Ultrasonic image enhancement method based on ultrasonic Gaussian kernel and non-sharpening mask sharpening

Abstract

The invention discloses an ultrasonic image enhancement method based on an ultrasonic Gaussian kernel and non-sharpening mask sharpening. The method comprises the following steps: acquiring an original image; removing the noise of the original image by using an ultrasonic Gaussian kernel to obtain a denoised image; performing Gaussian blur processing on the denoised image to obtain a Gaussian blur image; extracting high-frequency information in the original image; sharpening the extracted high-frequency information part to obtain a sharpened image; performing weighted fusion on the sharpened image and the original image to obtain a weighted image; the weighted image is converted to a Lab color space, and the brightness channel contrast is enhanced; and restoring the contrast-enhanced image to the RGB color space to generate a final enhanced image. According to the method, the Gaussian kernel denoising and the non-sharpening mask sharpening technology are combined, noise in the ultrasonic image is effectively removed, image details are enhanced, and the identifiability of the image is further improved through self-adaptive contrast enhancement.

Description

Technical Field

[0001] The present invention belongs to the technical field of image processing and computer vision, and particularly relates to an ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking sharpening. Background Art

[0002] In the field of medical image processing, the image quality directly affects the diagnosis and treatment effect of diseases. Medical imaging technologies such as ultrasound and contrast imaging are widely used in clinical practice, and these images can provide important information about the internal body for doctors. However, in practical applications, medical images are often affected by problems such as noise, blurring, and low contrast, resulting in a decline in image quality and even affecting the accuracy of diagnosis.

[0003] Therefore, it is necessary to perform denoising, sharpening, etc. on medical images. Traditional image denoising methods, such as mean filtering, Gaussian filtering, etc., although can remove the noise in the image to a certain extent, often cause the loss of image details and cannot effectively retain important tissue structures or lesion information. And the sharpening technology is to enhance the edges and details of the image to improve the clarity of the image, but oversharpening is also prone to generate artifacts and affect the diagnosis result.

[0004] Therefore, how to achieve a balance in the processing of denoising, sharpening, etc. in medical images, that is, to remove noise and retain the details of the image, is a key technical problem in medical image processing. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems existing in the related technologies to some extent.

[0006] The purpose of the present invention is to provide an ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking sharpening, which organically combines a variety of image enhancement technologies to optimize the quality of medical images and improve the clarity and detail performance of the images.

[0007] To achieve the above purpose, on the one hand, the present invention provides an ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking sharpening, including: S1. Obtain the original image through medical imaging technology; S2. Create an ultrasonic Gaussian kernel, and use this ultrasonic Gaussian kernel to remove the noise of the original image to obtain a denoised image; S3. Perform Gaussian blur processing on the denoised image to obtain a Gaussian blurred image; calculate the difference between the original image and the Gaussian blurred image, and extract the high-frequency information in the original image; S4. Create a mask, mark the extracted high-frequency information part as the area to be sharpened, and sharpen this area to be sharpened to obtain a sharpened image; S5. Weightedly fuse the sharpened image and the original image to obtain a weighted image; S6. Convert the weighted image to the Lab color space and enhance the contrast of the lightness channel; S7. Restore the image with enhanced contrast to the RGB color space to generate a final enhanced image.

[0008] A further preferred technical solution of the present invention is that the core of the ultrasonic Gaussian kernel created in step S2 is a Gaussian function, and its two-dimensional form is expressed as:

[0009] where is the value of the Gaussian kernel; is the standard deviation, which is used to control the spread degree of the Gaussian distribution; is the position coordinate relative to the center of the Gaussian kernel; is the normalization factor to ensure that the sum of the Gaussian kernel is 1.

[0010] Preferably, in step S2, the ultrasonic Gaussian kernel is used for Gaussian filtering to remove the noise of the original image. The specific method is as follows: Use the ultrasonic Gaussian kernel to convolve the original image. The mathematical expression of the convolution calculation is:

[0011] where is the pixel value of the original image; is the pixel value after filtering; is the weight of the Gaussian kernel; is the size of the Gaussian kernel; Then perform normalization calculation to ensure that the pixel value after filtering is between 0 and 255. The normalization is expressed as:

[0012] represents the denoised image.

[0013] Preferably, in step S3, the denoised image is subjected to Gaussian blur processing to obtain a Gaussian blurred image , which is expressed as:

[0014] where is the Gaussian kernel, and the parameters of the Gaussian kernel , .

