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

Muscle injury ultrasound contrastographic image segmentation method based on maximum structured information decomposition

A technology for structured information and muscle damage, applied in image analysis, image data processing, ultrasound/sonic/infrasonic diagnosis, etc., can solve problems such as roughness

Inactive Publication Date: 2015-06-24
SHANGHAI MARITIME UNIVERSITY
View PDF2 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In recent years, researchers have proposed many adaptive algorithms to process CEUS images, but these algorithms can only extract a rough edge of the injured muscle, so the existing image segmentation algorithms are not very ideal in some cases

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
  • Muscle injury ultrasound contrastographic image segmentation method based on maximum structured information decomposition
  • Muscle injury ultrasound contrastographic image segmentation method based on maximum structured information decomposition
  • Muscle injury ultrasound contrastographic image segmentation method based on maximum structured information decomposition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0054] A method for segmenting a muscle injury contrast-enhanced ultrasound image based on the maximum decomposition of structured information. The specific implementation method includes the following steps:

[0055] Step 1: Selection of image frames when the signal strength peaks.

[0056] First, select a time window for the obtained image. The selected method is to observe the intensity of the gray value of the image, and record the moment when the intensity of the gray value is the strongest as t max , with t max As the central moment, select the interval A total of t seconds of time window, a total of m frames of images. All the images in the window are kept, and the rest are discarded to obtain muscle damage images with higher energy values.

[0057] Step 2: Extraction of structured texture features.

[0058] For the image obtained in step 1, the following two-step processing is performed frame by frame, including the generation of label information and the calculat...

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 an image segmentation method, in particular to a muscle injury ultrasound contrastographic image segmentation method. The muscle injury ultrasound contrastographic image segmentation method comprises the steps that firstly, an acquired ultrasound contrastographic image is extracted according to a structured textural feature extracting method; afterwards, independent components of the structured textural image are obtained according to an independent component analysis method based on maximum structured mutual information decomposition; finally, a muscle injury boundary is obtained by means of the independent component obtained after decomposition according to a classification method based on information entropy and an image segmentation method based on union images. The muscle injury ultrasound contrastographic image segmentation method has the advantages that on one hand, the structural information in the image is extracted by means of the local textural features of the image instead of gray values, and thus the situation that subsequent analysis is affected due to the fact that the gray values are not stable is avoided; on the other hand, the influence of noise is avoided, and the accurate rate of muscle injury boundary recognition is increased.

Description

technical field [0001] The invention relates to an image segmentation method, in particular to a segmentation method for muscle injury ultrasound contrast images. Background technique [0002] In daily life, muscle damage occurs from time to time. The rehabilitation effect of muscle injury requires real-time and long-term observation. Modern medicine believes that compared with computerized tomography and magnetic resonance imaging, contrast-enhanced ultrasound technology has the advantages of low radiation and portability. By infusing microbubble contrast agents into observed tissues, diagnostic personnel can be assisted in collecting important medical information, and the evolution of diseases can also be observed. In recent years, researchers have proposed many adaptive algorithms to process CEUS images, but these algorithms can only extract a rough edge of the injured muscle, so the existing image segmentation algorithms are not very ideal in some cases . [0003] Th...

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): G06T7/00A61B8/00
Inventor 陈东太郎徐琪曾卫明
Owner SHANGHAI MARITIME UNIVERSITY
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