Ultrasonic measurement method and device for liver fatty degeneration based on image processing

Abstract

The present invention discloses an image processing-based ultrasonic measurement method for hepatic steatosis. The method comprises preprocessing a set of RF signals from the abdominal region, including the liver, acquired by ultrasound imaging and converting the signals into a grayscale image; processing the grayscale image to obtain a first segmentation template for the liver region; removing interference signal regions from the first segmentation template to obtain a second segmentation template for the liver region; labeling the grayscale image with the second segmentation template to obtain a region of interest; and calculating an attenuation coefficient within the region of interest to characterize the degree of hepatic steatosis. This method allows the attenuation coefficient to be calculated only for sampling points within the liver and non-lesion areas, achieving more accurate hepatic steatosis measurement.

Description

Technical Field

[0001] The present invention relates to the technical field of liver fat measurement, and in particular to an ultrasonic measurement method and device for liver fatty degeneration based on image processing. Background Art

[0002] Hepatic steatosis is a common pathophysiological phenomenon in liver diseases, characterized by lipid metabolism disorders that lead to fat accumulation in the liver and poor liver function. Early diagnosis and assessment of hepatic steatosis and its extent are of great clinical value. Currently, hepatic steatosis is usually measured through biochemical analysis, magnetic resonance imaging (MRI), computed tomography (CT), ultrasound imaging and other technologies. Among them, although biochemical analysis is considered the gold standard, this technology is invasive and may have problems with sampling bias and sample variability; MRI and CT are not widely available and are expensive. Ultrasound imaging technology has the advantages of portability, low price, and non-invasiveness, and can provide an attractive solution for non-invasive quantification of liver fat content and accurate detection of hepatic steatosis.

[0003] In recent years, an increasing number of researchers have begun using ultrasound measurement methods based on radio-frequency (RF) signals to diagnose and assess hepatic steatosis. Because RF signals carry richer information, they can more accurately reflect tissue characteristics and enable precise measurement and quantitative analysis of hepatic steatosis. Currently, RF-based ultrasound measurement methods have been widely used to detect hepatic steatosis. However, existing RF-based methods for measuring hepatic steatosis do not segment the liver and lesion regions, resulting in low measurement accuracy.

[0004] Based on this, a new solution is needed. Summary of the Invention

[0005] The main purpose of the present invention is to provide an ultrasonic measurement method and device for liver steatosis based on image processing, so that the attenuation coefficient can be calculated only for sampling points in the liver and non-lesion areas, achieving more accurate measurement of liver steatosis.

[0006] The present invention provides an ultrasonic measurement method for liver fatty degeneration based on image processing, comprising the following steps:

[0007] Step S1, pre-processing a set of ultrasound radio frequency (RF) signals of the abdominal area including the liver area acquired by ultrasound imaging and converting the signals into a grayscale image;

[0008] Step S2: Processing the grayscale image to obtain a first segmentation template for the liver region;

[0009] Step S3, removing the interference signal area from the first liver region segmentation template to obtain a second liver region segmentation template;

[0010] Step S4, using the second segmentation template of the liver region to mark the grayscale image to obtain a region of interest;

[0011] Step S5: calculating the attenuation coefficient representing the degree of liver steatosis in the region of interest.

[0012] Preferably, the step S1 includes:

[0013] Step S11: performing interference elimination processing on the RF signal in the time domain and the frequency domain;

[0014] Step S12: obtaining the absolute value of the envelope of the processed RF signal;

[0015] Step S13: converting the RF signal after taking the absolute value into a grayscale image.

[0016] Preferably, step S2 includes:

[0017] Step S21, extracting the grayscale change trend of the grayscale image;

[0018] Step S22: using the grayscale change trend, obtaining the initial range of the liver;

[0019] Step S23, traverse each column of the initial range of the liver to determine the starting point and end point of the liver region in that column;

[0020] Step S24: Combine the start points and end points of all columns to obtain the first segmentation template of the liver region.

[0021] Preferably, in step S21, a local Gaussian weighted mean of the grayscale image is calculated to obtain an adaptive threshold surface of the grayscale image as the grayscale change trend of the grayscale image.

[0022] Preferably, between step S2 and step S3, the method further includes: performing noise reduction processing on the grayscale image.

[0023] Preferably, step S3 includes:

[0024] Step S31: Processing the grayscale image after noise reduction to obtain a segmentation threshold curve of the grayscale image;

[0025] Step S32: using the exponential decay characteristics of the ultrasonic signal in the tissue to modify the segmentation threshold curve;

[0026] Step S33: Calculate the segmentation multiple for distinguishing the interference signal area according to the modified segmentation threshold curve;

[0027] Step S34: removing the interference signal region from the first liver region segmentation template according to the segmentation multiple and a preset denoising coefficient to obtain the second liver region segmentation template.

[0028] Preferably, the step S33 includes:

[0029] Expand the modified segmentation threshold curve to obtain the average threshold surface;

[0030] The segmentation multiple is calculated using the grayscale value of the grayscale image after noise reduction processing and the grayscale value of the average threshold surface.

[0031] Preferably, the step S5 includes:

[0032] Performing envelope calculation on the RF signals of all columns within the region of interest to obtain envelope signals;

[0033] Averaging the envelope signals of all columns to obtain an average envelope signal representing the tissue within the region of interest;

[0034] The exponential decay coefficient of the average envelope signal was calculated as the attenuation coefficient representing the degree of hepatic steatosis.

[0035] In addition, to achieve the above-mentioned purpose, the present invention also proposes an ultrasonic measurement device for liver fatty degeneration based on image processing, comprising:

[0036] a signal acquisition module, configured to acquire a set of RF signals of an abdominal region including a liver region obtained by scanning with an ultrasound probe;

[0037] An image conversion module, used for pre-processing the acquired RF signal and converting it into a grayscale image;

[0038] a first processing module, configured to process the grayscale image to obtain a first segmentation template for the liver region;

[0039] a second processing module, configured to remove the interference signal region from the first liver region segmentation template to obtain a second liver region segmentation template;

[0040] a marking module, configured to mark the grayscale image using the second segmentation template of the liver region to obtain a region of interest;

[0041] The calculation module is used to calculate the attenuation coefficient representing the degree of liver fatty degeneration in the region of interest.

[0042] Preferably, the method further comprises: a noise reduction module for performing noise reduction processing on the grayscale image.

[0043] According to another aspect of the present invention, a system for measuring liver steatosis by ultrasound based on image processing is provided, comprising an ultrasound probe and the above-mentioned device for measuring liver steatosis by ultrasound based on image processing.

[0044] According to another aspect of the present invention, there is also provided an ultrasonic measurement device for liver steatosis based on image processing, comprising:

[0045] Memory for storing computer programs;

[0046] The processor is configured to implement the steps of the above-mentioned method for ultrasonic measurement of liver steatosis based on image processing when executing the computer program.

[0047] According to another aspect of the present invention, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the steps of the above-mentioned method for ultrasonic measurement of liver steatosis based on image processing are implemented.

[0048] The beneficial effects of the technical solution provided by the present invention are as follows: the image processing-based ultrasonic measurement method and system for fatty degeneration of the liver provided by the present invention convert the RF signal collected by the ultrasonic probe into a grayscale image; then, the grayscale image is processed in a series of ways using an image processing algorithm to obtain an accurately segmented liver area as a first segmentation template of the liver area; then, the interference signal including the lesion area is removed from the first segmentation template of the liver area to obtain a mask template that does not include the interference signal; the mask template is then used to obtain a grayscale image of the marked liver area to achieve separation of the liver area and the lesion area; finally, the attenuation coefficient is calculated only for the sampling points in the liver and non-lesion areas to achieve more accurate measurement of fatty degeneration of the liver. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only embodiments of the invention. Those skilled in the art can also derive other drawings based on the provided drawings without inventive effort:

[0050] Figure 1 FIG2 is a flow chart of a method for ultrasonically measuring liver fatty degeneration based on image processing according to an embodiment of the present invention;

