Fatty liver characteristic parameter calculation system

Abstract

The invention provides a fatty liver characteristic parameter calculation system, which comprises a data acquisition unit used for acquiring liver detection data of a patient and determining a current diagnosis demand; the data conversion unit is used for selecting a first conversion mode established on the basis of a measured value range or a second conversion mode established on the basis of an MRI proton density fat fraction according to diagnosis requirements so as to convert the ultrasonic attenuation coefficient into an attenuation grade fraction in a percentage form; according to the attenuation grade score, constructing a fatty liver characteristic parameter; and the data analysis unit evaluates the fatty liver condition of the patient according to the fatty liver characteristic parameters. According to the method, the ultrasonic attenuation coefficient is converted into the attenuation grade score which is easier to understand and compare, so that a doctor can quickly evaluate the severity of the fatty liver without deeply understanding back physical parameters, a patient can be helped to better understand the health state of the patient, the diagnosis efficiency can be improved, doctor-patient communication can be enhanced, and the patient experience can be improved. And personalized medical services are realized.

Description

Technical Field

[0001] The present application relates to the field of fatty liver characteristic parameter calculation, and in particular, to a fatty liver characteristic parameter calculation system. Background Art

[0002] Fatty liver disease (MASLD) is a common metabolic-related disease with an estimated prevalence of 25%-30% in the general population. Its early diagnosis and accurate assessment are crucial for disease staging and treatment decisions. MRI can detect the difference in proton chemical shifts between triglycerides and water, providing a quantitative estimate of proton density fat fraction (MRI-PDFF). MRI-PDFF quantitatively assesses liver fat content by directly measuring proton signals in water and fat. The results are intuitive and easy to interpret clinically, and have been widely accepted as a non-invasive reference standard for assessing the degree of fatty liver. However, MRI equipment is expensive and complex, and is not suitable for screening for fatty liver disease, especially given its high prevalence of 25%-30%.

[0003] Ultrasound examination is the preferred method for liver imaging examination, but conventional ultrasound examination can only make subjective evaluations of fatty liver and cannot make quantitative diagnosis. Ultrasound attenuation coefficient (AC) is a non-invasive ultrasound quantitative parameter based on the acoustic characteristics of liver tissue. It can non-invasively evaluate the degree of fatty liver and has the characteristics of convenient operation and low cost. However, the AC unit is dB / cm / MHz, which is not easy for clinicians and patients to understand and accept. Summary of the invention

[0004] Based on the problems existing in the prior art, the present application provides a calculation system for characteristic parameters of fatty liver to solve at least one of the technical problems in the background technology. The specific scheme is as follows:

[0005] A calculation system for characteristic parameters of fatty liver, comprising:

[0006] A data acquisition unit, used to acquire the patient's liver detection data and determine the current diagnostic needs, wherein the liver detection data at least includes the ultrasonic attenuation coefficient of the liver;

[0007] A data conversion unit, configured to select a first conversion method based on a measurement range or a second conversion method based on MRI proton density fat fraction according to the diagnostic requirement, so as to convert the ultrasonic attenuation coefficient into an attenuation grade score in percentage form; and construct a fatty liver characteristic parameter according to the attenuation grade score;

[0008] The first conversion method is constructed based on the linear relationship between the ultrasound attenuation coefficient and the liver fat fraction and combined with the range distribution of the ultrasound attenuation coefficient; the second conversion method is constructed based on the MRI proton density fat fraction as the gold standard and combined with the relationship between the ultrasound attenuation coefficient and the MRI proton density fat fraction;

[0009] A data analysis unit is used to evaluate the patient's fatty liver condition based on fatty liver characteristic parameters.

[0010] In some specific embodiments, in the data conversion unit:

[0011] If the diagnostic speed requirement in the diagnostic requirement is higher than the preset speed, selecting the first conversion mode;

[0012] If the diagnostic accuracy requirement in the diagnostic requirement is higher than the preset accuracy, the second conversion method is selected.

