Magnetic resonance imaging method and device

Abstract

The invention discloses a magnetic resonance imaging method and device. The method combines a deep network model with a conventional acceleration reconstruction method in sequence. Firstly, the deep network model is used for recovering first imaging information with a high downsampling multiple to second imaging information with a low downsampling multiple, then, the conventional acceleration reconstruction method is used for completely reconstructing the second imaging information with the low downsampling multiple, and therefore, a final magnetic resonance image is obtained. Therefore, in the magnetic resonance imaging method provided by the invention, the output training sample of the deep neural network used for magnetic resonance quick imaging is not full sampling or super-full sampling data but is downsampling data, so that the output training sample of the training deep neural network can be obtained through a conventional downsampling method, the output training sample can be obtained through short collection time, and therefore, the deep neural network can be applied to a magnetic resonance imaging application scene with limited collection time, such as abdomen scanning.

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 tissue T1, T2 and proton density and other characteristics. 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 because of i...

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

Images