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

A magnetic resonance diffusion weighted imaging method and device

A technology of diffusion weighted imaging and magnetic resonance, applied in the field of medical imaging, can solve problems affecting the accuracy of medical image analysis, deformation, unfavorable application, etc.

Active Publication Date: 2021-09-14
SHANGHAI NEUSOFT MEDICAL TECH LTD +1
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Because DWI is very sensitive to phase changes caused by motion, normal physiological motion in the measured tissue may also produce motion artifacts in DWI images, which are difficult to effectively improve through calibration. At the same time, because of the inherent problems of single-shot EPI sequences, For example, the shortcomings of low imaging resolution and severe deformation lead to poor DWI image quality and affect the accuracy of medical image analysis
To solve these problems, there is currently a multi-shot (Multi-shot) method, which can improve the quality of DWI images by doing Multi-shot in the direction of readout encoding or in the direction of phase encoding, but it takes a long time, and image reconstruction usually requires More than 30 seconds, not conducive to clinical application

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 magnetic resonance diffusion weighted imaging method and device
  • A magnetic resonance diffusion weighted imaging method and device
  • A magnetic resonance diffusion weighted imaging method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0067] see image 3 , which is a flow chart of a magnetic resonance diffusion weighted imaging method provided in an embodiment of the present application.

[0068] Such as image 3 As shown, the magnetic resonance diffusion weighted imaging method provided in the embodiment of the present application includes:

[0069] Step 301: Obtain the DWI data of the clinically measured tissue collected after m excitations, where m is a positive integer.

[0070] In this embodiment, an EPI sequence, such as a DWI sequence or a DTI sequence, etc. is used to obtain the diffusion weighted imaging DWI data of the clinically measured tissue after m excitations. The specific type of the EPI sequence used in this embodiment is not limited.

[0071] The clinically measured tissue specifically refers to the tissue that actually needs to be imaged quickly and with high quality using the method. As an example, the clinically measured tissue may be brain tissue of a patient.

[0072] In this st...

Embodiment 2

[0086] see Figure 4 , which is a flow chart of another magnetic resonance diffusion weighted imaging method provided in an embodiment of the present application.

[0087] Such as Figure 4 As shown, the magnetic resonance diffusion weighted imaging method provided in this embodiment includes:

[0088] Step 401: Using the input set and the label set to train the neural network model, and obtain the parameters of the neural network model.

[0089] In this embodiment, the input set includes: the image reconstructed from the DWI data collected by the historical tissue under test after m times of excitation, and the label set includes: the image reconstructed from the DWI data collected by the historical tissue under test after n times of excitation image; said n is a positive integer greater than said m. As an example, m=2, n=4.

[0090] For ease of understanding, exemplary implementations of obtaining an input set image and an annotated set image are respectively provided be...

Embodiment 3

[0110] see Figure 8 , which is a flow chart of another MRI diffusion-weighted imaging method provided in this embodiment.

[0111] Such as Figure 8 As shown, the method includes:

[0112] Step 801: Obtain the DWI data of the clinically measured tissue collected on average by m times of excitation and q times.

[0113] Averaging refers to repeated acquisitions of data from the same tissue location. The scan time is related to the number of averages, the more averages, the longer the scan time. m≥1, q≥1, and both m and q are positive integers.

[0114] Step 802: Obtain an image to be processed by reconstructing the DWI data collected on average by m times of excitation and q times of the clinically measured tissue.

[0115] Through reconstruction, m×q images are obtained.

[0116] Step 803: The image to be processed is used as an input of a neural network obtained in advance to obtain an output image of the neural network, and the output image is used as a final DWI imag...

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 present application discloses a magnetic resonance diffusion weighted imaging method and device, which reconstructs DWI data collected by m times of excitation of a clinically measured tissue into an image to be processed. Due to the pre-trained neural network, the neural network can output an output image with higher quality than the input image, so after inputting the poor-quality image to be processed into the neural network, a high-quality DWI image can be quickly obtained, that is, the output corresponding to the image to be processed image. The neural network is used to improve the quality of DWI images and shorten the reconstruction time of DWI images. The data used to reconstruct the image to be processed in this application is the DWI data collected by m times of excitation of the clinically tested tissue, and the number of excitations m is a positive integer greater than or equal to 1, which can be very small, such as 4 times, 2 times or even a single excitation , so it can also effectively shorten the scan time. Compared with the prior art, the present application improves the acquisition speed of high-quality DWI images, which is beneficial to the popularization and application of DWI technology in clinic.

Description

technical field [0001] The present application relates to the technical field of medical imaging, in particular to a magnetic resonance diffusion weighted imaging method and device. Background technique [0002] Magnetic resonance imaging (Magnetic Resonance Imaging, MRI), as a multi-parameter, multi-contrast imaging technology, is one of the main imaging methods in modern medical imaging, which can reflect various characteristics such as tissue T1, T2 and proton density. Provide information for disease detection and diagnosis. The basic working principle of magnetic resonance imaging is to use the magnetic resonance phenomenon, use radio frequency excitation to excite hydrogen protons in the human body, use gradient field to encode the position, then use the receiving coil to receive the electromagnetic signal with position information, and finally use the Fourier transform to reconstruct the image information. see figure 1 , which is a structural diagram of a magnetic r...

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 Patents(China)
IPC IPC(8): G01R33/56
CPCG01R33/5602
Inventor 宋瑞波黄峰
Owner SHANGHAI NEUSOFT MEDICAL TECH LTD