Optimized fast GPU implementation of robust artificial-neural-networks for k-space interpolation (RAKI) reconstruction

Chi Zhang, Seyed Amir Hossein Hosseini, Sebastian Weingärtner, Kâmil Uǧurbil, Steen Moeller, Mehmet Akçakaya

Research output: Contribution to journalArticlepeer-review

1 Scopus citations

Abstract

Background Robust Artificial-neural-networks for k-space Interpolation (RAKI) is a recently proposed deep-learning-based reconstruction algorithm for parallel imaging. Its main premise is to perform k-space interpolation using convolutional neural networks (CNNs) trained on subject-specific autocalibration signal (ACS) data. Since training is performed individually for each subject, the reconstruction time is longer than approaches that pre-train on databases. In this study, we sought to reduce the computational time of RAKI. Methods RAKI was implemented using CPU multi-processing and process pooling to maximize the utility of GPU resources. We also proposed an alternative CNN architecture that interpolates all output channels jointly for specific skipped k-space lines. This new architecture was compared to the original CNN architecture in RAKI, as well as to GRAPPA in phantom, brain and knee MRI datasets, both qualitatively and quantitatively. Results The optimized GPU implementations were approximately 2-to-5-fold faster than a simple GPU implementation. The new CNN architecture further improved the computational time by 4-to-5-fold compared to the optimized GPU implementation using the original RAKI CNN architecture. It also provided significant improvement over GRAPPA both visually and quantitatively, although it performed slightly worse than the original RAKI CNN architecture. Conclusions The proposed implementations of RAKI bring the computational time towards clinically acceptable ranges. The new CNN architecture yields faster training, albeit at a slight performance loss, which may be acceptable for faster visualization in some settings.

Original languageEnglish (US)
Article numbere0223315
JournalPloS one
Volume14
Issue number10
DOIs
StatePublished - Oct 1 2019

Bibliographical note

Funding Information:
Funding:AuthorM.A.hasreceivedthefollowing grants:NationalInstitutesofHealth(NIH) R00HL111410,NationalScienceFoundation(NSF) CCF-1651825.AuthorK.U.hasreceivedthe followinggrants:NIHP41EB015894,NIH U01EB025144,NIHP41EB027061.Thefunders hadnoroleinstudydesign,datacollectionand analysis,decisiontopublish,orpreparationofthe manuscript.

Funding Information:
Author M.A. has received the following grants: National Institutes of Health (NIH) R00HL111410, National Science Foundation (NSF) CCF-1651825. Author K.U. has received the following grants: NIH P41EB015894, NIH U01EB025144, NIH P41EB027061. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript. Knee MRI data were obtained from the NYU fastMRI initiative database [23]. NYU fastMRI investigators provided data but did not participate in analysis or writing of this report. A listing of NYU fastMRI investigators, subject to updates, can be found at fastmri.med.nyu.edu.

Publisher Copyright:
© 2019 Zhang et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Fingerprint

Dive into the research topics of 'Optimized fast GPU implementation of robust artificial-neural-networks for k-space interpolation (RAKI) reconstruction'. Together they form a unique fingerprint.

Cite this