Ultrasonic image optimization processing method, system and device

Abstract

The present invention discloses an ultrasonic image optimization processing method, system and device, which downsamples the original ultrasonic image to obtain ultrasonic sampling images of different resolutions, and determines the original ultrasonic image and the pre-edge-enhanced ultrasonic image; performs edge enhancement processing on the pre-edge-enhanced ultrasonic image according to a preset image edge enhancement strategy to obtain an ultrasonic enhanced image; fuses the pre-edge-enhanced ultrasonic image and the ultrasonic enhanced image to obtain an ultrasonic fused image; upsamples the ultrasonic fused image to obtain an upsampled image, and fuses and reconstructs the upsampled image and the original ultrasonic image to obtain a final ultrasonic enhanced image. It can be seen that the present application can not only enhance the image edge, but also make the processed image more natural, and at the same time can meet the clinical real-time requirements for the method.

Description

Technical Field

[0001] The present invention relates to the field of ultrasonic image processing, and in particular to an ultrasonic image optimization processing method, system and device. Background Art

[0002] At present, in order to improve the quality of ultrasound images, the commonly used technical means are: according to the tissue structure contained in the ultrasound image, the ultrasound image is divided into a structural area and a non-structural area, and the structural area is anisotropically processed and the non-structural area is isotropically processed to achieve the purpose of enhancing the edge of the ultrasound image, thereby improving the quality of the ultrasound image. However, different image processing methods are used for different areas obtained by ultrasound image segmentation, resulting in obvious differences between different areas, which makes the ultrasound image after quality improvement less natural to a certain extent.

[0003] Therefore, how to provide a solution for optimizing the quality of ultrasound images is a problem that technicians in this field currently need to solve. Summary of the invention

[0004] The purpose of the present invention is to provide an ultrasound image optimization processing method, system and device, which can not only enhance the image edge, but also make the processed image more natural, and at the same time meet the clinical real-time requirements of the method.

[0005] In order to solve the above technical problems, the present invention provides an ultrasonic image optimization processing method, comprising:

[0006] Downsampling the original ultrasonic image to obtain ultrasonic sampling images with different resolutions, and determining the original ultrasonic image and the pre-edge-enhanced ultrasonic image;

[0007] Performing edge enhancement processing on the pre-edge-enhanced ultrasound image according to a preset image edge enhancement strategy to obtain an ultrasound-enhanced image;

[0008] fusing the pre-edge-enhanced ultrasound image with the ultrasound-enhanced image to obtain an ultrasound-fused image;

[0009] The ultrasound fusion image is upsampled to obtain an upsampled image, and the upsampled image and the original ultrasound image are fused and reconstructed to obtain a final ultrasound enhanced image.

[0010] Preferably, the process of downsampling the original ultrasonic image to obtain ultrasonic sampling images of different resolutions and determining the original ultrasonic image and the pre-edge-enhanced ultrasonic image includes:

[0011] The original ultrasonic image is downsampled in three layers to obtain three layers of ultrasonic sampling images with different resolutions; wherein the resolution of the first layer of ultrasonic sampling image is greater than the resolution of the second layer of ultrasonic sampling image and greater than the resolution of the third layer of ultrasonic sampling image;

[0012] Using the first layer of ultrasonic sampling images as original ultrasonic images, and using the second layer of ultrasonic sampling images and the third layer of ultrasonic sampling images as pre-edge-enhanced ultrasonic images;

[0013] Accordingly, the process of performing edge enhancement processing on the pre-edge-enhanced ultrasound image according to the preset image edge enhancement strategy to obtain the ultrasound enhanced image includes:

[0014] Performing edge enhancement processing on the second layer of ultrasonic sampling images according to a preset image edge enhancement strategy to obtain a second layer of ultrasonic enhanced images;

[0015] Performing edge enhancement processing on the third layer of ultrasonic sampling images according to a preset image edge enhancement strategy to obtain a third layer of ultrasonic enhanced images;

[0016] The process of fusing the pre-edge-enhanced ultrasound image with the ultrasound-enhanced image to obtain an ultrasound-fused image; upsampling the ultrasound-fused image to obtain an upsampled image, and fusing and reconstructing the upsampled image with the original ultrasound image to obtain a final ultrasound-enhanced image includes:

[0017] Fusing the third layer of ultrasonic sampling image with the third layer of ultrasonic enhanced image, and upsampling the fused ultrasonic image to obtain a third layer of ultrasonic upsampling image;

[0018] fusing and reconstructing the second-layer ultrasound sampling image, the second-layer ultrasound enhanced image, and the third-layer ultrasound up-sampled image, and up-sampling the fused and reconstructed ultrasound image to obtain a second-layer ultrasound up-sampled image;

[0019] The first layer of ultrasonic sampling images and the second layer of ultrasonic up-sampling images are fused and reconstructed to obtain a final ultrasonic enhanced image.

[0020] Preferably, the process of performing edge enhancement processing on the third layer of ultrasonic sampling images according to a preset image edge enhancement strategy to obtain a third layer of ultrasonic enhanced images includes:

[0021] The third layer of ultrasonic sampling images is subjected to multi-scale edge enhancement processing to obtain a third layer of ultrasonic enhanced images.

[0022] Preferably, the process of performing multi-scale edge enhancement processing on the third layer of ultrasonic sampling images to obtain the third layer of ultrasonic enhanced images includes:

[0023] The ultrasonic image that has been pre-processed with multi-scale edge enhancement is subjected to isotropic filtering and denoising to obtain the denoised ultrasonic image. Wherein, an iterative method is used to perform multi-scale edge enhancement; n is the number of iterations, and its maximum value is equal to a preset iteration threshold;

[0024] Ultrasound images Inputting into the pre-constructed odd filter and even filter respectively, obtaining odd filter responses and even filter responses at multiple scales, and calculating the difference between the odd and even filter responses to obtain the multi-scale edge responses;

[0025] The edge responses at multiple scales are fused to obtain an edge image, and the ultrasound image is analyzed based on the edge image. Perform multi-scale edge enhancement and image denoising to obtain an ultrasonic image

[0026] When the number of iterations of multi-scale edge enhancement is less than the preset iteration threshold, the ultrasound image The ultrasound image that has been pre-processed with multi-scale edge enhancement enters the next iterative processing; when the number of iterations of the multi-scale edge enhancement is equal to the preset iteration threshold, the iteration stops.

