Accelerated Simultaneous Multi-Slice MRI using Subject-Specific Convolutional Neural Networks

Chi Zhang, Steen Moeller, Sebastian Weingartner, Kamil Ugurbil, Mehmet Akcakaya

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

Abstract

Simultaneous multi-slice or multi-band (SMS/MB) imaging allows accelerated coverage in magnetic resonance imaging (MRI). Multiple slices are excited and acquired at the same time, and reconstructed using the redundancies in receiver coil arrays, similar to parallel imaging. SMS/MB reconstruction is currently performed with linear reconstruction techniques. Recently, a nonlinear reconstruction method for parallel imaging, Robust Artificial-neural-networks for k-space Interpolation (RAKI) was proposed and shown to improve upon linear methods. This method uses convolutional neural networks (CNN) trained solely on subject-specific calibration data. In this study, we sought to extend RAKI to SMS/MB imaging reconstruction. CNN training was performed on calibration data acquired prior to SMS/MB imaging, in a manner consistent with the existing linear methods. These CNNs were used to reconstruct a time series of functional MRI (fMRI) data. CNN network parameters were optimized using an extensive search of the parameter space. With these optimal parameters, RAKI substantially improves image quality compared to a commonly used linear reconstruction algorithm, especially for high acceleration rates.

Original languageEnglish (US)
Title of host publicationConference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018
EditorsMichael B. Matthews
PublisherIEEE Computer Society
Pages1636-1640
Number of pages5
ISBN (Electronic)9781538692189
DOIs
StatePublished - Feb 19 2019
Event52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018 - Pacific Grove, United States
Duration: Oct 28 2018Oct 31 2018

Publication series

NameConference Record - Asilomar Conference on Signals, Systems and Computers
Volume2018-October
ISSN (Print)1058-6393

Conference

Conference52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018
CountryUnited States
CityPacific Grove
Period10/28/1810/31/18

Fingerprint

Magnetic resonance
Neural networks
Imaging techniques
Interpolation
Calibration
Image quality
Redundancy
Time series

Cite this

Zhang, C., Moeller, S., Weingartner, S., Ugurbil, K., & Akcakaya, M. (2019). Accelerated Simultaneous Multi-Slice MRI using Subject-Specific Convolutional Neural Networks. In M. B. Matthews (Ed.), Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018 (pp. 1636-1640). [8645313] (Conference Record - Asilomar Conference on Signals, Systems and Computers; Vol. 2018-October). IEEE Computer Society. https://doi.org/10.1109/ACSSC.2018.8645313

Accelerated Simultaneous Multi-Slice MRI using Subject-Specific Convolutional Neural Networks. / Zhang, Chi; Moeller, Steen; Weingartner, Sebastian; Ugurbil, Kamil; Akcakaya, Mehmet.

Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018. ed. / Michael B. Matthews. IEEE Computer Society, 2019. p. 1636-1640 8645313 (Conference Record - Asilomar Conference on Signals, Systems and Computers; Vol. 2018-October).

