An image-enhanced cardiovascular surgical image processing system and method

Abstract

This invention provides a cardiovascular surgical image processing system and method for image enhancement, belonging to the field of image processing technology. The method includes: acquiring cardiovascular image data; extracting structural components, texture components, and noise components from the cardiovascular image data; enhancing the structural components of the cardiovascular image data to obtain a first structural enhancement component; extracting local structural features of the first structural enhancement component and generating a second structural enhancement component; enhancing the texture components of the cardiovascular image data to obtain a texture enhancement component; and fusing the first structural enhancement component, the second structural enhancement component, the texture enhancement component, and the noise component to obtain enhanced cardiovascular image data. This invention focuses on enhancing local details and avoids excessive noise enhancement, thereby improving image quality.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and in particular to an image enhancement system and method for cardiovascular surgical imaging. Background Technology

[0002] Cardiovascular surgical imaging includes medical images of the heart, arteries, veins, and related structures, such as echocardiography, CT angiography (CTA), magnetic resonance imaging (MRI), and angiography. The quality and clarity of these images directly affect the accuracy of diagnosis and surgical outcomes; therefore, image enhancement technology plays a crucial role in cardiovascular surgery.

[0003] Currently, image enhancement for cardiovascular surgical images primarily relies on histogram equalization (HE). Histogram equalization improves the overall contrast of an image by uniformly distributing the gray values ​​of pixels, and it has a significant effect on improving the visibility of low-contrast areas in cardiovascular images.

[0004] However, histogram equalization equalizes all pixel values ​​across the entire image range. While it can enhance contrast, it is not ideal for handling local details and can easily overlook subtle changes in local areas. In particular, in low-contrast areas, histogram equalization may over-amplify noise, causing noise to be amplified along with useful information in the image, resulting in a decrease in image quality, especially in noisy medical images. Summary of the Invention

[0005] To address the technical problems of existing technologies, such as imperfections in processing local details, the tendency to overlook subtle changes in local areas, and the potential for excessive noise enhancement that amplifies noise along with useful information in the image, leading to a decrease in image quality, this invention provides a cardiovascular surgical image processing system and method for image enhancement.

[0006] The technical solutions provided by the embodiments of the present invention are as follows:

[0007] A first aspect of this invention provides an image enhancement method for cardiovascular surgical images, comprising:

[0008] S1: Acquire cardiovascular imaging data;

[0009] S2: Extract the structural components, texture components, and noise components of the cardiovascular imaging data;

[0010] S3: Enhance the structural components of the cardiovascular imaging data to obtain the first structural enhancement component;

[0011] S4: Extract the local structural features of the first structural enhancement component and generate the second structural enhancement component;

[0012] S5: Enhance the texture components of the cardiovascular imaging data to obtain texture enhancement components;

[0013] S6: The first structural enhancement component, the second structural enhancement component, the texture enhancement component, and the noise component are fused to obtain cardiovascular enhanced image data.

[0014] A second aspect of the present invention provides an image enhancement cardiovascular surgical image processing system, comprising:

[0015] processor;

[0016] A memory storing computer-readable instructions, which, when executed by the processor, implement the image enhancement cardiovascular surgical image processing method as described in the first aspect.

[0017] Third aspect

[0018] A third aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon that, when executed by a processor, implements the image enhancement cardiovascular surgical image processing method as described in the first aspect.

[0019] The beneficial effects of the technical solutions provided by the embodiments of the present invention include at least the following:

[0020] In this invention, the structural components, texture components, and noise components of the cardiovascular imaging data are extracted. The structural components and the texture components of the details are enhanced separately, and then fused with the noise components. Emphasis is placed on enhancing local details, avoiding excessive noise enhancement, and improving image quality. Attached Figure Description

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

[0022] Figure 1 A schematic flowchart of an image enhancement method for cardiovascular surgical images provided in an embodiment of the present invention;

[0023] Figure 2 This is a schematic diagram of the structure of an image enhancement cardiovascular surgical image processing system provided in an embodiment of the present invention. Detailed Implementation

[0024] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0025] Reference manual attached Figure 1 The diagram shows a flowchart of an image enhancement method for cardiovascular surgical image processing provided by an embodiment of the present invention.

[0026] This invention provides an image enhancement method for cardiovascular surgical image processing. This method can be implemented using an image enhancement device for cardiovascular surgical image processing, which can be a terminal or a server. The processing flow of the image enhancement method for cardiovascular surgical image processing may include the following steps:

[0027] S1: Acquire cardiovascular imaging data.

