Deformation-free single-excitation plane echo imaging method and device based on deep learning

Abstract

The invention discloses a high-resolution high-signal-to-noise-ratio deformation-free single excitation plane echo imaging method and device based on deep learning, and the method comprises the steps:obtaining a first image and a related auxiliary image of a single excitation plane echo, and obtaining a second image which is collected in a mode of multiple excitation and meets a preset condition;performing deep neural network training according to the first image, the related auxiliary image and the second image to obtain a network weight parameter so as to generate a deep neural network; and receiving a third image and a related auxiliary image of the single excitation plane echo, and inputting the third image and the related auxiliary image into the deep neural network to generate an imaging result. According to the method, the high-resolution and high-signal-to-noise-ratio non-deformation magnetic resonance image can be obtained under rapid scanning of single excitation, and the problems that in an existing single excitation EPI technology, the signal-to-noise ratio and deformation artifacts are serious, and the resolution ratio is low are effectively solved, and the problem that the collection time is too long when a multi-excitation technology is used is effectively solved.

Description

technical field [0001] The present invention relates to the technical field of echo-planar imaging, in particular to a single-shot echo-planar imaging method and device based on deep learning with high resolution and high signal-to-noise ratio without deformation. Background technique [0002] EPI (Echo Planar Imaging, echo planar acquisition technology) has the advantages of fast imaging speed and insensitivity to motion due to its fast acquisition characteristics, and has been widely used in clinical practice, especially single-shot EPI. Acquisition of the entire k-space is of great value in applications that require high imaging speed, such as diffusion imaging, functional imaging, perfusion imaging, cardiac imaging, and real-time imaging. However, EPI acquisition also has its own disadvantages, the longer readout time will introduce The blurring effect caused by attenuation and the lower bandwidth in the phase encoding direction will lead to serious image distortion at...

AI Technical Summary

Problems solved by technology

However, the non-deformable imaging techniques mentioned above are all based on multiple excitation methods, which greatly prolong the acquisition time, and are often difficult to apply in clinical acquisitions that require high time efficiency, such as diffusion magnetic resonance imaging, functional magnetic resonance imaging, etc.

Images