A renal lesion ultrasound analysis and diagnosis and treatment auxiliary system based on renal ultrasound images

Abstract

The embodiment of the present invention discloses a renal lesion ultrasonic analysis diagnosis and treatment auxiliary system based on renal ultrasonic images, which relates to the field of ultrasonic diagnosis and treatment auxiliary technology. The system acquires renal ultrasonic image data through an ultrasonic image acquisition module, and the image analysis module performs registration according to the renal ultrasonic image data transmitted by the ultrasonic image acquisition module to obtain registered renal ultrasonic image data. The image analysis module performs image segmentation calculation, texture feature extraction, morphological feature extraction and calculation of renal blood flow velocity according to the registered renal ultrasonic image data to obtain segmented renal image data, renal texture feature value and renal morphological feature value. The lesion recognition module calculates the renal lesion position feature value according to the segmented renal image data, renal texture feature value, renal morphological feature value and renal blood flow velocity transmitted by the image analysis module through a built-in deep learning model, and the auxiliary diagnosis evaluation module performs diagnosis evaluation according to the lesion position feature value to generate an auxiliary evaluation report. It can assist in improving the accuracy of medical diagnosis of renal organs, thereby facilitating providing doctors with better auxiliary diagnosis analysis in the diagnosis and analysis of renal lesions.

Description

Technical Field

[0001] The present invention relates to the technical field of ultrasonic diagnosis and treatment assistance, and in particular to a renal lesion ultrasonic analysis and diagnosis and treatment assistance system based on renal ultrasonic images. Background Art

[0002] In the field of ultrasound diagnosis (Ultrasonic diagnostics), ultrasound imaging (ultrasonic image) assisted diagnosis technology has been widely used in clinical medicine as a common medical imaging diagnostic method. By acquiring image information through the propagation and echo of ultrasound in human tissue, ultrasound diagnosis technology has the advantages of being non-invasive, highly real-time, and low-cost, and plays an important role in the diagnosis and evaluation of kidney diseases.

[0003] In the diagnosis of kidney disease, the traditional ultrasound image-assisted diagnosis system mainly collects ultrasound image data, and clinicians rely on ultrasound images to locate and diagnose kidney lesions. However, since the traditional ultrasound image-assisted diagnosis system generally does not combine the ultrasound image of the kidney organ to extract the corresponding feature values ​​and locate the lesion, it often lacks an accurate description of the location and characteristics of the lesion, resulting in a lack of accuracy in the medical diagnosis and evaluation results of kidney organ lesions, making it difficult to provide doctors with better auxiliary diagnosis and analysis in the diagnosis and analysis of kidney lesions. Summary of the invention

[0004] In view of this, an embodiment of the present invention provides a renal lesion ultrasonic analysis and treatment auxiliary system based on renal ultrasonic imaging, which is equipped with an ultrasonic image acquisition module for acquiring ultrasonic image data of the kidney organ, an image analysis module for registering and extracting feature values ​​for the above data, a lesion recognition module for comprehensively calculating the above feature values ​​through a deep learning model to obtain feature values ​​of the lesion location, an auxiliary diagnosis and evaluation module for performing diagnostic evaluation based on the feature values ​​of the lesion location, and generating an auxiliary analysis and evaluation report, which can assist in improving the accuracy of medical diagnosis of the kidney organ, thereby facilitating providing doctors with better auxiliary diagnosis and analysis in the diagnosis and analysis of renal lesions.

[0005] In order to achieve the above object, the present invention adopts the following technical scheme:

[0006] A renal lesion ultrasound analysis and treatment auxiliary system based on renal ultrasound images, comprising an ultrasound image acquisition module, an image analysis module, a lesion recognition module and an auxiliary diagnosis and evaluation module;

[0007] The ultrasonic image acquisition module is connected to the image analysis module via a network;

[0008] The image analysis module is connected to the lesion identification module via a network;

[0009] The lesion identification module is connected to the auxiliary diagnosis and evaluation module via a network;

[0010] The ultrasound image acquisition module is used to acquire renal ultrasound image data Scsx and transmit the data to the image analysis module;

[0011] The image analysis module is used to perform registration according to the renal ultrasound image data Scsx transmitted by the ultrasound image acquisition module to obtain the registered renal ultrasound image data Pzcs;

