Magnetic resonance imaging method, device and system and storage medium

Abstract

An embodiment of the invention discloses a magnetic resonance imaging method, device and system and a storage medium. The magnetic resonance imaging method comprises the steps of: establishing an initial network model according to an original model of magnetic resonance imaging and an iterative algorithm used for solving the original model, wherein the iterative algorithm comprises an undeterminedsolving operator and an undetermined parameter structure relation; inputting undersampled K space data of a sample into the initial network model to obtain an output magnetic resonance image of the network model, and determining a loss function according to the output magnetic resonance image and a standard magnetic resonance image of the sample; and adjusting network parameters in the initial network model according to the loss function, and generating a network model for magnetic resonance imaging, wherein the network parameters in the initial network model are used for replacing the undetermined solving operator and the undetermined parameter structure relation in the iterative algorithm. According to the magnetic resonance imaging method, the to-be-processed undersampled K space datais acquired, and the undersampled K space data is input to the network model for magnetic resonance imaging to generate the magnetic resonance image, so that the quality of the magnetic resonance image is improved.

Description

technical field [0001] Embodiments of the present invention relate to deep learning technology, and in particular to a magnetic resonance imaging method, device, system and storage medium. Background technique [0002] Magnetic resonance uses static magnetic field and radio frequency magnetic field to image human tissue. It not only provides rich tissue contrast, but also is harmless to human body, so it has become a powerful tool for medical clinical diagnosis. However, the slow imaging speed has always been a major bottleneck restricting its rapid development. [0003] In terms of fast imaging, the commonly used technologies are parallel imaging and compressed sensing. Parallel imaging uses the correlation between multi-channel coils to accelerate acquisition, while compressed sensing uses the prior information of the sparseness of the imaged object to reduce k-space sampling points. However, limited by hardware and other conditions, the acceleration of parallel imaging ...

AI Technical Summary

Problems solved by technology

However, limited by hardware and other conditions, the acceleration of parallel imaging is limited, and with the increase of the acceleration, the image will appear noise amplification phenomenon; and compressed sensing technology uses iterative reconstruction to make the reconstruction time very long, and it is difficult to choose sparse transformation and Reconstruction parameters

Images