Generalizable Real-time Accelerated Dynamic MRI
Silpa Babu, Wahidul Alam, Rushdi Zahid Rusho, Sajan Goud Lingala, Namrata Vaswani
Abstract
We introduce a real-time undersampled dynamic MRI algorithm, termed FewShot-AltGDmin-MRI, that is generalizable: works for many different applications and sampling trajectories without any application-specific parameter tuning. FS-AGM-MRI operates in real-time after processing the first short mini-batch, i.e., it can provide a reconstruction of each new image frame as soon as the MRI scan data for that frame arrives. It also provides a second set of improved quality reconstructions after a short delay. We compare our algorithm against many state of the art batch MRI algorithms, including Deep Learning (DL) based ones, on 17 different retrospectively undersampled datasets and two prospective datasets. FS-AGM-MRI is the only approach that provides accurate recovery for all datasets while also being one of the fastest.
BibTeX
@inproceedings{icassp2025_generalizablerea,
title = {Generalizable Real-time Accelerated Dynamic MRI},
author = {Silpa Babu and Wahidul Alam and Rushdi Zahid Rusho and Sajan Goud Lingala and Namrata Vaswani},
booktitle = {ICASSP 2025},
year = {2025}
}