regions containing weak signals. By increasing the contrast between the weak signal and the background, a signal-enhanced three-dimensional intracardiac ultrasound image is obtained. Please refer to [link / reference]. Figure 4 Specifically, it manifests as follows:

[0086] Step 41 involves dividing the three-dimensional intracardiac ultrasound image into blocks based on a preset size, acquiring the grayscale histogram for each block, and applying contrast limits. When the frequency of a certain grayscale level exceeds a preset threshold, it is truncated to the threshold level, and the excess portion is evenly distributed to other grayscale levels to maintain the total area of ​​the histogram. This application captures local details in the image by dividing the ultrasound image into blocks. The size of the blocks can be set based on the image resolution, such as 16x16 or 32x32. The grayscale histogram represents the frequency of each grayscale level in the ultrasound image.

[0087] Step 42 performs contrast-limited histogram equalization, that is, by calculating the cumulative distribution function, the original gray values ​​are mapped to new gray values, so that the probability of each gray level appearing in the sub-block is equal, thereby enhancing the contrast of the sub-block. For regions containing weak signals, the contrast enhancement operation is focused. In this embodiment, the new gray values ​​are obtained based on a preset formula, wherein the preset formula is: Where L is the total number of gray levels in the ultrasound image. This is the cumulative distribution function value of gray level i. This application uses histogram equalization to uniformly adjust the gray-level distribution of the ultrasound image, thereby enhancing image contrast.

[0088] Step 43: The contrast-enhanced sub-blocks are re-merged to form a complete signal-enhanced three-dimensional intracardiac ultrasound image, which is used as the first enhanced ultrasound image. In this embodiment, an overlapping addition method is used, and the pixel values ​​of the overlapping areas are weighted and averaged to achieve a smooth transition at the boundary, avoiding discontinuities at the sub-block boundaries.

[0089] Step 203: Perform dimensionality reduction processing on the first enhanced ultrasound image to obtain the key feature vector of the first enhanced ultrasound image.

[0090] In this embodiment, the first enhanced ultrasound image undergoes dimensionality reduction processing; please refer to [reference needed]. Figure 5 The specific content includes:

[0091] Step 51: Expand the signal-enhanced three-dimensional intracardiac ultrasound image into a two-dimensional matrix and calculate the mean vector of the matrix; subtract the mean vector from each row of the matrix to obtain the centered matrix.

[0092] Step 52: Calculate the covariance matrix of the centered matrix; perform eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and corresponding eigenvectors.

[0093] Step 53: Arrange the feature values ​​in descending order; select the k largest feature values ​​and their corresponding feature vectors, where k is the number of dimensions to be retained after dimensionality reduction.

[0094] For example, the first enhanced ultrasound image data is unfolded into a two-dimensional matrix form. Assume the size of the first enhanced ultrasound image data is... Where m is the number of rows, n is the number of columns, and p is the number of layers, the first enhanced ultrasound image is reconstructed as... matrix Each row represents information about a pixel in the image across different dimensions.

[0095] Based on preset formula Get matrix mean vector , Each element is a matrix The mean of the corresponding column. (The matrix is ​​then...) Subtract the mean vector from each row The centered matrix is ​​obtained. ,in ,in , .pass Obtain the centralized matrix covariance matrix The covariance matrix The size is .

[0096] Perform eigenvalue decomposition on the covariance matrix to obtain eigenvalues. and the corresponding feature vector Eigenvalues ​​represent the variance of the data along the corresponding eigenvector direction; a larger variance indicates more information in that direction. The eigenvalues ​​are arranged in descending order, i.e. We select the k largest eigenvalues ​​and their corresponding eigenvectors, where k is the number of dimensions we want to retain after dimensionality reduction. The value of k can be determined based on the cumulative variance contribution rate, which is the proportion of the sum of the top k eigenvalues ​​to the sum of all eigenvalues.

[0097] In this embodiment of the application, obtaining the key feature vector of the first enhanced ultrasound image includes:

[0098] The selected k feature vectors are arranged into a feature vector matrix. The centered matrix is ​​multiplied by the feature vector matrix to obtain the dimension-reduced matrix, which is the information represented by the extracted key feature vectors, that is, the key feature vectors of the first enhanced ultrasound image.

[0099] For example, the selected k eigenvectors can be arranged column-wise to form an eigenvector matrix. The centered matrix With eigenvector matrix Multiplying them yields the reduced-dimensional matrix. ,Right now ,matrix The size is , denoted as the number of pixels, where each row represents the projection of the original image onto the k principal components after dimensionality reduction, which is the information represented by the extracted key feature vectors.

[0100] Step 204: Reconstruct the image based on the key feature vectors to obtain the second enhanced ultrasound imaging image.

