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

Pulmonary nodule risk assessment system

A pulmonary nodule and risk technology, applied in the system field of pulmonary nodule risk assessment, can solve the problems of decreased accuracy and sensitivity, the accuracy of lung cancer detection is less than 10%, and cannot meet the actual clinical needs, and the accuracy rate can be achieved and sensitivity-enhancing effects

Pending Publication Date: 2021-02-19
ZHUHAI LIVZON CYNVENIO DIAGNOSTICS +1
View PDF0 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] In the current reports that use AI technology to process CT images, the accuracy of detection results is more than 90%, and there are generally shortcomings of small survey samples and low thresholds.
When the sample size is enlarged, the accuracy and sensitivity of the detection results will decrease significantly. For example, Tao Xu et al. reported that when the number of tested patients reached 534, the analysis accuracy of AI was only 70% (Tao Xu, Chuoji Huang ,Yaoqi Liu,Jing Gao,Huan Chang,RonghuaYang,TianjiaoJiang,Zhaozhong Cheng,Wencheng Yu,JunchengZhang,ChunxueBai,Artificial intelligence based on deep learning for differential diagnosis between benignand malignant pulmonary nodules:A real-world,multicenter ofCuglinics.diagnosis, Oncology.), unable to meet the actual clinical needs
[0009] In addition, for small cell lung cancer and squamous cell carcinoma, it is difficult for radiologists to distinguish from images
Due to the inconspicuous characteristics on the image, the accuracy of the existing AI algorithm for the detection of this type of lung cancer is less than 10%.

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
  • Pulmonary nodule risk assessment system
  • Pulmonary nodule risk assessment system
  • Pulmonary nodule risk assessment system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0093]In this embodiment, a logistic regression analysis is performed on the age, gender, CT image AI analysis data, CAC detection data, and pathological analysis results of the 64 patients collected in Table 2, and a logistic regression model is successfully constructed, which specifically includes the following steps:

[0094](1) Build a logistic regression model

[0095]In R 3.6.0 statistical software, input the patient's CT image AI analysis results (x1) And CAC test data (x2), age (x3), gender identification (x4: Male is 1, female is 0) as the independent variable, pathological results as the dependent variable (π), and the regression equation logit(π)=θ0+θ1x1+θ2x2+θ3x3+θ4x4, Bring in the corresponding data of the 64 patients in Table 1, and calculate the coefficient θ by R 3.6.0 statistical software0, Θ1, Θ2, Θ3And θ4, The calculation result shows: θ0Is any value selected from -12.60 to 1.18, preferably -4.94; θ1Is any value selected from 3.08-15.05, preferably 7.92; θ2Is any number...

Embodiment 2

[0102]In this embodiment, using the CT image AI analysis data, CAC detection data, and pathological analysis results of 64 patients collected in Table 2, a decision tree model is successfully constructed, which specifically includes the following steps:

[0103](1) Divide the data collected in Table 2 into 10 randomly, and use 1 of them as the test set in turn, and the other 9 as the training set.

[0104](2) Considering the four characteristics of age, gender, "CT image AI malignant probability", and "CAC detection data", using the training set, passCalculate the situation after dividing according to the characteristic value of one of the characteristics, whereSelect the feature that minimizes Gini (D, A) as the partition node.

[0105](3) In the decision tree generation process, each node is evaluated before division. If the current node can improve the generalization performance of the decision tree, the current node is divided, otherwise no division is performed.

[0106](4) Repeat the abov...

Embodiment 3

[0112]In this example, using the CT image AI analysis data, CAC detection data, and pathological analysis results of 64 patients collected in Table 2, a random forest model was successfully constructed, which specifically includes the following steps:

[0113](1) Divide the data collected in Table 2 into 10 randomly, and use one of them as the test set in turn, and the other 9 as the training set.

[0114](2) Set the number of decision trees in the random forest to 100, and re-divide the training set data into 100 different data sets through the Bootstrap re-sampling method. Some observations are selected multiple times, and some are not.

[0115](3) For each data set in step (2), consider the four characteristics of age, gender, "CT image AI malignant probability", and "CAC detection data", set the tuning parameter mtry, and when each node needs to be split , First randomly select a subset of mtry features from the four features from the set of current nodes, and select the feature that min...

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 pulmonary nodule risk assessment system, and the system carries out the comprehensive assessment of the obtained image analysis data of a patient, the CAC detection data of the patient and the risk factors of the patient through a logistic regression model, a decision tree model or a random forest model, and carries out the assessment of the pulmonary nodule risk of the patient. Whether the pulmonary nodules exist or not can be evaluated, the risk of the existing pulmonary nodules can be predicted, and high accuracy is achieved.

Description

Technical field[0001]The present invention relates to the technical field of medical data processing, and in particular to a system for risk assessment of lung nodules.Background technique[0002]Sarcoidosis is a multi-system and multi-organ granulomatous disease with unknown etiology, which often invades lungs, bilateral hilar lymph nodes, eyes, skin and other organs, and its chest invasion rate is as high as 80% to 90%. It has a worldwide distribution. The incidence is higher in Europe and the United States. It is rare in Eastern peoples. It is more common in 20 to 40 years old. There are slightly more women than men.[0003]At present, the causes and pathogenesis of pulmonary nodules are still in the research stage. It is only proved that sarcoidosis is the result of an unknown antigen competing with the body's cellular and humoral immune functions. Due to individual differences (age, gender, race, genetic factors, hormones, HLA) and the regulation of antibody immune response, the de...

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
IPC IPC(8): G16H50/30G06T7/00G06T7/62G06T7/11G06N3/04G06N20/00
CPCG16H50/30G06T7/0012G06T7/62G06T7/11G06N3/04G06N20/00G06T2207/10081G06T2207/20081G06T2207/30064G06T2207/30096
Inventor 叶莘范献军周燕玲陈燕慈黄萌张俊成石剑峰
Owner ZHUHAI LIVZON CYNVENIO DIAGNOSTICS
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