Enhancing Ultra-low-field MRI with Segmentation-guided Adversarial Learning
For researchers and clinicians needing portable, low-cost MRI with improved image quality, this method offers a practical enhancement pipeline.
The paper addresses poor image quality in ultra-low-field MRI by using segmentation-guided adversarial learning and model ensembling to synthesize high-field-like MRIs from 64 mT scans, achieving results comparable to 3 T scans.
Ultra-low-field (ULF) MRI offers portable and low-cost imaging but suffers from poor image quality. To address this, we present our submission to the 2025 ULF Enhancement Challenge (ULF-EnC), where the goal is to synthesise high-field-like MRIs from 64 mT scans. Our pipeline enhances ULF MRI through a combination of anatomical conditioning and model ensembling. We first generate tissue segmentation priors using a Swin UNETR trained solely on challenge-provided data. These priors condition two independent enhancement networks - a CycleGAN and a transformer-based residual enhancement model (T-REX) - each trained to synthesise 3 T-like MRIs. Outputs from both models are combined using a weighted average. Our approach produces enhanced MRIs that were comparable to high-field scans both quantitatively and qualitatively.