Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Image omics feature extraction and screening method of CT image for constructing chronic hepatitis B cirrhosis prediction model

A CT image and predictive model technology, applied in image analysis, image data processing, character and pattern recognition, etc., can solve the problems of insufficient selection methods, cost problems, and inability to be widely used, so as to improve the reproducibility of functional clustering The effect of sex and feature selection is accurate

Pending Publication Date: 2022-07-05
何健
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problem that the existing methods for predicting liver fibrosis and liver cirrhosis cannot be widely used due to cost problems, and the selection method of the features used for prediction is not sound enough, and proposes a method for constructing chronic hepatitis B cirrhosis Radiomics Feature Extraction and Screening Method for CT Images of Prediction Model

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image omics feature extraction and screening method of CT image for constructing chronic hepatitis B cirrhosis prediction model
  • Image omics feature extraction and screening method of CT image for constructing chronic hepatitis B cirrhosis prediction model
  • Image omics feature extraction and screening method of CT image for constructing chronic hepatitis B cirrhosis prediction model

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0035] A radiomics feature extraction and screening method for CT images for building a prediction model for chronic hepatitis B cirrhosis in this embodiment, such as figure 1 As shown in the flowchart, the method is:

[0036] Step 1. Set exclusion criteria for HBV-infected patients with hepatic fibrosis pathological results detected by plain CT scan. For patients who are not within the exclusion criteria, the next step of CT image acquisition will be performed, and the total number of patients that can be included in CT image acquisition will be counted. , the exclusion criteria are:

[0037] (1) Lack of detailed pathological records of liver fibrosis (n=27);

[0038] (2) Abdominal plain CT images with a thickness of 1.5 mm were lacking (n=128);

[0039] (3) The interval between plain CT examination and biopsy was more than 3 months (n=16);

[0040] (4) Poor image quality (n=42); wherein, poor image quality refers to images with low scores assessed by PSNR, structural simi...

specific Embodiment approach 2

[0049] Different from the specific embodiment 1, a radiomics feature extraction and screening method for CT images used to construct a prediction model of chronic hepatitis B cirrhosis in this embodiment,

[0050] The radiomic feature extraction step includes:

[0051] Image preprocessing and feature extraction were performed using the open source Pyradiomics software package (http: / / www.radiomics.io / pyradiomics.html);

[0052] Second, the voxel spacing is normalized with a size of 1 × 1 × 1 mm, and the voxel intensity values ​​are discretized with a bin width of 25HU to reduce the interference of image noise and normalize the intensity;

[0053]Third, 828 radiomics features were extracted from each ROI, including 18 first-order statistics, 74 texture features, and 736 wavelet-based transform features;

[0054] Fourth, feature values ​​were normalized using z-scores in the training cohort; the standard score (z-score) applied in the validation cohort was used using the mean a...

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

No PUM Login to View More

Abstract

The invention discloses a radiomics feature extraction and screening method of a CT image for constructing a chronic hepatitis B cirrhosis prediction model. Existing liver fibrosis and liver cirrhosis prediction methods cannot be widely applied due to the cost problem, and the selection method of features used for prediction is not sound enough. According to the method, exclusion standards are set for HBV-infected patients with hepatic fibrosis pathological results in plain-scan CT examination, the total number of the patients capable of being included in CT image acquisition is counted, and an acquired person accepts CT examination in an upper supine position; the obtained plain-scan CT images are divided into two parts according to the counted total number, one part serves as a training group used for constructing a chronic hepatitis B cirrhosis prediction model, and the other part serves as a verification group used for verifying the effect of the chronic hepatitis B cirrhosis prediction model; and carrying out image segmentation and image omics feature extraction. The method provided by the invention can accurately extract and screen the features used for constructing the hepatocirrhosis prediction model.

Description

technical field [0001] The invention relates to a radiomic feature extraction and screening method for CT images used to construct a chronic hepatitis B liver cirrhosis prediction model. Background technique [0002] Current noninvasive methods for predicting the degree of liver fibrosis include serum index and elastography. TE and MRE are known to have excellent diagnostic performance for liver fibrosis staging. However, these well-performing device approaches have not been widely used due to their high price. In China, contrast-enhanced CT is usually recommended for HBV carriers to determine whether they have tumors, but many patients receive only plain CT because of limited cost-effectiveness. Although contrast-enhanced CT or MRI can provide more information than plain CT, we hope to study noninvasive models for predicting cirrhosis at relatively low cost based on readily available data. In addition, the selection method of the features used to construct the prediction...

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
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06V10/25
CPCG06T7/0012G06T2207/10081G06T2207/30056
Inventor 何健王锦程毛应凡徐珊珊汤盛楠吴锦
Owner 何健
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com