[0027] Preferably, the difference between the odd and even filter responses is calculated to obtain a multi-scale edge response; the edge responses of multiple scales are fused to obtain an edge image, and the ultrasound image is analyzed based on the edge image. Perform multi-scale edge enhancement and image denoising to obtain an ultrasonic image The process includes:

[0028] According to the edge response relation Compute the difference between the odd and even filter responses to get the edge response on scale s in, is the even filter response on scale s; is the odd filter response on scale s; T s is a noise threshold related to the scale s; x is a pixel point in the image;

[0029] According to the response fusion relation The edge responses at multiple scales are fused to obtain the edge image Eg3; The value range of is [0, 1]; m is the number of filter scales;

[0030] According to the image multi-scale enhancement relationship Ultrasound images Perform multi-scale edge enhancement and image denoising to obtain an ultrasonic image Among them, Δt is the time step and δ3 is the scale factor.

[0031] Preferably, the process of performing edge enhancement processing on the second layer of ultrasound sampling images according to a preset image edge enhancement strategy to obtain a second layer of ultrasound enhanced images includes:

[0032] The second layer of ultrasonic sampling images is subjected to multi-directional edge enhancement processing to obtain a second layer of ultrasonic enhanced images.

[0033] Preferably, the process of performing multi-directional edge enhancement processing on the second layer of ultrasonic sampling images to obtain the second layer of ultrasonic enhanced images includes:

[0034] Enhance the relationship in multiple directions according to the preset image Performing multi-directional edge enhancement processing and image denoising processing on the second-layer ultrasonic sampling image within a preset edge enhancement time T1 to obtain a second-layer ultrasonic enhanced image;

[0035] in, is the gradient operator; || is the gradient value; t is the time operator; k1 is the parameter for controlling smoothing; u0 is the initial iterative image; u is the ultrasound image obtained after the last diffusion process; β is a hyperparameter, β∈[0,1]; Eg is a phase-based edge operator with a value range of [0,1]; x is a pixel point in the image; g(x) divides the ultrasound image into two regions, Ω1={x∈Ω,g(x)≈1} and Ω2={x∈Ω,0≤g(x)<1}, Ω=Ω1+Ω2; ε represents a positive constant; s is a certain scale of the filter; m is the number of filter scales; F s is the phase-based filter feature at the s-th scale; is the even filter response on scale s; is the odd filter response on scale s; T s is a noise threshold related to the scale s.

[0036] Preferably, the process of fusing the third layer of ultrasound sampling images with the third layer of ultrasound enhanced images, and upsampling the fused ultrasound images to obtain the third layer of ultrasound upsampled images includes:

[0037] According to the preset image rough fusion relationship The third layer ultrasonic sampling image I3 is roughly fused with the third layer ultrasonic enhanced image Eh3 to obtain a third layer ultrasonic rough fusion image Fu3; wherein Th3 is a given threshold; μ is a parameter for controlling the degree of image edge enhancement; α is a parameter for controlling the degree of image enhancement; Eg3 is an edge image of the third layer ultrasonic sampling image, and its value range is [0, 1];

[0038] Upsampling the third-layer ultrasonic rough fusion image Fu3 to obtain a third-layer ultrasonic upsampled image U3;

[0039] According to the preset image fusion relationship Performing diffusion processing on the third-layer ultrasound upsampling image U3 within a preset fine fusion time T2 to obtain a third-layer ultrasound fusion reconstructed image R3; wherein U is the ultrasound image obtained after the last diffusion processing; div is a divergence operator; is the gradient operator; || is the gradient value; t is the time operator; U3 is the initial iterative image; k2 is the factor controlling diffusion.

[0040] Preferably, the process of fusing and reconstructing the second-layer ultrasound sampling image, the second-layer ultrasound enhanced image and the third-layer ultrasound up-sampled image, and up-sampling the fused and reconstructed ultrasound image to obtain the second-layer ultrasound up-sampled image includes:

[0041] According to the preset image weighted fusion relationship F2=w1Fu2+w2R3-sign(w1Fu2+w2R3-Th2)w3I2, the second layer of ultrasonic sampling image I2, the second layer of ultrasonic enhanced image Fu2 and the third layer of ultrasonic fusion reconstructed image R3 are fused and reconstructed to obtain a second layer of ultrasonic weighted fusion image F2; wherein Th2 is a given threshold, and w1, w2 and w3 are predefined coefficients;

[0042] The second-layer ultrasonic weighted fusion image F2 is upsampled to obtain a second-layer ultrasonic upsampled image U2.

[0043] Preferably, the process of fusing and reconstructing the first layer of ultrasound sampling images and the second layer of ultrasound upsampling images to obtain a final ultrasound enhanced image includes:

[0044] According to the preset image fusion relationship E=γU2+(1-γ)I1, the first layer ultrasound sampling image I1 and the second layer ultrasound up-sampling image U2 are fused and reconstructed to obtain the final ultrasound enhanced image E; wherein γ is a control factor.

[0045] In order to solve the above technical problems, the present invention also provides an ultrasonic image optimization processing system, comprising:

[0046] A downsampling module is used to downsample the original ultrasonic image to obtain ultrasonic sampling images with different resolutions;

[0047] An image determination module, used for determining an original ultrasonic image and a pre-edge-enhanced ultrasonic image from the ultrasonic sampling image;

[0048] An image enhancement module, used for performing edge enhancement processing on the pre-edge-enhanced ultrasound image according to a preset image edge enhancement strategy to obtain an ultrasound-enhanced image;

[0049] An image fusion module, used for fusing the pre-edge-enhanced ultrasound image with the ultrasound-enhanced image to obtain an ultrasound-fused image;

[0050] The image reconstruction module is used to upsample the ultrasound fusion image to obtain an upsampled image, and to fuse and reconstruct the upsampled image with the original ultrasound image to obtain a final ultrasound enhanced image.

[0051] In order to solve the above technical problems, the present invention also provides an ultrasonic image optimization processing device, comprising:

[0052] Memory for storing computer programs;

[0053] A processor is used to implement the steps of any of the above-mentioned ultrasound image optimization processing methods when executing the computer program.

[0054] The present invention provides an ultrasonic image optimization processing method, which downsamples the original ultrasonic image to obtain ultrasonic sampling images of different resolutions, determines the original ultrasonic image and the pre-edge-enhanced ultrasonic image; performs edge enhancement processing on the pre-edge-enhanced ultrasonic image according to a preset image edge enhancement strategy to obtain an ultrasonic enhanced image; fuses the pre-edge-enhanced ultrasonic image and the ultrasonic enhanced image to obtain an ultrasonic fused image; upsamples the ultrasonic fused image to obtain an upsampled image, and fuses and reconstructs the upsampled image and the original ultrasonic image to obtain a final ultrasonic enhanced image. It can be seen that the present application can not only enhance the image edge, but also make the processed image more natural, and at the same time can meet the clinical real-time requirements for the method.

[0055] The present invention also provides an ultrasonic image optimization processing system and device, which have the same beneficial effects as the above-mentioned optimization processing method. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the prior art and the drawings required for use in the embodiments are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0057] Figure 1 A flowchart of an ultrasonic image optimization processing method provided by an embodiment of the present invention;

[0058] Figure 2 A schematic diagram of an ultrasonic image optimization processing principle provided by an embodiment of the present invention;

[0059] Figure 3 A schematic diagram of the structure of an ultrasonic image optimization processing system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The core of the present invention is to provide an ultrasound image optimization processing method, system and device, which can not only enhance the image edge, but also make the processed image more natural, and at the same time meet the clinical real-time requirements of the method.

[0061] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] Please refer to Figure 1 , Figure 1 The present invention provides a flowchart of an ultrasonic image optimization processing method according to an embodiment of the present invention.

[0063] The ultrasound image optimization processing method comprises:

[0064] Step S1: down-sample the original ultrasonic image to obtain ultrasonic sampling images of different resolutions, and determine the original ultrasonic image and the pre-edge-enhanced ultrasonic image.

[0065] Specifically, first, the original ultrasound image to be optimized is obtained, and then the obtained original ultrasound image is downsampled. The main purpose is to obtain ultrasound sampling images of different resolutions, and the secondary purpose is to reduce the amount of preprocessing data of the ultrasound image to reduce the subsequent image processing time.

[0066] More specifically, the following downsampling methods can be used for downsampling the original ultrasonic image: 1) Downsampling based on the spatial domain (direct extraction method): downsampling the original ultrasonic image, specifically, extracting a certain number of units of "rows and columns" of the original image data to obtain an ultrasonic sampling image; such as 1, 2, ..., k in one-dimensional data, extracting a sample point every 2 units, and the extracted samples are 1, 3, ..., until the entire data is extracted. 2) Downsampling based on the spatial domain (extraction method after filtering): first filter the original image data to smooth the image and suppress noise, and then extract a certain number of units of "rows and columns" of the filtered original image data to obtain an ultrasonic sampling image. Of course, the present application can also use other image downsampling methods to obtain ultrasonic sampling images of different resolutions, and the present application does not make any special limitations here.

[0067] Based on this, after obtaining ultrasonic sampling images of different resolutions, the present application determines the original ultrasonic image (i.e., the ultrasonic sampling image without edge enhancement) and the pre-edge-enhanced ultrasonic image from the ultrasonic sampling image for subsequent image edge enhancement processing. More specifically, the edge enhancement of ultrasonic sampling images of different resolutions can be set as follows: ultrasonic sampling images of higher resolution do not require edge enhancement, and ultrasonic sampling images of lower resolution require edge enhancement. Such a setting helps to improve the subsequent image fusion effect. The present application does not make any special restrictions here, and it is set according to actual conditions.

[0068] Step S2: performing edge enhancement processing on the pre-edge-enhanced ultrasound image according to a preset image edge enhancement strategy to obtain an ultrasound-enhanced image.

[0069] Specifically, the present application needs to set in advance an image edge enhancement strategy for guiding the edge enhancement operation of the ultrasound image. After determining the pre-edge-enhanced ultrasound image, the pre-edge-enhanced ultrasound image is edge enhanced according to the set image edge enhancement strategy to obtain an ultrasound enhanced image.

[0070] Step S3: Fusing the pre-edge-enhanced ultrasound image and the ultrasound-enhanced image to obtain an ultrasound-fused image.

[0071] Specifically, after obtaining the ultrasound enhanced image, the present application fuses the ultrasound image before edge enhancement processing and the ultrasound enhanced image obtained after edge enhancement processing to obtain an ultrasound fused image for subsequent image reconstruction.

[0072] Step S4: up-sampling the ultrasound fusion image to obtain an up-sampled image, and fusing and reconstructing the up-sampled image and the original ultrasound image to obtain a final ultrasound enhanced image.

[0073] Specifically, after obtaining the ultrasound fusion image, the present application upsamples the ultrasound fusion image to obtain an upsampled image, and then fuses and reconstructs the upsampled image and the original ultrasound image to obtain the final ultrasound enhanced image. It can be seen that the present application combines ultrasound images of different resolutions to reconstruct the ultrasound image, which can not only enhance the image edge, but also make the processed image more natural, and at the same time can meet the clinical real-time requirements for the method.

[0074] The present invention provides a method for improving the quality of ultrasonic images, which downsamples the original ultrasonic image to obtain ultrasonic sampling images of different resolutions, determines the original ultrasonic image and the pre-edge-enhanced ultrasonic image; performs edge enhancement processing on the pre-edge-enhanced ultrasonic image according to a preset image edge enhancement strategy to obtain an ultrasonic enhanced image; fuses the pre-edge-enhanced ultrasonic image and the ultrasonic enhanced image to obtain an ultrasonic fused image; upsamples the ultrasonic fused image to obtain an upsampled image, and fuses and reconstructs the upsampled image and the original ultrasonic image to obtain a final ultrasonic enhanced image. It can be seen that the present application can not only enhance the image edge, but also make the processed image more natural, and at the same time can meet the clinical real-time requirements for the method.

[0075] Based on the above embodiments:

[0076] Please refer to Figure 2 , Figure 2 A schematic diagram of an ultrasonic image optimization processing principle provided by an embodiment of the present invention.

[0077] As an optional embodiment, the process of downsampling the original ultrasonic image to obtain ultrasonic sampling images with different resolutions and determining the original ultrasonic image and the pre-edge-enhanced ultrasonic image includes:

[0078] The original ultrasonic image is downsampled in three layers to obtain three layers of ultrasonic sampling images with different resolutions; wherein the resolution of the first layer of ultrasonic sampling image is greater than the resolution of the second layer of ultrasonic sampling image and greater than the resolution of the third layer of ultrasonic sampling image;

[0079] The first layer of ultrasonic sampling images is used as the original ultrasonic image, and the second layer of ultrasonic sampling images and the third layer of ultrasonic sampling images are used as pre-edge-enhanced ultrasonic images;

[0080] Accordingly, the process of performing edge enhancement processing on the pre-edge-enhanced ultrasound image according to the preset image edge enhancement strategy to obtain the ultrasound enhanced image includes:

[0081] Performing edge enhancement processing on the second layer of ultrasonic sampling images according to a preset image edge enhancement strategy to obtain a second layer of ultrasonic enhanced images;

