Abstract
Physics-guided deep learning (PG-DL) reconstruction has emerged as a powerful strategy for accelerated MRI. However, adopting PG-DL on 3D non-Cartesian MRI remains a challenge due to GPU hardware limitations. In this paper, we utilize multiple memory-efficient techniques to accomplish PG-DL on large-scale 3D kooshball coronary MRI. We first leverage a recently proposed approach to keep only one unrolled step on GPUs. We then utilize a Toeplitz approach to represent the multi-coil encoding operator. Subsequently, we distribute the most memory-consuming data consistency operations into multiple GPUs, enabling conjugate gradient iterations without necessitating coil compression. Finally, we employ mixed-precision training to further reduce memory consumption.The combination of these methods enable training of high-quality PG-DL reconstruction for 3D kooshball trajectories, and our results show reconstruction improvement compared to existing strategies.
Original language | English (US) |
---|---|
Title of host publication | ISBI 2022 - Proceedings |
Subtitle of host publication | 2022 IEEE International Symposium on Biomedical Imaging |
Publisher | IEEE Computer Society |
ISBN (Electronic) | 9781665429238 |
DOIs | |
State | Published - 2022 |
Event | 19th IEEE International Symposium on Biomedical Imaging, ISBI 2022 - Kolkata, India Duration: Mar 28 2022 → Mar 31 2022 |
Publication series
Name | Proceedings - International Symposium on Biomedical Imaging |
---|---|
Volume | 2022-March |
ISSN (Print) | 1945-7928 |
ISSN (Electronic) | 1945-8452 |
Conference
Conference | 19th IEEE International Symposium on Biomedical Imaging, ISBI 2022 |
---|---|
Country/Territory | India |
City | Kolkata |
Period | 3/28/22 → 3/31/22 |
Bibliographical note
Publisher Copyright:© 2022 IEEE.
Keywords
- GPU
- accelerated imaging
- deep learning
- implementation
- non-Cartesian MRI