[0015] Preferably, in step S3, the high-frequency information is obtained from the original image and the Gaussian blurred image is obtained by the difference and is expressed as:

[0016] wherein, R is a high-frequency residual image, representing the detailed information of edges and textures in the image.

[0017] Preferably, in step S4, a mask is created, the extracted high-frequency detail part is marked as the area to be sharpened, and the area to be sharpened is sharpened to obtain a sharpened image ; the specific method is: First, a mask is created and is expressed as:

[0018] wherein, T is the threshold, controlling which pixels are regarded as the high-frequency area; M is a binary mask, with a value of 1 only at the edges and 0 in the smooth areas; is the original image; is the Gaussian blurred image; Then, a soft mask is calculated using Gaussian blur and is expressed as:

[0019] wherein, is the soft mask after Gaussian blur, used to smooth the transition of the sharpened area; is the Gaussian kernel; The sharpened image is calculated by using weighted superposition, and the enhanced high-frequency information is added back to the original image, which is expressed as:

[0020] wherein, is the enhancement coefficient, used to control the sharpening intensity; is the image after preliminary sharpening; Meanwhile, the pixel values are constrained and are expressed as: .

[0021] Preferably, in step S5, the sharpened image and the original image are weighted and fused to obtain a weighted image, specifically: Combined with the soft mask, the sharpened image and the original image are weighted and fused in proportion, which is expressed as:

[0022] wherein, means that the areas not selected by the mask remain the original image; , indicating that the area selected by the mask is enhanced and sharpened; is the mean value of the soft mask, which is used to smooth the transition of the sharpened area.

[0023] Preferably, in step S6, when enhancing the contrast of the luminance channel, the image is divided into multiple small blocks, and histogram equalization is performed within each small block to enhance the contrast of the luminance channel; The transformation function of histogram equalization is expressed as:

[0024] where is the pixel value after equalization; is the cumulative distribution function of the luminance channel L; and are respectively the minimum and maximum values of the cumulative distribution; When enhancing the contrast of the luminance channel by using histogram equalization, the maximum value of the histogram cumulative distribution is restricted.

[0025] On the other hand, the present invention provides a non-transitory computer-readable storage medium, on which computer instructions are stored, and the computer instructions cause the computer to execute the above-mentioned ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking sharpening.

[0026] On another aspect, the present invention provides an electronic device, including: a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus, and the processor calls the logical instructions in the memory to execute the above-mentioned ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking sharpening.

[0027] On yet another aspect, the present invention provides a computer program product, the computer program product includes a computer program, the computer program is stored on a non-transitory computer-readable storage medium, and when the computer program is executed by a processor, the computer executes the above-mentioned ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking sharpening.

[0028] Beneficial effects: The ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking sharpening of the present invention uses a custom ultrasonic Gaussian kernel to efficiently remove noise and retain key details, can effectively remove the noise in medical images, and at the same time avoid the image blurring and detail loss caused by traditional filtering methods, thereby ensuring the clarity of tissue structure and lesion information; The present invention combines unsharp masking and adaptive edge enhancement technology to intelligently sharpen the key areas in the image, enhance the edge features, make the lesion contour clearer, improve the doctor's ability to identify lesions, and at the same time avoid artifacts caused by oversharpening; The present invention adopts ultrasonic image enhancement technology to effectively improve the local contrast of medical images, with contrast self-adaptive enhancement, which can improve the problem of low contrast, making the details in the low-contrast area more obvious and helping doctors observe the lesion area more accurately. The present invention has strong adaptability and is applicable to various medical imaging modes such as ultrasound and contrast imaging. It can be optimized according to the characteristics of different types of images, improve the image quality under different imaging devices, and enhance the versatility of medical images. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 It is a flowchart of the ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking sharpening of the present invention.

[0030] Figure 2 It is a flowchart of Gaussian blur and sharpening in Embodiment 1 of the present invention.

[0031] Figure 3 It is a flowchart of histogram equalization in Embodiment 1 of the present invention.

[0032] Figure 4 It is the effect diagram of the processing process of the original ultrasonic image of the normal uterus, denoising, sharpening, and enhancing contrast.

[0033] Figure 5 It is the effect diagram of the processing process of the original contrast image of the normal uterus, denoising, sharpening, and enhancing contrast.

