Unlock instant, AI-driven research and patent intelligence for your innovation.

4dct radiomic feature extraction image reconstruction method, medium and device

A radiomics and feature extraction technology, applied in 2D image generation, image data processing, medical science, etc., can solve the problems of low light input, blurred images, large distortion, etc., and achieve the effect of improving prediction ability.

Active Publication Date: 2020-09-15
李夏东
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

If the moving speed of the subject’s tumor is fast and the shutter of the camera is not fast enough, it will cause oversampling within the same exposure time, which will eventually lead to blurred images; undersampling
Existing reconstruction methods for 4DCT images of lung tumors include methods such as AIP and MIP, all of which have large distortions in the processing of 4DCT images of lung tumors

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
  • 4dct radiomic feature extraction image reconstruction method, medium and device
  • 4dct radiomic feature extraction image reconstruction method, medium and device
  • 4dct radiomic feature extraction image reconstruction method, medium and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] This embodiment provides a special image reconstruction method for radiomics feature extraction based on 4DCT images of lung tumors, which aims at how to extract radiomics feature parameters close to static CT images from reconstructed images of 4DCT images and these Regarding the influence of radiomics characteristic parameters on predictive model modeling, the concept and mathematical model (Minimumgradient density projection matrix, MGDPM) of reconstructing images based on the minimum gradient density projection matrix (Minimumgradient density projection matrix, MGPM) were proposed through the temporal gradient analysis of the tumor centroid motion curve, and Compared with the current traditional AIP and MIP image extraction features, the prediction ability of this method in the early metastasis of non-small cell lung cancer NSCLC was verified.

[0050] Through the method of this embodiment, the three-dimensional trajectory of the centroid movement of each patient's t...

Embodiment 2

[0276] This embodiment provides a medium on which the rebuilding method described in Embodiment 1 is recorded.

Embodiment 3

[0278] This embodiment provides a special image reconstruction device for radiomics feature extraction based on 4DCT images of lung tumors, which includes a first processing module for completing step S1 in embodiment 1, and for completing step S2. The second processing module, the third processing module for completing step S3, the fourth processing module for completing step S4, the fifth processing module for completing step S5, and the sixth processing module for completing step S6.

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 relates to the technical field of 4DCT image reconstruction, in particular to a reconstruction method, a medium and a device for reconstructing a special image for performing image omicsfeature extraction based on a lung tumor 4DCT image. The objective of the invention is to solve the problem of how to extract iconomics characteristic parameters close to a static CT image from a reconstructed image of a 4DCT image and how to influence modeling of a prediction model by the iconomics characteristic parameters. A concept and a mathematical model (MGDPM) for reconstructing an imageon the basis of a minimum gradient density projection matrix are provided by analyzing the time domain gradient of a tumor centroid motion curve, and the concept and the mathematical model are used for reconstructing the image on the basis of the minimum gradient density projection matrix. Compared with the existing traditional average density projection, the invention provides the prediction capability of MIP (Maximum Intensity Projection) image extraction characteristics in NSCLC (Non-Small Cell Lung Cancer) early metastasis, in particular to a prediction capability of MIP (Maximum IntensityProjection) image extraction characteristics in NSCLC early metastasis.

Description

technical field [0001] The present invention relates to the technical field of 4DCT image reconstruction, in particular to a special image reconstruction method, medium and device for extracting radiomics features based on 4DCT images of lung tumors. Background technique [0002] The concept of radiomics was first proposed by Professor Philippe Lambina of Maastricht University Medical Center in the Netherlands in 2012 and published in the European Journal of Oncology. This technology is a new processing and analysis technology based on multimodal medical images. . Based on high-performance computers and algorithms, it automatically extracts and analyzes massive amounts of data from computer tomography CT, magnetic resonance image MRI, and positron emission / tomography PET / CT, which are widely used at present, and can provide early diagnosis of diseases and identification of benign and malignant tumors. , disease treatment management, individualized precision treatment and ot...

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 Patents(China)
IPC IPC(8): G06T11/00A61B6/00
CPCA61B6/5211A61B6/5264G06T11/003
Inventor 李骏甫李夏东
Owner 李夏东