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

Convolutional-neural-network-based multi-contrast magnetic resonance image reconstruction method

A convolutional neural network and magnetic resonance image technology, applied in neural learning methods, biological neural network models, image enhancement, etc., can solve the problems of long MRI imaging time, motion artifacts, and reduced imaging quality.

Active Publication Date: 2018-05-29
XIAMEN UNIV
View PDF8 Cites 24 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the high-resolution MRI imaging takes a long time, and it is easy to cause motion artifacts and reduce the imaging quality in the case of the heart and other situations that require fast imaging.

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
  • Convolutional-neural-network-based multi-contrast magnetic resonance image reconstruction method
  • Convolutional-neural-network-based multi-contrast magnetic resonance image reconstruction method
  • Convolutional-neural-network-based multi-contrast magnetic resonance image reconstruction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] The embodiment of the present invention is a specific process of multi-resolution reconstruction of a multi-contrast MRI brain map using a convolutional neural network, and is a detailed description of the method proposed by the present invention.

[0041] The specific implementation process is as follows:

[0042] Step 1: Obtain a multi-contrast dataset for training

[0043] The data set used in this embodiment is a multi-contrast image derived from BrainWeb's MRI database (http: / / brainweb.bic.mni.mcgill.ca / brainweb / ), and the image pixel size used is 1mm × 1mm, and the slice thickness is 1mm , noise-free and non-uniform field intensity simulated images. There are 119 high-resolution T1-weighted images and 119 high-resolution T2-weighted images, and the size of each image is 230×194. High-resolution T1-weighted imagesX T1,H As a reference image, the high-resolution T2-weighted image X T2,H Blur using a Gaussian kernel with window size 3×3 and variance 1:

[0044] ...

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 magnetic resonance imaging field, provides a convolutional-neural-network-based multi-contrast magnetic resonance image reconstruction method. A low-resolution image andhigh-resolution image of a multi-contrast magnetic resonance are obtained; a convolutional neural network model of multi-contrast magnetic resonance image reconstruction is established; the convolutional neural network is trained by using the multi-contrast magnetic resonance image as a training set; and then the low-resolution magnetic resonance image and a corresponding reference image are inputted into the network to reconstruct a high-resolution magnetic resonance image. On the basis of deep learning, the image reconstruction method with structural similarity between multi-contrast imageshas characteristics of high reconstruction speed and good reconstruction effect.

Description

technical field [0001] The present invention relates to magnetic resonance imaging, and in particular to a method of using multi-contrast images to improve the quality of super-resolution reconstruction and using absolute value regularization and a gradient optimization algorithm based on adaptive moment estimation to speed up the convergence speed of training convolutional neural networks. A Convolutional Neural Network Based Multi-Contrast Magnetic Resonance Image Reconstruction Method. Background technique [0002] Magnetic resonance imaging (Magnetic Resonance Imaging, MRI) is an imaging technique for medical clinical detection, which has the characteristics of non-invasive and non-invasive, and is an important clinical medical diagnostic tool. [0003] In clinical diagnosis and post-image analysis, high-resolution MRI images are usually required. However, the high-resolution MRI imaging takes a long time, and it is easy to cause motion artifacts and reduce the imaging ...

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): G06T3/40G06N3/08
CPCG06N3/084G06T3/4053G06T2207/10088G06T2207/20081
Inventor 屈小波
Owner XIAMEN UNIV
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