[0028] Optionally, cardiovascular imaging data may include echocardiography, CT angiography (CTA), magnetic resonance imaging (MRI), and angiography.

[0029] S2: Extract the structural, texture, and noise components from cardiovascular imaging data.

[0030] The structural components include key anatomical features in cardiovascular imaging, such as the outlines of blood vessels and the boundaries of heart chambers. These structural components, after special processing, allow physicians to visualize important anatomical structures more clearly.

[0031] Texture components contain details of cardiovascular tissue (such as subtle changes in myocardial fibers or arterial walls). Enhancing these texture components helps to highlight minute features of diseased tissue.

[0032] Noise components can affect the diagnostic accuracy of medical images. By isolating the noise components, denoising algorithms can be used to process them, thereby reducing unnecessary interference and improving image clarity.

[0033] In one possible implementation, S2 specifically includes sub-steps S201 to S205:

[0034] S201: The cardiovascular imaging data is filtered using Gaussian filtering to obtain a filtered image.

[0035] Gaussian filtering is a classic smoothing filtering method in image processing, mainly used to remove noise from images while preserving their overall structure. Its basic principle is to perform a weighted average of the pixels in the image, with the weights distributed according to a Gaussian function, thereby smoothing the image. Gaussian filtering is a mature technology and will not be elaborated upon further in this invention.

[0036] S202: Extract the structural components of cardiovascular imaging data from filtered images using the total variational image reconstruction algorithm.

[0037] Total Variation Image Reconstruction (TV) is a commonly used technique for image denoising, reconstruction, and enhancement, particularly effective in removing noise while preserving image edge details. The basic idea of ​​TV is to remove noise from an image by minimizing the total variation (TV) while maintaining edge details. TV is a mature technology and will not be elaborated upon further in this invention.

[0038] S203: Determine the detailed components of cardiovascular imaging data based on the structural components of the data.

[0039] Optionally, S203 specifically involves determining the detailed components of the cardiovascular imaging data according to the following formula:

[0040] I D =II S

[0041] Among them, I D Indicates detailed components; I represents raw cardiovascular imaging data. S Indicates structural components.

[0042] S204: Anisotropic diffusion filtering is used to filter the detail components of cardiovascular image data to obtain the texture components of the cardiovascular image data.

[0043] Anisotropic diffusion filtering (ADF) is an advanced filtering technique for image denoising and smoothing, aiming to reduce noise in images while preserving edge and important structural details to the maximum extent possible. The core idea of ​​ADF is that during image smoothing, flat areas (areas with more noise) should be smoothed more strongly, while edge areas (areas with drastic gray-level changes) should retain details and have a reduced smoothing effect. This differs from traditional isotropic filtering (such as Gaussian filtering), which performs the same smoothing operation in all areas (whether smooth or edge), resulting in blurred edges. Anisotropic diffusion filtering is a mature technology and will not be elaborated upon further in this invention.

[0044] S205: Determine the noise component of cardiovascular imaging data based on the texture component.

[0045] Optionally, S205 specifically involves determining the noise component of the cardiovascular imaging data according to the following formula:

[0046] I N =I D -I T

[0047] Among them, I N Indicates noise components, I D Indicating details, I T Indicates texture components.

[0048] In this invention, by decomposing cardiovascular imaging data into structural, textural, and noise components, noise interference can be reduced while preserving important image information, thereby significantly improving image contrast and clarity. This decomposition and processing method helps physicians observe cardiovascular structures more clearly, identify lesions, and provide more precise imaging evidence for surgical planning. Furthermore, it enhances the performance of automated image analysis algorithms, improving diagnostic accuracy.

[0049] S3: Enhance the structural components of cardiovascular imaging data to obtain the first structural enhancement component.

[0050] In one possible implementation, S3 specifically involves: using the CLAHE algorithm to enhance the structural components of cardiovascular imaging data to obtain a first structural enhancement component.

[0051] Among them, CLAHE (Contrast-Limited Adaptive Histogram Equalization) is an improved image enhancement method specifically designed to improve local contrast in images, especially suitable for images with low contrast and blurred details. CLAHE is an improved version of traditional Adaptive Histogram Equalization (AHE). By limiting the contrast of local histograms, it avoids the over-enhancement that may occur with AHE methods. Particularly in noisy medical images, CLAHE can better balance enhancement effect and noise control.

