A single-scan spatio-temporal coding imaging reconstruction method based on residual network

Abstract

The invention discloses a single scan space-time coding imaging reconstruction method based on the residual network, which relates to a magnetic resonance imaging reconstruction technique based on a deep learning network. The invention provides a single scan space-time coding imaging reconstruction method based on a residual network for obtaining a two-dimensional image in a single scan and reconstructing by a deep learning method. The excitation pulse is replaced by a linear sweep pulse, which effectively resists image distortion caused by the nonuniform magnetic field and chemical shift, andat the same time obtains imaging speed, resolution and signal-to-noise ratio similar to EPI. The SPEN imaging is undersampled along the phase encoding direction. Although the space-time coding imaging signal itself can reflect the contour of the imaged object without reconstruction, the inherent resolution of the contour is typically very low. The single scan space-time coding imaging reconstruction method based on residual network utilizes deep learning to reconstruct SPEN images from low-resolution signal space, greatly improves image resolution, exhibits proton density distribution, and obtains high signal-to-noise ratio while obtaining a resolution similar to conventional deconvolution reconstruction methods.

Description

technical field [0001] The present invention relates to a magnetic resonance image reconstruction technology based on a deep learning network, in particular to a single-scan spatio-temporal encoding imaging reconstruction technology based on a residual network. Background technique [0002] Magnetic resonance imaging (MRI) is an imaging technique that non-destructively analyzes the internal tissue structure information of an object. In clinical practice, MRI plays an extremely important role in neuroimaging, cardiovascular imaging, and functional magnetic resonance imaging. Magnetic resonance imaging is to detect the generated signals by applying radio frequency pulses of a certain frequency to the protons, combined with an external three-dimensional gradient field. It usually takes several minutes or even dozens of minutes to obtain a single magnetic resonance image in a conventional multi-scanning magnetic resonance sequence, which is not suitable for the clinical applica...

AI Technical Summary

Problems solved by technology

[0003] Since the SPEN scanning method introduces a quadratic phase distribution related to the spatial position through the frequency sweep pulse, combined with the stable phase approximation theorem, the magnetic resonance image can be obtained by simple modulo acquisition, but compared with the method of EPI through Fourier transform, The spatial resolution of the modulus image drops seriously

In 2010, Ben-Eliezer et al. found that the signal sampled by the SPEN method has redundancy, that is, there is overlap in the phase stable region of each sample [3]

Although the existing methods can perform super-resolution reconstruction, the algorithm takes a long time to run and the denoising effect is not obvious

Images