This framework brings whole-brain posterior sampling to low-field super-resolution without sacrificing volumetric accuracy and matches a leading general-purpose regression approach in volumetric accuracy.
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.
The proposed modular unrolled end-to-end deep learning method and its underlying method offer an efficient and flexible solution to denoise low-field MR data and make quantitative low-field MRI a feasible diagnostic tool for clinical applications.
Catarina Redshaw Kranich, C. Prieto, Christoph Kolbitsch et al.· 0 citations
A novel transfer-learning framework is proposed that pre-trains an INR on a high-resolution template and then adapts it to subject-specific scans via registration and fine-tuning, outperforming competing INR-based methods across both image quality and domain-specific metrics.
Abdulkader Ghandoura, Marsil Zakour, William Consagra et al.· 1 citation
LUCID (Laminography with Unified Consistent Diffusion), a framework that combines multi-view diffusion priors with projection-domain data consistency, is introduced, which substantially improves spatial fidelity and restores missing Fourier components, outperforming baseline methods.
Wen-Xuan Fang, Abraham L. Levitan, Ana Diaz et al.· 0 citations
VIPP-SR (View-Independent Patched Projection Super-Resolution), a cross-contrast guided super-resolution framework that restores the inter-plane resolution of an existing anisotropic T2w volume without an isotropic ground-truth T2w, is proposed.
M. Shen, Haicheng Wang, Meghna Trivedi et al.· 0 citations
Super-resolution diffusion bridge model (SR-DBM), a super-resolution diffusion bridge model that casts SR as a stochastic transport between the LR and HR image distributions, is proposed, which developed an efficient diffusion framework that reconstructs HR MRI directly from LR data.
M. Safari, Han Yu, Zach Eidex et al.· arXiv.org· 0 citations
AGW-PBR improves brain MRI SR while preserving tissue-transition information relevant to downstream analysis and support tissue-mixture entropy as an effective supervision signal for partial-volume-aware MRI reconstruction.
Xiaoli Tong, Wen-Yun Yang, Zi-Heng Zhang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.