[0052] Specifically, S3 includes:

[0053] S301: The input cardiovascular image is divided into multiple small blocks (local regions), and each block is processed separately. This allows each part of the image to be enhanced independently, avoiding excessive contrast enhancement or unevenness caused by global histogram equalization.

[0054] S302: Perform histogram equalization on the pixels within each small block, calculate its gray value distribution, and redistribute the gray values ​​to improve the contrast of the local area.

[0055] S303: Contrast limiting restricts the frequency (i.e., number of pixels) of a certain gray level in the histogram from exceeding a threshold. For portions exceeding the threshold, a "clip" is applied, distributing them evenly across other gray levels. This step is to avoid enhanced noise and local artifacts.

[0056] S304: After performing histogram equalization on each small block, discontinuous transition regions may be generated between the blocks. To solve this problem, CLAHE uses bilinear interpolation to smooth the pixels between adjacent blocks, making the entire image look natural and coherent, and avoiding block artifacts.

[0057] In this invention, the CLAHE algorithm, through adaptive local processing and contrast limiting, can significantly enhance local details and contrast in cardiovascular images, and is particularly suitable for enhancing structural components.

[0058] S4: Extract the local structural features of the first structural enhancement component and generate the second structural enhancement component.

[0059] In one possible implementation, S4 specifically involves: extracting local structural features of the first structural enhancement component using the STS operator, and generating the second structural enhancement component.

[0060] It should be noted that the first structural enhancement component (e.g., the enhancement component obtained through the CLAHE algorithm) has already improved the global contrast of the image, highlighting some important structural information. However, contrast enhancement alone may not be sufficient to capture more refined local structural features, such as edges, corners, or texture details. The STS operator can further extract local salient features, especially strong edges and complex geometric shapes in the image. Through this operation, key structures in the image can be made clearer, such as blood vessel walls, bifurcation points, and heart valves in cardiovascular images.

[0061] Among them, the STS (Structure Tensor Saliency Detection) operator is an image processing method based on structure tensors, used to extract local geometric structural features in images, such as edges, corners, and textures. By calculating local gradient changes in an image, the STS operator can identify salient structural information in the image.

[0062] Specifically, given an image matrix, the structure tensor is as follows:

[0063]

[0064] Where ST represents the structure tensor, w represents the local window, and E i E represents the gradient in the i-th direction. jThis represents the gradient in the j-direction.

[0065] The eigenvalues ​​of the structure tensor provide more information about the local geometry of the input image. The specific calculation method for the eigenvalues ​​of the structure tensor is as follows:

[0066]

[0067] Here, v1 represents the first feature, which usually represents strong edges or salient features in a local area of ​​the image, and v2 represents the second feature, which usually represents flat areas or directions with small gradient changes.

[0068] Furthermore, the STS operator is specifically as follows:

[0069]

[0070] Here, STS represents the STS operator.

[0071] In this invention, local structural features are extracted using the STS operator to generate a second structural enhancement component, which can further enhance key features in the image, such as edges, corners, and fine structures. This enhancement method, while preserving important information, reducing noise amplification, and improving local details, can better adapt to the complex needs of medical image processing, especially in cardiovascular image analysis, providing doctors with clearer and more accurate diagnostic information.

[0072] S5: Enhance the texture components of cardiovascular imaging data to obtain texture enhancement components.

[0073] In one possible implementation, S5 specifically includes sub-steps S501 and S502:

[0074] S501: Edge extraction of texture components in cardiovascular imaging data is performed using the Canny edge detection algorithm.

[0075] The Canny edge detection algorithm is a classic and efficient edge detection method widely used in computer vision and image processing. It accurately extracts edges from an image through a series of steps while minimizing noise interference. The goal of Canny edge detection is to identify significant edges in an image, ensuring accurate edge localization and good continuity of edge lines. The Canny edge detection algorithm is a mature technology and will not be elaborated upon further in this invention.

[0076] S502: Enhance the texture components of cardiovascular imaging data based on the edge extraction results to obtain texture enhancement components:

[0077] I Ca =max(I T ,ICanny )

[0078] Among them, I Ca This represents the texture enhancement component, where max indicates taking a larger value, and I T Indicates texture components, I Canny This represents the edge features extracted using the Canny edge detection algorithm.

[0079] S6: The first structural enhancement component, the second structural enhancement component, the texture enhancement component, and the noise component are fused to obtain cardiovascular enhanced imaging data.

