Magnitude-image based data-consistent deep learning method for MRI super resolution

TL;DR

This paper introduces a magnitude-image based data consistency deep learning approach for MRI super resolution that enhances image quality without requiring raw k-space data, reducing artifacts and improving metrics.

Contribution

It proposes a novel data consistency method using magnitude images, enabling high-quality MRI super resolution without raw k-space data, unlike previous methods.

Findings

Improved NRMSE and SSIM metrics over baseline CNN models

Effective artifact reduction in super resolution images

No need for raw k-space data in the proposed method

Abstract

Magnetic Resonance Imaging (MRI) is important in clinic to produce high resolution images for diagnosis, but its acquisition time is long for high resolution images. Deep learning based MRI super resolution methods can reduce scan time without complicated sequence programming, but may create additional artifacts due to the discrepancy between training data and testing data. Data consistency layer can improve the deep learning results but needs raw k-space data. In this work, we propose a magnitude-image based data consistency deep learning MRI super resolution method to improve super resolution images' quality without raw k-space data. Our experiments show that the proposed method can improve NRMSE and SSIM of super resolution images compared to the same Convolutional Neural Network (CNN) block without data consistency module.