# Zero-shot Dynamic MRI Reconstruction with Global-to-local Diffusion Model

arXiv: https://arxiv.org/abs/2411.03723 · HTML: https://mlsanity.com/paper/2411.03723/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 24 of its 53 references that are in the map.
- First posted on arXiv 6 Nov 2024.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 24 of 24)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Maximum Likelihood Training of Score-Based Diffusion Models](https://mlsanity.com/paper/2101.09258/) (2021)
- [Learning a Variational Network for Reconstruction of Accelerated MRI Data](https://mlsanity.com/paper/1704.00447/) (2017)
- [Score-based diffusion models for accelerated MRI](https://mlsanity.com/paper/2110.05243/) (2021)
- [Robust Compressed Sensing MRI with Deep Generative Priors](https://mlsanity.com/paper/2108.01368/) (2021)
- [Score-Based Generative Modeling with Critically-Damped Langevin Diffusion](https://mlsanity.com/paper/2112.07068/) (2021)
- [A Deep Cascade of Convolutional Neural Networks for Dynamic MR Image Reconstruction](https://mlsanity.com/paper/1704.02422/) (2017)
- [Accelerating Diffusion Models via Early Stop of the Diffusion Process](https://mlsanity.com/paper/2205.12524/) (2022)
- [CNN-Based Projected Gradient Descent for Consistent Image Reconstruction](https://mlsanity.com/paper/1709.01809/) (2017)
- [Score-based Generative Modeling Secretly Minimizes the Wasserstein Distance](https://mlsanity.com/paper/2212.06359/) (2022)
- [MR image reconstruction using deep density priors](https://mlsanity.com/paper/1711.11386/) (2017)
- [OCMR (v1.0)--Open-Access Multi-Coil k-Space Dataset for Cardiovascular Magnetic Resonance Imaging](https://mlsanity.com/paper/2008.03410/) (2020)
- [Deep Learning with Domain Adaptation for Accelerated Projection-Reconstruction MR](https://mlsanity.com/paper/1703.01135/) (2017)
- [DSFormer: A Dual-domain Self-supervised Transformer for Accelerated Multi-contrast MRI Reconstruction](https://mlsanity.com/paper/2201.10776/) (2022)
- [Model Learning: Primal Dual Networks for Fast MR imaging](https://mlsanity.com/paper/1908.02426/) (2019)
- [Real-time Cardiovascular MR with Spatio-temporal Artifact Suppression using Deep Learning - Proof of Concept in Congenital Heart Disease](https://mlsanity.com/paper/1803.05192/) (2018)
- [A Two-Stage Cascade Model with Variational Autoencoders and Attention Gates for MRI Brain Tumor Segmentation](https://mlsanity.com/paper/2011.02881/) (2020)
- [Global k-Space Interpolation for Dynamic MRI Reconstruction using Masked Image Modeling](https://mlsanity.com/paper/2307.12672/) (2023)
- [Off-the-Grid Recovery of Piecewise Constant Images from Few Fourier Samples](https://mlsanity.com/paper/1510.00384/) (2015)
- [Deep artifact learning for compressed sensing and parallel MRI](https://mlsanity.com/paper/1703.01120/) (2017)
- [K-space and Image Domain Collaborative Energy based Model for Parallel MRI Reconstruction](https://mlsanity.com/paper/2203.10776/) (2022)
- [Deep Learning Diffuse Optical Tomography](https://mlsanity.com/paper/1712.00912/) (2017)

## Abstract (arXiv)

Diffusion models have recently demonstrated considerable advancement in the generation and reconstruction of magnetic resonance imaging (MRI) data. These models exhibit great potential in handling unsampled data and reducing noise, highlighting their promise as generative models. However, their application in dynamic MRI remains relatively underexplored. This is primarily due to the substantial amount of fully-sampled data typically required for training, which is difficult to obtain in dynamic MRI due to its spatio-temporal complexity and high acquisition costs. To address this challenge, we propose a dynamic MRI reconstruction method based on a time-interleaved acquisition scheme, termed the Glob-al-to-local Diffusion Model. Specifically, fully encoded full-resolution reference data are constructed by merging under-sampled k-space data from adjacent time frames, generating two distinct bulk training datasets for global and local models. The global-to-local diffusion framework alternately optimizes global information and local image details, enabling zero-shot reconstruction. Extensive experiments demonstrate that the proposed method performs well in terms of noise reduction and detail preservation, achieving reconstruction quality comparable to that of supervised approaches.