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

Zhang, C, Moeller, S, Weingartner, S, Ugurbil, K & Akcakaya, M 2019, Accelerated Simultaneous Multi-Slice MRI using Subject-Specific Convolutional Neural Networks. in MB Matthews (ed.), Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018., 8645313, Conference Record - Asilomar Conference on Signals, Systems and Computers, vol. 2018-October, IEEE Computer Society, pp. 1636-1640, 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018, Pacific Grove, United States, 10/28/18. https://doi.org/10.1109/ACSSC.2018.8645313
Zhang C, Moeller S, Weingartner S, Ugurbil K, Akcakaya M. Accelerated Simultaneous Multi-Slice MRI using Subject-Specific Convolutional Neural Networks. In Matthews MB, editor, Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018. IEEE Computer Society. 2019. p. 1636-1640. 8645313. (Conference Record - Asilomar Conference on Signals, Systems and Computers). https://doi.org/10.1109/ACSSC.2018.8645313
Zhang, Chi ; Moeller, Steen ; Weingartner, Sebastian ; Ugurbil, Kamil ; Akcakaya, Mehmet. / Accelerated Simultaneous Multi-Slice MRI using Subject-Specific Convolutional Neural Networks. Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018. editor / Michael B. Matthews. IEEE Computer Society, 2019. pp. 1636-1640 (Conference Record - Asilomar Conference on Signals, Systems and Computers).
@inproceedings{2d262c10bfd84bb8aa3f94af5b757baf,
title = "Accelerated Simultaneous Multi-Slice MRI using Subject-Specific Convolutional Neural Networks",
abstract = "Simultaneous multi-slice or multi-band (SMS/MB) imaging allows accelerated coverage in magnetic resonance imaging (MRI). Multiple slices are excited and acquired at the same time, and reconstructed using the redundancies in receiver coil arrays, similar to parallel imaging. SMS/MB reconstruction is currently performed with linear reconstruction techniques. Recently, a nonlinear reconstruction method for parallel imaging, Robust Artificial-neural-networks for k-space Interpolation (RAKI) was proposed and shown to improve upon linear methods. This method uses convolutional neural networks (CNN) trained solely on subject-specific calibration data. In this study, we sought to extend RAKI to SMS/MB imaging reconstruction. CNN training was performed on calibration data acquired prior to SMS/MB imaging, in a manner consistent with the existing linear methods. These CNNs were used to reconstruct a time series of functional MRI (fMRI) data. CNN network parameters were optimized using an extensive search of the parameter space. With these optimal parameters, RAKI substantially improves image quality compared to a commonly used linear reconstruction algorithm, especially for high acceleration rates.",
author = "Chi Zhang and Steen Moeller and Sebastian Weingartner and Kamil Ugurbil and Mehmet Akcakaya",
year = "2019",
month = "2",
day = "19",
doi = "10.1109/ACSSC.2018.8645313",
language = "English (US)",
series = "Conference Record - Asilomar Conference on Signals, Systems and Computers",
publisher = "IEEE Computer Society",
pages = "1636--1640",
editor = "Matthews, {Michael B.}",
booktitle = "Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018",

}

TY - GEN

T1 - Accelerated Simultaneous Multi-Slice MRI using Subject-Specific Convolutional Neural Networks

AU - Zhang, Chi

AU - Moeller, Steen

AU - Weingartner, Sebastian

AU - Ugurbil, Kamil

AU - Akcakaya, Mehmet

PY - 2019/2/19

Y1 - 2019/2/19

N2 - Simultaneous multi-slice or multi-band (SMS/MB) imaging allows accelerated coverage in magnetic resonance imaging (MRI). Multiple slices are excited and acquired at the same time, and reconstructed using the redundancies in receiver coil arrays, similar to parallel imaging. SMS/MB reconstruction is currently performed with linear reconstruction techniques. Recently, a nonlinear reconstruction method for parallel imaging, Robust Artificial-neural-networks for k-space Interpolation (RAKI) was proposed and shown to improve upon linear methods. This method uses convolutional neural networks (CNN) trained solely on subject-specific calibration data. In this study, we sought to extend RAKI to SMS/MB imaging reconstruction. CNN training was performed on calibration data acquired prior to SMS/MB imaging, in a manner consistent with the existing linear methods. These CNNs were used to reconstruct a time series of functional MRI (fMRI) data. CNN network parameters were optimized using an extensive search of the parameter space. With these optimal parameters, RAKI substantially improves image quality compared to a commonly used linear reconstruction algorithm, especially for high acceleration rates.

AB - Simultaneous multi-slice or multi-band (SMS/MB) imaging allows accelerated coverage in magnetic resonance imaging (MRI). Multiple slices are excited and acquired at the same time, and reconstructed using the redundancies in receiver coil arrays, similar to parallel imaging. SMS/MB reconstruction is currently performed with linear reconstruction techniques. Recently, a nonlinear reconstruction method for parallel imaging, Robust Artificial-neural-networks for k-space Interpolation (RAKI) was proposed and shown to improve upon linear methods. This method uses convolutional neural networks (CNN) trained solely on subject-specific calibration data. In this study, we sought to extend RAKI to SMS/MB imaging reconstruction. CNN training was performed on calibration data acquired prior to SMS/MB imaging, in a manner consistent with the existing linear methods. These CNNs were used to reconstruct a time series of functional MRI (fMRI) data. CNN network parameters were optimized using an extensive search of the parameter space. With these optimal parameters, RAKI substantially improves image quality compared to a commonly used linear reconstruction algorithm, especially for high acceleration rates.

UR - http://www.scopus.com/inward/record.url?scp=85062985178&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85062985178&partnerID=8YFLogxK

U2 - 10.1109/ACSSC.2018.8645313

DO - 10.1109/ACSSC.2018.8645313

M3 - Conference contribution

T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers

SP - 1636

EP - 1640

BT - Conference Record of the 52nd Asilomar Conference on Signals, Systems and Computers, ACSSC 2018

A2 - Matthews, Michael B.

PB - IEEE Computer Society

ER -