Ultra low-field MRI gets clearer 3D images with uncertainty estimates
Uncertainty-Aware 3D Residual Wavelet Diffusion for Ultra Low-Field MRI Super-Resolution
Computer Vision and Pattern Recognition
Summary
Low-field MRI machines produce fuzzy brain scans that miss some details. The authors developed a new computer method that creates clearer 3D images from these scans while showing how confident it is about different parts. Their approach uses wavelets and residual learning to make the process faster and fit whole brains in memory. It works well on healthy brains and keeps important disease features visible in people with cognitive problems.
What this means in practice
- •For medical imaging engineers: Improve brain MRI super-resolution workflows by generating clearer images with uncertainty maps from low-field scanners without paired high-field data.
- •For clinical mri technologists: Use enhanced ultra low-field MRI scans that preserve disease features and indicate uncertain regions to aid diagnosis in cognitive impairment cases.
Authors
Rui W. Yeow, Millie Beament, Fred Dick, Raha Razin, Martina Bocchetta, David L. Thomas, Henry F. J. Tregidgo, Daniel C. Alexander, James H. Cole
Abstract
Ultra low-field MRI expands global access to neuroimaging but produces scans with low signal-to-noise ratio, reduced contrast, and thick slices. While regression-based super-resolution can recover anatomical detail for segmentation, it returns a single deterministic estimate that gives no indication of regions where the low-field input leaves anatomy underdetermined. Generative diffusion models offer an alternative by sampling the posterior distribution of plausible high-field images, quantifying this anatomical ambiguity. However, applying them to 3D whole-brain MRI is restricted by memory bottlenecks, slow sampling, and scanner domain shifts. We propose a 3D residual wavelet diffusion model that combines three ideas to overcome these hurdles. A lossless wavelet reparameterisation shrinks the spatial grid to fit a whole brain on a single GPU, residual shifting accelerates sampling by starting from the low-field input, and domain randomisation promotes scanner generalisation without paired training data. As the high-field reference is not a voxel-aligned ground truth, we evaluate downstream volumetric agreement. On a healthy cohort (n=19) imaged at 0.064T and 3T, our method matches a leading general-purpose regression approach in volumetric accuracy while additionally generating per-voxel uncertainty maps highlighting underdetermined regions. Furthermore, on a pilot dataset (n=11) of participants with cognitive impairment, disease-relevant atrophy is preserved rather than normalised towards a healthy prior. Our framework brings whole-brain posterior sampling to low-field super-resolution without sacrificing volumetric accuracy.