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

Sparse-representation-based multi-mode magnetic resonance image segmentation method and device

A magnetic resonance image, sparse representation technology, applied in the field of image processing, can solve problems such as slow running speed and low segmentation accuracy

Active Publication Date: 2014-04-09
SHENZHEN INST OF ADVANCED TECH
View PDF2 Cites 51 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The purpose of the present invention is to provide a segmentation method of multimodal magnetic resonance images based on sparse representation, which solves the technical problems of low segmentation accuracy and slow running speed in the prior art

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
  • Sparse-representation-based multi-mode magnetic resonance image segmentation method and device
  • Sparse-representation-based multi-mode magnetic resonance image segmentation method and device
  • Sparse-representation-based multi-mode magnetic resonance image segmentation method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054] Embodiment 1 of the present invention provides a sparse representation-based multimodal magnetic resonance image segmentation method, such as figure 1 As shown, the method includes:

[0055] Step S101: register the magnetic resonance images of different imaging modalities of the patient;

[0056] Step S102: Extract training samples of tumor T, edema E, and background B from the registered multi-modal images, and perform dictionary training on the training samples of each category;

[0057] Step S103: Maximum likelihood estimation, using the dictionary to perform sparse coding on test samples, and obtain the sparse coding coefficient of each test sample;

[0058] Step S104: Establish an image segmentation model based on the MAP-MRF framework, and use a graph cut method to accurately segment the image.

[0059] In step S101, the multimodal magnetic resonance image includes T 1 Weighted image, T 2 Weighted image, T 1c Enhanced image and Flair image; the multimodal MR image correspo...

Embodiment 2

[0110] Embodiment 2 of the present invention provides a sparse representation-based multi-modal magnetic resonance image segmentation device. According to the sparse representation-based multi-modal magnetic resonance image segmentation method in Embodiment 1, the multi-modal image is segmented ,Such as figure 2 As shown, the device includes: a registration module 100, a dictionary training module 200, a sparse coding module 300, and an image segmentation module 400.

[0111] Among them, the registration classification module 100 is used to register the magnetic resonance images of different imaging modalities of the patient; the dictionary training module 200 is used to extract training samples for tumor T, edema E, and background B, and train each category The sample performs dictionary training; the sparse coding module 300 is used to perform sparse coding on the training samples from the dictionary to obtain the sparse coding coefficient of each training sample; the image seg...

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 the technical field of image processing, and particularly relates to a sparse-representation-based multi-mode magnetic resonance image segmentation method and a device. A sparse-representation-based classification SRC (sparse representation based classification) algorithm is adopted by the segmentation method. An image is accurately segmented via establishing an image segmentation model on the basis of an MAP-MRF framework by the segmentation method. A Markov random field is utilized, and influence of adjacent pixels in surrounding space of the pixels is fully considered so that accuracy of image segmentation is increased. Meanwhile, an online dictionary learning method and an image segmentation optimization method are adopted so that operation speed is enhanced.

Description

【Technical Field】 [0001] The present invention relates to the technical field of image processing, in particular to a method and device for segmenting multimodal magnetic resonance images based on sparse representation. 【Background technique】 [0002] Brain tumor is a kind of abnormal tissue hyperplasia, divided into benign tumor and malignant tumor. Due to its swelling and infiltrating growth, once occupying a certain space in the skull, whether it is benign or malignant, it will inevitably increase the intracranial pressure, compress the brain tissue, cause central nervous system damage, and endanger the life of the patient. [0003] Magnetic resonance imaging (MRI) technology has the advantages of high soft tissue resolution, high image contrast, and basically no harm to the human body. It has been widely used in the diagnosis of brain tumors. In order to quantitatively analyze the local lesions of brain tumors, doctors need to segment the tumors in brain images to understand t...

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): G06T7/00G06K9/66
Inventor 李玉红秦璟贾富仓王平安
Owner SHENZHEN INST OF ADVANCED TECH
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