Full Description
This book constitutes the proceedings of the First ULF-EnC 2025 Challenge on Enhancing Ultra-Low-Field MRI with Paired High-Field MRI Comparisons for Brain Imaging, held in conjunction with MICCAI 2025.
The 19 papers included in this book were carefully reviewed and selected from 21 short papers submitted to the proceedings.
The challenge addressed a timely and clinically significant problem: bridging the quality gap between ultra-low-field (64 mT) and high-field (3T) brain MRI through algorithmic enhancement using paired imaging data.
Contents
Robust and Lightweight Low-to-High Field MRI Synthesis Guided by Semantic Prior.- Ultra Low-Field MRI Enhancement via Conditional Di usion Model.- Utilizing an Ensemble of 3-Dimensional U-Nets to Predict High-Field MRI T1-, T2-, and Flair-Images from Ultra-Low-Field MRI Images.- Augment to Augment: Diverse Augmentations Enable Competitive Ultra-Low-Field MRI Enhancement.- From 64mT to 3T: Multi-Sequence Low-Field MRI Enhancement via 3D U-Net.- Multi-view Fusion-guided Brownian Bridge Di usion Model for Ultra-Low-Field MRI Enhancement.- Bridged Denoising Di usion in Ultra-Low Field MRI Enhancement Challenge.- LowDM: A Di usion-Based Deep Learning Framework for Generating High-Field Quality Images from Portable Low-Field MRI.- Super-Resolution of Ultra-Low-Field MRI Using a GAN-Based Visual Transformer Network.- UltraMR-Enforce: A Uni ed Ensemble Framework for Enhancement of Ultra-Low-Field MR Image.- NAF-GAN: Anatomically Constrained GAN for Ultra-Low-Field MRI Enhancement.- Enhancing Ultra-low-field MRI with Segmentation-guided Adversarial Learning.- Ultra-Low-Field Brain MRI Enhancement using Resfusion and Residual Artifact Suppression Network.- Stable and Generalizable Acceleration of Conditional Score-SDEs for Multi-Contrast MRI Enhancement.- Ultra-Low-Field MRI Image Enhancement using Transformer Models with Latent Space Exploitation.- A 3D Vision Transformer Trained with Synthetic and Real MRI Data for Enhancing ULF-MRI.- Ultra-Low-Field Brain MRI Enhancement using a Slice-Based Vision Transformer.- Multi-input Generalised-Hilbert MAMBA for Super-resolution of Ultra-Low-Field MRI.- Enhancing Ultra-Low-Field to High-Field MRI Using Multi-cycle GAN and Flow Matching Models.
