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

Construction Method of Similarity Matrix in ncut Segmentation of Ultrasonic Image

A similarity matrix, ultrasonic image technology, applied in image analysis, image data processing, instruments, etc.

Inactive Publication Date: 2016-08-24
WUHAN UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although there are many methods for region-based texture feature extraction, they are not very suitable for Ncut algorithm

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
  • Construction Method of Similarity Matrix in ncut Segmentation of Ultrasonic Image
  • Construction Method of Similarity Matrix in ncut Segmentation of Ultrasonic Image
  • Construction Method of Similarity Matrix in ncut Segmentation of Ultrasonic Image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] figure 2 (a) is an ultrasound image with a size of 240x240 (unit: pixel), which is preprocessed by anisotropic diffusion and homomorphic filtering in sequence. The preprocessing results are shown in figure 2 (b) and figure 2 (c); A simple linear iterative clustering algorithm is used to divide the preprocessed image into a plurality of subregions with irregular boundaries, namely superpixels, wherein the number K of pixels contained in each small region is 700, See figure 2 (d); calculate the average gray value of each sub-region and the Euclidean distance of the average gray value between the sub-regions; calculate the texture feature vector of each sub-region and use the chi-square distance to represent the dissimilarity between the sub-regions, The two are combined according to formula (7) to obtain a new similarity matrix, and then verify the validity of the similarity matrix, and use the Ncut algorithm to cluster these sub-regions into two categories. The clu...

Embodiment 2

[0056] image 3 (a) is an ultrasound image with a size of 240x240 (unit: pixel), which is preprocessed by anisotropic diffusion and homomorphic filtering in sequence. For the results of anisotropic diffusion filtering, see image 3 (b), the results of homomorphic filtering are shown in image 3 (c), using a simple linear iterative clustering algorithm to divide the preprocessed image into multiple sub-regions with irregular boundaries, namely superpixels, wherein the number K of pixels contained in each small region is 700, See image 3 (d); Calculate the average gray value of each sub-region and the Euclidean distance of the average gray value between the sub-regions; calculate the texture feature vector of each sub-region and use the Jeffrey divergence distance to represent the difference between the sub-regions Similarity, the two are combined according to formula (7) to obtain a new similarity matrix, and then the validity of the similarity matrix is ​​verified, and the ...

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 method for constructing a similarity matrix in the ultrasound image Ncut segmentation process. The method includes the following steps of firstly, preprocessing an ultrasound image; secondly, conducting over-segmentation on the ultrasound image through a simple linear iterative clustering method to generate even-medium sub-areas with irregular borders; thirdly, enabling average gray level information of all the sub-areas to serve as one characteristic for constructing the Ncut similarity matrix, and calculating the texture characteristics of all the sub-areas through a gray level co-occurrence matrix at the same time, wherein the texture characteristics totally include 24 characteristics with six characteristics in each of the four directions, and the 24 data are combined to form a texture characteristic vector, namely, another characteristic for constructing the Ncut similarity matrix; fourthly, calculating the distance between the characteristics of every two adjacent sub-areas, and combining the sub-areas according to a certain proportion to form a new Ncut similarity matrix calculation formula. When the method is used for segmenting the ultrasound image based on Ncut clustering, a good segmentation result is obtained, the problems that the ultrasound image is high in noise and low in contrast ratio are solved, and the tumor areas and the background areas can be effectively separated.

Description

technical field [0001] The invention relates to a method for constructing a similarity matrix in ultrasonic image Ncut segmentation, and belongs to the field of ultrasonic image segmentation. Background technique [0002] With the advent of high-intensity focused ultrasound, it has become more and more widely used in non-invasive treatment of tumors. This treatment system has great advantages in clinical practice, such as no surgery, no scars, non-invasive or minimally invasive, real-time detection and treatment, not limited by tumor size, and low total cost. These advantages determine that the high-intensity focused ultrasound therapy system has great development and application prospects. The most critical thing in the high-intensity focused ultrasound treatment system is to navigate the patient's tumor in real time, and the navigation process requires the positioning of the tumor in the real-time ultrasound image. Changing the traditional manual positioning method to au...

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): G06T7/00G06T7/11
Inventor 张东刘雨龙群芳徐梦龙杨艳
Owner WUHAN UNIV
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