[0013] In some specific embodiments, it also includes:

[0014] The data fusion unit is used to analyze whether the MRI proton density fat fraction of the liver exists in the liver monitoring data, and if so, to fuse the attenuation level score and the MRI proton density fat fraction to obtain fatty liver characteristic parameters.

[0015] In some specific embodiments, the expression of the first conversion mode specifically includes:

[0016]

[0017] Wherein, AGFF represents the attenuation grade fraction, and AC represents the ultrasonic attenuation coefficient.

[0018] In some specific embodiments, the second conversion method specifically includes:

[0019] The MRI proton density fat fraction and ultrasound attenuation coefficient of multiple patient samples were collected in advance to establish a data pairing relationship between the MRI proton density fat fraction and the ultrasound attenuation coefficient;

[0020] Fitting a regression equation based on the data pairing relationship table;

[0021] Substituting the ultrasound attenuation coefficient into the regression equation, the corresponding MRI proton density fat fraction is obtained, and the MRI proton density fat fraction is used as the attenuation grade score.

[0022] In some specific embodiments, the expression of the regression equation specifically includes:

[0023] AGFF=(k*AC-b) 2

[0024] Wherein, AGFF represents the attenuation grade fraction, AC represents the ultrasonic attenuation coefficient, k represents the slope, and b is a constant term.

[0025] In some specific embodiments, the calculation expression of the fatty liver characteristic parameter is:

[0026] FFF=w1·AGFF+w2·PDFF

[0027] Among them, FFF represents the characteristic parameter of fatty liver, AGFF represents the attenuation grade score, PDFF represents the MRI proton density fat fraction, w1 represents the first weight coefficient, and w2 represents the second weight coefficient.

[0028] In some specific embodiments, the first weight coefficient is 0.5, and the second weight coefficient is 2.

[0029] In some specific embodiments, the value of k is 7.21 and the value of b is 1.95.

[0030] In some specific embodiments, when the characteristic parameter of fatty liver is between 33% and 53%, the patient is identified as having mild fatty liver;

[0031] When the characteristic parameter of fatty liver is greater than 53% and less than 72%, the patient is considered to have moderate fatty liver;

[0032] When the characteristic parameter of fatty liver is not less than 72%, the patient is deemed to have severe fatty liver.

[0033] Beneficial effects: This application proposes a calculation system for characteristic parameters of fatty liver, which converts the ultrasonic attenuation coefficient into an attenuation grade score that is easier to understand and compare. It can not only help doctors quickly assess the severity of fatty liver without the need for an in-depth understanding of the physical parameters behind it, but also help patients better understand their health status, help improve diagnostic efficiency, strengthen doctor-patient communication, and achieve personalized medical services. A selection logic based on diagnostic speed and accuracy requirements is introduced to ensure that the most suitable conversion method can be used in different situations. Combining the ultrasonic attenuation coefficient with the MRI proton density fat score provides a more comprehensive and reliable basis for evaluation.

[0034] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0036] Figure 1 is a module schematic diagram of the computing system of the present application;

[0037] Figure 2 is a schematic diagram of the principle of the computing system of the present application;

[0038] Figure 3 is a schematic diagram of a fitting curve of the present application;

[0039] Figure 4 It is a flow chart of the control method of the present application.

[0040] Figure numerals: 1-data acquisition unit; 2-data conversion unit; 3-data parsing unit; 4-data fusion unit. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0042] This application proposes a calculation system for characteristic parameters of fatty liver, which converts the ultrasonic attenuation coefficient into an attenuation grade score that is easier to understand and compare. It can not only help doctors quickly assess the severity of fatty liver without in-depth understanding of the physical parameters behind it, but also help patients better understand their health status, help improve diagnostic efficiency, strengthen doctor-patient communication, and realize personalized medical services. The module diagram of the calculation system is shown in the attached figure. Figure 1 The principle is shown in the attached Figure 2 The specific plan is as follows:

[0043] A calculation system for characteristic parameters of fatty liver, comprising:

[0044] A data acquisition unit 1 is used to acquire the patient's liver detection data and determine the current diagnostic needs, wherein the liver detection data at least includes the ultrasonic attenuation coefficient of the liver;

[0045] The data conversion unit 2 is used to select a first conversion method based on a measurement range or a second conversion method based on MRI proton density fat fraction according to the diagnostic requirements, so as to convert the ultrasonic attenuation coefficient into an attenuation grade score in percentage form; and construct a fatty liver characteristic parameter according to the attenuation grade score;

[0046] The first conversion method is constructed based on the linear relationship between the ultrasound attenuation coefficient and the liver fat fraction and combined with the range distribution of the ultrasound attenuation coefficient; the second conversion method is constructed based on the MRI proton density fat fraction as the gold standard and combined with the relationship between the ultrasound attenuation coefficient and the MRI proton density fat fraction;

[0047] The data analysis unit 3 is used to evaluate the fatty liver condition of the patient according to the fatty liver characteristic parameters.

[0048] This application converts the ultrasonic attenuation coefficient into a percentage form, which is used as the basis for evaluating the condition of fatty liver, so as to realize the intuitive and standardized detection of liver fat degree. Different conversion schemes are selected according to different medical needs, taking into account both primary screening and accurate diagnosis. The ultrasonic attenuation coefficient of the patient's liver is obtained through ultrasonic detection, and its detection cost is much lower than more complex imaging technologies such as MRI, which is especially important for medical institutions with limited resources or patients whose economic conditions do not allow it. Compared with MRI, ultrasound examination is not only cheaper, but also easy to operate, does not require special appointments, can get results immediately, and is more comfortable for patients because it is a non-invasive process that does not require exposure to radiation.

[0049] The data acquisition unit 1 is responsible for collecting liver test data and determining the diagnostic requirements. The diagnostic requirements need to be determined based on the current medical scenario to clarify what kind of assessment or diagnosis is needed. The diagnostic data of this application at least includes the ultrasonic attenuation coefficient (ie, AC measurement value).

[0050] In practical applications, AC measurement values ​​may be obtained through ultrasonic attenuation imaging (USAT, Ultrasound Attenution) or through attenuation imaging (ATI).

[0051] When using USAT, the patient lies flat with the right arm raised to the side of the head. The adult abdominal examination mode is selected, and the probe is placed in the right intercostal scan. Note that the incident direction of the ultrasound beam is perpendicular to the liver capsule, and the patient is asked to breathe steadily. Press "Fatty liver lab" on the touch screen to start fatty liver assessment, and the acoustic attenuation (USAT) is the default setting. After entering USAT, a large ROI box and a small ROI box appear. The large ROI box is the USAT imaging area, which covers as much liver parenchyma as possible. The small green ROI box is the USAT measurement box, with a default size of 2×2 cm. The size and position of the measurement box can be adjusted. It is recommended to select the S5 / S6 segment liver parenchyma. Note that the upper edge of the measurement box is 1-2 cm away from the liver capsule, and the measurement box should avoid large blood vessels and rib acoustic shadows. Press UPDATE to start USAT imaging and measurement, the image is automatically frozen, and the measurement results are automatically displayed, including: mean, maximum, minimum, and standard deviation. The measurement frame position can be moved after the image is frozen, and the result will be automatically updated; the reliability map (RLB-MAP) and motion stability index (M-STB INDEX) are used as quality control parameters for acoustic attenuation imaging. RLB-MAP is recommended to be above 80%, and M-STB INDEX is green 4 stars or above; select the same position and measure the average value 5 times in a row. Detection failure standard: The reliability map (RLB-MAP) of 5 consecutive measurements is less than 80%. Unreliable detection standard: The ratio of the median to the interquartile range of 5 consecutive measurements is greater than 30%.

