Skip to content
Open access

Memory-efficient image reconstruction using diffusion models for accelerated 3D non-Cartesian UTE imaging.

Aug 2026 · MAGMA · 0 citations · 15 references
Medicine

TL;DR

A novel, memory-efficient image reconstruction framework using score-based diffusion models tailored for highly undersampled 3D radial UTE acquisitions is proposed that enables robust and high-fidelity reconstructions from as few as 4000 spokes-representing up to 50 × undersampling relative to Nyquist.

Abstract

Purpose

Accelerated 3D non-Cartesian MRI presents unique challenges in balancing high-resolution reconstruction with computational and memory constraints. In this work, a novel, memory-efficient image reconstruction framework using score-based diffusion models tailored for highly undersampled 3D radial UTE acquisitions is proposed.

Methods

The method leverages a volumetric extension of the NCSN++ architecture with efficient NUFFT operations and integrates a conjugate gradient-based data consistency mechanism within a predictor-corrector sampling scheme.

Results

This approach enables robust and high-fidelity reconstructions from as few as 4000 spokes-representing up to 50 × undersampling relative to Nyquist. Generalizable performance across knee, ankle, and out-of-distribution shoulder datasets is demonstrated and superior image quality compared to compressed sensing and conventional iterative methods, especially at high acceleration factors is shown.

Conclusion

The proposed framework marks a significant step toward practical deployment of diffusion models in non-Cartesian MRI reconstruction.

Read PDF

Similar papers

Sep 2026

SGAM: Shared Gaussian Geometry with Implicit Amplitude Modeling for Scan-Specific 3D Multi-Contrast MRI Reconstruction

Three-dimensional (3D) multi-contrast magnetic resonance imaging (MCMRI) provides rich anatomical and quantitative information but requires long acquisition times, motivating k-space undersampling. However, reconstruction of large volumetric datasets imposes substantial computational and memory demands. To address this...

Jing-Ran Xu, Dong Liang, Hai-Rong Zheng et al. · 0 citations
Sep 2026

Efficient 3D Medical Reconstruction From Sparse Views via 2D Diffusion Models With Curvature Priors

Reconstructing medical images from partial measurements is a critical inverse problem in computed tomography (CT) and magnetic resonance imaging (MRI). While diffusion models excel in 2D medical imaging, their extension to 3D reconstruction remains challenging due to high computational costs. In this work, we achieve e...

Qing Zhou, Ming Li, Xiang-Yu Xu et al. · 0 citations
Preprint Sep 2026

Highly accelerated 3D Cartesian MPnRAGE with implicit neural representation reconstruction

MPnRAGE enables multiple inversion contrast images in a single scan, allowing quantitative T1 mapping, tissue nulled contrasts, and standard MPRAGE synthesis. However, current 3D scan times remain clinically impractical, motivating accelerated 3D MPnRAGE. This work provides a highly accelerated Cartesian 3D MPnRAGE seq...

Natascha Niessen, A. Solana, Carolin M. Pirkl et al. · 0 citations
Sep 2026

Highly Accelerating Joint Intracranial and Carotid Vessel Wall Imaging Using ESPIRiT‐Driven Diffusion Model Reconstruction

To propose ESPIRiT‐Diffusion, a physics‐guided score‐based diffusion reconstruction framework incorporating multi‐set ESPIRiT map‐based data‐consistency constraints for 8.8‐ and 10.7‐fold accelerated joint intracranial and carotid vessel wall imaging (VWI) with an isotropic resolution of 0.6 mm3.

Tian Zhou, Yu-Long Qi, Seng Jia et al. · 0 citations
#diffusion models Preprint Aug 2026

Patch-Based Diffusion Reconstruction for Accelerated Cardiac Cine

CineDiff enabled high-quality reconstruction of highly accelerated 2D RT cine CMR and reduced block-like artifacts and preserved finer anatomical detail compared with traditional compressed sensing and a variational network method, termed CineVN.

Xuan Lei, Philip Schniter, Juliet Varghese et al. · 0 citations
Preprint Aug 2026

Consistency Models for Fast MRI Reconstruction Using Regularization by Denoising

The proposed CM-RED method consistently outperforms existing DM- and CM-based approaches in both quantitative metrics and visual fidelity, and exhibits strong robustness to hyperparameter variations, highlighting CM-RED as an efficient and effective generative framework for accelerated MRI reconstruction.

Merve Gülle, Junno Yun, Y. Alçalar 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.