Unlock instant, AI-driven research and patent intelligence for your innovation.

SFT-based transform multi-modal fusion rapid MRI reconstruction method and device

A multi-modal and fast technology, applied in the field of image processing, can solve the problems of image edge blur and signal-to-noise ratio reduction, and achieve the effect of avoiding variation, avoiding accuracy, and improving reconstruction effect.

Pending Publication Date: 2021-07-09
ZHEJIANG UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The purpose of this application is to provide a fast MRI reconstruction method and device based on SFT transform multimodal fusion, which solves the problems of reduced signal-to-noise ratio and blurred image edges after traditional brain MRI image 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
  • SFT-based transform multi-modal fusion rapid MRI reconstruction method and device
  • SFT-based transform multi-modal fusion rapid MRI reconstruction method and device
  • SFT-based transform multi-modal fusion rapid MRI reconstruction method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0045] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, not to limit the present application.

[0046] When using the traditional network to reconstruct MRI, the traditional neural network learns too much redundant information, and learning this redundant information may have a negative impact on the reconstruction ability of the network. At the same time, the traditional method lacks the utilization of other modality information, which will discard the richer detail information that other modality images can provide. In the convolutional neural network, only the pixel space is super-resolved, and the super-resolved image will be too smooth. Therefore, it is necessary to find a suita...

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 SFT-based transform multi-modal fusion fast MRI reconstruction method and device. After an MRI image is denoised, undersampling is carried out on a T2 image, Fourier operation is carried out on a T1 image and the undersampled T2 image once to transform the T1 image and the undersampled T2 image into K space data, Mask mask sampling is carried out on the K space data, and then multi-modal fusion and SFT supervised fusion are carried out. The T1 and the undersampled T2 are subjected to multi-modal fusion, the enhancement effect of the T2 image on a reconstruction result is exerted, the defect that the picture is over-smooth after super-division in a traditional method is effectively improved, the texture details of the image are greatly enhanced by applying an SFT supervision mechanism, and the problem that low-frequency information of a source image varies along with reconstruction can also be avoided by a data consistency layer.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a fast MRI reconstruction method and device based on SFT transform multimodal fusion, which are used for accelerated and high-precision reconstruction of brain MRI images. Background technique [0002] At present, medical imaging has become an important clinical medical tool and diagnostic basis in the process of diagnosis and treatment of diseases. With the continuous development of modern medical imaging technology, the importance of medical imaging as a diagnostic basis and tool continues to increase. [0003] In the acquisition of magnetic resonance imaging MRI, there are problems such as long acquisition time, high cost, and difficult acquisition process. In addition, problems such as motion artifacts also plague the development of MRI imaging in the medical field. [0004] Since the neural network was applied to the field of MRI reconstruction, it has demonstrate...

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): G06K9/62G06K9/46G06T5/00G06N3/04G06N3/08
CPCG06N3/08G06T2207/10088G06V10/462G06N3/045G06F18/253G06T5/70
Inventor 李伟吉涛楼鑫杰曹迪
Owner ZHEJIANG UNIV OF TECH