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

An MRI Image Segmentation Method Based on Shape Priors

A technology of nuclear magnetic resonance image and prior shape, applied in image analysis, image data processing, instrument and other directions, can solve the problems of evolution curve leakage, over-segmentation, and segmentation failure, etc.

Inactive Publication Date: 2016-04-13
NANJING UNIV OF INFORMATION SCI & TECH
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, when the difference between the edge of the target and the background gray level is small, the evolution curve will appear leaky or over-segmented, resulting in segmentation failure
And when there is noise, clutter or occlusion in the image, ordinary segmentation models cannot extract the target of interest

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
  • An MRI Image Segmentation Method Based on Shape Priors
  • An MRI Image Segmentation Method Based on Shape Priors
  • An MRI Image Segmentation Method Based on Shape Priors

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The specific implementation manners of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0031] Such as figure 1 As shown, the present invention has designed a kind of nuclear magnetic resonance image segmentation method based on prior shape, comprises the steps:

[0032] Step 001. Obtain N magnetic resonance training images of the target body of the same size, mark the target body contour in each training image respectively, and use two different types of Values ​​are binarized;

[0033]Step 002. For N training images, select a training image as a benchmark, and register with other N-1 training images using Euclidean geometric similarity transformation, and add the training images as benchmarks to obtain a total of N registrations Training images, where registration is performed according to the following registration function:

[0034] E a l ...

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 a method for segmenting nuclear magnetic resonance images on the basis of prior shapes. The method has the advantages that adaptive region information and boundary information are integrated by the aid of shape prior information, so that target objects in complicated backgrounds and images can be effectively segmented, problems that gray levels of pixels of interested target objects in images are uneven, edge gradients of the target objects are unobvious, the interested target objects are shielded and the like can be effectively solved, and the computational complexity can be greatly reduced.

Description

technical field [0001] The invention relates to a method for segmenting nuclear magnetic resonance images based on prior shapes. Background technique [0002] Breast cancer is one of the most common malignant tumors in middle-aged and elderly women. It has already ranked first in female malignant tumors in China, and has a tendency of increasing year by year and younger incidence. At present, there is no good strategy for the prevention of breast cancer. The detection and analysis of breast images is an important basis for the successful detection, diagnosis and treatment of tumors, especially the segmentation of breast regions is of great significance to the subsequent research and analysis of tumors. However, due to the similar density of breast tissue and body part soft tissue, it is difficult to segment the breast region separately. At present, active contour models and level set methods have been widely used in image segmentation. Active contour models are mainly divid...

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): G06T7/00
Inventor 徐军曹冬梅
Owner NANJING UNIV OF INFORMATION SCI & TECH