[0082] Performing edge enhancement processing on the third layer of ultrasonic sampling images according to a preset image edge enhancement strategy to obtain a third layer of ultrasonic enhanced images;

[0083] The process of fusing the pre-edge-enhanced ultrasound image and the ultrasound-enhanced image to obtain an ultrasound-fused image; upsampling the ultrasound-fused image to obtain an upsampled image, and fusing and reconstructing the upsampled image and the original ultrasound image to obtain a final ultrasound-enhanced image includes:

[0084] The third layer of ultrasonic sampling image is fused with the third layer of ultrasonic enhanced image, and the fused ultrasonic image is upsampled to obtain a third layer of ultrasonic upsampled image;

[0085] The second layer of ultrasonic sampling image, the second layer of ultrasonic enhanced image and the third layer of ultrasonic up-sampling image are fused and reconstructed, and the fused and reconstructed ultrasonic image is up-sampled to obtain a second layer of ultrasonic up-sampling image;

[0086] The first layer of ultrasonic sampling images and the second layer of ultrasonic upsampling images are fused and reconstructed to obtain the final ultrasonic enhanced image.

[0087] Specifically, the present application performs three-layer downsampling on the original ultrasound image, and correspondingly obtains three layers of ultrasound sampling images with different resolutions, and the resolutions from high to low are the first layer ultrasound sampling image I1, the second layer ultrasound sampling image I2, and the third layer ultrasound sampling image I3.

[0088] Considering that the ultrasonic sampling images with higher resolution do not need edge enhancement, while the ultrasonic sampling images with lower resolution need edge enhancement, such a setting helps to improve the subsequent image fusion effect, so the present application specifically uses the first layer of ultrasonic sampling images as the original ultrasonic images, that is, the ultrasonic images without edge enhancement, and uses the second layer of ultrasonic sampling images and the third layer of ultrasonic sampling images as pre-edge-enhanced ultrasonic images. Specifically, the second layer of ultrasonic sampling images is edge-enhanced to obtain the second layer of ultrasonic enhanced images; the third layer of ultrasonic sampling images is edge-enhanced to obtain the third layer of ultrasonic enhanced images.

[0089] Based on this, Figure 2As shown, the ultrasonic image processing and reconstruction process of the present application specifically includes: 1) fusing the third layer ultrasonic sampling image before edge enhancement of the third layer image with the third layer ultrasonic enhanced image obtained after edge enhancement to obtain a fused ultrasonic image, and upsampling the fused ultrasonic image to obtain a third layer ultrasonic upsampling image; 2) fusing and reconstructing the second layer ultrasonic sampling image before edge enhancement of the second layer image and the second layer ultrasonic enhanced image obtained after edge enhancement together with the third layer ultrasonic upsampling image to obtain a fused and reconstructed ultrasonic image, and upsampling the fused and reconstructed ultrasonic image to obtain a second layer ultrasonic upsampling image; 3) fusing and reconstructing the first layer ultrasonic sampling image with the second layer ultrasonic upsampling image to obtain a final ultrasonic enhanced image.

[0090] As an optional embodiment, the process of performing edge enhancement processing on the third layer of ultrasonic sampling images according to a preset image edge enhancement strategy to obtain the third layer of ultrasonic enhanced images includes:

[0091] The third layer of ultrasonic sampling images is subjected to multi-scale edge enhancement processing to obtain a third layer of ultrasonic enhanced images.

[0092] Specifically, considering that ultrasound sampling images with lower resolution are more suitable for multi-scale edge enhancement processing, the present application specifically performs multi-scale edge enhancement processing on the third layer of ultrasound sampling image I3 to obtain a third layer of ultrasound enhanced image.

[0093] As an optional embodiment, the process of performing multi-scale edge enhancement processing on the third layer of ultrasonic sampling images to obtain the third layer of ultrasonic enhanced images includes:

[0094] The ultrasonic image that has been pre-processed with multi-scale edge enhancement is subjected to isotropic filtering and denoising to obtain the denoised ultrasonic image. Wherein, an iterative method is used to perform multi-scale edge enhancement; n is the number of iterations, and its maximum value is equal to a preset iteration threshold;

[0095] Ultrasound images Inputting into the pre-constructed odd filter and even filter respectively, obtaining odd filter responses and even filter responses at multiple scales, and calculating the difference between the odd and even filter responses to obtain the multi-scale edge responses;

[0096] The edge responses at multiple scales are fused to obtain edge images, and the ultrasound images are analyzed based on the edge images. Perform multi-scale edge enhancement and image denoising to obtain an ultrasonic image

[0097] When the number of iterations of multi-scale edge enhancement is less than the preset iteration threshold, the ultrasound image The ultrasound image that has been pre-processed with multi-scale edge enhancement enters the next iterative processing; when the number of iterations of the multi-scale edge enhancement is equal to the preset iteration threshold, the iteration stops.

[0098] Specifically, the present application does not describe this embodiment first, but describes it in detail in conjunction with the subsequent embodiments.

[0099] As an optional embodiment, the difference between the odd and even filter responses is calculated to obtain a multi-scale edge response; the edge responses of multiple scales are fused to obtain an edge image, and the ultrasound image is analyzed based on the edge image. Perform multi-scale edge enhancement and image denoising to obtain an ultrasonic image The process includes:

[0100] According to the edge response relation Compute the difference between the odd and even filter responses to get the edge response on scale s in, is the even filter response on scale s; is the odd filter response on scale s; T s is a noise threshold related to the scale s; x is a pixel point in the image;

[0101] According to the response fusion relation The edge responses at multiple scales are fused to obtain the edge image Eg3; The value range of is [0, 1]; m is the number of filter scales;

[0102] According to the image multi-scale enhancement relationship Ultrasound images Perform multi-scale edge enhancement and image denoising to obtain an ultrasonic image Among them, Δt is the time step and δ3 is the scale factor.

[0103] Specifically, this embodiment introduces the principle of multi-scale image edge enhancement:

[0104] At present, traditional image edge enhancement methods usually detect image edges through changes in grayscale information, that is, gradients. However, in ultrasonic images, due to the influence of unfavorable factors such as uneven grayscale and high noise, grayscale-based image edge detection may fail. Therefore, the present application adopts a phase consistency method to detect image edges, that is, the phase information of the ultrasonic image is used. In this way, both grayscale features such as step features of ultrasonic images and Mach band phenomena of ultrasonic images can be detected, and the reliability of image edge detection is relatively high.

[0105] The specific principle of the phase-based image edge detection method is: the image is filtered with an odd filter and an even filter respectively. When the response of the odd filter and the even filter differ greatly, the pixel point is often located on the edge of the image. More specifically, both the odd filter and the even filter have multiple scales. Applying the odd filter and the even filter to image edge detection can obtain multi-scale edge responses, and then fusing the edge responses of multiple scales to obtain the edge of the image, that is, the edge image.

[0106] Based on this, this application sets the image multi-scale enhancement relationship in advance The setting principle is: multi-scale image edge enhancement is performed in an iterative manner, and when the number of iterations is equal to a preset iteration threshold, the iteration stops. More specifically, when the third layer ultrasound sampling image is iterated for the nth time, the multi-scale image edge enhancement process is as follows: 1) the ultrasound image obtained in the previous iteration is subjected to isotropic filtering denoising, such as using isotropic filtering methods such as mean filtering and median filtering to remove noise from the ultrasound image and obtain a denoised ultrasound image 2) Ultrasound image Input into the pre-constructed odd filter and even filter respectively to obtain the odd filter response and even filter response on multiple scales; 3) According to the edge response relation Calculate the difference between the odd and even filter responses to get the edge response at the sth scale at the nth iteration 4) According to the response fusion relationship The edge responses of multiple scales are fused to obtain the edge image corresponding to the third layer of ultrasonic sampling image at the nth iteration. 5) According to the image multi-scale enhancement relationship Ultrasound imaging Perform multi-scale edge enhancement and image denoising to obtain the ultrasound image after the nth iteration This achieves multi-scale image edge enhancement.

[0107] As an optional embodiment, the process of performing edge enhancement processing on the second layer of ultrasonic sampling images according to a preset image edge enhancement strategy to obtain the second layer of ultrasonic enhanced images includes:

[0108] The second layer of ultrasonic sampling images is subjected to multi-directional edge enhancement processing to obtain a second layer of ultrasonic enhanced images.

[0109] Specifically, considering that higher-resolution ultrasonic sampling images are more suitable for multi-directional edge enhancement processing, the present application specifically performs multi-directional edge enhancement processing on the second-layer ultrasonic sampling image I2 to obtain a second-layer ultrasonic enhanced image.

[0110] In summary, the present application provides different edge enhancement processing methods for ultrasound images with different layers of pre-edge enhancement, specifically including a multi-directional edge enhancement processing method and a multi-scale edge enhancement processing method.

[0111] As an optional embodiment, the process of performing multi-directional edge enhancement processing on the second layer of ultrasonic sampling images to obtain the second layer of ultrasonic enhanced images includes:

[0112] Enhance the relationship in multiple directions according to the preset image Performing multi-directional edge enhancement processing and image denoising processing on the second-layer ultrasonic sampling image within a preset edge enhancement time T1 to obtain a second-layer ultrasonic enhanced image;

[0113] in, is the gradient operator; || is the gradient value; t is the time operator; k1 is the parameter for controlling smoothing; u0 is the initial iterative image; u is the ultrasound image obtained after the last diffusion process; β is a hyperparameter, β∈[0,1]; Eg is a phase-based edge operator with a value range of [0,1]; x is a pixel point in the image; g(x) divides the ultrasound image into two regions, Ω1={x∈Ω,g(x)≈1} and Ω2={x∈Ω,0≤g(x)<1}, Ω=Ω1+Ω2; ε represents a positive constant; s is a certain scale of the filter; m is the number of filter scales; F s is the phase-based filter feature at the s-th scale; is the even filter response on scale s; is the odd filter response on scale s; T s is a noise threshold related to the scale s.

[0114] Specifically, this embodiment introduces the principle of multi-directional image edge enhancement:

[0115] At present, anisotropic diffusion models represented by PM (Perona-Malik algorithm) are usually used for multi-directional image edge enhancement, which can smooth the image while retaining the image edge. Specifically, the basic principle of the PM model is to use the gradient operator to control diffusion smoothing. When the gradient value is large, the image is smoothed less in this area through the smaller diffusion coefficient in the diffusion equation, thereby maintaining the edge; conversely, when the gradient value is small, the image is smoothed more in this area through the larger diffusion coefficient in the diffusion equation. However, the gradient operator of the PM model is calculated by the change of the image grayscale information. Due to the influence of unfavorable factors such as uneven grayscale and large noise, ultrasound images are very sensitive to the gradient operator based on grayscale changes. Therefore, for ultrasound images, the image edge enhancement effect of the PM model is often poor.

[0116] To solve the above problems, the anisotropic model proposed in this application uses a phase-based edge operator to construct the diffusion equation, which is mathematically defined as: Among them, Eg is the phase-based edge operator, which is mathematically expressed as: (ε plays a role in avoiding division by zero); g(x) divides the ultrasound image into two regions, Ω1={x∈Ω,g(x)≈1} and Ω2={x∈Ω,0≤g(x)<1}, Ω=Ω1+Ω2.

[0117] At the same time, considering that the PM model only considers the influence of local gradients, resulting in poor overall image enhancement effect, the anisotropic model proposed in this application comprehensively considers the influence of local gradients and overall image changes, and its mathematical definition is: Thereby improving the overall effect of image enhancement.

[0118] In addition, it should be noted that the above-mentioned image edge enhancement solution not only realizes the enhancement of the image edge well, but also removes the image noise while enhancing the image edge, and the effect is good.

[0119] As an optional embodiment, the process of fusing the third layer of ultrasonic sampling images with the third layer of ultrasonic enhanced images, and upsampling the fused ultrasonic images to obtain the third layer of ultrasonic upsampled images includes:

[0120] According to the preset image rough fusion relationship The third-layer ultrasonic sampling image I3 and the third-layer ultrasonic enhanced image Eh3 are roughly fused to obtain the third-layer ultrasonic rough fusion image Fu3; wherein Th3 is a given threshold; μ is a parameter for controlling the degree of image edge enhancement; α is a parameter for controlling the degree of image enhancement; Eg3 is the edge image of the third-layer ultrasonic sampling image, and its value range is [0, 1];

[0121] Upsampling the third-layer ultrasonic rough fusion image Fu3 to obtain the third-layer ultrasonic upsampled image U3;

[0122] According to the preset image fusion relationship The third-layer ultrasound upsampling image U3 is diffused within the preset fine fusion time T2 to obtain the third-layer ultrasound fusion reconstructed image R3; wherein U is the ultrasound image obtained after the last diffusion processing; div is the divergence operator; is the gradient operator; || is the gradient value; t is the time operator; U3 is the initial iterative image; k2 is the factor controlling diffusion.

[0123] Specifically, the third-layer ultrasound image reconstruction process is completed by image coarse fusion, image upsampling and image fine fusion:

[0124] 1) Image coarse fusion: The image coarse fusion process of the present application not only considers the third-layer ultrasonic enhanced image Eh3 and the third-layer ultrasonic sampling image I3 after diffusion processing, but also considers the edge image Eg3 of the third-layer ultrasonic image. When the value of the edge image is greater than a certain threshold, the importance of the edge image needs to be enhanced, that is, the third-layer ultrasonic enhanced image Eh3 is fused with the third-layer ultrasonic sampling image I3 with a larger weight; conversely, when the value of the edge image is less than a certain threshold, the importance of the edge image needs to be weakened, that is, the third-layer ultrasonic enhanced image Eh3 is fused with the third-layer ultrasonic sampling image I3 with a smaller weight. Specifically, the fusion weight of the third-layer ultrasonic enhanced image Eh3 is designed to be positively correlated with the edge image Eg3. When the value of the edge image Eg3 is larger, the fusion weight of the third-layer ultrasonic enhanced image Eh3 is also larger.

[0125] Based on this, according to the edge image Eg3, the third layer of ultrasonic enhanced image Eh3 and the third layer of ultrasonic sampling image I3 are roughly fused to obtain the third layer of ultrasonic rough fusion image Fu3: Among them, sign is the sign function, Th3 is the given threshold, when Eg3-Th3>0, sign(Eg3-Th3) takes a positive value, otherwise it takes a negative value.

[0126] 2) Image upsampling: The third-layer ultrasonic rough fusion image Fu3 is upsampled to obtain the third-layer ultrasonic upsampled image U3. Specifically, upsampling methods such as cubic and bilinear can be used.

[0127] 3) Image detail fusion: The above-mentioned image upsampling method belongs to a linear model. Although it is simple and easy to implement, it limits the details of its ability to restore high frequencies. In the field of medical imaging, doctors need more image details to make accurate judgments. The details of the image belong to the area where the grayscale value changes greatly, but noise also appears in this area, so this application uses a diffusion model and uses detail information such as gradient information to improve the image resolution without amplifying the noise, thereby reducing the impact of noise on the reconstructed image. At the same time, considering that the change of the global image plays a very important role in the integrity of the reconstructed image, the diffusion model of this application not only considers the change of the local gradient, but also considers the change of the global grayscale information. Its mathematical definition is: Therefore, after the third-layer ultrasound upsampling image U3 is diffused, a third-layer ultrasound fusion reconstructed image R3 is obtained.

[0128] As an optional embodiment, a process of fusing and reconstructing a second-layer ultrasonic sampling image, a second-layer ultrasonic enhanced image, and a third-layer ultrasonic upsampled image, and upsampling the fused and reconstructed ultrasonic image to obtain a second-layer ultrasonic upsampled image includes:

[0129] According to the preset image weighted fusion relationship F2=w1Fu2+w2R3-sign(w1Fu2+w2R3-Th2)w3I2, the second layer ultrasonic sampling image I2, the second layer ultrasonic enhanced image Fu2 and the third layer ultrasonic fusion reconstructed image R3 are fused and reconstructed to obtain the second layer ultrasonic weighted fusion image F2; wherein Th2 is a given threshold, and w1, w2 and w3 are predefined coefficients;

[0130] The second layer ultrasonic weighted fusion image F2 is upsampled to obtain a second layer ultrasonic upsampled image U2.

[0131] Specifically, the second-layer ultrasound image reconstruction process is completed by image weighted fusion and image upsampling:

[0132] 1) Image weighted fusion: The second-layer ultrasound enhanced image Fu2 and the third-layer ultrasound fusion reconstructed image R3 are weightedly fused and reconstructed. If the weighted fusion reconstructed image is greater than a certain specified threshold, the influence of the second-layer ultrasound sampling image I2 is reduced. Otherwise, the influence of the second-layer ultrasound sampling image I2 is increased. The mathematical definition of the fused second-layer ultrasound weighted fusion image F2 is: F2 = w1Fu2 + w2R3 - sign (w1Fu2 + w2R3 - Th2) w3I2, where sign is the symbol Function, when w1Fu2+w2R3-Th2>0, sign takes a positive value, otherwise, sign takes a negative value; w1, w2 and w3 can be defined by the ratio of the image mean to the variance, specifically, w1 is defined by the ratio of the mean to the variance of the second-layer ultrasound enhanced image Fu2, w2 is defined by the ratio of the mean to the variance of the third-layer ultrasound fusion reconstructed image R3; w3 is defined by the ratio of the mean to the variance of the second-layer ultrasound sampling image I2; or, w1, w2 and w3 can also be specified by the user.

[0133] 2) Image upsampling: The second-layer ultrasound weighted fusion image F2 is upsampled to obtain a second-layer ultrasound upsampled image U2. Specifically, the same upsampling method as the third-layer ultrasound image may be used.

[0134] As an optional embodiment, the process of fusing and reconstructing the first layer of ultrasound sampling images and the second layer of ultrasound upsampling images to obtain the final ultrasound enhanced image includes:

[0135] According to the preset image fusion relationship E=γU2+(1-γ)I1, the first layer ultrasound sampling image I1 and the second layer ultrasound upsampling image U2 are fused and reconstructed to obtain the final ultrasound enhanced image E; wherein γ is a control factor.

[0136] Specifically, the first layer ultrasound sampling image I1 and the second layer ultrasound upsampling image U2 are fused and reconstructed to obtain a final ultrasound enhanced image E. The mathematical definition of the ultrasound enhanced image E obtained after fusion is specifically: E=γU2+(1-γ)I1.

[0137] In summary, the present application adopts a bottom-up mechanism to integrate three-layer resolution images to reconstruct high-resolution images, which can effectively remove image noise, enhance image edges, improve image signal-to-noise ratio, and increase image contrast; and the algorithm feasibility of the multi-resolution strategy is relatively high; in addition, images of different layers of resolution contain different image details, which can enlarge the image without losing image details, which is beneficial to the doctor's diagnosis.

[0138] Please refer to Figure 3 , Figure 3 A schematic diagram of the structure of an ultrasonic image optimization processing system provided by an embodiment of the present invention.