[0051] Figure 2 Shown Figure 1The schematic flow chart of step S1 is shown;

[0052] Figure 3 Shown is a set of RF signals before preprocessing and their 3D visualization results;

[0053] Figure 4 Shown are the preprocessed grayscale images and their 3D visualization results;

[0054] Figure 5 Shown is the Figure 4 The first segmentation template of the liver region is obtained after processing the grayscale image shown;

[0055] Figure 6 Shown Figure 1 The schematic flow chart of step S2 shown;

[0056] Figure 7 Shown is the Figure 4 The grayscale image shown is the result after noise reduction processing;

[0057] Figure 8 shown Figure 5 The second segmentation template of the liver region is obtained by removing the interference signal from the first segmentation template of the liver region shown;

[0058] Figure 9 Shown Figure 1 The schematic flow chart of step S3 shown;

[0059] Figure 10 Shown is the corrected mean threshold surface;

[0060] Figure 11 FIG2 is a schematic diagram of a liver fatty degeneration ultrasound measurement device based on image processing provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0061] To facilitate understanding of the invention, the invention will be described more fully below with reference to the accompanying drawings. The drawings illustrate exemplary embodiments of the invention. However, the invention may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and comprehensive disclosure of the invention.

[0062] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the invention pertains. The terms used in the specification of the invention herein are for the purpose of describing specific embodiments only and are not intended to limit the invention.

[0063] To achieve the above object, the present invention provides an ultrasonic measurement method for liver steatosis based on image processing, referring to Figure 1The method for measuring liver steatosis by ultrasound based on image processing comprises the following steps:

[0064] Step S1, pre-processing a set of ultrasound radio frequency (RF) signals of the abdominal area including the liver area acquired by ultrasound imaging and converting the signals into a grayscale image;

[0065] Specifically, in this embodiment, RF signal data acquired through ultrasound imaging is imported, where a set of RF signals refers to a series of ultrasound radio frequency signals having one of 2 to 256 columns. Then, the imported RF signals are preprocessed into a grayscale image format with pixel values ​​between [0, 1], which can facilitate subsequent data processing while reducing computational costs.

[0066] Furthermore, in one embodiment of the present invention, Figure 2 As shown in Figure 2, the entire preprocessing process includes the following steps:

[0067] Step S11: performing interference elimination processing on the RF signal in the time domain and the frequency domain;

[0068] Specifically, in this embodiment, hardware interference must be eliminated for each column of RF signal data. For example, pulse interference at a fixed depth is eliminated. Frequency filtering is then performed to remove low-frequency interference and perform an inverse Fourier transform to restore the signal. The interference-eliminated RF signal is then converted to a float value type using a data type conversion function.

[0069] Step S12: obtaining the absolute value of the envelope of the processed RF signal;

[0070] Specifically, in this embodiment, an envelope function or a filter function is used to obtain the upper envelope of the signal, and then the absolute value thereof is obtained.

[0071] Step S13: converting the RF signal after taking the absolute value into a grayscale image.

[0072] Specifically, in this embodiment, the signal after taking the absolute value is converted into a grayscale image through matrix operation.

[0073] Figure 3 Shown is a set of RF signals before preprocessing and their 3D visualization results. Figure 4 is the preprocessed RF signal and its 3D visualization result. Figure 3 and Figure 4 As shown in Figure 3, the image pixel values ​​of the grayscale image obtained after preprocessing and conversion are between [0, 1], while retaining the key features.

[0074] Step S2: Process the grayscale image to obtain a first segmentation template for the liver region.

[0075] Specifically, in this embodiment, from the overall image analysis, the signal shows a continuous attenuation trend within the liver region, while suddenly increasing at the liver edge. Utilizing this feature, we first use image processing methods to extract the grayscale variation trend of the image and find the initial range of the liver. Then, within this initial range, we traverse each column of the grayscale image and find the first valley point or lowest point, as well as the nearest vertex or maximum point before the first valley point or lowest point. These two points are the starting and ending points of the liver region in that column. The liver region is then obtained by combining the information from all columns. Figure 5 That is right Figure 4 The first segmentation template of the liver region is obtained after processing as shown in FIG. Figure 6 As shown, step S2 includes:

[0076] Step S21, extracting the grayscale change trend of the grayscale image;

[0077] Specifically, in this embodiment, the local Gaussian weighted mean of the grayscale image is first calculated to obtain an adaptive threshold surface of the image, which reflects the grayscale change trend of the image.