[0080] In one possible implementation, S6 specifically involves fusing the first structural enhancement component, the second structural enhancement component, the texture enhancement component, and the noise component according to the following formula to obtain cardiovascular enhancement image data:

[0081] I E =λ1I CL +λ2I STS +λ3I Ca +λ4I N

[0082] Among them, I E Indicates cardiovascular enhancement imaging, I CL Indicates the first structural reinforcing component, I STS Indicates the second structural reinforcing component, I Ca Indicates texture enhancement component, I N Let λ1 represent the weighting coefficient of the first structural enhancement component, λ2 represent the weighting coefficient of the second structural enhancement component, λ3 represent the weighting coefficient of the texture enhancement component, and λ4 represent the weighting coefficient of the noise component.

[0083] In this invention, cardiovascular enhanced image data is generated by weighted fusion of the first structural enhancement component, the second structural enhancement component, the texture enhancement component, and the noise component. This can optimize the quality of cardiovascular images at multiple levels and ensure a good balance between enhanced contrast, detail representation, and noise control.

[0084] In one possible implementation, the weight coefficients of the first structural enhancement component, the second structural enhancement component, the texture enhancement component, and the noise component are determined by the firefly algorithm.

[0085] Specifically, the fitness function of the firefly algorithm is set as follows:

[0086]

[0087] Where f represents the fitness function, θ represents the set of weight coefficients, which includes the weight coefficients of the first structural enhancement component, the second structural enhancement component, the texture enhancement component, and the noise component, V represents the variance of the original cardiovascular image, M represents the mean of the output cardiovascular enhanced image, and E out E represents the entropy of the output cardiovascular enhancement image. in G represents the entropy of the original cardiovascular image. out G represents the average gradient of the output cardiovascular enhancement image. in The average gradient of the original cardiovascular image is represented by I, and PSNR represents the peak signal-to-noise ratio. E This represents the output cardiovascular enhancement image, where I represents the initial cardiovascular image, and PSNR(I) represents the output image. E I) represents the peak signal-to-noise ratio between the output enhanced cardiovascular image and the original cardiovascular image.

[0088] In this invention, the fitness function integrates entropy, average gradient, and peak signal-to-noise ratio (PSNR). By optimizing entropy and average gradient, important details and edges in the image can be preserved or enhanced. This is crucial for the identification of important structures such as blood vessels and heart valves in cardiovascular imaging. Furthermore, by introducing PSNR as a metric, distortion caused by over-enhancement can be avoided, maintaining the similarity between the enhanced image and the original image. This is very important for avoiding false edges or spurious structures, especially in medical imaging, to prevent misleading doctors' judgments.

[0089] Initialize firefly individuals. Each firefly individual represents a feasible set of weight coefficients. Each firefly individual consists of multiple dimensional components. Each component represents the weight coefficients of the first structure enhancement component, the second structure enhancement component, the texture enhancement component, and the noise component.

[0090] Each individual firefly is compared with other individuals in the population to generate a random number u, and then moved according to the following adaptive movement rules:

[0091]

[0092] in, This represents the position of the i-th firefly individual at iteration t+1, where ω represents the inertia weight factor. This represents the position of the i-th firefly at the t-th iteration. Let represent the position of the j-th firefly individual in the t-th iteration, β represent attraction, α represent the step size factor, sign represent the sign function, r represent a random number in the range of 0 to 1, Levy represent the Levy flight random step size, exp represent an exponential function with the natural constant e as the base, b represent the logarithmic spiral shape parameter, l represent a uniform random number between -1 and 1, and Rt Let represent the adaptive switching factor at the t-th iteration, and u represent a uniform random number between 0 and 1.

[0093] In this invention, an adaptive switching factor allows individual fireflies to automatically select search strategies based on changes in their global fitness during different iterations. When the random number is greater than the adaptive switching factor, Levy flight with randomness is employed. This is a search method with a long jump characteristic and a random step size, allowing the firefly to explore a wider search space, thereby increasing the probability of finding the global optimum. When the random number is less than the adaptive switching factor, a logarithmic spiral search is used. This is a refined local search method that can perform precise local searches near already relatively good solutions, thereby finding a local optimum.

[0094] Optionally, the attraction is specifically:

[0095]

[0096] Where β0 represents the attraction between two fireflies when the distance between them is 0, exp represents an exponential function with the natural constant e as the base, γ represents the light intensity attraction coefficient, and r ij Let represent the Euclidean distance between the i-th firefly individual and the j-th firefly individual.

