A magnetic resonance image segmentation method combining global and local information

A magnetic resonance image and nuclear magnetic resonance image technology, applied in the field of digital images, can solve the problem of low segmentation accuracy of MRI images, achieve good segmentation results and improve segmentation accuracy

Active Publication Date: 2019-03-15
SOUTHEAST UNIV
View PDF3 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0011] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art, provide a brain magnetic resonance image segmentation method that combines global and local in

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
  • A magnetic resonance image segmentation method combining global and local information
  • A magnetic resonance image segmentation method combining global and local information
  • A magnetic resonance image segmentation method combining global and local information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] Embodiments of the present invention will be described below in conjunction with the accompanying drawings.

[0049] Such as figure 1 As shown, the present invention designs a brain magnetic resonance image segmentation method combining global and local information. First, train an end-to-end convolutional neural network model and obtain preliminary segmentation results through the model. Here, the brain magnetic resonance image is utilized The global information of the supervoxel; then use the simple iterative clustering supervoxel algorithm to generate supervoxels; finally, the segmentation results are further improved by fusing the supervoxel prior information to achieve the recognition of white matter, gray matter and cerebrospinal fluid in brain MRI images. For accurate segmentation, the local information of the brain MRI image is used here, and the method of fusing the supervoxel prior information is based on the proportion of each category in the supervoxel. 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 brain magnetic resonance image segmentation method combining global and local information, which comprises the following steps: segmenting the brain magnetic resonance imageby using an end-to-end convolution neural network constructed to obtain various prediction probability distributions; The supervoxels are generated by linear iterative clustering supervoxel algorithmfor brain MRI images. A magnetic resonance image of that brain in which a segmentation result is obtain by fusing the segmentation result prediction probability distribution and the generate supervoxels comprises the following step of: finding out the corresponding regions of the supervoxels in the prediction probability distribution of each category; Background, cerebrospinal fluid (CSF), gray matter (GM) and white matter (WM) were counted and the specific gravity of each category was calculated. The supervoxel class proportion method is used to re-assign the prediction probability distribution of each class. The class with the highest probability of classification and the class label of the pixel are obtained to obtain the segmentation result of the brain magnetic resonance image. The invention can improve the segmentation precision and obtain a better segmentation result of the magnetic resonance image of the brain.

Description

technical field [0001] The invention relates to a brain magnetic resonance image segmentation method combining global and local information, belonging to the technical field of digital images. Background technique [0002] The brain is the highest regulating organ of all physiological activities of the human body and the central organ of psychological thinking activities. It is the most special and important organ of the human body. Its health is extremely important, so it is necessary to pay attention to the health of the brain. However, with the rapid development of society, accelerated pace of life, aging body, environmental factors, traffic and accidents and other factors, brain diseases such as epilepsy, cerebrovascular disease, cerebral palsy and intracranial tumors are more common now. Brain diseases have become an important factor threatening people's health. Effective diagnosis and treatment of brain diseases is extremely beneficial for improving human life expecta...

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): G06K9/34G06K9/62
CPCG06V10/267G06F18/23213
Inventor 孔佑勇吴飞杨雨婷伍家松杨淳沨舒华忠
Owner SOUTHEAST UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap