Training method and application of radiation pneumonia early warning model

A radiation pneumonia and early warning model technology, applied in the field of machine learning, can solve the problem of not considering the differences between high lung function areas and low lung function areas, and achieve the effect of Lubang's prediction effect.

Pending Publication Date: 2022-08-05
HENAN CANCER HOSPITAL
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a training method and application of a radiation pneumonitis early warning model, to solve the problem in the prior art that the early warning model does not consider the difference between areas with high lung function and areas with low lung function

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
  • Training method and application of radiation pneumonia early warning model
  • Training method and application of radiation pneumonia early warning model
  • Training method and application of radiation pneumonia early warning model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] like Figure 1 to Figure 4 As shown, a method for training an early warning model of radiation pneumonia in an embodiment of the present invention is introduced, and the method includes the following steps.

[0038] In step S101, the lung CT image is divided into a high lung function area and a low lung function area according to the lung function image.

[0039] Collect lung function imaging and radiotherapy data of screened patients, including: planning CT images, 3D dose data, profile files and clinical information. Planning CT images, 3D dose data and profile files can all be exported from the radiation therapy planning system as DICOM files .

[0040] The above information also needs data preprocessing. The DICOM files of planned CT images and 3D dose data exported from the radiation therapy planning system need to be converted into mha format files; the contour DICOM files are converted into mha mask data for feature extraction. Format requirements for data entry....

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 training method and application of a radiation pneumonia early warning model, and the device comprises a data preprocessing module which is used for dividing a lung CT image into a high lung function region and a low lung function region according to a lung function image; the feature extraction module is used for extracting radiomics and dosiomics from the high-lung function region and the low-lung function region respectively so as to screen out an optimal feature set; and the training module is used for training a radiation pneumonitis early warning model according to the optimal feature set. According to the training method and application of the radiation pneumonia early warning model, the regional difference of high and low functional lungs is fully considered, so that the early warning model obtains a more accurate and robust prediction effect.

Description

technical field [0001] The present invention relates to the field of machine learning, in particular to a training method and application of a radiation pneumonia early warning model. Background technique [0002] At present, machine learning has been widely used in clinical medicine, not only to assist clinical diagnosis, but also to predict clinical outcomes. Among them, there have been a lot of studies on the prediction of radiation pneumonitis toxicity in lung cancer radiotherapy. It uses radiomics and dosimic features of lung CT images and dose distribution, as well as machine learning classification algorithms, combined with clinical results from the training set, to build a radiation pneumonitis prediction model. CT image-based radiomics is the analysis of lung statistics, shape parameters, and grayscale texture information. Dosimetric factors based on three-dimensional dose distribution include dose histogram factor, dose gradient status, dose distribution and text...

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): G16H50/50G06T7/00G06T7/11G06T7/136G06T7/30
CPCG16H50/50G06T7/0012G06T7/11G06T7/136G06T7/30G06T2207/10081G06T2207/20081G06T2207/30061
Inventor 李兵孟令广任格郭伟陶红艳程宸黄心莹娄朝阳雷宏昌蔡璟葛红
Owner HENAN CANCER HOSPITAL
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap