Cargando…

Accelerated coronary MRI with sRAKI: A database-free self-consistent neural network k-space reconstruction for arbitrary undersampling

PURPOSE: To accelerate coronary MRI acquisitions with arbitrary undersampling patterns by using a novel reconstruction algorithm that applies coil self-consistency using subject-specific neural networks. METHODS: Self-consistent robust artificial-neural-networks for k-space interpolation (sRAKI) per...

Descripción completa

Detalles Bibliográficos
Autores principales: Hosseini, Seyed Amir Hossein, Zhang, Chi, Weingärtner, Sebastian, Moeller, Steen, Stuber, Matthias, Ugurbil, Kamil, Akçakaya, Mehmet
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Public Library of Science 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7034900/
https://www.ncbi.nlm.nih.gov/pubmed/32084235
http://dx.doi.org/10.1371/journal.pone.0229418
_version_ 1783499966128324608
author Hosseini, Seyed Amir Hossein
Zhang, Chi
Weingärtner, Sebastian
Moeller, Steen
Stuber, Matthias
Ugurbil, Kamil
Akçakaya, Mehmet
author_facet Hosseini, Seyed Amir Hossein
Zhang, Chi
Weingärtner, Sebastian
Moeller, Steen
Stuber, Matthias
Ugurbil, Kamil
Akçakaya, Mehmet
author_sort Hosseini, Seyed Amir Hossein
collection PubMed
description PURPOSE: To accelerate coronary MRI acquisitions with arbitrary undersampling patterns by using a novel reconstruction algorithm that applies coil self-consistency using subject-specific neural networks. METHODS: Self-consistent robust artificial-neural-networks for k-space interpolation (sRAKI) performs iterative parallel imaging reconstruction by enforcing self-consistency among coils. The approach bears similarity to SPIRiT, but extends the linear convolutions in SPIRiT to nonlinear interpolation using convolutional neural networks (CNNs). These CNNs are trained individually for each scan using the scan-specific autocalibrating signal (ACS) data. Reconstruction is performed by imposing the learned self-consistency and data-consistency, which enables sRAKI to support random undersampling patterns. Fully-sampled targeted right coronary artery MRI was acquired in six healthy subjects. The data were retrospectively undersampled, and reconstructed using SPIRiT, l(1)-SPIRiT and sRAKI for acceleration rates of 2 to 5. Additionally, prospectively undersampled whole-heart coronary MRI was acquired to further evaluate reconstruction performance. RESULTS: sRAKI reduces noise amplification and blurring artifacts compared with SPIRiT and l(1)-SPIRiT, especially at high acceleration rates in targeted coronary MRI. Quantitative analysis shows that sRAKI outperforms these techniques in terms of normalized mean-squared-error (~44% and ~21% over SPIRiT and [Image: see text] -SPIRiT at rate 5) and vessel sharpness (~10% and ~20% over SPIRiT and l(1)-SPIRiT at rate 5). Whole-heart data shows the sharpest coronary arteries when resolved using sRAKI, with 11% and 15% improvement in vessel sharpness over SPIRiT and l(1)-SPIRiT, respectively. CONCLUSION: sRAKI is a database-free neural network-based reconstruction technique that may further accelerate coronary MRI with arbitrary undersampling patterns, while improving noise resilience over linear parallel imaging and image sharpness over l(1) regularization techniques.
format Online
Article
Text
id pubmed-7034900
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher Public Library of Science
record_format MEDLINE/PubMed
spelling pubmed-70349002020-02-27 Accelerated coronary MRI with sRAKI: A database-free self-consistent neural network k-space reconstruction for arbitrary undersampling Hosseini, Seyed Amir Hossein Zhang, Chi Weingärtner, Sebastian Moeller, Steen Stuber, Matthias Ugurbil, Kamil Akçakaya, Mehmet PLoS One Research Article PURPOSE: To accelerate coronary MRI acquisitions with arbitrary undersampling patterns by using a novel reconstruction algorithm that applies coil self-consistency using subject-specific neural networks. METHODS: Self-consistent robust artificial-neural-networks for k-space interpolation (sRAKI) performs iterative parallel imaging reconstruction by enforcing self-consistency among