Learning from a Handful Volumes: MRI Resolution Enhancement with Volumetric Super-Resolution Forests

TL;DR

This paper introduces volumetric super-resolution forests (VSRF), a novel method for enhancing MRI resolution retrospectively, which is efficient, effective with limited data, and outperforms existing techniques.

Contribution

The paper presents VSRF, a new random forest-based approach tailored for 3D MRI super-resolution that works well even with minimal training data.

Findings

VSRF outperforms state-of-the-art super-resolution methods in MRI quality.

VSRF is more efficient in training and inference.

Effective with just a handful or a single volume for training.

Abstract

Magnetic resonance imaging (MRI) enables 3-D imaging of anatomical structures. However, the acquisition of MR volumes with high spatial resolution leads to long scan times. To this end, we propose volumetric super-resolution forests (VSRF) to enhance MRI resolution retrospectively. Our method learns a locally linear mapping between low-resolution and high-resolution volumetric image patches by employing random forest regression. We customize features suitable for volumetric MRI to train the random forest and propose a median tree ensemble for robust regression. VSRF outperforms state-of-the-art example-based super-resolution in term of image quality and efficiency for model training and inference in different MRI datasets. It is also superior to unsupervised methods with just a handful or even a single volume to assemble training data.