[0052] When using the ATI mode of the ultrasound imaging system to obtain AC measurements, the subject is preferably in the supine position. If the image display is insufficient, the left side can be used, but the left angle is <30 degrees. Activate the ATI imaging mode and examine the right liver lobe through the intercostal window perpendicular to the skin. Try to keep the ATI green fan-shaped sampling frame in the place where the liver biopsy was performed. The sampling frame should be as large as possible to obtain more average data. The sampling frame is placed about 1.5 cm below the liver capsule to avoid reverberation artifacts. The sampling frame should be placed away from larger blood vessels, bile ducts and other structures as much as possible. ATI will also automatically remove non-uniform areas such as large blood vessels and cystic structures from the ATI region of interest data through the automatic data recognition system. Freeze the image while the subject holds his breath, and set the measurement region of interest (white ROI) in the green sampling frame of ATI for measurement ( Figure 1). The white ROI sampling frame is adjusted to the minimum adjustable value of the system. Then, the average attenuation coefficient result is displayed in dB / cm / MHz. The quality control parameter (determination coefficient) R2 value is used to determine whether the attenuation coefficient of each acquisition is qualified. The R2 value can be divided into poor (R2<0.80), good (R2=0.80-0.89) or excellent (R2>0.90). Only the attenuation coefficient results with R2>0.80 are considered qualified and valid. Five ATI images are acquired continuously and the corresponding effective acoustic attenuation coefficient is obtained. The skin capsule distance (SCD) is measured in the ATI examination, that is, the distance between the skin surface and the liver capsule. In each patient, all measurements were performed in the intercostal acoustic window of the same patient holding his breath.

[0053] The data conversion unit 2 selects an appropriate algorithm according to the diagnostic requirements to convert the ultrasound attenuation coefficient into an attenuation grade score in percentage form.

[0054] In the present application, the first conversion method is to calculate the attenuation grade score by a standardized formula based on the liver AC measurement range. The AC measurement range is 0.5-1.0dB / cm / MHz, which is linearly related to the liver fat score, and the AC measurement values ​​of the population are normally distributed within the range of 0.5-1.0dB / cm / MHz. A calculation formula is constructed based on the normal distribution range, and the collected liver AC measurement values ​​are substituted into the formula for calculation, and the attenuation grade score in percentage units is directly output. In some specific embodiments, the expression of the first conversion method specifically includes:

[0055]

[0056] Wherein, AGFF represents the attenuation grade fraction, and AC represents the ultrasonic attenuation coefficient.

[0057] The first conversion method can achieve rapid conversion. By providing a unified grade score evaluation formula, it makes the representation of liver fat change more intuitive, reduces operation dependence and subjective differences, and is suitable for rapid screening scenarios. In primary care and large-scale screening scenarios, the position of the measured value in the overall range can be simply and intuitively evaluated to determine whether the patient needs further diagnosis.

[0058] The second conversion method calculates the PDFF conversion score through the regression equation of AC measurement and MRI-PDFF (MRI proton density fat fraction). In some specific embodiments, the second conversion method specifically includes: pre-collecting the MRI proton density fat fraction and ultrasonic attenuation coefficient of multiple patient samples, establishing a data pairing relationship between the MRI proton density fat fraction and the ultrasonic attenuation coefficient; fitting a regression equation based on the data pairing relationship table; substituting the ultrasonic attenuation coefficient into the regression equation to obtain the corresponding MRI proton density fat fraction, and using the MRI proton density fat fraction as the attenuation grade score. Using MRI-PDFF as the gold standard, a linear regression equation is established using the collected liver AC measurement. The square root of the fat percentage is calculated by the formula, and then the total PDFF value is obtained by inverse square. In practical applications, the patient sample is a patient with suspected fatty liver, and the ultrasonic AC value and MRI-PDFF of the patient are measured at the same time to establish a data pairing relationship. The regression coefficient in the above formula is fitted by linear regression analysis. Substitute the ultrasonic AC value into the formula to output the fat percentage consistent with MRI. In practical applications, the linear formula is replaced with a nonlinear model such as polynomial regression and neural network to optimize the evaluation of complex cases.

