Beyond Diffusion: Consistency Models for One-Step, High-Fidelity MRI Reconstruction

Mary-Brenda Akoda, Chen Qin
Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, PMLR 315:2019-2037, 2026.

Abstract

Magnetic resonance imaging (MRI) provides excellent soft-tissue contrast, but suffers from long acquisition times, limiting throughput and increasing patient discomfort. Diffusion-based generative models have recently achieved state-of-the-art reconstruction quality for accelerated MRI, but typically require hundreds to thousands of neural function evaluations (NFEs), which severely limits their practicality in time-sensitive clinical settings. We introduce C-MORE (Consistency-Model-based One-step REconstruction for MRI), to our knowledge, the first one-step consistency model framework for accelerated MRI reconstruction. C-MORE investigates an unconditional one-step prior and solves the inverse problem in one NFE by leveraging measurement-guided encoding and tunable physics-based refinement, thus eliminating multi-NFE diffusion sampling, while retaining a controllable quality-speed trade-off. On the MICCAI CMR$\times$Recon dataset spanning multiple cardiac contrasts and both single- and multi-coil acquisitions, C-MORE outperforms state-of-the-art diffusion-based samplers and strong non-diffusion unrolled methods across accelerations in just 1 NFE, while reconstructing images in $0.18-0.52$ s ($\approx$$22-193$$\times$ faster than diffusion-based methods requiring hundreds of NFEs). Remarkably, without any retraining or finetuning, C-MORE also demonstrates cross-anatomy generalisation to the unseen fastMRI knee dataset from NYU Langone Health and Facebook AI Research, again surpassing state-of-the-art methods across accelerations. These results establish C-MORE as a practical blueprint for real-time, high-fidelity MRI reconstruction across diverse contrasts, acquisition settings, anatomies, and accelerations.

Cite this Paper

BibTeX
@InProceedings{pmlr-v315-akoda26a, title = {Beyond Diffusion: Consistency Models for One-Step, High-Fidelity MRI Reconstruction}, author = {Akoda, Mary-Brenda and Qin, Chen}, booktitle = {Proceedings of The 9th International Conference on Medical Imaging with Deep Learning}, pages = {2019--2037}, year = {2026}, editor = {Huo, Yuankai and Gao, Mingchen and Kuo, Chang-Fu and Jin, Yueming and Deng, Ruining}, volume = {315}, series = {Proceedings of Machine Learning Research}, month = {08--10 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v315/main/assets/akoda26a/akoda26a.pdf}, url = {https://proceedings.mlr.press/v315/akoda26a.html}, abstract = {Magnetic resonance imaging (MRI) provides excellent soft-tissue contrast, but suffers from long acquisition times, limiting throughput and increasing patient discomfort. Diffusion-based generative models have recently achieved state-of-the-art reconstruction quality for accelerated MRI, but typically require hundreds to thousands of neural function evaluations (NFEs), which severely limits their practicality in time-sensitive clinical settings. We introduce C-MORE (Consistency-Model-based One-step REconstruction for MRI), to our knowledge, the first one-step consistency model framework for accelerated MRI reconstruction. C-MORE investigates an unconditional one-step prior and solves the inverse problem in one NFE by leveraging measurement-guided encoding and tunable physics-based refinement, thus eliminating multi-NFE diffusion sampling, while retaining a controllable quality-speed trade-off. On the MICCAI CMR$\times$Recon dataset spanning multiple cardiac contrasts and both single- and multi-coil acquisitions, C-MORE outperforms state-of-the-art diffusion-based samplers and strong non-diffusion unrolled methods across accelerations in just 1 NFE, while reconstructing images in $0.18-0.52$ s ($\approx$$22-193$$\times$ faster than diffusion-based methods requiring hundreds of NFEs). Remarkably, without any retraining or finetuning, C-MORE also demonstrates cross-anatomy generalisation to the unseen fastMRI knee dataset from NYU Langone Health and Facebook AI Research, again surpassing state-of-the-art methods across accelerations. These results establish C-MORE as a practical blueprint for real-time, high-fidelity MRI reconstruction across diverse contrasts, acquisition settings, anatomies, and accelerations.} }
Endnote
%0 Conference Paper %T Beyond Diffusion: Consistency Models for One-Step, High-Fidelity MRI Reconstruction %A Mary-Brenda Akoda %A Chen Qin %B Proceedings of The 9th International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2026 %E Yuankai Huo %E Mingchen Gao %E Chang-Fu Kuo %E Yueming Jin %E Ruining Deng %F pmlr-v315-akoda26a %I PMLR %P 2019--2037 %U https://proceedings.mlr.press/v315/akoda26a.html %V 315 %X Magnetic resonance imaging (MRI) provides excellent soft-tissue contrast, but suffers from long acquisition times, limiting throughput and increasing patient discomfort. Diffusion-based generative models have recently achieved state-of-the-art reconstruction quality for accelerated MRI, but typically require hundreds to thousands of neural function evaluations (NFEs), which severely limits their practicality in time-sensitive clinical settings. We introduce C-MORE (Consistency-Model-based One-step REconstruction for MRI), to our knowledge, the first one-step consistency model framework for accelerated MRI reconstruction. C-MORE investigates an unconditional one-step prior and solves the inverse problem in one NFE by leveraging measurement-guided encoding and tunable physics-based refinement, thus eliminating multi-NFE diffusion sampling, while retaining a controllable quality-speed trade-off. On the MICCAI CMR$\times$Recon dataset spanning multiple cardiac contrasts and both single- and multi-coil acquisitions, C-MORE outperforms state-of-the-art diffusion-based samplers and strong non-diffusion unrolled methods across accelerations in just 1 NFE, while reconstructing images in $0.18-0.52$ s ($\approx$$22-193$$\times$ faster than diffusion-based methods requiring hundreds of NFEs). Remarkably, without any retraining or finetuning, C-MORE also demonstrates cross-anatomy generalisation to the unseen fastMRI knee dataset from NYU Langone Health and Facebook AI Research, again surpassing state-of-the-art methods across accelerations. These results establish C-MORE as a practical blueprint for real-time, high-fidelity MRI reconstruction across diverse contrasts, acquisition settings, anatomies, and accelerations.
APA
Akoda, M. & Qin, C.. (2026). Beyond Diffusion: Consistency Models for One-Step, High-Fidelity MRI Reconstruction. Proceedings of The 9th International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 315:2019-2037 Available from https://proceedings.mlr.press/v315/akoda26a.html.

Related Material