A magnetic resonance imaging method and device
A technology of magnetic resonance imaging and imaging methods, applied in the field of medical imaging, can solve problems such as long acquisition time of k-space data, inability to apply DNN, limited data acquisition time, etc.
Active Publication Date: 2021-06-18
SHANGHAI NEUSOFT MEDICAL TECH LTD
View PDF5 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Acquisition of the full-sampled or super-sampled k-space data requires a long acquisition time
[0005] However, in some application scenarios, such as abdominal scanning, the subject needs to hold his breath during the scan, because the breath-holding time of the subject will not be too long, so the data acquisition time is limited, and it is impossible to obtain a k-space with full sampling or super full sampling data
In this way, DNN cannot be applied to these MRI application scenarios with limited acquisition time
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0049] A prerequisite for DNN to be applied to accelerate magnetic resonance scanning is the need to train DNN. The training set sample used during training includes two parts: one part is an input sample, and the other part is an output sample. The input sample can be an image with a low signal-to-noise ratio, and the input sample can be obtained from down-sampled data. The output samples are usually high-quality and low-noise images. Only by deep learning of the input samples and output samples can a deep learning network capable of removing noise be obtained.
[0050] For applications that do not have motion or do not require high time resolution, the training set required for deep learning can be obtained regardless of the acquisition time. The output training samples can be collected by full sampling or super full sampling. The output training samples can be full Sampling or super-sampling K-space data or the image corresponding to the K-space data. The input training sa...
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
Login to View More Abstract
The present application discloses a magnetic resonance imaging method and device. The method sequentially combines a deep network model with a conventional accelerated reconstruction method. First, the deep network model is used to restore the first imaging information with a higher downsampling factor to a lower downsampling factor. Then, the second imaging information with a lower downsampling factor is completely reconstructed using a conventional accelerated reconstruction method, so as to obtain the final magnetic resonance image. In this way, in the magnetic resonance imaging method provided by the present application, the output training samples of the deep neural network used for fast magnetic resonance imaging are not full sampling or super full sampling data, but downsampled data, thus, the output of training deep neural network The training samples can be obtained by conventional downsampling methods, therefore, the output training samples can be obtained through a shorter acquisition time, thus, the deep neural network can be applied to MRI application scenarios with limited acquisition time, such as abdominal scan .
Description
technical field [0001] The present application relates to the technical field of medical imaging, in particular to a magnetic resonance 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. [0003] Deep learning has been widely used in research in various fields becaus...
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
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G01R33/561A61B5/055
CPCA61B5/055G01R33/561G01R33/5608G01R33/5611G01R33/4818
Inventor 黄峰韩冬梅玲
Owner SHANGHAI NEUSOFT MEDICAL TECH LTD