Peer-Reviewed Publication
Magn Reson Med2026;96(5):2396-2411.November 1, 2026Journal Article
Accelerating Stroke MRI With Diffusion Probabilistic Models Through Large-Scale Pre-Training and Target-Specific Fine-Tuning.
Yamin Arefeen1,2, Sidharth Kumar1, Steven Warach3, Hamidreza Saber3,4, Jonathan Isaac Tamir1,5,6
1Chandra Family Department of Electrical and Computer Engineering, The University of Texas at Austin, Austin, Texas, USA.
2Department of Imaging Physics, MD Anderson Cancer Center, Houston, Texas, USA.
3Dell Medical School Department of Neurology, The University of Texas at Austin, Austin, Texas, USA.
4Dell Medical School Department of Neurosurgery, The University of Texas at Austin, Austin, Texas, USA.
5Dell Medical School Department of Diagnostic Medicine, The University of Texas at Austin, Austin, Texas, USA.
6Oden Institute for Computational Engineering and Sciences, The University of Texas at Austin, Austin, Texas, USA.
Abstract
PURPOSE: To develop a data-efficient strategy for accelerated MRI reconstruction with Diffusion Probabilistic Generative Models (DPMs) that enables faster scan times in clinical stroke MRI when only limited fully-sampled data are available.
METHODS: Our simple training strategy first pre-trains a DPM on a large, diverse collection of publicly available fastMRI brain data and then fine-tunes on a…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans