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

CT image tumor tissue extraction method based on feature diffusion

A CT image and tumor tissue technology, applied in the field of medical image processing, can solve the problems of non-diffusion, low manual participation, fixed number, etc., and achieve the effects of high accuracy, improved accuracy, and high manual interaction.

Inactive Publication Date: 2014-11-19
THE FIRST AFFILIATED HOSPITAL OF MEDICAL COLLEGE OF XIAN JIAOTONG UNIV
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] 1. The human participation is low, and the effect of tumor tissue extraction is not human-oriented;
[0004] 2. The number of feature points is fixed and cannot spread, and the accuracy of tumor tissue extraction is poor

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
  • CT image tumor tissue extraction method based on feature diffusion
  • CT image tumor tissue extraction method based on feature diffusion
  • CT image tumor tissue extraction method based on feature diffusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The present invention will be further described in detail below in conjunction with specific embodiments, which are explanations of the present invention rather than limitations.

[0044] Technical scheme of the present invention:

[0045]Obtain the target CT image, add an appropriate amount of feature points representing tumor tissue, and obtain the coordinates of these feature points corresponding to the source image. Calculate the average value of the corresponding value of the feature point corresponding to the element in the CT image, and extract the first few points from the CT image whose values ​​are closest to the above average value, these points are called auxiliary feature points, and add them to the feature point set To assist the original feature points to serve the clustering method. Find the similarity matrix of the original CT image, and correct the value of the corresponding position of the feature point in the matrix to 1, which means that the probab...

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 CT image tumor tissue extraction method based on feature diffusion and mainly solves the problem of extraction of CT image tumor tissue. The method comprises the following processes: a target CT image is obtained and feature points are added, all pixel points are diffused in the whole CT image by using the distances among feature points, more pixel points which can represent the tumor tissue are included so as to form a transcendental feature point set, and the CT image is clustered under the guiding of the point set, so that the extraction of the CT image tumor tissue is realized. The CT image tumor tissue extraction method has the advantages of high artificial participation degree and high tumor tissue extraction accuracy and can be used for extraction of the CT image tumor tissue.

Description

technical field [0001] The invention belongs to the field of medical image processing, and relates to a method for extracting tumor tissue in CT using spectral clustering of characteristic diffusion, in particular to a method for extracting tumor tissue in CT images based on characteristic diffusion. Background technique [0002] The tissue extraction of CT images is a hot issue in the field of medical image processing in recent years. The existing extraction method based on spectral clustering is to manually add feature points as prior information, which plays a guiding role in the spectral clustering method. Obtain better tumor tissue extraction results. However, this method has the following disadvantages: if too few feature points are added, the ideal extraction effect cannot be achieved, and if too many feature points are added, the running speed of the method will be affected. Therefore, how to improve the accuracy of tumor tissue extraction in CT images without sacri...

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): G06T7/00
Inventor 张佳王健生
Owner THE FIRST AFFILIATED HOSPITAL OF MEDICAL COLLEGE OF XIAN JIAOTONG UNIV