High-Frequency Space Diffusion Models for Accelerated MRI

@article{Cao2022HighFrequencySD,
  title={High-Frequency Space Diffusion Models for Accelerated MRI},
  author={Chentao Cao and Zhuoxu Cui and Shaonan Liu and Dong Liang and Yanjie Zhu},
  journal={ArXiv},
  year={2022},
  volume={abs/2208.05481}
}
Denoising diffusion probabilistic models (DDPMs) have been shown to have superior performances in MRI reconstruction. From the perspective of continuous stochastic differential equations (SDEs), the reverse process of DDPM can be seen as maximizing the energy of the reconstructed MR image, leading to SDE sequence divergence. For this reason, a modified high-frequency DDPM model is proposed for MRI reconstruction. From its continuous SDE viewpoint, termed high-frequency space SDE (HFS-SDE), the… 

Figures from this paper

Diffusion Models for Medical Image Analysis: A Comprehensive Survey

provide a systematic taxonomy of diffusion models in the medical domain and propose a multi-perspective categorization based on their application, imaging modality, organ of interest, and algorithms.

Deep unfolding as iterative regularization for imaging inverse problems

This work modified the training procedure and proved that the unfolding method is an iterative regularization method and demonstrates with an example of MRI reconstruction that the proposed method outperforms conventional unfolding methods and traditional regularization methods in terms of reconstruction quality, stability and convergence speed.

Diffusion Models: A Comprehensive Survey of Methods and Applications

A comprehensive review of existing variants of the diffusion models and a thorough investigation into the applications of diffusion models, including computer vision, natural language processing, waveform signal processing, multi-modal modeling, molecular graph generation, time series modeling, and adversarial purification.

References

SHOWING 1-10 OF 26 REFERENCES

Accelerated Dynamic MRI Exploiting Sparsity and Low-Rank Structure: k-t SLR

A novel algorithm to reconstruct dynamic magnetic resonance imaging data from under-sampled k-t space data using the compact representation of the data in the Karhunen Louve transform (KLT) domain to exploit the correlations in the dataset.

PS-Net: Deep Partially Separable Modelling for Dynamic Magnetic Resonance Imaging

This paper unrolled the semi-quadratic splitting method (HQS) algorithm for the partially separable (PS) model to a network, in which the low-rank is adaptively characterized by a learnable null-space transform.

Deep Low-rank plus Sparse Network for Dynamic MR Imaging

Robust Compressed Sensing MRI with Deep Generative Priors

This paper presents the first successful application of the CSGM framework on clinical MRI data, and trains a generative prior on brain scans from the fastMRI dataset, and shows that posterior sampling via Langevin dynamics achieves high quality reconstructions.

Deep Low-rank Prior in Dynamic MR Imaging

Experimental results show that two novel and distinct schemes to introduce the learnable low-rank prior into deep network architectures in an unrolling manner and a plug-and-play manner can further improve the state-of-the-art CS methods, and sparsity-driven deep learning-based methods, both qualitatively and quantitatively.

Efficient Dynamic Parallel MRI Reconstruction for the Low-Rank Plus Sparse Model

This paper considers two accelerated alternatives for the L+S model, one based on the fast iterative shrinkage-thresholding algorithm (FISTA) and the other with the recent proximal optimized gradient method (POGM), and proposes an efficient variable splitting scheme in the augmented Lagrangian framework.

Equilibrated Zeroth-Order Unrolled Deep Networks for Accelerated MRI

This paper proposes to present a safeguarded methodology on network unrolling, focusing on accelerated MRI, which unroll a zeroth-order algorithm, of which the network module represents the regularizer itself, so that the network output can be still covered by the regularization model.

Denoising Diffusion Probabilistic Models

High quality image synthesis results are presented using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics, which naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding.

Solving Inverse Problems in Medical Imaging with Score-Based Generative Models

A score-based generative model on medical images to capture their prior distribution and a sampling method to reconstruct an image consistent with both the prior and the observed measurements is introduced.