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

Brain image segmentation method and system based on local similarity activity contour model

A technology of active contour model and image segmentation, which is applied in image analysis, image data processing, computer components, etc.

Active Publication Date: 2018-01-26
SHANDONG UNIV OF FINANCE & ECONOMICS
View PDF3 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The newly established segmentation model can better deal with the problem of gray level inhomogeneity, make up for the shortcomings of the existing active contour model in dealing with noise and gray level heterogeneity, and improve the accuracy and robustness of brain MR image segmentation

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
  • Brain image segmentation method and system based on local similarity activity contour model
  • Brain image segmentation method and system based on local similarity activity contour model
  • Brain image segmentation method and system based on local similarity activity contour model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0069] The present embodiment provides a brain image segmentation method based on the active contour model of local similarity learning, comprising the following steps:

[0070] Step 1: Obtain an MRI image to be segmented;

[0071] Step 2: performing superpixel segmentation on the nuclear magnetic resonance image to be segmented to obtain multiple superpixels;

[0072] Step 3: Extract the average gray value, texture features based on co-occurrence matrix, and local gray features for the plurality of superpixels; perform features in series on the average gray value, texture features based on co-occurrence matrix, and local gray features Fusion, get the features after fusion;

[0073] Step 4: Classify the superpixels by using a dictionary and a sparse representation classification method to obtain an initial target area;

[0074] Step 5: According to the initial target area, use the Gaussian probability density function to calculate the probability that each pixel belongs to t...

Embodiment 2

[0122] The purpose of this embodiment is to provide a computer-readable storage medium.

[0123] In order to achieve the above object, the present invention adopts the following technical scheme:

[0124] A computer-readable storage medium, on which a computer program is stored for MR image segmentation, and the program performs the following steps when executed by a processor:

[0125] Obtain an MRI image to be segmented;

[0126] Performing superpixel segmentation on the nuclear magnetic resonance image to be segmented to obtain a plurality of superpixels;

[0127] Extract the average gray value, the texture feature based on the co-occurrence matrix and the local gray feature from the plurality of superpixels; perform feature fusion on the average gray value, the texture feature based on the co-occurrence matrix and the local gray feature in series, and obtain features after fusion;

[0128] Classifying the superpixels by using a dictionary and a sparse representation cla...

Embodiment 3

[0132] The purpose of this embodiment is to provide a brain image segmentation system based on the local similarity active contour model.

[0133] In order to achieve the above object, the present invention adopts the following technical scheme:

[0134] A brain image segmentation system based on a local similarity active contour model, comprising a processor and a computer-readable storage medium, the processor is used to implement instructions; the computer-readable storage medium is used to store multiple instructions, and the instructions are suitable for Loaded by the processor and performs the following processing:

[0135] Obtain an MRI image to be segmented;

[0136] Performing superpixel segmentation on the nuclear magnetic resonance image to be segmented to obtain a plurality of superpixels;

[0137] Extract the average gray value, the texture feature based on the co-occurrence matrix and the local gray feature from the plurality of superpixels; perform feature fus...

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 brain image segmentation method and system based on a local similarity activity contour model. The method comprises steps that a to-be-segmented nuclear magnetic resonance image is acquired; super pixel segmentation of the to-be-segmented nuclear magnetic resonance image is carried out to acquire multiple super pixels; an average gray value, texture characteristics basedon a gray symbiosis matrix and local characteristics of the super pixels are extracted; characteristic fusion of all the characteristics is carried out in a serial mode; the super pixels are classified through employing a dictionary and a sparse expression classification method to acquire an initial target area; according to the initial target area, a Gaussian probability density function is utilized to calculate target probability of each pixel, and the probability is taken as the local similarity prior of learning; an activity contour model energy function based on local similarity learningis established, through a minimized energy function, the image segmentation result is acquired. The method is advantaged in that a gray non-uniform problem can be excellently processed through the activity contour model, and accuracy and robustness of brain image segmentation are improved.

Description

technical field [0001] The invention relates to the field of medical image segmentation, in particular to a brain image segmentation method and system based on a local similarity active contour model. Background technique [0002] Brain diseases seriously threaten human life and health. Due to its advantages of high contrast and rich information, magnetic resonance image (MR, magnetic resonance) has become the main imaging method for auxiliary diagnosis of brain diseases. Medical image segmentation technology can extract the region of interest, which is the basis for quantitative analysis and diagnosis of the lesion. Therefore, inventing a brain MR image segmentation method is of great significance for improving the accuracy and efficiency of brain disease diagnosis. [0003] The existing brain MR segmentation methods mainly include threshold method, method based on learning model, method based on active contour model and so on. However, there is a problem of gray level h...

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
IPC IPC(8): G06T7/10G06K9/46G06K9/62
Inventor 袭肖明尹义龙孟宪静聂秀山杨璐
Owner SHANDONG UNIV OF FINANCE & ECONOMICS
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com