[0012] The image analysis module is used to perform image segmentation calculation, texture feature extraction, morphological feature extraction and calculation of renal blood flow velocity Xlsd according to the registered renal ultrasound image data Pzcs, obtain segmented renal image data Fgtx, renal texture feature value Wltz and renal morphological feature value Xttz, and transmit the above calculated values ​​to the lesion recognition module;

[0013] The lesion recognition module has a built-in deep learning model;

[0014] The lesion recognition module is used to identify and calculate the renal lesion location characteristic value Bzwz based on the deep learning model according to the segmented renal image data Fgtx, renal texture characteristic value Wltz, renal morphology characteristic value Xttz and renal blood flow velocity Xlsd transmitted by the image analysis module, and transmit the lesion location characteristic value Bzwz to the auxiliary diagnosis and evaluation module;

[0015] The auxiliary diagnosis and evaluation module is used to perform a diagnosis and evaluation based on the lesion location characteristic value Bzwz and generate an auxiliary evaluation report.

[0016] Optionally, the ultrasound image acquisition module is used to acquire renal ultrasound image data Scsx through Doppler ultrasound, and transmit the image data to the image analysis module through a network.

[0017] Optionally, the image analysis module is used to perform registration according to the renal ultrasound image data Scsx transmitted by the ultrasound image acquisition module to obtain registered renal ultrasound image data Pzcs, and the registration formula is as follows:

[0018] Pzcs(i,j)=Scsx(change(i,j))

[0019] In the formula, Pzcs(i,j) represents the registered renal ultrasound image data, Scsx represents the original renal ultrasound image data, and change(i,j) represents the spatial transformation function.

[0020] Optionally, the image analysis module is used to perform image segmentation calculation according to the registered renal ultrasound image data Pzcs to obtain segmented renal image data Fgtx. The image segmentation formula is as follows:

[0021]

[0022] In the formula, Fgtx(i,j) represents the pixel value of the pixel in the segmented image, Scsx(i,j) represents the grayscale value of the pixel in the original image, and Qt represents the threshold set by the system.

[0023] Optionally, the image analysis module is used to calculate the renal texture feature value Wltz according to the registered renal ultrasound image data Pzcs, and the calculation formula is as follows:

[0024]

[0025] In the formula, Wltz represents the renal texture eigenvalue, Pzcs(i,j) represents the registered renal ultrasound image data, and i,j represent the coordinates of the registered renal ultrasound image.

[0026] Optionally, the image analysis module is used to calculate the renal morphological characteristic value Xttz according to the registered renal ultrasound image data Pzcs, and the calculation formula is as follows:

[0027]

[0028] In the formula, Xttz represents the kidney morphological characteristic value, Areax represents the kidney area, Width represents the width of the kidney's minimum enclosing rectangle, and Height represents the height of the kidney's minimum enclosing rectangle. The above values ​​are automatically obtained by the system.

[0029] Optionally, the image analysis module is used to calculate the renal blood flow velocity Xlsd according to the registered renal ultrasound image data Pzcs, and the calculation formula is as follows:

[0030]

[0031] In the formula, Xlsd represents the renal blood flow velocity, Ftp represents the frequency shift of Doppler ultrasound, Cst represents the speed of sound propagation in renal tissue, ft0 represents the frequency of Doppler ultrasound, and sinθ represents the angle between ultrasound and the direction of fluid flow. The above values ​​are automatically obtained by the system.

[0032] Optionally, the lesion recognition module is used to calculate the lesion location characteristic value Bzwz based on the deep learning model according to the segmented renal image data Fgtx, the renal texture characteristic value Wltz, the renal morphology characteristic value Xttz and the renal blood flow velocity Xlsd transmitted by the image analysis module, and the calculation formula is as follows:

[0033]

[0034] In the formula, Bzwz represents the lesion location feature value, Fgty represents the segmented renal image data, Wltz represents the renal texture feature value, Xttz represents the renal morphology feature value, and Xlsd represents the renal blood flow velocity.

[0035] Optionally, the auxiliary diagnosis and evaluation module is specifically used to perform diagnostic evaluation based on the lesion location characteristic value, generate an image of the lesion area of ​​the kidney organ, and output the evaluation report together with the image.

[0036] Optionally, it also includes: a feedback output module, which is used to receive the evaluation report and images output by the auxiliary diagnosis and evaluation module, and display the evaluation report and images on the doctor's work computer, so that the doctor can make a diagnosis result based on the evaluation report and images.

[0037] Compared with the prior art, the ultrasonic analysis and diagnosis and treatment auxiliary system for renal lesions based on renal ultrasonic images provided in the embodiment of the present invention acquires renal ultrasonic image data Scsx through an ultrasonic image acquisition module, and the image analysis module performs registration according to the renal ultrasonic image data Scsx transmitted by the ultrasonic image acquisition module to obtain registered renal ultrasonic image data Pzcs, and the image analysis module performs image segmentation calculation, texture feature extraction, morphological feature extraction and calculation of renal blood flow velocity Xlsd according to the registered renal ultrasonic image data Pzcs to obtain segmented renal image data Fgtx, renal texture feature value Wltz, and renal morphological feature value Xttz, and the lesion recognition module recognizes and calculates the renal lesion position feature value Bzwz according to the segmented renal image data Fgtx, renal texture feature value Wltz, renal morphological feature value Xttz and renal blood flow velocity Xlsd transmitted by the image analysis module through a built-in deep learning model, and the auxiliary diagnosis and evaluation module performs diagnostic evaluation according to the lesion position feature value Bzwz to generate an auxiliary analysis and evaluation report. The system of the present invention extracts various characteristic values ​​of the kidney organ, uses a big data model to accurately identify the location of the lesion, and gives an accurate and detailed evaluation and analysis report, which can help improve the accuracy of medical diagnosis of the kidney organ, thereby providing doctors with better auxiliary diagnosis and analysis in the diagnosis and analysis of kidney lesions. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is a schematic block diagram of the structure of a kidney disease ultrasound analysis and diagnosis and treatment auxiliary system based on kidney ultrasound images according to an embodiment of the present invention;

[0039] Figure 2 This is a schematic block diagram of the structure of a renal lesion ultrasound analysis and diagnosis and treatment auxiliary system based on renal ultrasound images according to another embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following is a detailed description of the renal lesion ultrasound analysis and diagnosis and treatment auxiliary system based on renal ultrasound images provided by the present invention in conjunction with the accompanying drawings;

[0041] See also Figure 1 , an embodiment of the present invention provides a renal lesion ultrasound analysis and treatment auxiliary system based on renal ultrasound images, comprising an ultrasound image acquisition module, an image analysis module, a lesion recognition module and an auxiliary diagnosis and evaluation module;

[0042] An ultrasound image acquisition module is used to acquire renal ultrasound image data Scsx through Doppler ultrasound, and transmit the image data to the image analysis module through a network;

[0043] The image analysis module is used to perform registration according to the renal ultrasound image data Scsx transmitted by the ultrasound image acquisition module to obtain the registered renal ultrasound image data Pzcs. The registration formula is as follows:

[0044] Pzcs(i,j)=Scsx(change(i,j))

[0045] Through registration processing, ultrasound images at different time points or in different modes can be aligned to achieve image consistency and accuracy. In this way, doctors can more accurately compare the lesion areas in the image and understand the development of the lesion. In the formula, Pzcs(i,j) represents the registered renal ultrasound image data, Scsx represents the original renal ultrasound image data, and change(i,j) represents the spatial transformation function. Through this function, the coordinates (i,j) of the image Scsx are mapped to the image Pzcs. By optimizing the spatial transformation parameters, the two images can be aligned in space, thereby achieving the purpose of image registration. The registered ultrasound image can be used for surgical planning to help doctors determine the surgical approach, target area and risk structure. Accurate registration information can provide more accurate navigation and positioning, and improve the safety and success rate of surgery.

[0046] Specifically, the image analysis module is used to perform registration according to the renal ultrasound image data Scsx transmitted by the ultrasound image acquisition module to obtain the registered renal ultrasound image data Pzcs, including: obtaining the original renal ultrasound image data Scsx;

[0047] Extract features from the original renal ultrasound image data Scsx, which are corner points or edge features in the image, for subsequent registration calculation;

[0048] Match the extracted feature points to establish the corresponding relationship between the feature points in the original image and the feature points in the target image;

[0049] The spatial transformation function change(i,j) is calculated using the result of feature point matching. In some embodiments, the least squares method can be used to map the feature points in the original image to the feature point positions in the target image through spatial transformation, thereby obtaining a spatial transformation function. The spatial transformation function change(i,j) describes the spatial transformation relationship between the original image and the target image.

[0050] Using the calculated spatial transformation function, according to the registration formula:

[0051] Pzcs(i,j)=Scsx(change(i,j)) performs registration calculation on the original image. Specifically, according to the registration formula, a spatial transformation function is applied to each pixel (i,j) in the original image, mapped to the registered position, and the corresponding pixel value is obtained to obtain the registered renal ultrasound image data Pzcs.

