Augment to Augment: Diverse Augmentations Enable Competitive Ultra-Low-Field MRI Enhancement

TL;DR

This paper demonstrates that diverse, task-adapted data augmentations significantly improve ultra-low-field MRI image enhancement within strict data constraints, achieving competitive results in the ULF-EnC challenge.

Contribution

It introduces the use of strong, diverse augmentations, including auxiliary tasks, to enhance deep learning models for ULF MRI without external data.

Findings

Augmentations improve image fidelity substantially.

Auxiliary tasks on high-field data boost performance.

Achieved third and fourth place in challenge rankings.

Abstract

Ultra-low-field (ULF) MRI promises broader accessibility but suffers from low signal-to-noise ratio (SNR), reduced spatial resolution, and contrasts that deviate from high-field standards. Image-to-image translation can map ULF images to a high-field appearance, yet efficacy is limited by scarce paired training data. Working within the ULF-EnC challenge constraints (50 paired 3D volumes; no external data), we study how task-adapted data augmentations impact a standard deep model for ULF image enhancement. We show that strong, diverse augmentations, including auxiliary tasks on high-field data, substantially improve fidelity. Our submission ranked third by brain-masked SSIM on the public validation leaderboard and fourth by the official score on the final test leaderboard. Code is available at https://github.com/fzimmermann89/low-field-enhancement.