Reference-based Texture transfer for Single Image Super-resolution of Magnetic Resonance images

TL;DR

This paper introduces a novel reference-based texture transfer method for single image super-resolution in MRI, improving image quality by leveraging unpaired multi-contrast references and scattering transform features.

Contribution

It proposes a new unpaired multi-contrast texture transfer strategy using scattering transform for MRI super-resolution, enhancing existing architectures.

Findings

Improved PSNR and SSIM in 4x super-resolution tasks.

Effective texture transfer across unpaired MRI contrasts.

Versatile application across different super-resolution architectures.

Abstract

Magnetic Resonance Imaging (MRI) is a valuable clinical diagnostic modality for spine pathologies with excellent characterization for infection, tumor, degenerations, fractures and herniations. However in surgery, image-guided spinal procedures continue to rely on CT and fluoroscopy, as MRI slice resolutions are typically insufficient. Building upon state-of-the-art single image super-resolution, we propose a reference-based, unpaired multi-contrast texture-transfer strategy for deep learning based in-plane and across-plane MRI super-resolution. We use the scattering transform to relate the texture features of image patches to unpaired reference image patches, and additionally a loss term for multi-contrast texture. We apply our scheme in different super-resolution architectures, observing improvement in PSNR and SSIM for 4x super-resolution in most of the cases.