Reference-based Texture transfer for Single Image Super-resolution of Magnetic Resonance images
This work addresses a domain-specific problem for medical imaging, particularly in spine surgery, by incrementally enhancing existing super-resolution methods.
The paper tackled the problem of insufficient MRI slice resolutions for image-guided spinal procedures by proposing a reference-based, unpaired multi-contrast texture-transfer strategy for deep learning-based MRI super-resolution, resulting in improved PSNR and SSIM for 4x super-resolution in most cases.
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.