[0139] The ultrasound image optimization processing system comprises:

[0140] Downsampling module 1, used for downsampling the original ultrasonic image to obtain ultrasonic sampling images with different resolutions;

[0141] An image determination module 2 is used to determine an original ultrasound image and a pre-edge-enhanced ultrasound image from the ultrasound sampling image;

[0142] The image enhancement module 3 is used to perform edge enhancement processing on the pre-edge-enhanced ultrasound image according to a preset image edge enhancement strategy to obtain an ultrasound-enhanced image;

[0143] An image fusion module 4 is used to fuse the pre-edge-enhanced ultrasound image and the ultrasound-enhanced image to obtain an ultrasound-fused image;

[0144] The image reconstruction module 5 is used to upsample the ultrasound fusion image to obtain an upsampled image, and to fuse and reconstruct the upsampled image and the original ultrasound image to obtain a final ultrasound enhanced image.

[0145] For an introduction to the optimization processing system provided in this application, please refer to the embodiments of the above-mentioned optimization processing method, and this application will not go into details here.

[0146] The present application also provides an ultrasound image optimization processing device, comprising:

[0147] Memory for storing computer programs;

[0148] A processor is used to implement the steps of any of the above-mentioned ultrasound image optimization processing methods when executing a computer program.

[0149] For an introduction to the optimization processing device provided in this application, please refer to the embodiment of the above-mentioned optimization processing method, and this application will not go into details here.

[0150] It should also be noted that, in this specification, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0151] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for optimizing ultrasonic image processing, characterized in that: include: Downsampling the original ultrasonic image to obtain ultrasonic sampling images with different resolutions, and determining the original ultrasonic image and the pre-edge-enhanced ultrasonic image; The process of downsampling the original ultrasonic image to obtain ultrasonic sampling images of different resolutions and determining the original ultrasonic image and the pre-edge-enhanced ultrasonic image includes: The original ultrasonic image is downsampled in three layers to obtain three layers of ultrasonic sampling images with different resolutions; wherein the resolution of the first layer of ultrasonic sampling image is greater than the resolution of the second layer of ultrasonic sampling image and greater than the resolution of the third layer of ultrasonic sampling image; Using the first layer of ultrasonic sampling images as original ultrasonic images, and using the second layer of ultrasonic sampling images and the third layer of ultrasonic sampling images as pre-edge-enhanced ultrasonic images; Performing edge enhancement processing on the pre-edge-enhanced ultrasound image according to a preset image edge enhancement strategy to obtain an ultrasound-enhanced image; fusing the pre-edge-enhanced ultrasound image with the ultrasound-enhanced image to obtain an ultrasound-fused image; Upsampling the ultrasound fusion image to obtain an upsampled image, and fusing and reconstructing the upsampled image and the original ultrasound image to obtain a final ultrasound enhanced image; The second layer of ultrasonic sampling images is subjected to edge enhancement processing to obtain a second layer of ultrasonic enhanced images; the third layer of ultrasonic sampling images is subjected to edge enhancement processing to obtain a third layer of ultrasonic enhanced images; Accordingly, the process of fusing the pre-edge-enhanced ultrasound image and the ultrasound-enhanced image to obtain an ultrasound-fused image; upsampling the ultrasound-fused image to obtain an upsampled image, and fusing and reconstructing the upsampled image and the original ultrasound image to obtain a final ultrasound-enhanced image includes: Fusing the third layer of ultrasonic sampling images with the third layer of ultrasonic enhanced images, and upsampling the fused ultrasonic images to obtain a third layer of ultrasonic upsampling images; fusing and reconstructing the second-layer ultrasound sampling image, the second-layer ultrasound enhanced image, and the third-layer ultrasound up-sampled image, and up-sampling the fused and reconstructed ultrasound image to obtain a second-layer ultrasound up-sampled image; The first layer of ultrasonic sampling images and the second layer of ultrasonic up-sampling images are fused and reconstructed to obtain a final ultrasonic enhanced image.

2. The ultrasonic image optimization processing method according to claim 1, characterized in that: The process of performing edge enhancement processing on the pre-edge-enhanced ultrasound image according to a preset image edge enhancement strategy to obtain an ultrasound-enhanced image includes: Performing edge enhancement processing on the second layer of ultrasonic sampling images according to a preset image edge enhancement strategy to obtain a second layer of ultrasonic enhanced images; The third layer of ultrasonic sampling images is subjected to edge enhancement processing according to a preset image edge enhancement strategy to obtain a third layer of ultrasonic enhanced images.

3. The ultrasonic image optimization processing method according to claim 2, characterized in that: The process of performing edge enhancement processing on the third layer of ultrasonic sampling images according to a preset image edge enhancement strategy to obtain a third layer of ultrasonic enhanced images includes: The third layer of ultrasonic sampling images is subjected to multi-scale edge enhancement processing to obtain a third layer of ultrasonic enhanced images.

4. The ultrasonic image optimization processing method according to claim 3, characterized in that: The process of performing multi-scale edge enhancement processing on the third layer of ultrasonic sampling images to obtain the third layer of ultrasonic enhanced images includes: The ultrasonic image that has been pre-processed with multi-scale edge enhancement is subjected to isotropic filtering and denoising to obtain the denoised ultrasonic image. Wherein, an iterative method is used to perform multi-scale edge enhancement; n is the number of iterations, and its maximum value is equal to a preset iteration threshold; Ultrasound images Inputting into the pre-constructed odd filter and even filter respectively, obtaining odd filter responses and even filter responses at multiple scales, and calculating the difference between the odd and even filter responses to obtain the multi-scale edge responses; The edge responses at multiple scales are fused to obtain an edge image, and the ultrasound image is analyzed based on the edge image. Perform multi-scale edge enhancement and image denoising to obtain an ultrasonic image When the number of iterations of multi-scale edge enhancement is less than the preset iteration threshold, the ultrasound image The ultrasound image that has been pre-processed with multi-scale edge enhancement enters the next iterative processing; when the number of iterations of the multi-scale edge enhancement is equal to the preset iteration threshold, the iteration stops.

5. The ultrasonic image optimization processing method according to claim 4, characterized in that: The difference between the odd and even filter responses is calculated to obtain a multi-scale edge response; the edge responses of multiple scales are fused to obtain an edge image, and the ultrasound image is imaged based on the edge image. Perform multi-scale edge enhancement and image denoising to obtain an ultrasonic image The process includes: According to the edge response relation Compute the difference between the odd and even filter responses to get the edge response on scale s in, is the even filter response on scale s; is the odd filter response on scale s; T s is a noise threshold related to the scale s; x is a pixel point in the image; According to the response fusion relation The edge responses at multiple scales are fused to obtain the edge image Eg3; The value range of is [0, 1]; m is the number of filter scales; According to the image multi-scale enhancement relationship Ultrasound images Perform multi-scale edge enhancement and image denoising to obtain an ultrasonic image Among them, Δt is the time step and δ3 is the scale factor.