[0052] In some embodiments, the image analysis module is used to perform image segmentation calculation, texture feature extraction, morphological feature extraction and calculation of renal blood flow velocity Xlsd according to the registered renal ultrasound image data Pzcs, to obtain segmented renal image data Fgtx, renal texture feature value Wltz, and renal morphological feature value Xttz, wherein the image segmentation formula is as follows:

[0053]

[0054] Through image segmentation, the lesion area in the medical image can be separated from the healthy tissue, so as to locate the lesion area more accurately and help doctors diagnose and treat diseases more accurately. In the formula, Fgtx(i,j) represents the pixel value of the pixel in the segmented image, Scsx(i,j) represents the gray value of the pixel in the original image, and Qt represents the threshold set by the system. The pixel values ​​of 0 and 1 are obtained by judging the size relationship between Scsx(i,j) and Qt. When the gray value of the pixel in the original image is greater than the threshold set by the system, 1 is returned, otherwise 0 is returned. The system segments the image according to the pixel value. Image segmentation can help doctors identify the boundary between the lesion and the surrounding normal tissue, provide clearer image information, and assist doctors in making accurate diagnosis and evaluation.

[0055] The calculation formula of kidney texture eigenvalue Wltz is as follows:

[0056]

[0057] The texture features of kidneys can reflect the microstructure and distribution of tissues. By calculating the texture features, doctors can better distinguish normal tissues from abnormal tissues and improve the accuracy of disease diagnosis and classification. In the formula, Wltz represents the kidney texture feature value, Pzcs(i,j) represents the registered kidney ultrasound image data, and i,j represents the coordinates of the registered kidney ultrasound image. The weighted sum of the texture features of the kidney is used to obtain the texture feature value of the kidney. Calculating the texture features of the kidney can evaluate the uniformity, heterogeneity, and changes of kidney tissue, which is helpful for quantitatively evaluating the severity and scope of kidney disease.

[0058] The calculation formula of kidney morphological characteristic value Xttz is as follows:

[0059]

[0060] The kidney morphological characteristic value can reflect the morphological structure and size of the kidney organ. By calculating the morphological characteristics, doctors can better diagnose and classify kidney diseases. In the formula, Xttz represents the kidney morphological characteristic value, Areax represents the kidney area, Width represents the width of the kidney's minimum enclosing rectangle, and Height represents the height of the kidney's minimum enclosing rectangle. The above values ​​are automatically obtained by the system. By obtaining the value of the kidney organ area Areax, the value is divided by the product of the height and width of the kidney area rectangle Width*Height to obtain the accurate kidney morphological characteristic value. The calculation of kidney morphological characteristics can help doctors detect abnormal structures, foreign bodies, masses and other lesions in the kidney, further improving the detection rate of lesions.

[0061] The calculation formula of renal blood flow velocity Xlsd is as follows:

[0062]

[0063] Renal blood flow velocity is one of the important indicators for evaluating kidney function. By measuring the blood flow velocity in the renal artery, we can understand the perfusion and blood flow of the kidney, and provide important information for evaluating the filtration and metabolic functions of the kidney. In the formula, Xlsd represents the renal blood flow velocity, Ftp represents the frequency shift of Doppler ultrasound, Cst represents the speed of sound propagation in renal tissue, ft0 represents the frequency of Doppler ultrasound, and sinθ represents the angle between ultrasound and the flow direction of the fluid. The above values ​​are automatically obtained by the system. By calculating the value of Ftp*Cst and dividing the result by 2*ft0*sinθ, the renal blood flow velocity is obtained. Abnormal blood flow velocity can reflect potential vascular lesions or local diseases, which is helpful for further examination and diagnosis in time.

[0064] The lesion recognition module is based on a deep learning model that identifies and calculates the renal lesion location eigenvalue Bzwz based on the segmented renal image data Fgtx, renal texture eigenvalue Wltz, renal morphology eigenvalue Xttz, and renal blood flow velocity Xlsd transmitted by the image analysis module. The calculation formula is as follows:

[0065]

[0066] The renal lesion location feature value refers to the characteristic parameters of the lesion location obtained by analyzing renal images and related features, which can characterize the coordinate information, size, shape, boundary of the lesion, and the relative position relationship with the surrounding normal tissue. When using deep learning models for lesion identification, the lesion location feature value can help the model accurately locate and describe abnormal structures and lesions inside the kidney, thereby realizing automatic identification and location of renal lesions.