[0078] Step S22: using the grayscale change trend to obtain an initial range of the liver image;

[0079] Specifically, in this embodiment, the adaptive threshold surface obtained above is first flipped row by row; the minimum pixel value of each corresponding point on the adaptive threshold surface before and after the flip is obtained to obtain a symmetrical adaptive threshold surface; then, the maximum value of each row in the symmetrical adaptive threshold surface is obtained as an adaptive threshold curve; then, the adaptive threshold curve is smoothed, and the range enclosed by the smoothed adaptive threshold curve is used as the initial range of the liver image.

[0080] Furthermore, in one embodiment of the present invention, a moving average filter with a span equal to M is required to smooth the threshold curve. This process is equivalent to low-pass filtering. s (i) is the smoothed value of the first data point, N is y s (i) The number of adjacent data points on both sides, 2*N+1 is the span, and its smooth response is implemented by the following difference equation:

[0081] y s ()=[(+N)+y(i+N-1)+...+(-N)] / (2*N+1)

[0082] Step S23, traversing each column of the initial range of the liver image to determine the starting point and the end point of the liver image area in that column;

[0083] Specifically, in this embodiment, first, the first local minimum point A of the adaptive threshold curve is found within the preset row range [ROIStart, ROIEnd], and then the nearest vertex or maximum point B after point A is found. Then, each column of the initial range of the liver image is traversed, and for each column of image data: the moving average filter is first used to smooth the image data of the column; then the nearest valley point or grayscale minimum point C is found within the row range [ROIStart, B]. n Then in the row range [ROIStart,D n ] to find the maximum gray value point D n , row range [C n , D n ] is the liver area of ​​this column.

[0084] Step S24: Combine the start points and end points of all columns to obtain the first segmentation template of the liver region.

[0085] Step S3, removing the interference signal area from the first liver region segmentation template to obtain a second liver region segmentation template;

[0086] Specifically, in this embodiment, the interference signal region refers to the region in the grayscale image that is particularly bright or dark compared to the surrounding tissue caused by the blood vessels or other tissue structures in the liver. Before removing the interference signal region in the first segmentation template of the liver region, the grayscale image is first subjected to noise reduction processing. For example, Figure 7 As shown in FIG, performing denoising on a grayscale image can achieve anisotropic diffusion smoothing of the grayscale image, and retain the edge sharpness during denoising.

[0087] Specifically, in this embodiment, due to the influence of hardware devices or lesions, the collected RF signal may suddenly increase, or suddenly decrease when encountering blood vessels. Using these features, we first calculate the local adaptive segmentation threshold, then modify the segmentation threshold based on the prior knowledge of the exponential decay characteristics of ultrasound signals in tissues and the manually set denoising coefficient, detect the location of the interference signal area, and finally remove it in the first mask template of the liver area, obtaining the following: Figure 8 The second segmentation template of the liver region is shown in FIG. Figure 9 As shown, step S3 includes:

[0088] Step S31: Processing the grayscale image after noise reduction to obtain a segmentation threshold curve of the grayscale image;

[0089] Specifically, in this embodiment, the local mean intensity of the denoised grayscale image is first calculated to obtain an average threshold surface. The average threshold surface is then flipped row by row, and the minimum pixel value of each corresponding point on the average threshold surface before and after the flip is taken to obtain a symmetrical average threshold surface. The average value of each row of this average threshold surface is then calculated to serve as the segmentation threshold curve for the grayscale image.

[0090] Step S32: using the exponential decay characteristics of the ultrasonic signal in the tissue to modify the segmentation threshold curve;

[0091] Specifically, in this embodiment, the minimum point E and the maximum point F of the segmentation threshold curve are calculated respectively; within the range [, F], the absolute value of the segmentation threshold curve is first calculated, and then an exponential function is used to fit it; finally, the absolute value and the minimum value of the fitting result are used to replace the corresponding part of the segmentation threshold curve.

