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

A deep learning high under-sampling hyperpolarized gas lung MRI reconstruction method

A deep learning and undersampling technology, applied in neural learning methods, 2D image generation, image data processing, etc., can solve problems such as difficulty in accurately estimating noise

Active Publication Date: 2019-03-01
INNOVATION ACAD FOR PRECISION MEASUREMENT SCI & TECH CAS
View PDF10 Cites 21 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

But in MRI, accurate noise estimation is a difficult task, because the noise may be non-stationary Rician noise

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 deep learning high under-sampling hyperpolarized gas lung MRI reconstruction method
  • A deep learning high under-sampling hyperpolarized gas lung MRI reconstruction method
  • A deep learning high under-sampling hyperpolarized gas lung MRI reconstruction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] A high undersampling hyperpolarized gas lung MRI reconstruction method based on deep learning, comprising the following steps:

[0051] Step 1, constructing hyperpolarized gas lung MRI image training set, hyperpolarized gas in this embodiment is 129 Xe, the training set of hyperpolarized gas lung MRI images is 129 Xe lung MRI image training set;

[0052] In step 1.1, fully sampled hyperpolarized gas lung magnetic resonance k-space data and corresponding proton images were collected from 72 volunteers. The full-sampled hyperpolarized gas lung magnetic resonance k-space data were acquired by 3D bSSFP sequence, the sampling matrix size was 96×84, and the number of slices was 24. Fast Fourier transform is performed on the full-sampled hyperpolarized gas lung magnetic resonance k-space data, and the obtained reconstruction result is used as the reference image y, and the images whose signal area of ​​the lung is smaller than 10% of the image size are eliminated, and a tota...

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 deep learning high under-sampling hyperpolarized gas lung MRI reconstruction method. The method comprises the following steps: constructing and constructing a hyperpolarizedgas lung MRI image training set; according to the method, the cascade CNN model is used, lung contour information is added into a loss function, an accurate reconstructed image can be obtained under the high under-sampling multiple, and the imaging speed is remarkably increased.

Description

technical field [0001] The present invention relates to the technical fields of magnetic resonance imaging (Magnetic Resonance Imaging, MRI), deep learning, undersampling reconstruction, etc., and specifically relates to a high undersampling hyperpolarized gas lung MRI reconstruction method for deep learning, which is suitable for accelerating hyperpolarization Inert gases (such as 129 Xe, 3 He et al.) the imaging speed of lung MRI and improve the imaging quality. Background technique [0002] MRI is a non-invasive, ionizing radiation-free imaging method that can provide high-resolution structural and functional information for clinical use. Traditional MRI focuses on hydrogen protons, while the lungs are mainly composed of cavities with a low density of hydrogen protons, so the lungs are a blind area of ​​traditional MRI. Spin-exchange optical pumping technology can convert noble gases (such as 3 He, 129 Xe, etc.) Polarizability increased by 10 3 ~10 5 times, thus ma...

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 Applications(China)
IPC IPC(8): G06T11/00G06T7/11G06N3/08
CPCG06N3/08G06T11/005G06T2207/10088G06T2207/20081G06T7/11
Inventor 周欣段曹辉邓鹤肖洒李海东孙献平叶朝辉
Owner INNOVATION ACAD FOR PRECISION MEASUREMENT SCI & TECH CAS
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