[0067] Among them, abnormal structures and lesions inside the kidney may include: cysts, masses, and inflammation. Calculating the characteristic value of the location of renal lesions can help detect lesions early, thereby facilitating early diagnosis and intervention and improving treatment effects. In the formula, Bzwz represents the characteristic value of the location of the lesion, Fgtx represents the segmented renal image data, Wltz represents the characteristic value of the renal texture, Xttz represents the characteristic value of the renal morphology, and Xlsd represents the renal blood flow velocity. Calculating the characteristic value of the renal lesion is of great significance for the early diagnosis, quantitative evaluation, treatment guidance, preoperative evaluation, and prognosis evaluation of renal diseases, and helps to optimize the patient's treatment plan, improve the treatment effect, and improve the patient's quality of life.

[0068] The auxiliary diagnosis evaluation module is used to perform diagnostic evaluation based on the lesion location characteristic value Bzwz and generate an evaluation report for the doctor to make a diagnosis based on the report.

[0069] The system provided by the embodiment of the present invention can assist in improving the accuracy of medical diagnosis of kidney organs by extracting various characteristic values ​​of the kidney organ, using a big data model to accurately identify the location and size of the lesion, etc., and providing an accurate and detailed evaluation and analysis report, thereby facilitating the provision of better auxiliary diagnosis and analysis for doctors in the diagnosis and analysis of kidney lesions.

[0070] In some embodiments, the auxiliary diagnosis and evaluation module is specifically used to perform diagnostic evaluation based on the lesion location characteristic value, generate an image of the lesion area of ​​the kidney organ, and output the evaluation report together with the image.

[0071] See also Figure 2 In some embodiments, it also includes: a feedback output module, which is used to receive the evaluation report and image output by the auxiliary diagnosis and evaluation module, and display the evaluation report and image on the doctor's work computer, so that the doctor can make a diagnosis result by combining the evaluation report and image.

[0072] In the embodiment of the present invention, various characteristic values ​​of the kidney organ are extracted, the location of the lesion is accurately identified using a big data model, and an accurate and detailed evaluation and analysis report is given. The doctor can use the analysis report as a reference to give the patient an accurate diagnosis of the disease. The system obtains ultrasound images of the kidney organ through Doppler ultrasound, and accurately identifies the location of the lesion by extracting a series of characteristic values ​​of the ultrasound image of the organ, which can assist in improving the accuracy of medical diagnosis of the kidney organ, thereby facilitating the provision of better auxiliary diagnostic analysis effects for doctors in the diagnosis and analysis of renal lesions.

[0073] It should be clear that the described embodiments are only some embodiments of the present invention, not all 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.

[0074] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A renal lesion ultrasound analysis and diagnosis and treatment auxiliary system based on renal ultrasound images, It is characterized in that It includes ultrasound image acquisition module, image analysis module, lesion identification module and auxiliary diagnosis and evaluation module; The ultrasonic image acquisition module is connected to the image analysis module via a network; The image analysis module is connected to the lesion identification module via a network; The lesion identification module is connected to the auxiliary diagnosis and evaluation module via a network; The ultrasound image acquisition module is used to acquire renal ultrasound image data Scsx through Doppler ultrasound and transmit the data to the image analysis module; The image analysis module is used to perform registration according to the renal ultrasound image data Scsx transmitted by the ultrasound image acquisition module to obtain the registered renal ultrasound image data Pzcs; The image analysis module is used to perform image segmentation calculation, texture feature extraction, morphological feature extraction and calculation of renal blood flow velocity Xlsd according to the registered renal ultrasound image data Pzcs, obtain segmented renal image data Fgtx, renal texture feature value Wltz and renal morphological feature value Xttz, and transmit the calculated values ​​to the lesion recognition module; The lesion recognition module has a built-in deep learning model; The lesion recognition module is used to identify and calculate the renal lesion location characteristic value Bzwz based on the deep learning model according to the segmented renal image data Fgtx, renal texture characteristic value Wltz, renal morphology characteristic value Xttz and renal blood flow velocity Xlsd transmitted by the image analysis module, and transmit the lesion location characteristic value Bzwz to the auxiliary diagnosis and evaluation module; The auxiliary diagnosis and evaluation module is used to perform a diagnosis and evaluation based on the lesion location characteristic value Bzwz and generate an auxiliary evaluation report; The registering the renal ultrasound image data Scsx transmitted by the ultrasound image acquisition module to obtain the registered renal ultrasound image data Pzcs includes: acquiring the original renal ultrasound image data Scsx; Extracting features from the original renal ultrasound image data Scsx, wherein the features are corner points or edge features in the image, for subsequent registration calculation; Match the extracted feature points to establish the corresponding relationship between the feature points in the original image and the feature points in the target image; Using the result of feature point matching and the least square method, the feature points in the original image are mapped to the feature point positions in the target image through spatial transformation to obtain a spatial transformation function, which describes the spatial transformation relationship between the original image and the target image. Using the calculated spatial transformation function, according to the registration formula: Pzcs(i,j)=Scsx(change(i,j)) performs registration calculation on the original image; The original image is registered according to the registration formula: Pzcs(i,j)=Scsx(change(i,j)), specifically: according to the registration formula, a spatial transformation function is applied to each pixel (i,j) in the original image, and it is mapped to the registered position, and the corresponding pixel value is obtained to obtain the registered renal ultrasound image data Pzcs; The image analysis module is used to perform image segmentation calculation based on the registered renal ultrasound image data Pzcs, separate the lesion area from the healthy tissue in the medical image, and obtain the segmented renal image data Fgtx. The image segmentation formula is as follows: In the formula, Fgtx(i,j) represents the pixel value of the pixel in the segmented image, Scsx(i,j) represents the grayscale value of the pixel in the original image, and Qt represents the threshold set by the system.