[0092] Step S33: Calculate the segmentation multiple for distinguishing the interference signal area according to the modified segmentation threshold curve;

[0093] Specifically, in this embodiment, the modified segmentation threshold curve is first smoothed; then the modified segmentation threshold curve is expanded to obtain a new average threshold surface, such as Figure 10 As shown; the segmentation multiple is calculated by using the grayscale value of the grayscale image after noise reduction processing and the grayscale value of the average threshold surface.

[0094] Step S34: removing the interference signal region from the first liver region segmentation template to obtain the second liver region segmentation template.

[0095] Specifically, in this embodiment, each row and column in the first segmentation template of the liver region is traversed: first, the area with a grayscale value greater than a first preset threshold or less than a second preset threshold is removed; then, the area with less than a preset number of pixels in each column or less than a preset number of pixels in each row is removed, and the remaining area is the calculated valid area, that is, the second segmentation template of the liver region, such as Figure 8 shown.

[0096] Step S4, using the second segmentation template of the liver region to mark the grayscale image to obtain a region of interest;

[0097] Specifically, in this embodiment, Figure 8 The second segmentation template of the liver region after removing the interference signal region is shown Figure 7 By multiplying the grayscale image after noise reduction as shown, the region of interest can be obtained. Therefore, the attenuation coefficient can be calculated only for the sampling points in the liver and non-lesion areas, achieving more accurate measurement of hepatic steatosis.

[0098] Step S5: calculating the attenuation coefficient representing the degree of liver steatosis in the region of interest.

[0099] Specifically, in this embodiment, first, envelope calculation is performed on the RF signals of all columns within the region of interest to obtain an envelope signal; the envelope signals of all columns are averaged to obtain an average envelope signal representing the tissue within the region of interest; and the exponential attenuation coefficient of the average envelope signal is calculated as the attenuation coefficient representing the degree of fatty degeneration of the liver.

[0100] This embodiment converts the RF signal collected by the ultrasound probe into a grayscale image. Subsequently, the grayscale image is processed using an image processing algorithm to obtain an accurately segmented liver region, which serves as a first segmentation template for the liver region. Then, the interference signal region including the lesion region is removed from the first segmentation template of the liver region to obtain a mask template that does not include the interference signal region. The mask template is then used to obtain a grayscale image of the marked liver region to achieve separation of the liver region and the lesion region. Finally, the attenuation coefficient is calculated only for sampling points in the liver and non-lesion regions to achieve more accurate measurement of hepatic steatosis.

[0101] The present invention also provides an ultrasonic measuring device for liver fatty degeneration based on image processing, such as Figure 11 As shown, the liver fatty degeneration ultrasound measurement device based on image processing includes:

[0102] The signal acquisition module 1110 is configured to acquire a set of RF signals of the abdominal region including the liver region obtained by scanning with an ultrasound probe;

[0103] An image conversion module 1120 is used to pre-process the acquired RF signal and convert it into a grayscale image;

[0104] A first processing module 1130 is configured to process the grayscale image to obtain a first segmentation template for the liver region;

[0105] a noise reduction module 1140, configured to perform noise reduction processing on the grayscale image;

[0106] A second processing module 1150 is configured to remove the interference signal region from the first liver region segmentation template to obtain a second liver region segmentation template;

[0107] a marking module 1160, configured to mark the grayscale image using the second segmentation template of the liver region to obtain a region of interest;

[0108] The calculation module 1170 is configured to calculate an attenuation coefficient representing the degree of liver steatosis in the region of interest.

[0109] Those skilled in the art will understand that the above is an embodiment of the liver fatty degeneration ultrasonic measurement device based on image processing provided by an embodiment of the present invention. The device and the above-mentioned liver fatty degeneration ultrasonic measurement method based on image processing belong to the same inventive concept. For details not fully described in the embodiment of the liver fatty degeneration ultrasonic measurement device based on image processing, please refer to the embodiment of the above-mentioned liver fatty degeneration ultrasonic measurement method based on image processing.

