Towards performant and reliable undersampled MR reconstruction via diffusion model sampling

TL;DR

DiffuseRecon introduces a diffusion model-based approach for MR image reconstruction that is robust, stochastic, and does not require retraining for different acceleration factors, achieving state-of-the-art results.

Contribution

The paper presents DiffuseRecon, a novel diffusion model-based MR reconstruction method that offers robustness, stochasticity, and no need for retraining on specific acceleration factors.

Findings

Achieves state-of-the-art performance on fastMRI and SKM-TEA datasets.

Provides multiple potential reconstructions for better reliability.

Does not require additional training for different acceleration factors.

Abstract

Magnetic Resonance (MR) image reconstruction from under-sampled acquisition promises faster scanning time. To this end, current State-of-The-Art (SoTA) approaches leverage deep neural networks and supervised training to learn a recovery model. While these approaches achieve impressive performances, the learned model can be fragile on unseen degradation, e.g. when given a different acceleration factor. These methods are also generally deterministic and provide a single solution to an ill-posed problem; as such, it can be difficult for practitioners to understand the reliability of the reconstruction. We introduce DiffuseRecon, a novel diffusion model-based MR reconstruction method. DiffuseRecon guides the generation process based on the observed signals and a pre-trained diffusion model, and does not require additional training on specific acceleration factors. DiffuseRecon is stochastic in nature and generates results from a distribution of fully-sampled MR images; as such, it allows us to explicitly visualize different potential reconstruction solutions. Lastly, DiffuseRecon proposes an accelerated, coarse-to-fine Monte-Carlo sampling scheme to approximate the most likely reconstruction candidate. The proposed DiffuseRecon achieves SoTA performances reconstructing from raw acquisition signals in fastMRI and SKM-TEA. Code will be open-sourced at www.github.com/cpeng93/DiffuseRecon.