Scale-Agnostic Super-Resolution in MRI using Feature-Based Coordinate Networks

TL;DR

This paper introduces a scale-agnostic MRI super-resolution method using coordinate networks, allowing arbitrary resolution queries, and evaluates its performance with denoising strategies and radiologist feedback.

Contribution

It presents a novel coordinate network-based super-resolution approach for MRI that is scale-agnostic and compares it with traditional methods through comprehensive evaluations.

Findings

Coordinate networks enable arbitrary resolution super-resolution in MRI.

Denoising strategies improve super-resolution quality.

Method outperforms standard convolutional decoders in evaluations.

Abstract

We propose using a coordinate network decoder for the task of super-resolution in MRI. The continuous signal representation of coordinate networks enables this approach to be scale-agnostic, i.e. one can train over a continuous range of scales and subsequently query at arbitrary resolutions. Due to the difficulty of performing super-resolution on inherently noisy data, we analyze network behavior under multiple denoising strategies. Lastly we compare this method to a standard convolutional decoder using both quantitative metrics and a radiologist study implemented in Voxel, our newly developed tool for web-based evaluation of medical images.