Single-Shot Adaptation using Score-Based Models for MRI Reconstruction
Marius Arvinte1, Ajil Jalal1, Giannis Daras2, Eric Price2, Alex Dimakis1, and Jonathan I Tamir1,3,4
1Electrical and Computer Engineering, The University of Texas at Austin, Austin, TX, United States, 2Computer Science, The University of Texas at Austin, Austin, TX, United States, 3Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, Austin, TX, United States, 4Diagnostic Medicine, Dell Medical School, The University of Texas at Austin, Austin, TX, United States
This work deals with the problem of few-shot adaptation in data-driven MRI reconstruction, where models must efficiently adapt to new distributions. We introduce score-based models for MRI reconstruction and an algorithm for adjusting inference parameters (step size, noise level and stopping point), investigate the impact of these parameters on reconstruction performance, and demonstrate average gains of at least 2 dB in PSNR across a range of acceleration values, all while using a pretrained model that was trained for brain MRI and fine-tuned using only a single fully-sampled 2D knee scan from the fastMRI database.
This abstract and the presentation materials are available to members only;
a login is required.