Accelerated coronary mri using 3d spirit-raki with sparsity regularization

Seyed Amir Hossein Hosseini, Steen Moeller, Sebastian Weingartner, Kamil Ugurbil, Mehmet Akcakaya

Research output: Contribution to journalArticleScientificpeer-review

8 Citations (Scopus)

Abstract

Coronary MRI is a non-invasive radiation-free imaging tool for the diagnosis of coronary artery disease. One of its limitations is the long scan time, due to the need for high resolution imaging in the presence of respiratory and cardiac motions. Machine learning (ML) methods have been recently utilized to accelerate MRI. In particular, a scan-specific ML technique, called Robust Artifical-neural-network for k-space Interpolation (RAKI) has shown promise in cardiac MRI. However, it requires uniform undersampling. In this study, we sought to extend this approach to arbitrary sampling patterns, using coil self-consistency. This technique, called SPIRiTRAKI,
utilizes scan-specific convolutional neural networks to nonlinearly enforce coil self-consistency. Additionally, regularization terms can also be incorporated. SPIRiT-RAKI was
used to accelerate right coronary MRI. Reconstructions were compared to SPIRiT for different undersampling patterns and acceleration rates. Results show SPIRiT-RAKI reduces
residual aliasing and blurring artifacts compared to SPIRiT.
Original languageEnglish
Pages (from-to)1692-1695
Number of pages4
JournalInternational Symposium on Biomedical Imaging. Proceedings
DOIs
Publication statusPublished - 2019
Externally publishedYes

Keywords

  • Accelerated imaging
  • Compressed sensing
  • Coronary MRI
  • Deep learning
  • Image reconstruction
  • Machine learning
  • Neural networks
  • Parallel imaging

Cite this