[0034] Figure 6 It is the effect diagram of the processing process of the original ultrasonic image of the diseased uterus, denoising, sharpening, and enhancing contrast. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] To make the objectives, technical solutions, and advantages of the present invention clearer, the technical solutions in the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention, and they should not be construed as limitations to the present invention. Based on the embodiments in the present invention, all other embodiments obtained by those of ordinary skill in the art without making creative efforts fall within the scope of protection of the present invention. In the description of the present invention, it should be understood that the terms used are only for the purpose of description and cannot be construed as indicating or implying relative importance.

[0036] The following will be combined with Figures 1-6 Describe the ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking sharpening provided by the present invention.

[0037] Example 1: This example provides an ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking sharpening. The method aims to improve the quality of the image, enhance the visibility of details through various image enhancement techniques, and is widely used in medical image processing, especially suitable for image data with low contrast and large noise interference.

[0038] The overall process of this method is as Figure 1 shown, including the following steps: S1. Obtain the original image through medical imaging technology; S2. Create an ultrasonic Gaussian kernel, and use this ultrasonic Gaussian kernel to remove the noise of the original image to obtain a denoised image; S3. Perform Gaussian blur processing on the denoised image to obtain a Gaussian blurred image; calculate the difference between the original image and the Gaussian blurred image, and extract the high-frequency information in the original image; S4. Create a mask, mark the extracted high-frequency information part as the area to be sharpened, and sharpen this area to be sharpened to obtain a sharpened image; S5. Perform weighted fusion on the sharpened image and the original image to obtain a weighted image; S6. Convert the weighted image to the Lab color space and enhance the contrast of the luminance channel; S7. Restore the image with enhanced contrast to the RGB color space to generate the final enhanced image.

[0039] The following is a detailed description of each step.

[0040] In step S2, using the ultrasonic Gaussian kernel to remove the noise of the original image is to perform convolution on the image using a custom ultrasonic Gaussian filter kernel, removing the noise points in the image and trying to retain the edge information of the image as much as possible.

[0041] The core of the ultrasonic Gaussian kernel created in step S2 is the Gaussian function, and its two-dimensional form is expressed as:

[0042] Among them, is the value of the Gaussian kernel, which determines the weighting degree of the filter for neighboring pixels; is the standard deviation, which is used to control the expansion degree of the Gaussian distribution. The larger the value, the stronger the blurring degree; is the position coordinate relative to the center of the Gaussian kernel; is the normalization factor, which ensures that the sum of the Gaussian kernel is 1, so that the filtering process keeps the overall brightness of the image unchanged.

[0043] Using this ultrasonic Gaussian kernel for Gaussian filtering to remove the noise of the original image, the specific method is: Using the ultrasonic Gaussian kernel for the original image Perform convolution. The mathematical expression for convolution calculation is as follows:

[0044] Where is the pixel value of the original image; is the pixel value after filtering; is the weight of the Gaussian kernel; is the size of the Gaussian kernel, which is set to 5 in this embodiment; Then perform normalization calculation to ensure that the pixel value after filtering is between 0 and 255. The normalization is expressed as:

[0045] represents the denoised image.

[0046] In step S3, extracting the high-frequency details D is to calculate the difference between the original image and the blurred image to extract the high-frequency information, that is, the detailed part in the image.

[0047] As Figure 2 shown, first perform Gaussian blur processing on the denoised image to obtain the Gaussian blurred image , which is expressed as:

[0048] Where is the Gaussian kernel.

[0049] Then calculate the difference between the original image and the Gaussian blurred image , which is expressed as:

[0050] Where R is the high-frequency residual image, representing the detailed information of edges and textures in the image.

[0051] In this embodiment, Gaussian processing is performed twice. The first Gaussian denoising, that is, the parameters of the Gaussian kernel in step S2 are: , , which is used to smooth the image to remove noise. The second use of the Gaussian kernel is for sharpening, calculating the high-frequency residual image, subtracting the Gaussian blurred image from the original image. The parameters of the Gaussian kernel , .