6. The ultrasonic image optimization processing method according to claim 2, characterized in that: The process of performing edge enhancement processing on the second layer of ultrasonic sampling images according to a preset image edge enhancement strategy to obtain a second layer of ultrasonic enhanced images includes: The second layer of ultrasonic sampling images is subjected to multi-directional edge enhancement processing to obtain a second layer of ultrasonic enhanced images.

7. The ultrasonic image optimization processing method according to claim 6, characterized in that: The process of performing multi-directional edge enhancement processing on the second layer of ultrasonic sampling images to obtain the second layer of ultrasonic enhanced images includes: Enhance the relationship in multiple directions according to the preset image Performing multi-directional edge enhancement processing and image denoising processing on the second-layer ultrasonic sampling image within a preset edge enhancement time T1 to obtain a second-layer ultrasonic enhanced image; in, is the gradient operator; || is the gradient value; t is the time operator; k1 is the parameter for controlling smoothing; u0 is the initial iterative image; u is the ultrasound image obtained after the last diffusion process; β is a hyperparameter, β∈[0,1]; Eg is a phase-based edge operator with a value range of [0,1]; x is a pixel point in the image; g(x) divides the ultrasound image into two regions, Ω1={x∈Ω,g(x)≈1} and Ω2={x∈Ω,0≤g(x)<1}, Ω=Ω1+Ω2; ε represents a positive constant; s is a certain scale of the filter; m is the number of filter scales; F s is the phase-based filter feature at the s-th scale; is the even filter response on scale s; is the odd filter response on scale s; T s is a noise threshold related to the scale s.

8. The ultrasonic image optimization processing method according to claim 2, characterized in that: The process of fusing the third layer of ultrasonic sampling images with the third layer of ultrasonic enhanced images, and upsampling the fused ultrasonic images to obtain the third layer of ultrasonic upsampled images includes: According to the preset image rough fusion relationship The third layer ultrasonic sampling image I3 is roughly fused with the third layer ultrasonic enhanced image Eh3 to obtain a third layer ultrasonic rough fusion image Fu3; wherein Th3 is a given threshold; μ is a parameter for controlling the degree of image edge enhancement; α is a parameter for controlling the degree of image enhancement; Eg3 is an edge image of the third layer ultrasonic sampling image, and its value range is [0, 1]; Upsampling the third-layer ultrasonic rough fusion image Fu3 to obtain a third-layer ultrasonic upsampled image U3; According to the preset image fusion relationship Performing diffusion processing on the third-layer ultrasound upsampling image U3 within a preset fine fusion time T2 to obtain a third-layer ultrasound fusion reconstructed image R3; wherein U is the ultrasound image obtained after the last diffusion processing; div is a divergence operator; is the gradient operator; || is the gradient value; t is the time operator; U3 is the initial iterative image; k2 is the factor controlling diffusion; c is the diffusion equation.

9. The ultrasonic image optimization processing method according to claim 8, characterized in that: The process of fusing and reconstructing the second-layer ultrasound sampling image, the second-layer ultrasound enhanced image and the third-layer ultrasound up-sampled image, and up-sampling the fused and reconstructed ultrasound image to obtain the second-layer ultrasound up-sampled image includes: According to the preset image weighted fusion relationship F2=w1Fu2+w2R3-sign(w1Fu2+w2R3-Th2)w3I2, the second layer of ultrasonic sampling image I2, the second layer of ultrasonic enhanced image Fu2 and the third layer of ultrasonic fusion reconstructed image R3 are fused and reconstructed to obtain a second layer of ultrasonic weighted fusion image F2; wherein Th2 is a given threshold, and w1, w2 and w3 are predefined coefficients; The second-layer ultrasonic weighted fusion image F2 is upsampled to obtain a second-layer ultrasonic upsampled image U2.

10. The ultrasonic image optimization processing method according to claim 9, characterized in that: The process of fusing and reconstructing the first layer of ultrasound sampling images and the second layer of ultrasound upsampling images to obtain a final ultrasound enhanced image includes: According to the preset image fusion relationship E=γU2+(1-γ)I1, the first layer ultrasound sampling image I1 and the second layer ultrasound up-sampling image U2 are fused and reconstructed to obtain the final ultrasound enhanced image E; wherein γ is a control factor.

11. An ultrasonic image optimization processing system, characterized in that: include: A downsampling module is used to downsample the original ultrasonic image to obtain ultrasonic sampling images with different resolutions; An image determination module, used for determining an original ultrasonic image and a pre-edge-enhanced ultrasonic image from the ultrasonic sampling image; Wherein, the image determination module is used for: The original ultrasonic image is downsampled in three layers to obtain three layers of ultrasonic sampling images with different resolutions; wherein the resolution of the first layer of ultrasonic sampling image is greater than the resolution of the second layer of ultrasonic sampling image and greater than the resolution of the third layer of ultrasonic sampling image; Using the first layer of ultrasonic sampling images as original ultrasonic images, and using the second layer of ultrasonic sampling images and the third layer of ultrasonic sampling images as pre-edge-enhanced ultrasonic images; An image enhancement module, configured to perform edge enhancement processing on the pre-edge-enhanced ultrasound image according to a preset image edge enhancement strategy to obtain an ultrasound-enhanced image; wherein the second-layer ultrasound sampling image is edge-enhanced to obtain a second-layer ultrasound-enhanced image; and the third-layer ultrasound sampling image is edge-enhanced to obtain a third-layer ultrasound-enhanced image; An image fusion module, used for fusing the pre-edge-enhanced ultrasound image with the ultrasound-enhanced image to obtain an ultrasound-fused image; An image reconstruction module, used for upsampling the ultrasound fusion image to obtain an upsampled image, and fusing and reconstructing the upsampled image with the original ultrasound image to obtain a final ultrasound enhanced image; Wherein, the image fusion module and the image reconstruction module are used for: Fusing the third layer of ultrasonic sampling image with the third layer of ultrasonic enhanced image, and upsampling the fused ultrasonic image to obtain a third layer of ultrasonic upsampling image; fusing and reconstructing the second-layer ultrasound sampling image, the second-layer ultrasound enhanced image, and the third-layer ultrasound up-sampled image, and up-sampling the fused and reconstructed ultrasound image to obtain a second-layer ultrasound up-sampled image; The first layer of ultrasonic sampling images and the second layer of ultrasonic up-sampling images are fused and reconstructed to obtain a final ultrasonic enhanced image.

12. An ultrasonic image optimization processing device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the ultrasound image optimization processing method as described in any one of claims 1 to 10 when executing the computer program.

Images