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

Voxel incoherent movement imaging acceleration method and device based on deep learning

A technology of deep learning and deep learning network, applied in the field of incoherent motion imaging within a voxel, can solve the problem of long acquisition time, and achieve the effect of shortening the time

Active Publication Date: 2020-07-24
浙江拉莫医学影像科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, IVIM imaging requires the acquisition of diffuse signals with multiple b-values ​​(about 10 b-values), which takes a long time and is easily affected by motion artifacts

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
  • Voxel incoherent movement imaging acceleration method and device based on deep learning
  • Voxel incoherent movement imaging acceleration method and device based on deep learning
  • Voxel incoherent movement imaging acceleration method and device based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0073] The above-mentioned accelerated method based on deep learning for voxel-incoherent motion imaging was tested on the data of nine subjects whose pregnancy was between 28 and 36 weeks. Magnetic resonance scans were performed on a General Electric SIGNA HDXT 1.5T scanner, and placental images were collected from the maternal sagittal position using a diffusion-weighted echo-planar imaging sequence: echo time (TE) / repetition time (TR) = 76 / 3000ms, field of view (FOV)=320×320mm, the in-plane resolution is 1.25×1.25mm, the layer thickness is 4mm, and there are 15 layers in total. The diffusion weighted gradient is applied in three directions with gradient values ​​of 0, 10, 20, 50, 80, 100, 150, 200, 300, 500 and 800s respectively / mm 2 . In this embodiment, the iterative registration operation in step 2 is repeated 10 times.

[0074] At the same time, in order to compare and demonstrate the technical effects of the present invention, this implementation compares the result...

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 placenta voxel incoherent movement imaging acceleration method and device based on deep learning. The method comprises the following steps: firstly, carrying out rigid body registration and affine transformation registration on the placenta data by utilizing an iterative multi-registration mode to obtain registered placenta data information; secondly, using the registeredplacenta data to employ experts to outline regions of interest in the placenta data to establish a voxel database in the placenta; and finally, training by utilizing the obtained voxel data to obtaincorresponding feature information. Therefore, the acceleration of the incoherent movement imaging in the voxel in the placenta is realized. According to the invention, an acceleration scheme based ondeep learning is provided for an existing intraplacental voxel incoherent movement imaging method; according to the method, image information similar to the same quality can be obtained under the condition that the collection time is shorter, the accuracy and precision are high, and the effect is superior to that of other intraplacental voxel incoherent movement imaging methods at present.

Description

technical field [0001] The present application relates to the field of magnetic resonance image processing and the field of artificial intelligence, in particular to a method and device for incoherent motion imaging within a voxel based on deep learning. Background technique [0002] Diffusion imaging is a non-destructive magnetic resonance imaging method for measuring the movement of water molecules in living tissues. Its image contrast is mainly related to the speed and direction of water molecule movement, rather than the weight of T1, T2 and proton density formed by conventional MRI methods. Therefore, diffusion imaging can provide microstructure information that cannot be obtained by conventional MRI methods, and plays an important role in the detection of central nervous system diseases, such as the identification of benign and malignant tumors, and the evaluation and prediction of curative effect. [0003] Conventional diffusion imaging usually uses a single excitatio...

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): G06T11/00G06T3/00G06N3/08G06N3/04A61B5/00A61B5/055
CPCG06T11/005G06T11/008G06N3/08A61B5/4343A61B5/055A61B5/004G06N3/045G06T3/147G06T3/14
Inventor 吴丹黄凡颜国辉邹煜郑天舒张祎
Owner 浙江拉莫医学影像科技有限公司
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