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

Felix F Zimmermann
11/12/2025
eess.IVcs.CVphysics.med-ph

Official code: fzimmermann89/low-field-enhancement (0 stars, last commit 2026-01-09).

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.

View on arXivView PDF

Code Implementations(1)

fzimmermann89/low-field-enhancementOfficial100%

ULF-EnC MICCAI 2025 Challange submission "trotteliger_otter" (4th place). https://arxiv.org/abs/2511.09366

00PythonJan 9, 20269 months ago

Similar Papers

Pretext Task Adversarial Learning for Unpaired Low-field to Ultra High-field MRI Synthesis

85% match1 repo42025

MR imaging in the low-field: Leveraging the power of machine learning

83% match2025

Cyclic Self-Supervised Diffusion for Ultra Low-field to High-field MRI Synthesis

82% match1 repo12025

Transferring Ultrahigh-Field Representations for Intensity-Guided Brain Segmentation of Low-Field Magnetic Resonance Imaging

81% match2024

Low-Resource Vision Challenges for Foundation Models

81% match1 repo82026

CutMIB: Boosting Light Field Super-Resolution via Multi-View Image Blending

80% match2026

Cite this paper

@article{zimmermann2025augment,
  title  = {Augment to Augment: Diverse Augmentations Enable Competitive Ultra-Low-Field MRI Enhancement},
  author = {Felix F Zimmermann},
  year   = {2025},
  eprint = {2511.09366},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2511.09366v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2511.09366.svg)](https://codeofpaper.com/paper/2511.09366)

Discussion