A system and method for screening pulmonary vasodilation in patients with liver cirrhosis
By designing the intrapulmonary vasodilation screening system for patients with cirrhosis, and using data collection, processing and analysis modules combined with cirrhosis grade to judge intrapulmonary vasodilation, the problem of intrapulmonary vasodilation in the existing technology cannot be effectively judged intrapulmonary vasodilation in patients with cirrhosis. Improved screening accuracy and safety.
Patent Information
- Application Number
- CN202411207846.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-30
- Publication Date
- 2024-12-03
- Estimated Expiration
- 2044-08-30
AI Technical Summary
The existing technology has not yet used routine clinical data to conduct a comprehensive analysis of patients with cirrhosis, and it is impossible to effectively judge the occurrence of vascular dilation in the lungs of patients with cirrhosis, which increases the risk of perioperative lung infection, respiratory failure and death.
A screening system for intrapulmonary vasodilation in patients with cirrhosis was designed. The data collection module collected liver-related data, the data processing module performed preprocessing and functional evaluation, and the data analysis module performed CT image segmentation and feature extraction, combined with cirrhosis level judgment Intrapulmonary vasculature is dilated, and a pre-established intrapulmonary vascular discrimination model is used for screening and early warning.
The cirrhosis level of patients with cirrhosis is achieved based on the data, and the cirrhosis level is combined with the cirrhosis level to judge the vascular dilation in the lung, which improves the accuracy of screening for vascular dilation in the lung and reduces the risk of perioperative complications.
Smart Images

Figure CN118737484B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of artificial intelligence medical technology, and specifically to a system and method for screening pulmonary vasodilation in patients with liver cirrhosis. Background Art
[0002] Pulmonary vasodilation is a pathological change of hepatopulmonary syndrome, which is a serious complication of chronic end-stage liver disease. Positive pulmonary vasodilation can significantly increase the risk of liver failure. The incidence of pulmonary vasodilation is high in patients with cirrhosis, and its occurrence significantly increases perioperative lung infection, respiratory failure, and even death.
[0003] Currently, there are correlation analyses of intrapulmonary vasodilation based on single indicators, but there is no means to conduct a comprehensive and comprehensive analysis of patients with cirrhosis using routine clinical data. Summary of the invention
[0004] In order to solve the deficiencies mentioned in the above-mentioned background technology, the purpose of the present invention is to provide a system and method for screening pulmonary vascular dilatation in patients with cirrhosis, which can determine the level of cirrhosis of patients with cirrhosis based on data, and judge the pulmonary vascular dilatation based on the level of cirrhosis of patients with cirrhosis.
[0005] In a first aspect, the purpose of the present invention can be achieved by the following technical solution: a system for screening pulmonary vasodilation in patients with liver cirrhosis, comprising:
[0006] Data acquisition module: used to collect liver-related data; send the liver-related data to the data processing module, wherein the liver-related data includes: serum liver function data, serum liver fibrosis data and liver elasticity scanning data;
[0007] Data processing module: used for preprocessing liver-related data, marking the processed liver-related data, performing liver function evaluation calculation on the marked liver-related data, obtaining a comprehensive liver function evaluation coefficient, and sending the comprehensive liver function evaluation coefficient to the data analysis module;
[0008] Data analysis module: used to obtain liver CT images, perform image segmentation on the liver CT images, obtain multiple levels of liver segmentation area images, wherein the multiple levels include high-level liver segmentation area images, intermediate-level liver segmentation area images and low-level liver segmentation area images, respectively extract liver cirrhosis feature data using the segmented liver segmentation area images of multiple levels, calculate liver cirrhosis performance index using the extracted liver cirrhosis feature data and the comprehensive liver function evaluation coefficient, obtain the comprehensive liver cirrhosis performance index coefficient, set the comprehensive liver cirrhosis performance index threshold, compare the comprehensive liver cirrhosis performance index coefficient with the comprehensive liver cirrhosis performance index threshold, define the liver cirrhosis level according to the comparison result, and send different levels of liver cirrhosis signals to the expansion screening module;
[0009] Dilatation screening module: obtain the pre-established pulmonary vascular discrimination model stored in the control center, and obtain the pulmonary vascular dilatation data; input the pulmonary vascular dilatation data into the pre-established pulmonary vascular discrimination model, output the vascular dilatation discrimination result, combine the vascular dilatation discrimination result with different levels of liver cirrhosis signals to judge the pulmonary vascular dilatation screening result, and send it to the early warning module, wherein the pulmonary vascular dilatation screening result includes negative and positive;
[0010] Control center: used to obtain and store the pulmonary vascular discrimination model;
[0011] Early warning module: used to warn that the patient is positive when a positive pulmonary vasodilation screening result is received, and to warn that the patient is negative when a negative pulmonary vasodilation screening result is received.
[0012] In combination with the first aspect, in some implementations of the first aspect, the system further includes: a calculation process of the data processing module:
[0013] The serum liver function data is marked as Gi, the serum liver fibrosis data is marked as Xi, and the liver elasticity scan data is marked as Si, where i is the number of acquisition times of the data acquisition module, and i=1, 2, 3, ..., n, and n is the total number of acquisition times of the data acquisition module;
[0014] The liver function assessment calculation process includes:
[0015]
[0016] Wherein, Zgi is the comprehensive liver function evaluation coefficient, G0 is the preset standard serum liver function coefficient, X0 is the preset standard serum liver fibrosis coefficient, S0 is the preset standard liver elasticity scanning coefficient, a1 is the serum liver function influence coefficient, a2 is the serum liver fibrosis influence coefficient, a3 is the liver elasticity scanning influence coefficient, and k is the preset evaluation correlation coefficient.
[0017] In combination with the first aspect, in certain implementations of the first aspect, the system further includes: a process in which the data analysis module performs image segmentation on the liver CT image:
[0018] For liver CT images, find the middle hepatic vein, left hepatic vein, and right hepatic vein on the liver CT images;
[0019] Taking the middle hepatic vein as a line, the area between the middle hepatic vein and the left hepatic vein and the right hepatic vein is divided into an advanced liver segmentation area image;
[0020] The area from the left hepatic vein to the left edge of the liver is divided into an intermediate liver segmentation area image;
[0021] The area from the right hepatic vein to the right edge of the liver is divided into a low-level liver segmentation area image.
[0022] In combination with the first aspect, in some implementations of the first aspect, the system further includes: the data analysis module extracts liver cirrhosis feature data respectively using the segmented liver segmentation region images at multiple levels; including high-level liver cirrhosis feature data, intermediate-level liver cirrhosis feature data and low-level liver cirrhosis feature data; marked as Y1i, Y2i and Y3i respectively;
[0023] The calculation process of the comprehensive liver cirrhosis performance index coefficient is as follows:
[0024] Using the formula The comprehensive liver cirrhosis performance index coefficient Pi is calculated; where T is the comprehensive preset correlation coefficient.
[0025] In combination with the first aspect, in some implementations of the first aspect, the system further includes: an analysis process of the data analysis module:
[0026] Set the comprehensive liver cirrhosis performance index threshold value P0;
[0027] like , determining that the liver cirrhosis level is level one, and sending a level one liver cirrhosis signal to the expansion screening module;
[0028] like , determining that the liver cirrhosis level is level 2, and sending a level 2 liver cirrhosis signal to the expansion screening module;
[0029] like , the liver cirrhosis level is determined to be level three, and a level three liver cirrhosis signal is sent to the expansion screening module.
[0030] In combination with the first aspect, in certain implementations of the first aspect, the system further includes: the vascular dilation discrimination result of the dilation screening module includes: a main vascular dilation discrimination result, a right pulmonary vascular dilation discrimination result, and a left pulmonary vascular dilation discrimination result;
[0031] The screening process is as follows:
[0032] When a primary liver cirrhosis signal is received, if the vascular dilation discrimination results are all positive, the pulmonary vascular dilation screening result is determined to be positive at this time and sent to the early warning module; if the vascular dilation discrimination results are not all positive, the pulmonary vascular dilation screening result is determined to be negative at this time and sent to the early warning module;
[0033] When a secondary liver cirrhosis signal is received, if at least two of the vascular dilation discrimination results are positive, the pulmonary vascular dilation screening result is determined to be positive and sent to the early warning module; if only one of the vascular dilation discrimination results is positive, the pulmonary vascular dilation screening result is determined to be negative and sent to the early warning module;
[0034] When a third-level liver cirrhosis signal is received, if at least one of the vasodilation discrimination results is positive, the pulmonary vasodilation screening result is determined to be positive and sent to the early warning module; if all vasodilation discrimination results are negative, the pulmonary vasodilation screening result is determined to be negative and sent to the early warning module.
[0035] In combination with the first aspect, in certain implementations of the first aspect, the system further includes: the pre-established intrapulmonary vascular discrimination model stored in the control center is trained based on an artificial intelligence model;
[0036] Collecting standard intrapulmonary vascular expansion data and standard lung index data through a data collection unit in the control center, wherein the intrapulmonary vascular expansion data includes: a standard pulmonary artery trunk inner diameter, a standard right pulmonary artery inner diameter, and a standard left pulmonary artery inner diameter;
[0037] The standard pulmonary vascular dilation data and the standard lung index data are combined to obtain a lung standard data set, which is input into an artificial intelligence model to output a pulmonary vascular discrimination model.
[0038] In a second aspect, in order to achieve the above-mentioned object, the present invention discloses a method for screening pulmonary vasodilation in patients with liver cirrhosis, the method comprising the following steps:
[0039] Acquire liver-related data, perform preprocessing and data labeling on the liver data, obtain labeled liver-related data, perform liver function evaluation calculation on the labeled liver-related data, and obtain a comprehensive liver function evaluation coefficient, wherein the liver-related data includes: serum liver function data, serum liver fibrosis data, and liver elasticity scanning data;
[0040] Acquire a liver CT image, perform image segmentation on the liver CT image, obtain multiple levels of liver segmentation region images, respectively extract liver cirrhosis feature data using the segmented multiple levels of liver segmentation region images, calculate liver cirrhosis performance index using the liver cirrhosis feature data and a comprehensive liver function evaluation coefficient, and obtain a comprehensive liver cirrhosis performance index coefficient;
[0041] Set a comprehensive liver cirrhosis performance index threshold, compare the comprehensive liver cirrhosis performance index coefficient with the comprehensive liver cirrhosis performance index threshold, define the liver cirrhosis level according to the comparison result, and perform different degrees of lung expansion screening for different levels of liver cirrhosis;
[0042] Acquire the intrapulmonary vascular dilation data, input the intrapulmonary vascular dilation data into a pre-established intrapulmonary vascular discrimination model, output a vascular dilation discrimination result, and combine the vascular dilation discrimination result with the liver cirrhosis level to determine the intrapulmonary vascular dilation screening result, wherein the intrapulmonary vascular dilation screening result includes negative and positive.
[0043] Beneficial effects of the present invention:
[0044] The present invention collects liver-related data through a data acquisition module, then calculates the liver-related data through a data processing module to obtain a comprehensive liver function evaluation coefficient, then obtains a liver CT image through a data analysis module, then performs image segmentation and feature extraction to obtain liver cirrhosis feature data, then calculates the liver cirrhosis feature data and the comprehensive liver function evaluation coefficient index to obtain a comprehensive liver cirrhosis performance index coefficient, compares the data by setting a threshold, and defines the liver cirrhosis level according to the comparison result, then inputs the intrapulmonary vascular dilation data of the dilation screening module into the intrapulmonary vascular discrimination model stored in the control center to obtain a vascular dilation discrimination result, and basically determines the intrapulmonary vascular dilation screening result in combination with liver cirrhosis, and sends it to the early warning module for early warning prompts, thereby realizing the function of being able to determine the liver cirrhosis level of a cirrhotic patient according to the data, and judging the intrapulmonary vascular dilation in combination with the liver cirrhosis level of the cirrhotic patient. BRIEF DESCRIPTION OF THE DRAWINGS
[0045] In order to more clearly illustrate the embodiments of the present 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, for those skilled in the art, other drawings can be obtained based on these drawings without creative work.
[0046] Figure 1 It is a schematic diagram of the system structure of the present invention;
[0047] Figure 2 It is a schematic flow chart of the method of the present invention. DETAILED DESCRIPTION
[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0049] Embodiment 1:
[0050] The following is an introduction to the relevant terms involved in the embodiments of the present application:
[0051] Image segmentation is the technology and process of dividing an image into several specific regions with unique properties and proposing objects of interest. It is a key step from image processing to image analysis. Existing image segmentation methods are mainly divided into the following categories: threshold-based segmentation methods, region-based segmentation methods, edge-based segmentation methods, and segmentation methods based on specific theories. From a mathematical point of view, image segmentation is the process of dividing a digital image into non-intersecting regions. The image segmentation process is also a labeling process, that is, pixels belonging to the same region are assigned the same number.
[0052] like Figure 1 As shown, a system for screening pulmonary vasodilation in patients with liver cirrhosis comprises:
[0053] Data acquisition module, data processing module, data analysis module, expansion screening module, early warning module and control center;
[0054] The data acquisition module is used to acquire liver-related data; the acquired liver-related data is sent to the data processing module for processing, wherein the liver-related data includes: serum liver function data, serum liver fibrosis data and liver elasticity scanning data;
[0055] Specifically, the present invention is further described below by way of embodiments:
[0056] The serum liver function data include total bilirubin, direct bilirubin, aspartate aminotransferase, alanine aminotransferase, albumin, globulin, glutamyl transpeptidase, alkaline phosphatase, etc.;
[0057] The serum liver fibrosis data is a serological test index for checking whether the liver has fibrosis and the development of chronic hepatitis. It is currently the main index for clinical diagnosis of liver fibrosis in chronic hepatitis. The four liver fibrosis items include type IV collagen, type III procollagen, hyaluronidase and laminin.
[0058] Liver elasticity scan data: Liver elasticity detection uses ultrasound technology to evaluate the elasticity and hardness of the liver through the elasticity value reflected by the liver tissue from low-frequency ultrasonic vibration waves. The normal value is 2.5~7.0Kpa. The larger the detection value, the higher the degree of liver fibrosis.
[0059] After receiving the liver-related data sent by the data acquisition module, the data processing module performs data processing. Specifically, the processing process of the data processing module includes the following steps:
[0060] The liver-related data are preprocessed, including data format standardization, abnormal data removal, error correction, and duplicate data removal, to obtain processed liver-related data.
[0061] The processed liver-related data is labeled, wherein the data labeling process includes:
[0062] The serum liver function data is marked as Gi, the serum liver fibrosis data is marked as Xi, and the liver elasticity scan data is marked as Si, where i is the number of acquisition times of the data acquisition module, and i=1, 2, 3, ..., n, and n is the total number of acquisition times of the data acquisition module;
[0063] The marked liver-related data is subjected to liver function evaluation calculation to obtain a comprehensive liver function evaluation coefficient, wherein the liver function evaluation calculation process includes:
[0064]
[0065] Wherein, Zgi is the comprehensive liver function evaluation coefficient, G0 is the preset standard serum liver function coefficient, X0 is the preset standard serum liver fibrosis coefficient, S0 is the preset standard liver elasticity scanning coefficient, a1 is the serum liver function influence coefficient, a2 is the serum liver fibrosis influence coefficient, a3 is the liver elasticity scanning influence coefficient, and k is the preset evaluation correlation coefficient;
[0066] Among them, in this embodiment, the serum liver function influence coefficient, serum liver fibrosis influence coefficient and liver elasticity scanning influence coefficient are calculated by comprehensive evaluation based on external factors when collecting serum liver function, serum liver fibrosis and testing liver elasticity on a daily basis, including human factors, machine detection and environmental factors, etc.; human factors are caused by human operation or improper scanning;
[0067] Sending the calculated comprehensive liver function assessment coefficient to the data analysis module;
[0068] After receiving the comprehensive liver function evaluation coefficient sent by the data processing module, the data analysis module performs data analysis. Specifically, the data analysis process includes the following steps:
[0069] Acquire a liver CT image, perform image segmentation on the liver CT image, and obtain multiple levels of liver segmentation region images; wherein the multiple levels include a high-level liver segmentation region image, a medium-level liver segmentation region image, and a low-level liver segmentation region image;
[0070] It needs to be further explained that the segmentation process of the liver CT image is as follows:
[0071] For liver CT images, find the middle hepatic vein, left hepatic vein, and right hepatic vein on the liver CT images;
[0072] Taking the middle hepatic vein as a line, the area between the middle hepatic vein and the left hepatic vein and the right hepatic vein is divided into an advanced liver segmentation area image;
[0073] The area from the left hepatic vein to the left edge of the liver is divided into an intermediate liver segmentation area image;
[0074] The area from the right hepatic vein to the right edge of the liver is divided into a low-level liver segmentation area image;
[0075] The segmentation method used in this embodiment is to perform image segmentation by means of a convolutional neural network, wherein the convolutional neural network gradually extracts image features through multi-layer convolution and pooling operations. Since liver CT images have spatial correlation, convolutional neural networks have achieved good results in liver segmentation.
[0076] The liver segmentation region images of multiple levels after segmentation are used to extract liver cirrhosis feature data respectively; including high-level liver cirrhosis feature data, intermediate-level liver cirrhosis feature data and low-level liver cirrhosis feature data; marked as Y1i, Y2i and Y3i respectively;
[0077] The extracted liver cirrhosis characteristic data and the comprehensive liver function evaluation coefficient are used to calculate the liver cirrhosis performance index, and the comprehensive liver cirrhosis performance index coefficient is obtained. The specific calculation process is as follows:
[0078] Using the formula The comprehensive liver cirrhosis performance index coefficient Pi is calculated; where T is the comprehensive preset correlation coefficient;
[0079] It should be noted that the proportion of high-level liver cirrhosis characteristic data, intermediate-level liver cirrhosis characteristic data and low-level liver cirrhosis characteristic data in the calculation formula is 5:3:2, which represents the importance in calculating the comprehensive liver cirrhosis performance index coefficient;
[0080] Set the comprehensive liver cirrhosis performance index threshold value P0;
[0081] The calculated comprehensive liver cirrhosis performance index coefficient Pi is compared with the comprehensive liver cirrhosis performance index threshold P0, and the liver cirrhosis level is determined according to the comparison result, and different levels of liver cirrhosis signals are sent to the expansion screening module;
[0082] The specific comparison process is as follows:
[0083] like , determining that the liver cirrhosis level is level one, and sending a level one liver cirrhosis signal to the expansion screening module;
[0084] like , determining that the liver cirrhosis level is level 2, and sending a level 2 liver cirrhosis signal to the expansion screening module;
[0085] like , the liver cirrhosis level is determined to be level three, and a level three liver cirrhosis signal is sent to the expansion screening module.
[0086] After receiving the different levels of liver cirrhosis signals, the expansion screening module performs different levels of lung expansion screening according to the different levels of liver cirrhosis. Specifically, the expansion screening process of the expansion screening module includes the following steps:
[0087] acquiring a pre-established pulmonary vascular discrimination model stored in a control center;
[0088] Acquiring intrapulmonary vascular expansion data; wherein the intrapulmonary vascular expansion data includes the inner diameter of the pulmonary artery trunk, the inner diameter of the right pulmonary artery, and the inner diameter of the left pulmonary artery;
[0089] If a primary liver cirrhosis signal is received, the inner diameter of the pulmonary artery trunk, the inner diameter of the right pulmonary artery, and the inner diameter of the left pulmonary artery are respectively input into a pre-established pulmonary vascular discrimination model, and a vascular dilation discrimination result is output, wherein the vascular dilation discrimination result includes: a main vessel dilation discrimination result, a right pulmonary vascular dilation discrimination result, and a left pulmonary vascular dilation discrimination result. If the vascular dilation discrimination results are all positive, the pulmonary vascular dilation screening result is determined to be positive at this time, and is sent to the early warning module. If the vascular dilation discrimination results are not all positive, the pulmonary vascular dilation screening result is determined to be negative at this time, and is sent to the early warning module.
[0090] If a secondary liver cirrhosis signal is received, the inner diameter of the pulmonary artery trunk, the inner diameter of the right pulmonary artery, and the inner diameter of the left pulmonary artery are respectively input into the pre-established pulmonary vascular discrimination model, and the vascular dilation discrimination result is output. If at least two of the vascular dilation discrimination results are positive, the pulmonary vascular dilation screening result is determined to be positive at this time and sent to the early warning module. If only one of the vascular dilation discrimination results is positive, the pulmonary vascular dilation screening result is determined to be negative at this time and sent to the early warning module.
[0091] If a third-level liver cirrhosis signal is received, the inner diameter of the pulmonary artery trunk, the inner diameter of the right pulmonary artery, and the inner diameter of the left pulmonary artery are respectively input into the pre-established pulmonary vascular discrimination model, and the vascular dilation discrimination result is output. If at least one of the vascular dilation discrimination results is positive, the pulmonary vascular dilation screening result is determined to be positive at this time and sent to the early warning module. If all the vascular dilation discrimination results are negative, the pulmonary vascular dilation screening result is determined to be negative at this time and sent to the early warning module.
[0092] When the early warning module receives a positive pulmonary vascular dilation screening result, it warns that the patient is positive, and when it receives a negative pulmonary vascular dilation screening result, it warns that the patient is negative;
[0093] The pre-established pulmonary vascular discrimination model stored in the control center is based on artificial intelligence model training;
[0094] Collecting standard intrapulmonary vascular expansion data and standard lung index data through a data collection unit in the control center, wherein the intrapulmonary vascular expansion data includes: a standard pulmonary artery trunk inner diameter, a standard right pulmonary artery inner diameter, and a standard left pulmonary artery inner diameter;
[0095] It should be further explained that, in the specific implementation process, the standard pulmonary vascular dilation data is obtained by collecting the inner diameter of the normal human lung for multiple times and then performing standardization processing; the standard lung index data is obtained by collecting the relevant index data of the normal human lung and then performing standardization processing;
[0096] The standard pulmonary vascular dilation data and the standard pulmonary index data are combined to obtain a standard lung data set, which is input into an artificial intelligence model to output a pulmonary vascular discrimination model, wherein the artificial intelligence model includes a deep convolutional neural network model and an RBF neural network model.
[0097] Embodiment 2: A method for screening pulmonary vasodilation in patients with liver cirrhosis, the method comprising the following steps:
[0098] S101: Acquire liver-related data, perform preprocessing and data labeling on the liver data, obtain labeled liver-related data, perform liver function evaluation calculation on the labeled liver-related data, and obtain a comprehensive liver function evaluation coefficient, wherein the liver-related data includes: serum liver function data, serum liver fibrosis data, and liver elasticity scanning data;
[0099] S102: Acquire a liver CT image, perform image segmentation on the liver CT image, obtain multiple levels of liver segmentation region images, respectively extract liver cirrhosis feature data using the segmented multiple levels of liver segmentation region images, calculate liver cirrhosis performance index using the liver cirrhosis feature data and a comprehensive liver function evaluation coefficient, and obtain a comprehensive liver cirrhosis performance index coefficient;
[0100] S103: setting a comprehensive liver cirrhosis performance index threshold, comparing the comprehensive liver cirrhosis performance index coefficient with the comprehensive liver cirrhosis performance index threshold, defining liver cirrhosis levels according to the comparison results, and performing different degrees of lung expansion screening for different levels of liver cirrhosis;
[0101] S104: Acquire the intrapulmonary vascular dilation data, input the intrapulmonary vascular dilation data into a pre-established intrapulmonary vascular discrimination model, output a vascular dilation discrimination result, and combine the vascular dilation discrimination result with the liver cirrhosis level to determine the intrapulmonary vascular dilation screening result, wherein the intrapulmonary vascular dilation screening result includes negative and positive.
[0102] Based on the same inventive concept, the present invention also provides a computer device, which includes: one or more processors, and a memory for storing one or more computer programs; the program includes program instructions, and the processor is used to execute the program instructions stored in the memory. The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. It is the computing core and control core of the terminal, which is used to implement one or more instructions, specifically for loading and executing one or more instructions in a computer storage medium to implement the above method.
[0103] It should be further explained that, based on the same inventive concept, the present invention also provides a computer storage medium, on which a computer program is stored, and the computer program is executed by the processor to execute the above method. The storage medium can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electrical, magnetic, 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 the present invention, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.
[0104] The above formulas are all calculated by removing dimensions and taking numerical values. The formula is a formula that is closest to the actual situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained by simulating a large amount of data.
[0105] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.
[0106] The above shows and describes the basic principles, main features and advantages of the present disclosure. Those skilled in the art should understand that the present disclosure is not limited by the above embodiments, and the above embodiments and descriptions are only for explaining the principles of the present disclosure. Without departing from the spirit and scope of the present disclosure, the present disclosure may have various changes and improvements, and these changes and improvements fall within the scope of the present disclosure to be protected.
Claims
1. A system for screening pulmonary vasodilation in patients with liver cirrhosis, characterized in that: include: Data acquisition module: used to collect liver-related data; Sending liver-related data to a data processing module, wherein the liver-related data includes: serum liver function data, serum liver fibrosis data, and liver elasticity scanning data; Data processing module: used for preprocessing liver-related data, marking the processed liver-related data, performing liver function evaluation calculation on the marked liver-related data, obtaining a comprehensive liver function evaluation coefficient, and sending the comprehensive liver function evaluation coefficient to the data analysis module; The calculation process of the data processing module: The serum liver function data is marked as Gi, the serum liver fibrosis data is marked as Xi, and the liver elasticity scan data is marked as Si, where i is the number of acquisition times of the data acquisition module, and i=1, 2, 3, ..., n, and n is the total number of acquisition times of the data acquisition module; The liver function assessment calculation process includes: Wherein, Zgi is the comprehensive liver function evaluation coefficient, G0 is the preset standard serum liver function coefficient, X0 is the preset standard serum liver fibrosis coefficient, S0 is the preset standard liver elasticity scanning coefficient, a1 is the serum liver function influence coefficient, a2 is the serum liver fibrosis influence coefficient, a3 is the liver elasticity scanning influence coefficient, and k is the preset evaluation correlation coefficient; Data analysis module: used to obtain liver CT images, perform image segmentation on the liver CT images, obtain multiple levels of liver segmentation area images, wherein the multiple levels include high-level liver segmentation area images, intermediate-level liver segmentation area images and low-level liver segmentation area images, respectively extract liver cirrhosis feature data using the segmented liver segmentation area images of multiple levels, calculate liver cirrhosis performance index using the extracted liver cirrhosis feature data and the comprehensive liver function evaluation coefficient, obtain the comprehensive liver cirrhosis performance index coefficient, set the comprehensive liver cirrhosis performance index threshold, compare the comprehensive liver cirrhosis performance index coefficient with the comprehensive liver cirrhosis performance index threshold, define the liver cirrhosis level according to the comparison result, and send different levels of liver cirrhosis signals to the expansion screening module; The process of image segmentation of liver CT images by the data analysis module: For liver CT images, find the middle hepatic vein, left hepatic vein, and right hepatic vein on the liver CT images; Taking the middle hepatic vein as a line, the area between the middle hepatic vein and the left hepatic vein and the right hepatic vein is divided into an advanced liver segmentation area image; The area from the left hepatic vein to the left edge of the liver is divided into an intermediate liver segmentation area image; The area from the right hepatic vein to the right edge of the liver is divided into a low-level liver segmentation area image; Dilatation screening module: obtain the pre-established pulmonary vascular discrimination model stored in the control center, and obtain the pulmonary vascular dilatation data; input the pulmonary vascular dilatation data into the pre-established pulmonary vascular discrimination model, output the vascular dilatation discrimination result, combine the vascular dilatation discrimination result with different levels of liver cirrhosis signals to judge the pulmonary vascular dilatation screening result, and send it to the early warning module, wherein the pulmonary vascular dilatation screening result includes negative and positive; Control center: used to obtain and store the pulmonary vascular discrimination model; Early warning module: used to warn that the patient is positive when a positive pulmonary vasodilation screening result is received, and to warn that the patient is negative when a negative pulmonary vasodilation screening result is received.
2. A system for screening pulmonary vasodilation in patients with liver cirrhosis according to claim 1, characterized in that: The data analysis module uses the segmented liver segmentation region images at multiple levels to extract liver cirrhosis feature data respectively; Including high-grade liver cirrhosis feature data, intermediate-grade liver cirrhosis feature data and low-grade liver cirrhosis feature data; They are marked as Y1i, Y2i and Y3i respectively; The calculation process of the comprehensive liver cirrhosis performance index coefficient is as follows: Using the formula The comprehensive liver cirrhosis performance index coefficient Pi is calculated; where T is the comprehensive preset correlation coefficient.
3. A system for screening pulmonary vasodilation in patients with liver cirrhosis according to claim 2, characterized in that: The analysis process of the data analysis module: Set the comprehensive liver cirrhosis performance index threshold value P0; like , determining that the liver cirrhosis level is level one, and sending a level one liver cirrhosis signal to the expansion screening module; like , determining that the liver cirrhosis level is level 2, and sending a level 2 liver cirrhosis signal to the expansion screening module; like , the liver cirrhosis level is determined to be level three, and a level three liver cirrhosis signal is sent to the expansion screening module.