[0110] An embodiment of the present invention further provides an ultrasonic measurement device for liver fatty degeneration based on image processing, which may include:

[0111] Memory for storing computer programs;

[0112] The processor, when used to execute the computer program stored in the above-mentioned memory, can implement the following steps:

[0113] A set of RF signals of the abdominal area, including the liver area, acquired by ultrasound imaging are preprocessed and converted into a grayscale image; the grayscale image is processed to obtain a first segmentation template of the liver area; the interference signal area is removed from the first segmentation template of the liver area to obtain a second segmentation template of the liver area; the grayscale image is marked with the second segmentation template of the liver area to obtain a region of interest; and within the region of interest, an attenuation coefficient representing the degree of liver fatty degeneration is calculated.

[0114] An embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps can be implemented:

[0115] A set of RF signals of the abdominal area, including the liver area, acquired by ultrasound imaging are preprocessed and converted into a grayscale image; the grayscale image is processed to obtain a first segmentation template of the liver area; the interference signal area is removed from the first segmentation template of the liver area to obtain a second segmentation template of the liver area; the grayscale image is marked with the second segmentation template of the liver area to obtain a region of interest; and within the region of interest, an attenuation coefficient representing the degree of liver fatty degeneration is calculated.

[0116] The computer-readable storage medium may include: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and other media that can store program codes.

[0117] In the description provided herein, numerous specific details are described. However, it is understood that embodiments of the present invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques are not shown in detail so as not to obscure the understanding of this description.

[0118] Similarly, it should be understood that in order to streamline the present disclosure and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as reflected in the claims below, inventive aspects lie in less than all the features of the individual embodiments disclosed above. Accordingly, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of the invention.

[0119] Those skilled in the art will appreciate that the modules in the devices in the embodiments can be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments can be combined into one module or unit or component, and in addition they can be divided into multiple submodules or subunits or subassemblies. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification and all processes or units of any method or device disclosed in this manner can be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification can be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0120] Furthermore, those skilled in the art will appreciate that although some embodiments described herein include certain features included in other embodiments but not other features, combinations of features from different embodiments are intended to be within the scope of the present invention and to form different embodiments. For example, any of the claimed embodiments may be used in any combination.

[0121] The various component embodiments of the present invention can be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It will be appreciated by those skilled in the art that a microprocessor or digital signal processor (DSP) can be used in practice to implement some or all of the functions of some or all of the components in accordance with the embodiments of the present invention. The present invention can also be implemented as a device or apparatus program (e.g., a computer program and a computer program product) for executing a portion or all of the methods described herein. Such a program implementing the present invention can be stored on a computer-readable medium, or can have the form of one or more signals. Such a signal can be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0122] It should be noted that the above embodiments illustrate rather than limit the invention, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbols between brackets should not be construed as limiting the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising several different elements and by means of appropriately programmed computers. Several of these devices may be embodied by the same item of hardware. The use of the words first, second, and third, etc. does not indicate any order. These words may be interpreted as names.

Claims

1. A method for measuring liver steatosis by ultrasound based on image processing, characterized in that: The following steps are involved: Step S1, pre-processing a set of ultrasound radio frequency (RF) signals of the abdominal area including the liver area acquired by ultrasound imaging and converting the signals into a grayscale image; Step S2: Processing the grayscale image to obtain a first segmentation template for the liver region; Step S3, removing the interference signal area from the first liver region segmentation template to obtain a second liver region segmentation template; Step S4, using the second segmentation template of the liver region to mark the grayscale image to obtain a region of interest; Step S5: calculating an attenuation coefficient representing the degree of liver steatosis within the region of interest; The step S3 comprises: Step S31: Processing the grayscale image after noise reduction to obtain a segmentation threshold curve of the grayscale image; Step S32: using the exponential decay characteristics of the ultrasonic signal in the tissue to modify the segmentation threshold curve; Step S33: Calculate the segmentation multiple for distinguishing the interference signal area according to the modified segmentation threshold curve; Step S34: removing the interference signal region from the first liver region segmentation template according to the segmentation multiple and a preset denoising coefficient to obtain the second liver region segmentation template.

