Scan-specific robust artificial-neural-networks for k-space interpolation (RAKI) reconstruction

Database-free deep learning for fast imaging

Mehmet Akcakaya, Steen Moeller, Sebastian Weingärtner, Kamil Ugurbil

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Purpose: To develop an improved k-space reconstruction method using scan-specific deep learning that is trained on autocalibration signal (ACS) data. Theory: Robust artificial-neural-networks for k-space interpolation (RAKI) reconstruction trains convolutional neural networks on ACS data. This enables nonlinear estimation of missing k-space lines from acquired k-space data with improved noise resilience, as opposed to conventional linear k-space interpolation-based methods, such as GRAPPA, which are based on linear convolutional kernels. Methods: The training algorithm is implemented using a mean square error loss function over the target points in the ACS region, using a gradient descent algorithm. The neural network contains 3 layers of convolutional operators, with 2 of these including nonlinear activation functions. The noise performance and reconstruction quality of the RAKI method was compared with GRAPPA in phantom, as well as in neurological and cardiac in vivo data sets. Results: Phantom imaging shows that the proposed RAKI method outperforms GRAPPA at high (≥4) acceleration rates, both visually and quantitatively. Quantitative cardiac imaging shows improved noise resilience at high acceleration rates (rate 4:23% and rate 5:48%) over GRAPPA. The same trend of improved noise resilience is also observed in high-resolution brain imaging at high acceleration rates. Conclusion: The RAKI method offers a training database-free deep learning approach for MRI reconstruction, with the potential to improve many existing reconstruction approaches, and is compatible with conventional data acquisition protocols.

Original languageEnglish (US)
Pages (from-to)439-453
Number of pages15
JournalMagnetic resonance in medicine
Volume81
Issue number1
DOIs
StatePublished - Jan 1 2019

Fingerprint

Learning
Databases
Noise
Imaging Phantoms
Neuroimaging

Keywords

  • accelerated imaging
  • convolutional neural networks
  • deep learning
  • image reconstruction
  • k-space interpolation
  • nonlinear estimation
  • parallel imaging

PubMed: MeSH publication types

  • Journal Article
  • Research Support, U.S. Gov't, Non-P.H.S.
  • Research Support, N.I.H., Extramural

Cite this

@article{36bf7d95cdc84296ab1c02ab486e388c,
title = "Scan-specific robust artificial-neural-networks for k-space interpolation (RAKI) reconstruction: Database-free deep learning for fast imaging",
abstract = "Purpose: To develop an improved k-space reconstruction method using scan-specific deep learning that is trained on autocalibration signal (ACS) data. Theory: Robust artificial-neural-networks for k-space interpolation (RAKI) reconstruction trains convolutional neural networks on ACS data. This enables nonlinear estimation of missing k-space lines from acquired k-space data with improved noise resilience, as opposed to conventional linear k-space interpolation-based methods, such as GRAPPA, which are based on linear convolutional kernels. Methods: The training algorithm is implemented using a mean square error loss function over the target points in the ACS region, using a gradient descent algorithm. The neural network contains 3 layers of convolutional operators, with 2 of these including nonlinear activation functions. The noise performance and reconstruction quality of the RAKI method was compared with GRAPPA in phantom, as well as in neurological and cardiac in vivo data sets. Results: Phantom imaging shows that the proposed RAKI method outperforms GRAPPA at high (≥4) acceleration rates, both visually and quantitatively. Quantitative cardiac imaging shows improved noise resilience at high acceleration rates (rate 4:23{\%} and rate 5:48{\%}) over GRAPPA. The same trend of improved noise resilience is also observed in high-resolution brain imaging at high acceleration rates. Conclusion: The RAKI method offers a training database-free deep learning approach for MRI reconstruction, with the potential to improve many existing reconstruction approaches, and is compatible with conventional data acquisition protocols.",
keywords = "accelerated imaging, convolutional neural networks, deep learning, image reconstruction, k-space interpolation, nonlinear estimation, parallel imaging",
author = "Mehmet Akcakaya and Steen Moeller and Sebastian Weing{\"a}rtner and Kamil Ugurbil",
year = "2019",
month = "1",
day = "1",
doi = "10.1002/mrm.27420",
language = "English (US)",
volume = "81",
pages = "439--453",
journal = "Magnetic Resonance in Medicine",
issn = "0740-3194",
publisher = "John Wiley and Sons Inc.",
number = "1",

}

TY - JOUR

T1 - Scan-specific robust artificial-neural-networks for k-space interpolation (RAKI) reconstruction

T2 - Database-free deep learning for fast imaging

AU - Akcakaya, Mehmet

AU - Moeller, Steen

AU - Weingärtner, Sebastian

AU - Ugurbil, Kamil

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Purpose: To develop an improved k-space reconstruction method using scan-specific deep learning that is trained on autocalibration signal (ACS) data. Theory: Robust artificial-neural-networks for k-space interpolation (RAKI) reconstruction trains convolutional neural networks on ACS data. This enables nonlinear estimation of missing k-space lines from acquired k-space data with improved noise resilience, as opposed to conventional linear k-space interpolation-based methods, such as GRAPPA, which are based on linear convolutional kernels. Methods: The training algorithm is implemented using a mean square error loss function over the target points in the ACS region, using a gradient descent algorithm. The neural network contains 3 layers of convolutional operators, with 2 of these including nonlinear activation functions. The noise performance and reconstruction quality of the RAKI method was compared with GRAPPA in phantom, as well as in neurological and cardiac in vivo data sets. Results: Phantom imaging shows that the proposed RAKI method outperforms GRAPPA at high (≥4) acceleration rates, both visually and quantitatively. Quantitative cardiac imaging shows improved noise resilience at high acceleration rates (rate 4:23% and rate 5:48%) over GRAPPA. The same trend of improved noise resilience is also observed in high-resolution brain imaging at high acceleration rates. Conclusion: The RAKI method offers a training database-free deep learning approach for MRI reconstruction, with the potential to improve many existing reconstruction approaches, and is compatible with conventional data acquisition protocols.

AB - Purpose: To develop an improved k-space reconstruction method using scan-specific deep learning that is trained on autocalibration signal (ACS) data. Theory: Robust artificial-neural-networks for k-space interpolation (RAKI) reconstruction trains convolutional neural networks on ACS data. This enables nonlinear estimation of missing k-space lines from acquired k-space data with improved noise resilience, as opposed to conventional linear k-space interpolation-based methods, such as GRAPPA, which are based on linear convolutional kernels. Methods: The training algorithm is implemented using a mean square error loss function over the target points in the ACS region, using a gradient descent algorithm. The neural network contains 3 layers of convolutional operators, with 2 of these including nonlinear activation functions. The noise performance and reconstruction quality of the RAKI method was compared with GRAPPA in phantom, as well as in neurological and cardiac in vivo data sets. Results: Phantom imaging shows that the proposed RAKI method outperforms GRAPPA at high (≥4) acceleration rates, both visually and quantitatively. Quantitative cardiac imaging shows improved noise resilience at high acceleration rates (rate 4:23% and rate 5:48%) over GRAPPA. The same trend of improved noise resilience is also observed in high-resolution brain imaging at high acceleration rates. Conclusion: The RAKI method offers a training database-free deep learning approach for MRI reconstruction, with the potential to improve many existing reconstruction approaches, and is compatible with conventional data acquisition protocols.

KW - accelerated imaging

KW - convolutional neural networks

KW - deep learning

KW - image reconstruction

KW - k-space interpolation

KW - nonlinear estimation

KW - parallel imaging

UR - http://www.scopus.com/inward/record.url?scp=85053534549&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85053534549&partnerID=8YFLogxK

U2 - 10.1002/mrm.27420

DO - 10.1002/mrm.27420

M3 - Article

VL - 81

SP - 439

EP - 453

JO - Magnetic Resonance in Medicine

JF - Magnetic Resonance in Medicine

SN - 0740-3194

IS - 1

ER -