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

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (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 (US)
Title of host publicationISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging
PublisherIEEE Computer Society
Pages1692-1695
Number of pages4
ISBN (Electronic)9781538636411
DOIs
StatePublished - Apr 2019
Event16th IEEE International Symposium on Biomedical Imaging, ISBI 2019 - Venice, Italy
Duration: Apr 8 2019Apr 11 2019

Publication series

NameProceedings - International Symposium on Biomedical Imaging
Volume2019-April
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Conference

Conference16th IEEE International Symposium on Biomedical Imaging, ISBI 2019
CountryItaly
CityVenice
Period4/8/194/11/19

Fingerprint

Magnetic resonance imaging
Neural networks
Interpolation
Artifacts
Learning systems
Coronary Artery Disease
Radiation
Imaging techniques
Sampling
Machine Learning

Keywords

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

PubMed: MeSH publication types

  • Journal Article

Cite this

Hosseini, S. A. H., Moeller, S., Weingartner, S., Ugurbil, K., & Akcakaya, M. (2019). Accelerated coronary mri using 3d spirit-raki with sparsity regularization. In ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging (pp. 1692-1695). [8759459] (Proceedings - International Symposium on Biomedical Imaging; Vol. 2019-April). IEEE Computer Society. https://doi.org/10.1109/ISBI.2019.8759459

Accelerated coronary mri using 3d spirit-raki with sparsity regularization. / Hosseini, Seyed Amir Hossein; Moeller, Steen; Weingartner, Sebastian; Ugurbil, Kamil; Akcakaya, Mehmet.

ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging. IEEE Computer Society, 2019. p. 1692-1695 8759459 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2019-April).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Hosseini, SAH, Moeller, S, Weingartner, S, Ugurbil, K & Akcakaya, M 2019, Accelerated coronary mri using 3d spirit-raki with sparsity regularization. in ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging., 8759459, Proceedings - International Symposium on Biomedical Imaging, vol. 2019-April, IEEE Computer Society, pp. 1692-1695, 16th IEEE International Symposium on Biomedical Imaging, ISBI 2019, Venice, Italy, 4/8/19. https://doi.org/10.1109/ISBI.2019.8759459
Hosseini SAH, Moeller S, Weingartner S, Ugurbil K, Akcakaya M. Accelerated coronary mri using 3d spirit-raki with sparsity regularization. In ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging. IEEE Computer Society. 2019. p. 1692-1695. 8759459. (Proceedings - International Symposium on Biomedical Imaging). https://doi.org/10.1109/ISBI.2019.8759459
Hosseini, Seyed Amir Hossein ; Moeller, Steen ; Weingartner, Sebastian ; Ugurbil, Kamil ; Akcakaya, Mehmet. / Accelerated coronary mri using 3d spirit-raki with sparsity regularization. ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging. IEEE Computer Society, 2019. pp. 1692-1695 (Proceedings - International Symposium on Biomedical Imaging).
@inproceedings{2b8737ceb4d247d8ba191073fa0920d9,
title = "Accelerated coronary mri using 3d spirit-raki with sparsity regularization",
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.",
keywords = "Accelerated imaging, Compressed sensing, Coronary MRI, Deep learning, Image reconstruction, Machine learning, Neural networks, Parallel imaging",
author = "Hosseini, {Seyed Amir Hossein} and Steen Moeller and Sebastian Weingartner and Kamil Ugurbil and Mehmet Akcakaya",
year = "2019",
month = "4",
doi = "10.1109/ISBI.2019.8759459",
language = "English (US)",
series = "Proceedings - International Symposium on Biomedical Imaging",
publisher = "IEEE Computer Society",
pages = "1692--1695",
booktitle = "ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging",

}

TY - GEN

T1 - Accelerated coronary mri using 3d spirit-raki with sparsity regularization

AU - Hosseini, Seyed Amir Hossein

AU - Moeller, Steen

AU - Weingartner, Sebastian

AU - Ugurbil, Kamil

AU - Akcakaya, Mehmet

PY - 2019/4

Y1 - 2019/4

N2 - 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.

AB - 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.

KW - Accelerated imaging

KW - Compressed sensing

KW - Coronary MRI

KW - Deep learning

KW - Image reconstruction

KW - Machine learning

KW - Neural networks

KW - Parallel imaging

UR - http://www.scopus.com/inward/record.url?scp=85073894207&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85073894207&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2019.8759459

DO - 10.1109/ISBI.2019.8759459

M3 - Conference contribution

C2 - 31893013

AN - SCOPUS:85073894207

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 1692

EP - 1695

BT - ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging

PB - IEEE Computer Society

ER -