[0059] In some specific embodiments, the expression of the regression equation specifically includes:

[0060] AGFF=(k*AC-b) 2

[0061] Wherein, AGFF represents the attenuation grade fraction, AC represents the ultrasonic attenuation coefficient, k represents the slope, and b is a constant term.

[0062] In some specific embodiments, the value of k is 7.21 and the value of b is 1.95. The fitting curve is shown in the attached figure. Figure 3 shown.

[0063] The second conversion method provides a standardized formula based on MRI, which is applicable to different models of ultrasound equipment and is suitable for scenarios with precise graded diagnosis requirements, such as specialized hospitals or clinical research.

[0064] In some specific embodiments, in the data conversion unit 2: if the diagnostic speed requirement in the diagnostic demand is higher than the preset speed, the first conversion method is selected; if the diagnostic accuracy requirement in the diagnostic demand is higher than the preset accuracy, the second conversion method is selected. The attenuation grade score (AGFF) obtained by the first conversion method is obtained based on the measurement range of the ultrasonic attenuation coefficient (AC). It is calculated by a standardized formula and can quickly screen the degree of fatty liver, which is suitable for low fat content or large-scale screening scenarios. The PDFF conversion score obtained by the second conversion method can provide a high-precision quantitative assessment of fat content, which is particularly suitable for the diagnosis of patients with high fat content.

[0065] In some specific embodiments, it also includes:

[0066] The data fusion unit 4 is used to analyze whether there is an MRI proton density fat score of the liver in the liver monitoring data. If so, the attenuation grade score and the MRI proton density fat score are fused to obtain the fatty liver characteristic parameter. The data fusion unit 4 checks whether the input data set contains the proton density fat score (PDFF) provided by MRI. This step ensures that the subsequent data fusion operation will only be performed if more detailed information is indeed available. According to whether PDFF exists and the accuracy requirements of the diagnostic needs, it is determined whether data fusion needs to be performed. If fusion is determined, a specific algorithm or model is used to combine the attenuation grade score obtained by converting the ultrasound attenuation coefficient with the MRI PDFF. This fusion may be based on weighted average, machine learning model or other statistical methods to ensure that the newly generated fatty liver characteristic parameter can better reflect the actual liver condition. Finally, a comprehensive fatty liver characteristic parameter is output, which integrates the advantages of data from two different sources and provides a more comprehensive and accurate liver health assessment. By introducing the data fusion unit 4, the computing system can not only use conventional ultrasound detection data, but also integrate high-precision PDFF information from MRI, thereby providing a more comprehensive and reliable fatty liver assessment. It can be applied to situations that require highly accurate diagnosis, such as scientific research projects, consultation on difficult diseases or long-term follow-up monitoring. It also reflects the advantage of the system's flexibility, automatically adjusting its processing mode according to the available data resources to meet different clinical needs.

[0067] In some specific embodiments, the calculation of the fatty liver feature parameter (FFF, Fatty Liver Feature Factor) adopts the form of weighted sum, combining the ultrasound attenuation grade fraction (AGFF, Attenuation Grade Fat Fraction) and the MRI proton density fat fraction (PDFF, Proton Density Fat Fraction). This calculation method not only takes into account the information provided by two different detection methods, but also reflects the importance of each data through weight allocation. The calculation expression of the fatty liver feature parameter is:

[0068] FFF=w1·AGFF+w2·PDFF

[0069] Among them, FFF represents the characteristic parameter of fatty liver, AGFF represents the attenuation grade score, PDFF represents the MRI proton density fat score, w1 represents the first weight coefficient, and w2 represents the second weight coefficient. The result of the fusion score is a unified fat percentage, which is suitable for screening and precise diagnosis scenarios. As a unified indicator, the fusion score facilitates the follow-up monitoring of the degree of fatty liver and helps evaluate the treatment effect.

