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

AI-based human body multi-core DWI joint reconstruction method

A multi-core, human body technology, applied in the field of AI-based multi-core DWI joint reconstruction of the human body, can solve the problems of low signal-to-noise ratio of hyperpolarized DWI images, insufficient training sets, etc., to improve reconstruction effect, improve imaging speed, and ensure consistency Effect

Active Publication Date: 2020-05-15
INNOVATION ACAD FOR PRECISION MEASUREMENT SCI & TECH CAS
View PDF5 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the low SNR and insufficient training set of hyperpolarized DWI images, there is no research on applying AI to the field of hyperpolarized DWI reconstruction.

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
  • AI-based human body multi-core DWI joint reconstruction method
  • AI-based human body multi-core DWI joint reconstruction method
  • AI-based human body multi-core DWI joint reconstruction method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] An AI-based human body multi-core DWI joint reconstruction method, comprising the following steps:

[0041] Step 1. Construct a human body multi-core DWI image training set. In this embodiment, the multi-core DWI of the human body is hyperpolarized 129 Xe lung DWI, human body multi-core DWI image training set is hyperpolarized 129 Xe lung DWI image training set.

[0042] Step 1.1. Obtain fully sampled hyperpolarization from the MRI machine 129 Xe lung ventilation image. A full sample of hyperpolarization was collected from 105 volunteers 129 Xe lung ventilation image. Fully sampled hyperpolarization 129 Xe lung ventilation images were acquired by 3D bSSFP sequence, the sampling matrix size was 96×84, the slice thickness was 8mm, and the number of slices was 24. Select images with a signal-to-noise ratio greater than 6.6, and obtain a total of 1404 fully sampled hyperpolarized 129 Xe lung ventilation image. Hyperpolarization for full sampling 129 Xe lung ventil...

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 an AI-based human body multi-core DWI joint reconstruction method. The method comprises the steps: establishing a human body multi-core DWI image training set; establishing a human body multi-core DWI joint reconstruction model; defining a loss function of the human body multi-core DWI joint reconstruction model; training a human body multi-core DWI joint reconstruction model by adopting a gradient descent algorithm; inputting a new under-sampling DWI image into the trained human body multi-core DWI joint reconstruction model, and performing forward propagation of the model to obtain a final reconstruction image containing different b values. According to the method, the high-quality reconstructed image can be obtained under the high acceleration multiple, and the reconstruction speed is high.

Description

technical field [0001] The present invention relates to technical fields such as multi-nuclear magnetic resonance imaging (MRI), artificial intelligence (AI), deep learning, under-sampling reconstruction, etc., and specifically relates to an AI-based multi-core DWI joint reconstruction method for human body, which is applicable to Accelerate human multi-core (such as 129 Xe, 3 He et al) the imaging speed of DWI, or obtain more data in the same time. Background technique [0002] Multinuclear MRI can provide rich physiological and pathological information, such as hyperpolarized gas ( 129 Xe, 3 He) Lung MRI can provide high-resolution images of lung structure and function. In particular, hyperpolarized gas lung DWI can sensitively assess structural and functional changes associated with lung disease. Combined with the theoretical model of gas diffusion, multi-b-value DWI can non-invasively and quantitatively obtain lung morphological parameters at the alveolar level, suc...

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): G06T11/00
CPCG06T11/003
Inventor 周欣段曹辉邓鹤娄昕孙献平叶朝辉
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