[0052] In step S4, in order to avoid sharpening the entire image but only enhancing the regions with significant edges, a mask needs to be calculated. The specific method, as Figure 2 shown, includes: First, create a mask , represented as:

[0053] Among them, T is the threshold value, set to 5.0 in this embodiment, which controls which pixels are regarded as high-frequency regions; M is a binary mask, with a value of 1 only at the edges and 0 in the smooth regions; is the original image; is the Gaussian blurred image; To make the mask smoother, a Gaussian blur is further used to calculate the soft mask, represented as:

[0054] Among them, is the soft mask after Gaussian blur, which is used to smooth the transition of the sharpened region. In this embodiment, radius = 3 is selected as the mask blur radius to make the edge transition of the sharpened region more natural; Calculate the sharpened image, and use the weighted superposition method to add the enhanced high-frequency information back to the original image, represented as:

[0055] Among them, is the enhancement coefficient, taken as 50 in this embodiment, which is used to control the sharpening intensity; is the image after preliminary sharpening; At the same time, in order to prevent the pixel values from exceeding the display range, the pixel values are constrained, represented as: .

[0056] In step S5, the sharpened image and the original image are weighted and fused. Linear weighting is performed on the sharpened image and the original image to adapt to the sharpening degree of different regions, thereby avoiding artifacts caused by oversharpening and enhancing the clarity of the image. Specifically: Combined with the soft mask, the sharpened image and the original image are weighted and fused proportionally to make the sharpening effect more natural, represented as:

[0057] Among them, , indicating that the regions not selected by the mask remain the original image; , indicating that the regions selected by the mask are sharpened; is the mean value of the soft mask, which is used to smooth the transition of the sharpened region.

[0058] Step S6 converts the image to the Lab color space, enhances the contrast of the luminance channel, and improves the visibility of details. Such asFigure 3 As shown, the specific method is as follows: Before performing contrast enhancement, it is first necessary to convert the image from the RGB color space to the Lab color space. The purpose is to enhance only the luminance channel (L channel) without affecting the color information (A and B channels).

[0059] The three components of the Lab color space: L channel (Luminance): Controls the light and dark information of the image A channel (Green - Red): Color information, representing the change from green to red B channel (Blue - Yellow): Color information, representing the change from blue to yellow The conversion relationship of the Lab color space is as follows:

[0060]

[0061]

[0062] where is the reference value of the white point; is a non - linear transformation function used to adjust the perceived luminance, expressed as:

[0063] Then extract the L channel and calculate the cumulative distribution function ; Adjust the contrast of the L channel through histogram equalization; The transformation function of histogram equalization is expressed as:

[0064] where is the pixel value after equalization; is the cumulative distribution function of the luminance channel L; and are respectively the minimum and maximum values of the cumulative distribution.

[0065] In this embodiment, on the basis of histogram equalization, two key improvements are added, including: 1. Local area processing (Tile Grid Size): Divide the image into multiple small blocks (e.g., 8×8 blocks), and perform histogram equalization separately within each small block.

[0066] 2. Contrast limit (Clip Limit): Limit the maximum value of the histogram cumulative distribution to prevent over - enhancement in local areas and avoid noise amplification.

[0067] It is reflected in the specific parameter settings: clipLimit = 2.5; The clipLimit parameter controls the contrast enhancement strength of the local histogram. The larger the value, the stronger the enhancement effect, but it may introduce over-enhancement artifacts.

[0068] tileGridSize = (8,8), which means the image is divided into 8×8 tiles, and each tile is independently equalized to adapt to the contrast changes in different areas.

[0069] Finally, the original A and B channels are combined with the adjusted L channel to reconstruct the Lab image.

[0070] This embodiment is a fusion method of multiple image processing technologies. It optimizes image quality and improves the reliability of disease diagnosis by means of weighted fusion and other means. The method of this embodiment is used to process normal uterine ultrasound images, normal uterine contrast images and lesion uterine ultrasound images respectively. The processing process is as follows: Figures 4-6 As shown. Among them, Figure 4 It shows the original image of normal uterine ultrasound, denoising, sharpening, and contrast enhancement process. Figure 5 It shows the original image of normal uterine angiography, denoising, sharpening, and contrast enhancement process. Figure 6 The original ultrasound image of the uterine lesion, the denoising, sharpening, and contrast enhancement process are shown. The combination of the figures shows that the present invention exhibits excellent effects in the enhancement processing of various uterine medical images.

[0071] First, in the denoising stage, a custom ultrasonic Gaussian kernel is used to effectively remove noise and redundant information, making the tissue interface smoother and the structure clearer. Secondly, the unsharp mask sharpening algorithm is used to enhance the edges and details, highlight the key anatomical structures, reduce the blurred areas, and avoid the noise amplification problem that may be caused by traditional sharpening methods. Finally, the brightness distribution of the image is optimized to make the layers clearer, improve the recognition of tissues and lesion areas, and ultimately improve the doctor's visual perception, providing more intuitive and clear medical imaging support for clinical diagnosis.

[0072] Before denoising: The original ultrasound image may contain a lot of speckle noise and artifacts, which affect the clarity of tissue boundaries and may make it difficult for doctors to distinguish between normal tissue and lesion areas.

[0073] After denoising: the noise is greatly reduced, the tissue structure is smoother, and the main anatomical features are preserved.

[0074] Before sharpening: The image edges are blurred and the tissue boundaries are not clear enough, which may affect the judgment of the scope of the lesion.

[0075] After sharpening: The tissue contour is clearer, the edge contrast is enhanced, which helps doctors accurately identify the lesion area.

[0076] Before Lab color space conversion: The original image may have uneven brightness distribution, which affects the visibility of the lesion area.

[0077] After Lab color space conversion: After the brightness channel is enhanced in contrast, the details in the dark part are highlighted, the bright part will not be overexposed, the overall visual effect is clearer, the contrast of the lesion area is enhanced, and the doctor's ability to identify the diseased tissue is improved.

[0078] Example 2: This example provides a non-transitory computer-readable storage medium, on which computer instructions are stored. These computer instructions cause the computer to execute an ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking sharpening. The method includes the following steps: S1. Obtain the original image through medical imaging technology; S2. Create an ultrasonic Gaussian kernel, and use this ultrasonic Gaussian kernel to remove the noise of the original image to obtain a denoised image; S3. Perform Gaussian blur processing on the denoised image to obtain a Gaussian blurred image; calculate the difference between the original image and the Gaussian blurred image, and extract the high-frequency information in the original image; S4. Create a mask, mark the extracted high-frequency information part as the area to be sharpened, and sharpen this area to be sharpened to obtain a sharpened image; S5. Perform weighted fusion of the sharpened image and the original image to obtain a weighted image; S6. Convert the weighted image to the Lab color space and enhance the contrast of the brightness channel; S7. Restore the image with enhanced contrast to the RGB color space to generate the final enhanced image.

[0079] Example 3: This example provides an electronic device, which may include: a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus. The processor can call the logical instructions in the memory to execute an ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking sharpening. The method includes the following steps: S1. Obtain the original image through medical imaging technology; S2. Create an ultrasonic Gaussian kernel, and use this ultrasonic Gaussian kernel to remove the noise of the original image to obtain a denoised image; S3. Perform Gaussian blur processing on the denoised image to obtain a Gaussian blurred image; calculate the difference between the original image and the Gaussian blurred image, and extract the high-frequency information in the original image; S4. Create a mask, mark the extracted high-frequency information part as the area to be sharpened, and sharpen the area to be sharpened to obtain a sharpened image; S5. Perform weighted fusion on the sharpened image and the original image to obtain a weighted image; S6. Convert the weighted image to the Lab color space and enhance the contrast of the luminance channel; S7. Restore the image with enhanced contrast to the RGB color space to generate the final enhanced image.

[0080] In addition, when the logic instructions in the above-mentioned memory are implemented in the form of software functional units and sold or used as an independent product, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0081] Embodiment 4: This embodiment provides a computer program product. The computer program product includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute an ultrasonic image enhancement method based on an ultrasonic Gaussian kernel and unsharp masking. The method includes the following steps: S1. Obtain an original image through medical imaging technology; S2. Create an ultrasonic Gaussian kernel and use the ultrasonic Gaussian kernel to remove the noise of the original image to obtain a denoised image; S3. Perform Gaussian blur processing on the denoised image to obtain a Gaussian blurred image; calculate the difference between the original image and the Gaussian blurred image, and extract the high-frequency information in the original image; S4. Create a mask, mark the extracted high-frequency information part as the area to be sharpened, and sharpen the area to be sharpened to obtain a sharpened image; S5. Perform weighted fusion on the sharpened image and the original image to obtain a weighted image; S6. Convert the weighted image to the Lab color space and enhance the contrast of the luminance channel; S7. Restore the image with enhanced contrast to the RGB color space to generate the final enhanced image.

[0082] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art can understand and implement it without creative efforts.