2. The renal lesion ultrasound analysis and treatment auxiliary system based on renal ultrasound imaging according to claim 1, It is characterized in that The image analysis module is used to calculate the renal texture feature value Wltz according to the registered renal ultrasound image data Pzcs, and the calculation formula is as follows: In the formula, Wltz represents the renal texture eigenvalue, Pzcs(i,j) represents the registered renal ultrasound image data, and i,j represent the coordinates of the registered renal ultrasound image.

3. The renal lesion ultrasound analysis and treatment auxiliary system based on renal ultrasound imaging according to claim 2, It is characterized in that The image analysis module is used to calculate the renal morphological characteristic value Xttz according to the registered renal ultrasound image data Pzcs, and the calculation formula is as follows: In the formula, Xttz represents the kidney morphological characteristic value, Areax represents the kidney area, Width represents the width of the kidney's minimum enclosing rectangle, and Height represents the height of the kidney's minimum enclosing rectangle. The above values ​​are automatically obtained by the system.

4. The renal lesion ultrasound analysis and treatment auxiliary system based on renal ultrasound imaging according to claim 3, It is characterized in that The image analysis module is used to calculate the renal blood flow velocity Xlsd according to the registered renal ultrasound image data Pzcs, and the calculation formula is as follows: In the formula, Xlsd represents the renal blood flow velocity, Ftp represents the frequency shift of Doppler ultrasound, Cst represents the speed of sound propagation in renal tissue, and ft 0 It represents the frequency of Doppler ultrasound, and sinθ represents the angle between ultrasound and the flow direction of the fluid. The above values ​​are automatically obtained by the system.

5. The renal lesion ultrasound analysis and treatment auxiliary system based on renal ultrasound imaging according to claim 4, It is characterized in that The lesion recognition module is used to calculate the lesion location characteristic value Bzwz based on the deep learning model according to the segmented kidney image data Fgtx, kidney texture characteristic value Wltz, kidney morphology characteristic value Xttz and kidney blood flow velocity Xlsd transmitted by the image analysis module. The calculation formula is as follows: In the formula, Bzwz represents the lesion location feature value, Fgtx represents the segmented renal image data, Wlta represents the renal texture feature value, Xttz represents the renal morphology feature value, and Xlsd represents the renal blood flow velocity.

6. The renal lesion ultrasound analysis and treatment auxiliary system based on renal ultrasound imaging according to claim 5, It is characterized in that The auxiliary diagnosis and evaluation module is specifically used to perform diagnostic evaluation based on the lesion location characteristic value Bzwz, generate an image of the renal organ lesion area, and output the evaluation report and the image.

7. The renal lesion ultrasound analysis and treatment auxiliary system based on renal ultrasound imaging according to claim 6, It is characterized in that Also includes: The feedback output module is used to receive the evaluation report and images output by the auxiliary diagnosis and evaluation module, and display the evaluation report and images on the doctor's work computer so that the doctor can make a diagnosis result by combining the evaluation report and images.

Images