[0097] In this invention, when the distance between two individual fireflies is small, the attraction is strong, causing them to quickly move closer to each other, which helps to enhance local search capabilities. Especially in the later stages of optimization, when the distance between individuals is small, the enhanced attraction allows for faster convergence to a local optimum. Furthermore, when individuals are close together, the stronger attraction allows for rapid approximation of the solution, enabling a refined search within the local region of the solution space.

[0098] Optionally, the adaptive switching factor is specifically:

[0099]

[0100] in, The fitness value represents the global best position at the (t-1)th iteration. This represents the fitness value of the globally optimal position at the (t-2)th iteration.

[0101] In this invention, an adaptive switching factor is used to dynamically adjust the search strategy based on the global best fitness value from the previous iterations, ensuring that the most suitable search behavior is adopted at different stages. By comparing the changes in the global best fitness value between two iterations, it is determined whether to conduct more global exploration or focus on local search. If the fitness improves significantly in the first two iterations, the algorithm may still be in the global exploration stage, and the algorithm tends to conduct more global search (i.e., using methods such as Levy flight) to discover new and better solutions. If the fitness improvement slows down, it indicates that the algorithm may have found some good local solutions, and the fitness value is small. In this case, the algorithm will focus more on local search (i.e., using strategies such as logarithmic spiral) to fine-tune the solution and improve the local convergence speed.

[0102] Optionally, the Levy flight random step size is as follows:

[0103]

[0104] Where, u follows The normal distribution of v, v follows The normal distribution is given by λ, where λ represents the exponential parameter.

[0105]

[0106] Where τ is the standard Gamma function.

[0107] In this invention, the main advantage of using Levy's random step size is that it can enhance the global search capability of the optimization algorithm, especially in complex, multi-peaked search spaces. Through the behavior of long jumps, it helps the algorithm avoid getting trapped in local optima and increases the probability of finding the global optimum.

[0108] After a firefly moves to a new location, its fitness is updated.

[0109] Determine if the current iteration count has reached the maximum iteration count; if so, output the set of weight coefficients represented by the firefly individual with the highest fitness; otherwise, return to continue iterating.

[0110] In this invention, the weight coefficients of the first structural enhancement component, the second structural enhancement component, the texture enhancement component, and the noise component are determined using the firefly algorithm, which can significantly improve the enhancement effect of cardiovascular images. This method combines global and local searches to adaptively adjust the weight coefficients, enabling the algorithm to dynamically optimize different components of the image, thereby enhancing image details, improving contrast, suppressing noise, and ultimately improving the overall image quality. Furthermore, it reduces the complexity of manual parameter tuning and improves optimization efficiency.

[0111] The beneficial effects of the technical solutions provided by the embodiments of the present invention include at least the following:

[0112] In this invention, structural components, texture components, and noise components are extracted from cardiovascular imaging data. The structural components and texture components of the details are enhanced separately, and then fused with the noise components. Emphasis is placed on enhancing local details, avoiding excessive noise enhancement, and improving image quality.

[0113] Reference manual attached Figure 2 The diagram shows a schematic of the structure of an image enhancement cardiovascular surgical image processing system provided by the present invention.

[0114] The present invention also provides an image enhancement cardiovascular surgical image processing system 20, applied to the above-described image enhancement cardiovascular surgical image processing method, comprising:

[0115] Processor 201.

[0116] The memory 202 stores computer-readable instructions that, when executed by the processor 201, implement the image enhancement cardiovascular surgical image processing method as described in the method embodiment.

[0117] The image enhancement cardiovascular surgical image processing system 20 provided by the present invention can perform the above-described image enhancement cardiovascular surgical image processing method and achieve the same or similar technical effects. To avoid repetition, the present invention will not elaborate further.

[0118] The beneficial effects of the technical solutions provided by the embodiments of the present invention include at least the following:

[0119] In this invention, the structural components, texture components, and noise components of the cardiovascular imaging data are extracted. The structural components and the texture components of the details are enhanced separately, and then fused with the noise components. Emphasis is placed on enhancing local details, avoiding excessive noise enhancement, and improving image quality.

[0120] It should be understood that the processor in the embodiments of the present invention can be a central processing unit (CPU), or it can be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or any conventional processor.

