Bayesian MRI Reconstruction with Joint Uncertainty Estimation using Diffusion Models

Abstract

We introduce a framework that enables efficient sampling from learned probability distributions for MRI reconstruction. Different from conventional deep learning-based MRI reconstruction techniques, samples are drawn from the posterior distribution given the measured k-space using the Markov chain Monte Carlo (MCMC) method. In addition to the maximum a posteriori (MAP) estimate for the image, which can be obtained with conventional methods, the minimum mean square error (MMSE) estimate and uncertainty maps can also be computed. The data-driven Markov chains are constructed from the generative model learned from a given image database and are independent of the forward operator that is used to model the k-space measurement. This provides flexibility because the method can be applied to k-space acquired with different sampling schemes or receive coils using the same pre-trained models. Furthermore, we use a framework based on a reverse diffusion process to be able to utilize advanced generative models. The performance of the method is evaluated on an open dataset using 10-fold undersampling in k-space.

References in corpus (4)

• Array Programming with NumPy
• Results of the 2020 fastMRI Challenge for Machine Learning MR Image Reconstruction
• PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications
• Deep, Deep Learning with BART

Cited by in corpus (13)

• Stable Deep MRI Reconstruction using Generative Priors
• Data and Physics driven Deep Learning Models for Fast MRI Reconstruction: Fundamentals and Methodologies
• Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Data
• Scan-specific Self-supervised Bayesian Deep Non-linear Inversion for Undersampled MRI Reconstruction
• Bias-Reduced Neural Networks for Parameter Estimation in Quantitative MRI
• A Tutorial on MRI Reconstruction: From Modern Methods to Clinical Implications
• Robust multi-coil MRI reconstruction via self-supervised denoising
• Self-Supervised Adversarial Diffusion Models for Fast MRI Reconstruction
• Noise Level Adaptive Diffusion Model for Robust Reconstruction of Accelerated MRI
• Generative Priors for MRI Reconstruction Trained from Magnitude-Only Images Using Phase Augmentation
• Robust Simultaneous Multislice MRI Reconstruction Using Slice-Wise Learned Generative Diffusion Priors
• Product-of-Gaussian-Mixture Diffusion Models for Joint Nonlinear MRI Reconstruction
• Fast and Robust Diffusion Posterior Sampling for MR Image Reconstruction Using the Preconditioned Unadjusted Langevin Algorithm