A method for constructing a calculation model of hepatic venous pressure gradient based on radiomics
A pressure gradient and calculation model technology, applied in the fields of calculation, computer parts, character and pattern recognition, etc., can solve the problems of large numerical variation, high operation difficulty, and many interference factors, and achieve large numerical variation, high operation difficulty, The effect of many interfering factors
Active Publication Date: 2020-12-04
祁小龙
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the main problems of research in this field at home and abroad are: the scope of assessment is limited to the main portal vein, and the overall influence of the hepatic vein-portal system is not considered; only portal hemodynamic factors are considered, and blood in patients with cirrhosis is ignored. Rheological changes, such as changes in blood viscosity and a decrease in the deformability of red blood cells, contribute to an increase in portal resistance
[0006] Various measurement techniques of portal pressure are still affected by their own interference factors, or they are highly invasive, difficult to operate, or have many interference factors and large value variations
At present, in the relevant reports at home and abroad, the diagnostic methods of portal hypertension, especially the early non-invasive diagnostic techniques, still need further research and improvement.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment 1
[0093] Example 1: R language glmnet toolkit for feature screening, modeling and calculation rHVPG
[0094] In the R language programming interface, first use library (glmnet) to import the glmnet toolkit, and use read.table("D: / train_list.csv", header=TRUE, sep=',') to include 189 examples of the training set The csv data of image features is imported into the variable train. Use as.matrix(train[,1:20648]) and as.matrix(train[,20649]) to store the feature matrix and outcome data in the train in the variables train_x and train_y respectively. Set the parameters of the glmnet function: x=train_x, y=train_y, family='binomial', nfold=10, the entire glmnet function call process uses lasso dimensionality reduction, and draws a feature screening map (such as Figure 31 shown) and the error curve (as Figure 32 shown), and then perform 10-fold cross-validation through the cv.glmnet function, and select the parameter lambda.min to select the optimal linear model. At this time, it cor...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present invention provides a radiomics-based hepatic venous pressure gradient (rHVPG) calculation model construction method, based on which a more advantageous hepatic venous pressure gradient calculation model can be constructed , providing a new way to calculate early non-invasive indicators in patients with portal hypertension. The present invention also provides a calculation system of hepatic venous pressure gradient based on radiomics. The invention can overcome many limitations of the existing non-invasive measurement methods. The rHVPG calculation system proposed by the present invention is feasible, and is expected to provide new ideas for non-invasive measurement of portal pressure, and play a positive role in improving the quality of life of patients with portal hypertension and reducing the burden of disease on families and society.
Description
technical field [0001] The invention relates to a method for constructing a hepatic venous pressure gradient calculation model based on radiomics. Background technique [0002] Globally, liver disease (viral infection, alcoholic liver disease, nonalcoholic fatty liver and related cirrhosis, hepatocellular carcinoma) is one of the leading causes of death, and in China alone, liver disease threatens nearly 3 The health and lives of 100 million people, seriously exacerbating the global burden of disease. Take chronic liver disease caused by hepatitis B virus infection as an example. According to the report of the World Health Organization, about 2 billion people in the world have been infected with hepatitis B virus, of which 240 million people are chronic hepatitis B virus infected people, and about 650,000 people die of hepatitis B virus infection every year. Liver cirrhosis, hepatocellular carcinoma, etc. Among patients with liver cirrhosis worldwide, 30% are caused by hep...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/32G06K9/46G06T7/40
CPCG06T7/40G06T2207/30101G06T2207/30056G06V10/25G06V10/40
Inventor 祁小龙张煜宁振源杨永平黄义飞邹佳良刘川惠佳亮侯金林
Owner 祁小龙