Edge, Structure and Texture Refinement for Retrospective High Quality MRI Restoration using Deep Learning

TL;DR

This paper proposes a deep learning approach using edge and structure-focused loss functions to improve high-quality MRI restoration, effectively enhancing resolution and reducing motion artifacts in clinical settings.

Contribution

It introduces a novel loss function combining SSIM and gradient map edge quality loss to better restore edges and structures in MRI images, trained on realistic low-resolution and artifact-affected data.

Findings

Enhanced MRI image quality with sharper edges and structures

Reduced motion artifacts in reconstructed images

Model trained on realistic data performs well in clinical scenarios

Abstract

22. Shortening acquisition time and reducing the motion-artifact are two of the most critical issues in MRI. As a promising solution, high-quality MRI image restoration provides a new approach to achieve higher resolution without costing additional acquisition time or modification on the pulse sequences. Recently, as to the rise of deep learning, convolutional neural networks have been proposed for super-resolution (SR) image generation and motion-artifact reduction (MAR) for MRI. Recent studies suggest that using perceptual feature space loss and k space loss to capture the perceptual information and high-frequency information of images, respectively. However, the quality of reconstructed SR and MAR MR images is limited because the most important details of the informative area in the MR image, the edges and the structure, cannot be very well restored. Besides, lots of the SR approaches are trained by using low-resolution images generated by applying bicubic or blur-downscale degradation, which cannot represent the real process of MRI measurement. Such inconsistencies lead to performance degradation in the reconstruction of SR images as well. This study reveals that using the L1 loss of SSIM and gradient map edge quality loss could force the deep learning model to focus on studying the features of edges and structure details of MR images, thus generating SR images with more accurate, fruitful information and reduced motion-artifact. We employed a state-of-the-art model, RCAN, as the network framework in both SR and MAR tasks, trained the model by using low-resolution images and motion-artifact affected images which were generated by emulating how they are measured in the real MRI measurement to ensure the model can be easily applied in the practical clinic environment, and verified the trained model could work fairly well.