[0083] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the essence of the above technical solution, or the part that contributes to the prior art, can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0084] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments or equivalently replace some of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking sharpening, characterized in that, Including: S1. Obtain the original image through medical imaging technology; S2. Create an ultrasonic Gaussian kernel, and use this ultrasonic Gaussian kernel to remove the noise of the original image to obtain a denoised image; S3. Perform Gaussian blur processing on the denoised image to obtain a Gaussian blurred image; calculate the difference between the original image and the Gaussian blurred image, and extract the high-frequency information in the original image; S4. Create a mask, mark the extracted high-frequency information part as the area to be sharpened, and sharpen the area to be sharpened to obtain a sharpened image; S5. Perform weighted fusion of the sharpened image and the original image to obtain a weighted image; S6. Convert the weighted image to the Lab color space and enhance the contrast of the luminance channel; S7. Restore the image with enhanced contrast to the RGB color space to generate the final enhanced image.

2. The ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking sharpening according to claim 1, wherein The core of the ultrasonic Gaussian kernel created in step S2 is the Gaussian function, and its two-dimensional form is expressed as: ； Among them, is the value of the Gaussian kernel; is the standard deviation, which is used to control the extent of the Gaussian distribution; are the position coordinates relative to the center of the Gaussian kernel; is the normalization factor to ensure that the sum of the Gaussian kernels is 1.

3. The ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking sharpening according to claim 2, wherein In step S2, use this ultrasonic Gaussian kernel for Gaussian filtering to remove the noise of the original image. The specific method is: Convolve the original image using an ultrasonic Gaussian kernel The mathematical expression for the convolution calculation is as follows: ； Among them, is the pixel value of the original image; is the pixel value after filtering; is the weight of the Gaussian kernel; is the size of the Gaussian kernel; Then perform normalization calculation to ensure that the pixel values after filtering are between 0 and 255. The normalization is expressed as: ； Denotes the denoised image.

4. The ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking sharpening according to claim 3, characterized in that In step S3, the denoised image is subjected to Gaussian blur processing to obtain a Gaussian blurred image , which is expressed as: ； wherein is a Gaussian kernel, and the parameter of the Gaussian kernel , .

5. The ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking sharpening according to claim 4, characterized in that, In step S3, the high-frequency information is obtained from the difference between the original image and the Gaussian blurred image and is expressed as: ； Among them, R is a high-frequency residual image, representing the detailed information of edges and textures in the image.

6. The ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking sharpening according to claim 1, characterized in that, In step S4, a mask is created, the extracted high-frequency detail part is marked as the area to be sharpened, and the area to be sharpened is sharpened to obtain a sharpened image ; The specific method is as follows: First, create a mask , denoted as: ； Among them, T is a threshold value that controls which pixels are regarded as high-frequency regions; M is a binary mask with a value of 1 only at the edges and 0 in the smooth regions; is the original image; is the Gaussian blurred image; Then use Gaussian blur to calculate the soft mask, which is expressed as: ； Among them, is the soft mask after Gaussian blur, which is used to smooth the transition of the sharpened area; is the Gaussian kernel; Calculate the sharpened image, and use the weighted superposition method to add the enhanced high-frequency information back to the original image, which is expressed as: ； Among them, is the enhancement coefficient, which is used to control the sharpening intensity; is the image after preliminary sharpening; At the same time, constrain the pixel values, which is expressed as: 。 7. The ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking sharpening according to claim 6, characterized in that, In step S5, perform weighted fusion of the sharpened image and the original image to obtain a weighted image. Specifically: Sharpen the image in combination with a soft mask with the original image and fuse them proportionally and weighted, expressed as: ； Among them, , it means that the area not selected by the mask remains the original image; , it means that the area selected by the mask is enhanced and sharpened; is the mean value of the soft mask, which is used to smooth the transition of the sharpened area.

8. The ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking sharpening according to claim 1, characterized in that, In step S6, when enhancing the contrast of the luminance channel, divide the image into multiple small blocks, and perform histogram equalization in each small block to enhance the contrast of the luminance channel; The transformation function of histogram equalization is expressed as: ； Among them, is the pixel value after equalization; is the cumulative distribution function of the luminance channel L; and are the minimum and maximum values of the cumulative distribution, respectively; When using histogram equalization to enhance the contrast of the luminance channel, limit the maximum value of the cumulative distribution of the histogram.

9. A non-transitory computer-readable storage medium, characterized in that, It stores computer instructions, and these computer instructions enable the computer to execute the ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking described in any one of claims 1-8.

10. An electronic device, characterized in that, Including: A processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete mutual communication through the communication bus. The processor calls the logical instructions in the memory to execute the ultrasonic image enhancement method based on ultrasonic Gaussian kernel and unsharp masking described in any one of claims 1-8.

Images