4. A system for screening pulmonary vasodilation in patients with liver cirrhosis according to claim 1, characterized in that: The vascular dilatation discrimination results of the dilatation screening module include: main vascular dilatation discrimination results, right pulmonary vascular dilatation discrimination results and left pulmonary vascular dilatation discrimination results; The screening process is as follows: When a primary liver cirrhosis signal is received, if the vascular dilation discrimination results are all positive, the pulmonary vascular dilation screening result is determined to be positive at this time and sent to the early warning module; if the vascular dilation discrimination results are not all positive, the pulmonary vascular dilation screening result is determined to be negative at this time and sent to the early warning module; When a secondary liver cirrhosis signal is received, if at least two of the vascular dilation discrimination results are positive, the pulmonary vascular dilation screening result is determined to be positive and sent to the early warning module; if only one of the vascular dilation discrimination results is positive, the pulmonary vascular dilation screening result is determined to be negative and sent to the early warning module; When a third-level liver cirrhosis signal is received, if at least one of the vasodilation discrimination results is positive, the pulmonary vasodilation screening result is determined to be positive and sent to the early warning module; if all vasodilation discrimination results are negative, the pulmonary vasodilation screening result is determined to be negative and sent to the early warning module.
5. The system for screening pulmonary vasodilation in patients with liver cirrhosis according to claim 1, characterized in that: The pre-established pulmonary vascular discrimination model stored in the control center is based on artificial intelligence model training; Collecting standard intrapulmonary vascular expansion data and standard lung index data through a data collection unit in the control center, wherein the intrapulmonary vascular expansion data includes: a standard pulmonary artery trunk inner diameter, a standard right pulmonary artery inner diameter, and a standard left pulmonary artery inner diameter; The standard pulmonary vascular dilation data and the standard lung index data are combined to obtain a lung standard data set, which is input into an artificial intelligence model to output a pulmonary vascular discrimination model.
6. A method for screening pulmonary vasodilation in patients with liver cirrhosis, characterized in that: The method comprises the following steps: Acquire liver-related data, perform preprocessing and data labeling on the liver data, obtain labeled liver-related data, perform liver function evaluation calculation on the labeled liver-related data, and obtain a comprehensive liver function evaluation coefficient, wherein the liver-related data includes: serum liver function data, serum liver fibrosis data, and liver elasticity scanning data; The serum liver function data is marked as Gi, the serum liver fibrosis data is marked as Xi, and the liver elasticity scan data is marked as Si, where i is the number of acquisition times of the data acquisition module, and i=1, 2, 3, ..., n, and n is the total number of acquisition times of the data acquisition module; The liver function assessment calculation process includes: Wherein, Zgi is the comprehensive liver function evaluation coefficient, G0 is the preset standard serum liver function coefficient, X0 is the preset standard serum liver fibrosis coefficient, S0 is the preset standard liver elasticity scanning coefficient, a1 is the serum liver function influence coefficient, a2 is the serum liver fibrosis influence coefficient, a3 is the liver elasticity scanning influence coefficient, and k is the preset evaluation correlation coefficient; Acquire a liver CT image, perform image segmentation on the liver CT image, obtain multiple levels of liver segmentation region images, respectively extract liver cirrhosis feature data using the segmented multiple levels of liver segmentation region images, calculate liver cirrhosis performance index using the liver cirrhosis feature data and a comprehensive liver function evaluation coefficient, and obtain a comprehensive liver cirrhosis performance index coefficient; For liver CT images, find the middle hepatic vein, left hepatic vein, and right hepatic vein on the liver CT images; Taking the middle hepatic vein as a line, the area between the middle hepatic vein and the left hepatic vein and the right hepatic vein is divided into an advanced liver segmentation area image; The area from the left hepatic vein to the left edge of the liver is divided into an intermediate liver segmentation area image; The area from the right hepatic vein to the right edge of the liver is divided into a low-level liver segmentation area image; Set a comprehensive liver cirrhosis performance index threshold, compare the comprehensive liver cirrhosis performance index coefficient with the comprehensive liver cirrhosis performance index threshold, define the liver cirrhosis level according to the comparison result, and perform different degrees of lung expansion screening for different levels of liver cirrhosis; Acquire the intrapulmonary vascular dilation data, input the intrapulmonary vascular dilation data into a pre-established intrapulmonary vascular discrimination model, output a vascular dilation discrimination result, and combine the vascular dilation discrimination result with the liver cirrhosis level to determine the intrapulmonary vascular dilation screening result, wherein the intrapulmonary vascular dilation screening result includes negative and positive.
