Score-based diffusion models for accelerated MRI

  title={Score-based diffusion models for accelerated MRI},
  author={Hyungjin Chung and Jong-Chul Ye},
MR Image Denoising and Super-Resolution Using Regularized Reverse Diffusion
This work proposes a new denoising method based on score-based reverse diffusion sampling, which overcomes all the aforementioned drawbacks and establishes state-of-the-art performance, while having desirable properties which prior MMSE denoisers did not have.
Measurement-conditioned Denoising Diffusion Probabilistic Model for Under-sampled Medical Image Reconstruction
This work proposes a novel and unified method, measurement-conditioned denoising diffusion probabilistic model (MC-DDPM), for under-sampled medical image reconstruction based on DDPM, and applies this method to accelerate MRI reconstruction.
Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contraction
This work shows that starting from Gaussian noise is unnecessary, and suggests a new sampling strategy, dubbed Come-Closer-Diffuse-Faster (CCDF), which can achieve state-ofthe-art reconstruction performance at significantly reduced sampling steps.
Towards performant and reliable undersampled MR reconstruction via diffusion model sampling
The proposed DiffuseRecon achieves SoTA performances reconstructing from raw acquisition signals in fastMRI and SKM-TEA, and proposes an accelerated, coarse-to-fine Monte-Carlo sampling scheme to approximate the most likely reconstruction candidate.
WKGM: Weight-K-space Generative Model for Parallel Imaging Reconstruction
Experimental results demonstrate that WKGM can attain state-of-the-art reconstruction results under the well-learned k-space generative prior, and is flexible and thus can synergistically combine various traditional k- space PI models, generating learning-based priors to produce high-fidelity reconstructions.


Solving Inverse Problems in Medical Imaging with Score-Based Generative Models
This work proposes a fully unsupervised technique for inverse problem solving, leveraging the recently introduced score-based generative models, and introduces a sampling method to reconstruct an image consistent with both the prior and the observed measurements.
DuDoRNet: Learning a Dual-Domain Recurrent Network for Fast MRI Reconstruction With Deep T1 Prior
  • Bo Zhou, S. K. Zhou
  • Computer Science
    2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2020
A Dual Domain Recurrent Network (DuDoRNet) with deep T1 prior embedded to simultaneously recover k-space and images for accelerating the acquisition of MRI with a long imaging protocol and is customized for dual domain restorations from undersampled MRI data.
Variational Diffusion Models
A family of diffusion-based generative models that obtain state-of-the-art likelihoods on standard image density estimation benchmarks are introduced, and it is shown how to use the model as part of a bits-back compression scheme, and demonstrate lossless compression rates close to the theoretical optimum.
Score Matching Model for Unbounded Data Score
This paper introduces Unbounded Diffusion Model (UDM) that resolves the score diverging problem with an easily applicable modification to any diffusion models, and introduces a new SDE that overcomes the theoretic and practical limitations of Variance Exploding SDE.
MRI Reconstruction Using Deep Energy-Based Model
A novel regularization strategy is introduced in this article which takes advantage of self-adversarial cogitation of the deep energy-based model to boost the performance of Magnetic Resonance Imaging (MRI) reconstruction.
Sliced Score Matching: A Scalable Approach to Density and Score Estimation
It is demonstrated that sliced score matching can learn deep energy-based models effectively, and can produce accurate score estimates for applications such as variational inference with implicit distributions and training Wasserstein Auto-Encoders.
Generative Modeling by Estimating Gradients of the Data Distribution
A new generative model where samples are produced via Langevin dynamics using gradients of the data distribution estimated with score matching, which allows flexible model architectures, requires no sampling during training or the use of adversarial methods, and provides a learning objective that can be used for principled model comparisons.
Robust Compressed Sensing MRI with Deep Generative Priors
This paper trains a generative prior on brain scans from the fastMRI dataset, and shows that posterior sampling via Langevin dynamics achieves high quality reconstructions and is robust to changes in the ground-truth distribution and measurement process.
Undersampled radial MRI with multiple coils. Iterative image reconstruction using a total variation constraint
An iterative reconstruction method for undersampled radial MRI which is based on a nonlinear optimization, allows for the incorporation of prior knowledge with use of penalty functions, and deals with data from multiple coils is developed.
fastMRI: An Open Dataset and Benchmarks for Accelerated MRI
The fastMRI dataset is introduced, a large-scale collection of both raw MR measurements and clinical MR images that can be used for training and evaluation of machine-learning approaches to MR image reconstruction.