Towards performant and reliable undersampled MR reconstruction via diffusion model sampling

Understand

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.