[0070] The choice of weight depends on many factors, including but not limited to the diagnostic needs, the quality of available data, and the specific situation of the medical institution. If there is a high requirement for diagnostic accuracy, a larger weight may be given to PDFF (ie, w2>w1) because MRI-PDFF provides a more accurate measurement of liver fat content. For situations where rapid results are required, more emphasis may be placed on AGFF (ie, w1>w2) because it can be obtained through faster and less expensive ultrasound examinations.

[0071] In some specific embodiments, the first weight coefficient is 0.5, and the second weight coefficient is 2. Setting the weight rule based on medical research reflects the law of fatty liver development and enhances the scientific nature of diagnosis.

[0072] In some embodiments, when the characteristic parameter of fatty liver is between 33% and 53%, the patient is considered to have mild fatty liver; when the characteristic parameter of fatty liver is greater than 53% and less than 72%, the patient is considered to have moderate fatty liver; when the characteristic parameter of fatty liver is not less than 72%, the patient is considered to have severe fatty liver. By establishing a clear fatty liver severity grading standard and matching the attenuation grade parameter with the fatty liver level, an intuitive reference framework is provided for doctors to help them quickly judge the condition and take corresponding measures. The standardized grading system facilitates information sharing and communication between different medical institutions.

[0073] In some embodiments, in addition to AC measurement, ultrasound parameters such as backscatter coefficient (BSC) and speed of sound (SOS) can be used to assess fat fraction.

[0074] The present application provides a control method for a computing system, which is used to implement the process of the computing system. The flow chart of the control method is attached. Figure 4 The specific plan is as follows:

[0075] 101. Obtain the patient's liver test data and determine the current diagnostic needs, where the liver test data at least includes the ultrasonic attenuation coefficient of the liver;

[0076] 102. Selecting a first conversion method based on a measurement range or a second conversion method based on MRI proton density fat fraction according to diagnostic requirements to convert the ultrasound attenuation coefficient into an attenuation grade score in percentage form; and constructing a fatty liver characteristic parameter according to the attenuation grade score;

[0077] The first conversion method is constructed based on the linear relationship between the ultrasound attenuation coefficient and the liver fat fraction and combined with the range distribution of the ultrasound attenuation coefficient; the second conversion method is constructed based on the MRI proton density fat fraction as the gold standard and combined with the relationship between the ultrasound attenuation coefficient and the MRI proton density fat fraction;

[0078] 103. Evaluate the patient's fatty liver condition based on fatty liver characteristic parameters.

[0079] The present application provides a computer program product, which includes computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes a calculation system for characteristic parameters of fatty liver. A calculation system for characteristic parameters of fatty liver is applied to a computer program product for easy execution.

[0080] The present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, a computing system as described above is implemented.

[0081] The computer storage medium of the present application may adopt any combination of one or more computer-readable media. The computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, device or device. The present application applies a calculation system for characteristic parameters of fatty liver to a computer-readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the clothing simulation method provided by the present application are implemented, which is simple and fast, easy to store, and not easy to lose.

[0082] This application proposes a calculation system for characteristic parameters of fatty liver, which converts the ultrasonic attenuation coefficient into an attenuation grade score that is easier to understand and compare. It can not only help doctors quickly assess the severity of fatty liver without in-depth understanding of the physical parameters behind it, but also help patients better understand their health status, help improve diagnostic efficiency, strengthen doctor-patient communication, and realize personalized medical services. The selection logic based on diagnostic speed and accuracy requirements is introduced to ensure that the most suitable conversion method can be used in different situations. Combining the ultrasonic attenuation coefficient with the MRI proton density fat score provides a more comprehensive and reliable evaluation basis.

[0083] Those skilled in the art should understand that the modules of the present application described above can be implemented by a general-purpose computing system, they can be concentrated on a single computing system, or distributed on a network composed of multiple computing systems, and optionally, they can be implemented by program codes executable by a computer system, so that they can be stored in a storage system and executed by the computing system, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present application is not limited to any specific combination of hardware and software.