[0121] It should also be understood that the memory in the embodiments of the present invention can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate synchronous DRAM (DDR SDRAM), enhanced synchronous DRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0122] This invention provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements the image enhancement cardiovascular surgical image processing method as described in the method embodiment.

[0123] The present invention provides a computer-readable storage medium that can implement the steps and effects of the image enhancement cardiovascular surgical image processing method described in the above method embodiments. To avoid repetition, the present invention will not repeat them.

[0124] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following:

[0125] In this invention, the structural components, texture components, and noise components of the cardiovascular imaging data are extracted. The structural components and the texture components of the details are enhanced separately, and then fused with the noise components. Emphasis is placed on enhancing local details, avoiding excessive noise enhancement, and improving image quality.

[0126] The above are merely specific embodiments of the present invention, but the scope of protection of the present invention is not limited thereto. The scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for image enhancement in cardiovascular surgery, characterized in that, include: S1: Acquire cardiovascular imaging data; S2: Extract the structural components, texture components, and noise components of the cardiovascular imaging data; S3: Enhance the structural components of the cardiovascular imaging data to obtain the first structural enhancement component; S4: Extract the local structural features of the first structural enhancement component and generate the second structural enhancement component; S5: Enhance the texture components of the cardiovascular imaging data to obtain texture enhancement components; S6: The first structural enhancement component, the second structural enhancement component, the texture enhancement component, and the noise component are fused according to the following formula to obtain cardiovascular enhanced image data: ； Among them, I E Indicates cardiovascular enhancement imaging, I CL Indicates the first structural reinforcing component, I STS Indicates the second structural reinforcing component, I Ca Indicates texture enhancement component, I N λ1 represents the weighting coefficient of the first structure enhancement component, λ2 represents the weighting coefficient of the second structure enhancement component, λ3 represents the weighting coefficient of the texture enhancement component, and λ4 represents the weighting coefficient of the noise component. The weighting coefficients of the first structural enhancement component, the second structural enhancement component, the texture enhancement component, and the noise component are determined by the firefly algorithm; The fitness function of the firefly algorithm: ； Where f represents the fitness function, θ represents the set of weight coefficients, which includes the weight coefficients of the first structural enhancement component, the second structural enhancement component, the texture enhancement component, and the noise component, V represents the variance of the original cardiovascular image, M represents the mean of the output cardiovascular enhanced image, and E out E represents the entropy of the output cardiovascular enhancement image. in G represents the entropy of the original cardiovascular image. out G represents the average gradient of the output cardiovascular enhancement image. in The average gradient of the original cardiovascular image is represented by I, and PSNR represents the peak signal-to-noise ratio. E This indicates the output cardiovascular enhancement image, where I represents the initial cardiovascular image. This represents the peak signal-to-noise ratio between the output enhanced cardiovascular image and the original cardiovascular image.

2. The image enhancement method for cardiovascular surgical images according to claim 1, characterized in that, S2 specifically includes: S201: The cardiovascular imaging data is filtered using Gaussian filtering to obtain a filtered image; S202: Extract the structural components of the cardiovascular imaging data from the filtered image using the total variational image reconstruction algorithm; S203: Determine the detailed components of the cardiovascular imaging data based on the structural components of the cardiovascular imaging data; S204: The detail components of the cardiovascular image data are filtered by anisotropic diffusion filtering to obtain the texture components of the cardiovascular image data; S205: Determine the noise component of the cardiovascular imaging data based on the texture component of the cardiovascular imaging data.

3. The image enhancement method for cardiovascular surgical images according to claim 1, characterized in that, Specifically, S3 is: The CLAHE algorithm is used to enhance the structural components of the cardiovascular imaging data to obtain the first structural enhancement component.

4. The image enhancement method for cardiovascular surgical images according to claim 1, characterized in that, Specifically, S4 is: The local structural features of the first structural enhancement component are extracted using the STS operator, and the second structural enhancement component is generated.

5. The image enhancement method for cardiovascular surgical images according to claim 1, characterized in that, S5 specifically includes: S501: The texture components of the cardiovascular imaging data are extracted using the Canny edge detection algorithm; S502: Enhance the texture components of the cardiovascular imaging data based on the edge extraction results to obtain texture enhancement components.

6. An image enhancement cardiovascular surgical image processing system, characterized in that, include: processor; A memory storing computer-readable instructions, which, when executed by the processor, implement the cardiovascular surgical image processing method for image enhancement as described in any one of claims 1 to 5.

Images