coils. The approach bears similarity to SPIRiT, but extends the linear convolutions in SPIRiT to nonlinear interpolation using convolutional neural networks (CNNs). These CNNs are trained individually for each scan using the scan-specific autocalibrating signal (ACS) data. Reconstruction is performed by imposing the learned self-consistency and data-consistency, which enables sRAKI to support random undersampling patterns. Fully-sampled targeted right coronary artery MRI was acquired in six healthy subjects. The data were retrospectively undersampled, and reconstructed using SPIRiT, l(1)-SPIRiT and sRAKI for acceleration rates of 2 to 5. Additionally, prospectively undersampled whole-heart coronary MRI was acquired to further evaluate reconstruction performance. RESULTS: sRAKI reduces noise amplification and blurring artifacts compared with SPIRiT and l(1)-SPIRiT, especially at high acceleration rates in targeted coronary MRI. Quantitative analysis shows that sRAKI outperforms these techniques in terms of normalized mean-squared-error (~44% and ~21% over SPIRiT and [Image: see text] -SPIRiT at rate 5) and vessel sharpness (~10% and ~20% over SPIRiT and l(1)-SPIRiT at rate 5). Whole-heart data shows the sharpest coronary arteries when resolved using sRAKI, with 11% and 15% improvement in vessel sharpness over SPIRiT and l(1)-SPIRiT, respectively. CONCLUSION: sRAKI is a database-free neural network-based reconstruction technique that may further accelerate coronary MRI with arbitrary undersampling patterns, while improving noise resilience over linear parallel imaging and image sharpness over l(1) regularization techniques. Public Library of Science 2020-02-21 /pmc/articles/PMC7034900/ /pubmed/32084235 http://dx.doi.org/10.1371/journal.pone.0229418 Text en © 2020 Hosseini et al http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
spellingShingle Research Article
Hosseini, Seyed Amir Hossein
Zhang, Chi
Weingärtner, Sebastian
Moeller, Steen
Stuber, Matthias
Ugurbil, Kamil
Akçakaya, Mehmet
Accelerated coronary MRI with sRAKI: A database-free self-consistent neural network k-space reconstruction for arbitrary undersampling
title Accelerated coronary MRI with sRAKI: A database-free self-consistent neural network k-space reconstruction for arbitrary undersampling
title_full Accelerated coronary MRI with sRAKI: A database-free self-consistent neural network k-space reconstruction for arbitrary undersampling
title_fullStr Accelerated coronary MRI with sRAKI: A database-free self-consistent neural network k-space reconstruction for arbitrary undersampling
title_full_unstemmed Accelerated coronary MRI with sRAKI: A database-free self-consistent neural network k-space reconstruction for arbitrary undersampling
title_short Accelerated coronary MRI with sRAKI: A database-free self-consistent neural network k-space reconstruction for arbitrary undersampling
title_sort accelerated coronary mri with sraki: a database-free self-consistent neural network k-space reconstruction for arbitrary undersampling
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7034900/
https://www.ncbi.nlm.nih.gov/pubmed/32084235
http://dx.doi.org/10.1371/journal.pone.0229418
work_keys_str_mv AT hosseiniseyedamirhossein acceleratedcoronarymriwithsrakiadatabasefreeselfconsistentneuralnetworkkspacereconstructionforarbitraryundersampling
AT zhangchi acceleratedcoronarymriwithsrakiadatabasefreeselfconsistentneuralnetworkkspacereconstructionforarbitraryundersampling
AT weingartnersebastian acceleratedcoronarymriwithsrakiadatabasefreeselfconsistentneuralnetworkkspacereconstructionforarbitraryundersampling
AT moellersteen acceleratedcoronarymriwithsrakiadatabasefreeselfconsistentneuralnetworkkspacereconstructionforarbitraryundersampling
AT stubermatthias acceleratedcoronarymriwithsrakiadatabasefreeselfconsistentneuralnetworkkspacereconstructionforarbitraryundersampling
AT ugurbilkamil acceleratedcoronarymriwithsrakiadatabasefreeselfconsistentneuralnetworkkspacereconstructionforarbitraryundersampling
AT akcakayamehmet acceleratedcoronarymriwithsrakiadatabasefreeselfconsistentneuralnetworkkspacereconstructionforarbitraryundersampling