[0084] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

[0085] The above disclosure only discloses several specific implementation scenarios of the present application. However, the present application is not limited thereto, and any changes that can be conceived by technicians in this field should fall within the scope of protection of the present application.

Claims

1. A system for calculating characteristic parameters of fatty liver, characterized in that: include: A data acquisition unit, used to acquire the patient's liver detection data and determine the current diagnostic needs, wherein the liver detection data at least includes the ultrasonic attenuation coefficient of the liver; A data conversion unit, configured to select a first conversion method based on a measurement range or a second conversion method based on MRI proton density fat fraction according to the diagnostic requirement, so as to convert the ultrasonic attenuation coefficient into an attenuation grade score in percentage form; and construct a fatty liver characteristic parameter according to the attenuation grade score; The first conversion method is constructed based on the linear relationship between the ultrasound attenuation coefficient and the liver fat fraction and combined with the range distribution of the ultrasound attenuation coefficient; the second conversion method is constructed based on the MRI proton density fat fraction as the gold standard and combined with the relationship between the ultrasound attenuation coefficient and the MRI proton density fat fraction; A data analysis unit is used to evaluate the patient's fatty liver condition based on fatty liver characteristic parameters.

2. The computing system according to claim 1, characterized in that In the data conversion unit: If the diagnostic speed requirement in the diagnostic requirement is higher than the preset speed, selecting the first conversion mode; If the diagnostic accuracy requirement in the diagnostic requirement is higher than the preset accuracy, the second conversion method is selected.

3. The computing system according to claim 1, characterized in that Also includes: The data fusion unit is used to analyze whether the MRI proton density fat fraction of the liver exists in the liver monitoring data, and if so, to fuse the attenuation level score and the MRI proton density fat fraction to obtain fatty liver characteristic parameters.

4. The computing system according to claim 1, characterized in that: The expression of the first conversion method specifically includes: Wherein, AGFF represents the attenuation grade fraction, and AC represents the ultrasonic attenuation coefficient.

5. The computing system according to claim 1, characterized in that: The second conversion method specifically includes: The MRI proton density fat fraction and ultrasound attenuation coefficient of multiple patient samples were collected in advance to establish a data pairing relationship between the MRI proton density fat fraction and the ultrasound attenuation coefficient; Fitting a regression equation based on the data pairing relationship table; Substituting the ultrasound attenuation coefficient into the regression equation, the corresponding MRI proton density fat fraction is obtained, and the MRI proton density fat fraction is used as the attenuation grade score.

6. The computing system according to claim 5, characterized in that: The expression of the regression equation specifically includes: <h2 style=";text-align:left;direction:ltr">AGFF = (k*AC-b)<h2 style=";text-align:left;direction:ltr"> 2 Wherein, AGFF represents the attenuation grade fraction, AC represents the ultrasonic attenuation coefficient, k represents the slope, and b is a constant term.

7. The computing system according to claim 3, characterized in that: The calculation expression of the fatty liver characteristic parameter is: FFF=w1·AGFF+w2·PDFF Among them, FFF represents the characteristic parameter of fatty liver, AGFF represents the attenuation grade score, PDFF represents the MRI proton density fat fraction, w1 represents the first weight coefficient, and w2 represents the second weight coefficient.

8. The computing system according to claim 7, characterized in that: The first weight coefficient is 0.5, and the second weight coefficient is 2.

9. The computing system according to claim 6, characterized in that: The value of k is 7.21 and the value of b is 1.

95.

10. The computing system according to claim 3, characterized in that: When the characteristic parameters of fatty liver are between 33% and 53%, the patient is considered to have mild fatty liver; When the characteristic parameter of fatty liver is greater than 53% and less than 72%, the patient is considered to have moderate fatty liver; When the characteristic parameter of fatty liver is not less than 72%, the patient is deemed to have severe fatty liver.

Images