2. The method for measuring liver steatosis by ultrasound based on image processing according to claim 1, wherein: The step S1 comprises: Step S11: performing interference elimination processing on the RF signal in the time domain and the frequency domain; Step S12: obtaining the absolute value of the envelope of the processed RF signal; Step S13: converting the RF signal after taking the absolute value into a grayscale image.

3. The method for measuring liver steatosis by ultrasound based on image processing according to claim 1, wherein: The step S2 comprises: Step S21, extracting the grayscale change trend of the grayscale image; Step S22: using the grayscale change trend, obtaining the initial range of the liver; Step S23, traverse each column of the initial range of the liver to determine the starting point and end point of the liver region in that column; Step S24: Combine the start points and end points of all columns to obtain the first segmentation template of the liver region.

4. The method for measuring liver steatosis by ultrasound based on image processing according to claim 3, wherein: In the step S21 , the local Gaussian weighted mean of the grayscale image is calculated to obtain an adaptive threshold surface of the grayscale image as the grayscale change trend of the grayscale image.

5. The method for measuring liver steatosis by ultrasound based on image processing according to claim 1, wherein: Between step S2 and step S3, the method further includes: performing noise reduction processing on the grayscale image.

6. The method for measuring liver steatosis by ultrasound based on image processing according to claim 1, wherein: In the step S33, it includes: Expand the modified segmentation threshold curve to obtain the average threshold surface; The segmentation multiple is calculated using the grayscale value of the grayscale image after noise reduction processing and the grayscale value of the average threshold surface.

7. The method for measuring liver steatosis by ultrasound based on image processing according to claim 1, wherein: In the step S5, it includes: Performing envelope calculation on the RF signals of all columns within the region of interest to obtain envelope signals; Averaging the envelope signals of all columns to obtain an average envelope signal representing the tissue within the region of interest; The exponential decay coefficient of the average envelope signal was calculated as the attenuation coefficient representing the degree of hepatic steatosis.

8. An ultrasonic measurement device for liver fatty degeneration based on image processing, characterized in that: include: a signal acquisition module, configured to acquire a set of RF signals of an abdominal region including a liver region obtained by scanning with an ultrasound probe; An image conversion module, used for pre-processing the acquired RF signal and converting it into a grayscale image; a first processing module, configured to process the grayscale image to obtain a first segmentation template for the liver region; A second processing module is configured to remove the interference signal region from the first liver region segmentation template to obtain a second liver region segmentation template, comprising: processing the grayscale image after noise reduction to obtain a segmentation threshold curve for the grayscale image; modifying the segmentation threshold curve using the exponential attenuation characteristics of ultrasound signals in tissue; calculating a segmentation factor for distinguishing the interference signal region based on the modified segmentation threshold curve; and removing the interference signal region from the first liver region segmentation template based on the segmentation factor and a preset denoising coefficient to obtain the second liver region segmentation template; a marking module, configured to mark the grayscale image using the second segmentation template of the liver region to obtain a region of interest; The calculation module is used to calculate the attenuation coefficient representing the degree of liver fatty degeneration in the region of interest.

9. The device for measuring liver fatty degeneration by ultrasound based on image processing according to claim 8, characterized in that: Also includes: The noise reduction module is used to perform noise reduction processing on the grayscale image.

10. A liver steatosis ultrasound measurement system based on image processing, characterized in that: The device comprises an ultrasound probe and the device for measuring liver steatosis based on image processing according to any one of claims 8 to 9.

11. An ultrasonic measurement device for liver fatty degeneration based on image processing, characterized in that: include: memory for storing computer programs; A processor is configured to implement the steps of the method for measuring liver fatty degeneration by ultrasound based on image processing according to any one of claims 1 to 7 when executing the computer program.

12. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method for measuring liver steatosis based on ultrasound image processing according to any one of claims 1 to 7 are implemented.

Images