[0101] In this embodiment, image reconstruction is performed based on key feature vectors to obtain a second enhanced ultrasound imaging image. Please refer to [link / reference]. Figure 6 The specific content includes:

[0102] Step 61, compare the dimensionality-reduced matrix with the eigenvector moments. Multiply by the transpose of the matrix to obtain the back projection matrix.

[0103] Step 62: Add the mean vector to each row of the back projection matrix to obtain the reconstructed two-dimensional matrix.

[0104] Step 63: Based on the dimensions of the original three-dimensional intracardiac ultrasound image, rearrange the reconstructed two-dimensional matrix into a three-dimensional array to obtain the reconstructed three-dimensional intracardiac ultrasound image, i.e., the second enhanced ultrasound imaging image.

[0105] For example, the reduced-dimensional matrix With eigenvector matrix transpose Multiplying them together yields a product of size 1. Back projection matrix The dimensionality-reduced data is then projected back onto the original data space using the following formula: . Matrix Add the mean vector to each row Obtain the reconstructed matrix ;Right now ,in , .

[0106] Based on the size of the original three-dimensional intracardiac ultrasound image The reconstructed two-dimensional matrix The images are rearranged into a three-dimensional array to obtain the reconstructed three-dimensional intracardiac ultrasound images.

[0107] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This computer program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the methods described above. The aforementioned storage medium can be a non-volatile storage medium such as a magnetic disk, optical disk, or read-only memory (ROM), or random access memory (RAM).

[0108] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0109] Continue to refer to Figure 7 The three-dimensional intracardiac ultrasound imaging image enhancement system described in this embodiment includes:

[0110] The weak signal region acquisition module 701 is used to acquire regions containing weak signals in three-dimensional intracardiac ultrasound images.

[0111] The first image enhancement module 702 is used to perform local contrast enhancement on the region containing weak signals to obtain a first enhanced ultrasound image;

[0112] The key feature vector extraction module 703 is used to perform dimensionality reduction processing on the first enhanced ultrasound image to obtain the key feature vector of the first enhanced ultrasound image.

[0113] The second image enhancement module 704 is used to reconstruct the image based on key feature vectors and obtain a second enhanced ultrasound imaging image.

[0114] To address the aforementioned technical problems, embodiments of this application also provide a computer device. Please refer to [link / reference needed]. Figure 8 , Figure 8 This is a basic structural block diagram of the computer device in this embodiment.

[0115] The computer device 8 includes a memory 8a, a processor 8b, and a network interface 8c that are interconnected via a system bus. It should be noted that only the computer device 8 with components 8a-8c is shown in the figure; however, it should be understood that it is not required to implement all the shown components, and more or fewer components can be implemented alternatively. Those skilled in the art will understand that the computer device described here is a device capable of automatically performing numerical calculations and / or information processing according to pre-set or stored instructions, and its hardware includes, but is not limited to, microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0116] The computer device can be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device can interact with the user via a keyboard, mouse, remote control, touchpad, or voice control.

[0117] The memory 8a includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 8a may be an internal storage unit of the computer device 8, such as the hard disk or memory of the computer device 8. In other embodiments, the memory 8a may also be an external storage device of the computer device 8, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 8. Of course, the memory 8a may also include both the internal storage unit and its external storage device of the computer device 8. In this embodiment, the memory 8a is typically used to store the operating system and various application software installed on the computer device 8, such as the program code of a three-dimensional intracardiac ultrasound imaging image enhancement method. In addition, the memory 8a can also be used to temporarily store various types of data that have been output or will be output.

[0118] In some embodiments, the processor 8b may be a central processing unit (CPU), controller, microcontroller, microprocessor, or other data processing chip. The processor 8b is typically used to control the overall operation of the computer device 8. In this embodiment, the processor 8b is used to run program code stored in the memory 8a or process data, for example, to run the program code for the three-dimensional intracardiac ultrasound imaging image enhancement method.

[0119] The network interface 8c may include a wireless network interface or a wired network interface, which is typically used to establish communication connections between the computer device 8 and other electronic devices.

[0120] This application also provides another embodiment, namely, a non-volatile computer-readable storage medium storing a program for a three-dimensional intracardiac ultrasound imaging image enhancement method, wherein the three-dimensional intracardiac ultrasound imaging image enhancement can be executed by at least one processor to cause the at least one processor to perform the steps of the three-dimensional intracardiac ultrasound imaging image enhancement method as described above.

[0121] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, air conditioner, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0122] Obviously, the embodiments described above are only some embodiments of this application, not all embodiments. The accompanying drawings show preferred embodiments of this application, but do not limit the patent scope of this application. This application can be implemented in many different forms; rather, the purpose of providing these embodiments is to provide a more thorough and comprehensive understanding of the disclosure of this application. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing specific embodiments, or make equivalent substitutions for some of the technical features. Any equivalent structures made using the content of this application's specification and drawings, directly or indirectly applied to other related technical fields, are similarly within the scope of patent protection of this application.

