Deep MR Brain Image Super-Resolution Using Spatio-Structural Priors

TL;DR

This paper introduces a novel deep learning approach for MR brain image super-resolution that incorporates image priors like low-rank structure and sharpness, leading to improved image quality and versatility.

Contribution

It proposes a new regularized network that integrates low-rank and sharpness priors analytically and through a learned architecture, addressing non-differentiability and enhancing super-resolution performance.

Findings

Significant improvements in SNR and image quality over state-of-the-art methods.

Effective incorporation of low-rank and sharpness priors into deep networks.

Versatility of the approach allows integration with various existing architectures.

Abstract

High resolution Magnetic Resonance (MR) images are desired for accurate diagnostics. In practice, image resolution is restricted by factors like hardware and processing constraints. Recently, deep learning methods have been shown to produce compelling state-of-the-art results for image enhancement/super-resolution. Paying particular attention to desired hi-resolution MR image structure, we propose a new regularized network that exploits image priors, namely a low-rank structure and a sharpness prior to enhance deep MR image super-resolution (SR). Our contributions are then incorporating these priors in an analytically tractable fashion \color{black} as well as towards a novel prior guided network architecture that accomplishes the super-resolution task. This is particularly challenging for the low rank prior since the rank is not a differentiable function of the image matrix(and hence the network parameters), an issue we address by pursuing differentiable approximations of the rank. Sharpness is emphasized by the variance of the Laplacian which we show can be implemented by a fixed feedback layer at the output of the network. As a key extension, we modify the fixed feedback (Laplacian) layer by learning a new set of training data driven filters that are optimized for enhanced sharpness. Experiments performed on publicly available MR brain image databases and comparisons against existing state-of-the-art methods show that the proposed prior guided network offers significant practical gains in terms of improved SNR/image quality measures. Because our priors are on output images, the proposed method is versatile and can be combined with a wide variety of existing network architectures to further enhance their performance.