Claims

1. A method of three-dimensional intracardiac ultrasound image enhancement, the method comprising: The method comprises the following steps: obtaining a region of a three-dimensional intracardiac ultrasound image containing weak signals; performing local contrast enhancement on the region containing weak signals to obtain a first enhanced ultrasound image; performing dimension reduction processing on the first enhanced ultrasound image to obtain a key feature vector of the first enhanced ultrasound image; performing image reconstruction based on the key feature vector to obtain a second enhanced ultrasound imaging image.

2. The three-dimensional intracardiac ultrasound imaging image enhancement method of claim 1, wherein, The method for obtaining a region of a three-dimensional intracardiac ultrasound image containing weak signals comprises the following steps: performing multi-scale decomposition on the three-dimensional intracardiac ultrasound image to obtain each frequency sub-band obtained by the multi-scale decomposition, and determining the region containing weak signals based on the energy distribution of different frequency sub-bands.

3. The three-dimensional intracardiac ultrasound imaging image enhancement method of claim 2, wherein, The method for determining the region containing weak signals comprises the following steps: filtering the three-dimensional intracardiac ultrasound image through a low-pass filter and a high-pass filter to obtain a first image; performing down-sampling on the first image to obtain first-level low-frequency coefficients and first-level high-frequency coefficients of the three-dimensional intracardiac ultrasound image under different scales; performing second wavelet transform on the first-level low-frequency coefficients to obtain second-level low-frequency coefficients; and iteratively performing the above steps until a preset number of iterations is reached, thereby completing the multi-scale decomposition of the three-dimensional intracardiac ultrasound image; obtaining each frequency sub-band obtained by the multi-scale decomposition, and determining the region containing weak signals based on the energy distribution of different frequency sub-bands.

4. The three-dimensional intracardiac ultrasound imaging image enhancement method of claim 1, wherein, The method for performing local contrast enhancement on the region containing weak signals to obtain a first enhanced ultrasound image comprises the following steps: performing local contrast enhancement on the region containing weak signals through contrast limited adaptive histogram equalization, and obtaining a signal-enhanced three-dimensional intracardiac ultrasound image by improving the contrast between weak signals and the background.

5. The method of claim 1, wherein, The method for performing dimension reduction processing on the first enhanced ultrasound image comprises the following steps: expanding the signal-enhanced three-dimensional intracardiac ultrasound image into a two-dimensional matrix form, and calculating a mean vector of the matrix; and subtracting the mean vector from each row of the matrix to obtain a centralized matrix; calculating a covariance matrix of the centralized matrix; and performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues and corresponding eigenvectors; arranging the eigenvalues in descending order; and selecting the first k largest eigenvalues and the corresponding eigenvectors, wherein k is the number of dimensions to be retained after dimension reduction.

6. The method of claim 1, wherein, The method for obtaining a key feature vector of the first enhanced ultrasound image comprises the following steps: arranging the selected k eigenvectors into a feature vector matrix in columns; and multiplying the centralized matrix and the feature vector matrix to obtain a reduced matrix, which represents the information of the extracted key feature vector.

7. The three-dimensional intracardiac ultrasound imaging image enhancement method of claim 1, wherein, The method for performing image reconstruction based on the key feature vector to obtain a second enhanced ultrasound imaging image comprises the following steps: multiplying the reduced matrix and the transpose of the feature vector matrix to obtain an inverse projection matrix; adding the mean vector to each row of the inverse projection matrix to obtain a reconstructed two-dimensional matrix; rearranging the reconstructed two-dimensional matrix into a three-dimensional array form based on the size of the original three-dimensional intracardiac ultrasound image to obtain a reconstructed three-dimensional intracardiac ultrasound image.

8. A three-dimensional intracardiac echographic image enhancement system for implementing the three-dimensional intracardiac echographic image enhancement method of claims 1-7, characterized in that, The method comprises the following steps: a weak signal region obtaining module, configured to obtain a region of a three-dimensional intracardiac ultrasound image containing weak signals; a first image enhancement module, configured to perform local contrast enhancement on the region containing weak signals to obtain a first enhanced ultrasound image; The key feature vector extraction module is configured to perform dimension reduction processing on the first enhanced ultrasound image to obtain a key feature vector of the first enhanced ultrasound image. The second image enhancement module is configured to perform image reconstruction based on the key feature vector to obtain a second enhanced ultrasound imaging image.

9. An electronic device, comprising: The method comprises: one or more processors; a memory configured to store one or more programs; when the one or more programs are executed by the one or more processors, the one or more processors implement the method of any one of claims 1-7.

10. A computer readable storage medium having stored thereon computer instructions, wherein, The instructions are executed by the processor to implement the steps of the method of any one of claims 1-7.

Images